Conference Paper

FreeDetector: Device-Free Occupancy Detection with Commodity WiFi

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... First, the camera can work only in a lineof-sight (LOS) environment with sufficient lighting [8][9][10][11][12]. Second, it does not preserve privacy concerns [8][9][10][12][13][14][15][16][17][18][19][20][21][22][23][24][25]. Finally, it cannot track activities or gestures through walls. ...
... This is achieved by analyzing the received signal strength indicator (RSSI) or channel state information (CSI) of the wireless signals received by different antennas. We can use wireless signals to work in LOS or non-LOS (NLOS) environments even in dark conditions [12] and thus preserve users' privacy [8][9][10]13,15,16,21,22,24,[26][27][28]. ...
... In healthcare, to monitor the movement of patients in hospitals or nursing homes and alert staff if a patient is wandering or falls [16,22,29]. ...
Article
Full-text available
The use of wireless signals for device-free activity recognition and precise indoor positioning has gained significant popularity recently. By taking advantage of the characteristics of the received signals, it is possible to establish a mapping between these signals and human activities. Existing approaches for detecting human walking direction have encountered challenges in adapting to changes in the surrounding environment or different people. In this paper, we propose a new approach that uses the channel state information of received wireless signals, a Hampel filter to remove the outliers, a Discrete wavelet transform to remove the noise and extract the important features, and finally, machine and deep learning algorithms to identify the walking direction for different people and in different environments. Through experimentation, we demonstrate that our approach achieved accuracy rates of 92.9%, 95.1%, and 89% in detecting human walking directions for untrained data collected from the classroom, the meeting room, and both rooms, respectively. Our results highlight the effectiveness of our approach even for people of different genders, heights, and environments, which utilizes machine and deep learning algorithms for low-cost deployment and device-free detection of human activities in indoor environments.
... al. [33] propose FreeSense where they use time and frequency domain information of Wi-Fi signals and trains a k-nearest neighbor (KNN) classifier to perform human identification. 3) FreeDetector: This scheme obtains channel state information from the PHY layer of commodity WiFi devices, analyzes the CSI variations and feeds them to a random forest classifier [40] to sense human presence. 4) WiWho: This model monitors the variation in the CSI data and collects walk segment feature of a person. ...
... Comparison with baseline models: To evaluate how BLECS performs compared to other supervised learning models, we developed PADS [27], FreeSense [33], FreeDetector [40], WiWho [35], and an LSTM classifier. We trained these models with our radio frequency features and fine tuned them with optimal parameters found by our empirical study. ...
... WiWho [35] is another devicefree sensing scheme that analyzes WiFi signals to find characteristics which can distinguish a person from a group of people. Other alternate approaches [30,40,41] use commodity WiFi routers and analyze the variations in RF measurements to predict human presence. ...
... The Signal tendency index (STI) [20,21] is based on Procrustes analysis to compare shape similarity across diferent packets. It is calculated from the Channel State Information (CSI) containing inegrained information of both the magnitude and the phase of each subcarrier between each transmitter-receiver antenna pair [17]. ...
... At irst glance, the results reported in this paper may seem to have fallen short of what similar systems have reported [21,16]. However, there is a major diference in how the evaluation is done and how the experiment (Tx and Rx) was setup. ...
... In other words, we train and test on completely diferent environments. On the other hand, existing works [21,16] collect a single dataset and then split it into training and testing sets. Due to the limited number of locations, their training and testing sets contain the same transmitter and receiver location pairsśwhich makes the classiication task easier. ...
Conference Paper
As robots penetrate into real-world environments, practical human-robot co-existence issues such as the requirement for safe human-robot interaction are becoming increasingly important. In almost every vision-capable mobile robot, the field of view of the robot is occluded by the presence of obstacles such as indoor walls, furniture, and humans. Such occlusions force the robots to be stationary or to move slowly so that they can avoid collisions and violations of entry into the personal spaces of humans. We see this as a barrier to robots being able to optimally plan motions with reasonable speeds. In order to solve this problem, we propose to augment the sensing capability of a robot by using a commodity WiFi receiver. Using our proposed method, a robot can observe the changes in the properties of received signals, and thus be able to infer whether a human is present behind the wall or obstacles, which enhances its ability to plan and navigate efficiently and intelligently.
... In addition, video-based systems suffer from field-of-view and privacy-related issues, since it is impossible to install video cameras in every room (e.g., toilets), or to ensure the absence of blind spots [10]. WiFi sensing: Beyond the approaches listed above, techniques based on WiFi sensing have become a prominent solution, thanks to WiFi's ubiquity, both indoor and outdoor, and the relatively low deployment costs of such commodity off-theshell WiFi routers [11], [12]. As shown in Figure 1, WiFi sensing exploits the Channel State Information (CSI) to gain an insight of how WiFi radio signals propagate from a transmitter (e.g., a WiFi router) to a receiver (e.g., a CSI sniffer). ...
... As shown in Figure 1, WiFi sensing exploits the Channel State Information (CSI) to gain an insight of how WiFi radio signals propagate from a transmitter (e.g., a WiFi router) to a receiver (e.g., a CSI sniffer). By analyzing the variations of the propagation pattern through ML techniques, different works have proposed to recognize the environment status, the number of its occupants, their identity, or the activities they perform [11]- [13]. WiFi sensing limitations: Even though WiFi sensing may seem a panacea for many sensing scenarios, its practical application is not straightforward for real-world cases. ...
... However, this presents several challenges as BLE devices often lack computation power, must be frugal with their energy, and lack channel state information (CSI) which state-of-the-art DfOD algorithms typically rely on [16,19,21]. Moreover, the majority of existing WiFi-based DfOD systems require multiple measurements and offloading data to the application server, resulting in high energy consumption and communication latency [18,22,24,25]. ...
... Less sensor-heavy approaches use only commodity Wi-Fi access points to predict the occupancy of a particular room [18,24,25]. These solutions may not scale well as deploying one or more access points in every room is costly. ...
Conference Paper
The emerging area of device-free occupancy detection (DfOD) has seen slow adoption due to deployability, scalability, and energy efficiency concerns resulting from the use of large, costly, and power-hungry devices like laptops and WiFi routers in the state-of-the-art solutions. Moreover, these approaches often rely on cloud-offloading for data processing which requires extra communication latency and energy. To overcome these challenges, we develop an RF-based DfOD system using easily-deployable Bluetooth Low Energy (BLE) devices. Our system uses a kilobyte-sized machine learning algorithm running on the BLE device to predict the occupancy of a room from a small number of wireless packets, thereby enabling energy-frugal realtime analytics. We validate our approach with experiments in two indoor rooms using four nRF52840 BLE radios. Initial results suggest our system can detect occupancy of an indoor environment with 95% accuracy, 96% precision, and 92% recall while drawing a meager amount of current.
... For efficient utilization of this equation, real-time occupancy data acquisition is necessary. Recent advancements in sensor and deep learning technologies have introduced methods such as infrared (IR) or deep vision-based people counters [44,45] and Wi-Fi connection-based occupancy inference [46] which provides high counting accuracy. For single-zone systems, the total number of occupants is used, while for multizone systems, the zone with the highest occupancy is considered. ...
Article
Full-text available
This study developed and evaluated an optimal ventilation strategy for variable air volume (VAV) systems, targeting carbon dioxide (CO2) and particulate matter less than 2.5 μm in diameter (PM2.5) concentrations. The strategy integrates system-level demand-controlled ventilation (DCV) based on real-time occupancy data and zone-level predictive control using indoor air quality (IAQ) prediction models. By predicting indoor CO2 and PM2.5 levels for the subsequent time step and dynamically adjusting control priorities, optimal airflow is determined. A co-simulation model integrating EnergyPlus, CONTAM, and Python was employed for model training and testing. The proposed strategy was compared with on–off control, CO2 predictive control, and PM2.5 predictive control, demonstrating superior prediction accuracy and stable IAQ maintenance. The optimal ventilation strategy achieved the highest performance, maintaining CO2 and PM2.5 levels below their respective upper limits of 100% and 97.33% of the time. Although this strategy resulted in slightly higher energy consumption compared to the other control algorithms due to its multivariable control approach, it effectively maintained IAQ standards. This method simplifies development and maintenance by circumventing the need for complex optimization, providing a flexible and cost-effective solution for IAQ management. Future research will focus on developing integrated VAV system control strategies that ensure comfort year-round, addressing both energy efficiency and thermal comfort.
... For instance, research detailed in [8] and [9] explores the use of CO 2 emission data as a means to estimate the number of occupants in commercial buildings. Additionally, the utilization of Wi-Fi routers for detecting occupancy has been investigated, as presented in [10]. Beyond single-sensor approaches like CO 2 or Wi-Fi routers, integrating multiple sensors, including those for temperature, humidity, sound, motion, and light, is also being explored to enhance occupancy detection accuracy, as discussed in [11]. ...
... , in general, cameras have other issues such as poor illumination conditions and occlusion. A recent body of work focuses on occupancy and activity detection from Wi-Fi signals(Zou et al., 2019), because of its ubiquitous presence, and better privacy guarantees.Zou et al. (2017Zou et al. ( , 2018c ...
Article
Full-text available
Energy consumption in buildings, both residential and commercial, accounts for approximately 40% of all energy usage in the United States, and similar numbers are being reported from countries around the world. This significant amount of energy is used to maintain a comfortable, secure, and productive environment for the occupants. So, it is crucial that energy consumption in buildings must be optimized, all the while maintaining satisfactory levels of occupant comfort, health, and safety. Machine learning (ML) has been proven to be an invaluable tool in deriving important insights from data and optimizing various systems. In this work, we review some of the most promising ways in which ML has been leveraged to make buildings smart and energy-efficient. For the convenience of readers, we provide a brief introduction to the relevant ML paradigms and the components and functioning of each smart building system we cover. Finally, we discuss the challenges faced while implementing machine learning algorithms in smart buildings and provide future avenues for research in this field.
... But recent studies have shown that Wi-Fi signals tend to get disturbed by the movement of residents and other movements in a zone [53]. For that, in Wi-Fi sensing data, Channel State Information (CSI) [54] applies to a range of applications such as sedentary behavior analysis [55], gesture recognition [56], vital sign detection [57], human detection [58], occupancy detection [59], crowd counting [60], and human activity recognition [61], etc. Compared to contact-based sensing methods, Wi-Fi signals have multiple excellent attributes and advantages over wearable devices. ...
Article
Full-text available
Digital Twin (DT) in Healthcare 4.0 (H4.0) presents a digital model of the patient with all its biological properties and characteristics. One of the application areas is patient respiration monitoring for enhanced patient care and decision support to healthcare professionals. Obtrusive methods of patient monitoring create hindrances in the patient’s daily routine. This research presents a novel DT model (ResDT) based on Wi-Fi Carrier State Information (CSI), improved signal processing, and Machine Learning (ML) algorithms for monitoring and classification (binary and multi-class) of patient respiration. A Wi-Fi sensor ESP32 with Wi-Fi CSI was utilized for the collection of respiration data. This provides an added advantage of unobtrusive monitoring of patient vital signs. The Patient’s Breaths Per Minute (BPM) is estimated from raw sensor data through the integration of multiple signal processing methodologies for denoising (smoothing and filtering) and dimensionality reduction (PCA, SVM, EMD, EMD-PCA). Multiple filters and dimensionality reduction methodologies are compared for accurate BPM estimation. The elliptical filter provides a relatively better estimation of the BPM with 87.5% accurate estimation as compared to other bandpass filters such as Butterworth (BF), Chebyshev type 1 Filter (CH1), Chebyshev type 2 Filter (CH2), and wavelet Decomposition (62.5%, 75%, 68.75%, and 75% respectively). Principal Component Analysis (PCA) was performed to provide better dimensionality reduction with 87.5% accurate BPM values compared to EMD, SVD, and EMD-PCA (57%, 44%, and 44% respectively). Additionally, the fine tree algorithm, from the implemented 21 ML supervised classification algorithms with K-fold crossvalidation, was observed to be the optimal choice for multi-class and binary-class classification problems in the presented ResDT model with 96.9% and 95.8% accuracy respectively.
... However, they require a higher maintenance cost [7], and have lower sensitivity in Non-Line-of-Sight (NLoS) and unreliable performance with a single occupant in large spaces. More recently, the widespread use of WiFi infrastructure in commercial and residential buildings has made the WiFi-based sensing technique more popular for occupancy monitoring [13,16,17]. In this paper, we also leverage the WiFi infrastructure and introduce a system supported by any WiFi-enabled IoT device to smartly sense the occupancy of the target zone. ...
Conference Paper
Full-text available
The building energy saving (BES) has been the subject of extensive research for reducing the energy consumption inside the buildings. One of the key solution for energy saving in buildings is to minimize the energy supply to the building areas that are not occupied by the inhabitants. However, this requires effective monitoring of occupants regardless of unpredictable variations in indoor environment, such as variation in the space size, furniture arrangement, nature of occupant’s activity (e.g., varied intensities and instances) etc. Currently, various occupancy monitory solutions have been employed in the existing smart buildings, namely PIR sensors, 𝐶𝑂2 sensors, cameras, etc. However, they are costly and sometimes not interoperable to the complex variations in indoor environments. In this paper, we leveraged the fine-grained information of physical layer (i.e., channel state information – CSI) of the commodity WiFi for occupancy detection and developed a self-adoptive method which is interoperable with complex variations in the indoor environment. In indoor contexts of different sized, varied intensities of physical activity, and various instances of activity of daily living (ADL), our testbed evaluation showed an average detection rate of 98.9%, 98.5%, and 98.1%, respectively.
... Features such as eigenvalues are given to a classifier such as a support vector machine (SVM) to determine decision boundaries. Periodicity following continuous wavelet transformation [36], the temporal similarity of CSIs across frequencies [37], histograms of CSI amplitude [38], and statistics from average Doppler spectrum [39] are among the other proposed methods. ...
Article
Full-text available
Applications for human sensing, also known as (human) occupancy detection, include energy management systems for intelligent buildings, intruder detection, e-health systems, the identification of everyday activity, and the monitoring of vital signs. These applications require intelligent decision-making that relies on human sensing. Multiple technologies based on vision, sensors, or radio signals can be used to detect occupancy. Vision-based systems use a multitude of cameras to recognize the human presence, but they are restricted by light availability, line-of-sight coverage, expensive equipment, and privacy concerns. Sensor-based techniques refer to a prospective method that employs various combinations of sensors. These solutions are static and necessitate costly equipment installation and maintenance. Due to technical advancements, radio-based signals, such as WiFi, have been integrated into various forms of infrastructure, including homes, offices, and constructions. Due to how human body movements affect wireless signal propagation, it is possible to detect human motions by analyzing the received wireless signals (such as reflection, diffraction, and scattering). Due to its low cost and non-intrusive nature, wireless-based human activity detection has received substantial attention and become a key topic of study. This article reviews the underlying principles, methodologies, and system architectures of radio-frequency-based occupancy detection systems. We classify the reviewed research studies based on the technical measures and applications they employ. In addition to focusing on the security aspects of occupancy detection and discussing future trends and difficulties, we also discuss practical considerations.
... For example, human motions within an indoor environment affect the propagation of wireless signals transmitted by the passive WiFi sensors [19]. These applications include HAR [20]- [22], fall detection [23], [24], sign language recognition [25], gesture recognition [26], [27], occupancy detection [28], crowd counting [29], respiration monitoring [30], among others. Specific IEEE 802.11 ...
Preprint
Full-text available
This paper presents a novel approach for multimodal data fusion based on the Vector-Quantized Variational Autoencoder (VQVAE) architecture. The proposed method is simple yet effective in achieving excellent reconstruction performance on paired MNIST-SVHN data and WiFi spectrogram data. Additionally, the multimodal VQVAE model is extended to the 5G communication scenario, where an end-to-end Channel State Information (CSI) feedback system is implemented to compress data transmitted between the base-station (eNodeB) and User Equipment (UE), without significant loss of performance. The proposed model learns a discriminative compressed feature space for various types of input data (CSI, spectrograms, natural images, etc), making it a suitable solution for applications with limited computational resources.
... A recent body of work focuses on occupancy and activity detection from WiFi signals [66], because of its ubiquitous presence, and better privacy guarantees. Authors in [67,68] use Channel State Information (CSI) data collected from WiFi sensors (a transmitter and a receiver) and measuring the shape similarity between adjacent time series CSI curves to infer the occupancy. They improve the detection mechanism in [69] by using convolutional neural networks on the CSI heatmaps to detect human gestures. ...
Preprint
Full-text available
Energy consumption in buildings, both residential and commercial, accounts for approximately 40% of all energy usage in the U.S., and similar numbers are being reported from countries around the world. This significant amount of energy is used to maintain a comfortable, secure, and productive environment for the occupants. So, it is crucial that the energy consumption in buildings must be optimized, all the while maintaining satisfactory levels of occupant comfort, health, and safety. Recently, Machine Learning has been proven to be an invaluable tool in deriving important insights from data and optimizing various systems. In this work, we review the ways in which machine learning has been leveraged to make buildings smart and energy-efficient. For the convenience of readers, we provide a brief introduction of several machine learning paradigms and the components and functioning of each smart building system we cover. Finally, we discuss challenges faced while implementing machine learning algorithms in smart buildings and provide future avenues for research at the intersection of smart buildings and machine learning.
... At the University of Southern California (USC), we have developed CrowdMap, a nonintrusive passive digital tracking platform that utilizes a large network of WiFi routers. Research has shown WiFi to be the most promising alternative to GPS for indoor, context-aware and location-based services [3], [4]. Due to privacy concerns, such a WiFi system collects only connection logs and their timestamps. ...
Conference Paper
Accurately monitoring the number of individuals inside a building is vital to limiting COVID-19 transmission. Low adoption of contact tracing apps due to privacy concerns has increased pervasiveness of passive digital tracking alternatives. Large arrays of WiFi access points can conveniently track mobile devices on university and industry campuses. The CrowdMap system employed by the University of Southern California enables such tracking by collecting aggregate statistics from connections to access points around campus. However, since these devices can be used to infer the movement of individuals, there is still a significant risk that even aggregate occupancy statistics will violate the location privacy of individuals. We examine the use of Differential Privacy in reporting statistics from this system as measured using point and range count queries. We propose discretization schemes to model the positions of users given only user connections to WiFi access points. Using this information we are able to release accurate counts of occupants in areas of campus buildings such as labs, hallways, and large discussion halls with minimized risk to individual users' privacy.
... Recently, it is observed that the motions of occupants impact the WiFi signals to some extent. Based on this insight, researchers manage to use channel state information (CSI) [4] to achieve wireless sensing for a variety of applications, including human activity recognition [5], occupancy detection [8], sedentary behavior analysis [6], crowd counting [7], gesture recognition [9], human identification [10] and vital sign detection [12], etc. Compared to the contact-based sensing methods, WiFi signals have a series of excellent characteristics that visual information and wearable devices do not possess. ...
... Including these factors too, the authors could check if these are important in the forecast. Random Forest has been proved to give the best results for classification in terms of efficiency and accuracy, for occupancy detection [16]. On the other hand, the drawback of running time aspect of the algorithm is not a concern in our application and type of situation, because we do not have a large number of features. ...
Article
Full-text available
Sensing and predicting occupancy in buildings is an important task that can lead to significant improvements in both energy efficiency and occupant comfort. Rich data streams are now available that allow for machine learning-based algorithm implementation of direct and indirect occupancy estimation. We evaluate ensemble models, namely, random forests, on data collected from an 8×8 PIR matrix thermopile sensor with the dual goal of predicting individual cell temperature values and subsequently detecting the occupancy status. Evaluation of the method is based on a real case study deployed in an IT Hub in Bucharest, for which we have collected over three weeks of ground data, analyzed, and used it in order to predict occupancy in a room. Results show a 2–4% mean absolute percentage error for the temperature prediction and >99% accuracy for a three-class model to detect human presence. The resulting outputs can be used by predictive building control models to optimize the commands to various subsystems. By separating the specific deployment from the system architecture and data structure, the application can be easily translated to other usage profiles and built environment entities. As compared to vision-based systems, our solution preserves privacy with improved performance when compared to single PIR or indirect estimation.
... Human Activity Recognition (HAR) plays a vital role in the thriving research field of human-computer interaction. It is an essential part of an Internet of Things (IoT) system as it equips the system with the ability to understand and detect users and the surrounding environment to provide better services [1]- [4]. It has important applications in health care, security, entertainment and so on. ...
Article
Full-text available
Channel State Information (CSI) based human activity recognition has received great attention in recent years due to its advantages in privacy protection, insensitivity to illumination, and no requirement for wearable devices. In this paper, we propose a Multimodal Channel State Information Based Activity Recognition (MCBAR) system that leverages existing WiFi infrastructures and monitors human activities from CSI measurements. MCBAR aims to address the performances degradation of WiFi-based human recognition systems due to environmental dynamics. Specifically, we address the issue of non-uniformly distributed unlabelled data with rarely-performed activities by taking advantages of the generative adversarial network (GAN) and semi-supervised learning. We apply a multimodal generator to approximate the CSI data distribution in different environment settings with limited measured CSI data. The generated CSI data using the multimodal generator can provide better diversity for knowledge transfer. This multimodal generator improves the ability of MCBAR to recognize specific activities with various CSI patterns caused by environmental dynamics. Compared to state-of-the-art CSI-based recognition systems, MCBAR is more robust as it is able to handle the non-uniformly distributed CSI data collected from a new environment setting. In addition, diverse generated data from the multimodal generator improves the stability of the system. We have tested MCBAR under multiple experimental settings at different places. The experimental results demonstrate that our algorithm overcomes environmental dynamics and outperforms existing human activity recognition systems.
... However, an increase in the number of persons affected the detection accuracy. Zou et al. [53] used two commodity Wi-Fi routers to detect a person moving past these routers by comparing the similarity between static CSI and occupied CSI measurements in the time domain. Compared to infrared and ultrasonic, Wi-Fi can provide better coverage and is suitable for a large hallway or entrance. ...
Article
Indoor device-free localization and tracking can bring both convenience and privacy to users compared with traditional solutions such as camera-based surveillance and RFID tag-based tracking. Technologies such as Wi-Fi, wireless sensor, and infrared have been used to localize and track people living in care homes and office buildings. However, the presence of multiple residents introduces further challenges, such as the ambiguity in sensor measurements and target identity, to localization and tracking. In this article, we survey the latest development of device-free indoor localization and tracking in the multi-resident environment. We first present the fundamentals of device-free localization and tracking. Then, we discuss and compare the technologies used in device-free indoor localization and tracking. After discussing the steps involved in multi-resident localization and tracking including target detection, target counting, target identification, localization, and tracking, the techniques related to each step are classified and discussed in detail along with the performance metrics. Finally, we identify the research gap and point out future research directions. To the best of our knowledge, this survey is the most comprehensive work that covers a wide spectrum of the research area of device-free indoor localization and tracking.
... It can also be used in environments involving human movement due to its disturbance of radio waves which can be detected in the WiFi channel. This has been used by previous work to count the number of people passing between two routers or even to implement hand gesture recognition from WiFi signals [8,18]. ...
Thesis
Full-text available
Indoor localization is a key technology for a world with mobile robots and ubiquitous computing. Reliable localization systems for outside environments already exist but quickly fail when applied to indoor situations. As more and more devices are integrated with a WiFi chip, locating a target with this becomes desirable. Using signal strength to achieve that is possible but only results in an accuracy of one to two meters in my experiments. The performance can be improved using the angle of arrival of the incoming signal which can be estimated from Channel State Information. To increase cost effectiveness and ease of deployment, the authors of SpotFi proposed a mathematical trick for performing this using commercial off-the-shelf devices which they implemented using the Intel WifiLink 5300 chip. This thesis describes how it is possible to extract Channel State Information for this purpose from cheaper and more widely used Atheros chips and determines for which of those it is supported. It discusses how the phase offset between antennas due to the internal wiring of a router can be calibrated by using a coaxial cable. An algorithm for filtering the obtained peaks in the MUSIC spectrum is proposed to allow clustering and detection of the direct path. The thesis investigates why angle of arrival estimation is not possible. The most likely reasons are the antenna spacing of the commodity WiFi devices being too large and the inability to calibrate the phase offset using a cable.
... Including these factors too, the authors could check if these are important in the forecast. Random Forest has been proved to give the best results for classification in terms of efficiency and accuracy, for occupancy detection [10]. On the other hand, the drawback of running time aspect of the algorithm is not a concern in our application and type of situation, because we do not have a large number of features. ...
Preprint
Full-text available
Manuscript draft of a privacy-preserving system for detecting and predicting occupancy in a building, deployed in a real application
... However, low degree of occupancy resolution, intrusiveness, and cost of execution are considered as the disadvantages of such methods [25]. To address these limitations, researchers [88][89][90][91][92][93][94][95][96][97][98] have leveraged Wi-Fi information for occupancy sensing (such as detection [99] and localization [100]) in commercial buildings. Wi-Fi networks are able to create databases based on the MAC addresses of Wi-Fi enabled devices (such as laptops and smartphones) to easily differentiate between users (i.e., occupants) in a building [101,102]. ...
... We evaluate our method on this sensor dataset. It was collected by IoTbased WiFi sensors and the Channel State Information (CSI) data [32] was extracted that represents the states of the WiFi propagation [33]. When persons perform actions, such CSI data will perform different patterns [26] that can be modeled by traditional models [34] or deep neural network [35] for activity recognition [36], [37], [38], [25], gesture recognition [13], and crowd counting [39]. ...
Article
Full-text available
Deep neural networks (DNNs) have made significant advances in computer vision and sensor-based smart sensing. DNNs achieve prominent results based on standard datasets and powerful servers, whereas in real applications with domain-shift data and resource-constrained environments such as Internet of Things (IoT) devices in the edge computing, DNNs are likely to have degraded performance in terms of accuracy and efficiency. To this end, we develop the MobileDA framework that learns transferable features while keeping the simple structure of the deep model. Our method allows a novel teacher network trained in the server to distill the knowledge for a student network running in the edge device, which is achieved by cross-domain distillation. Leveraging unlabeled data in the new environment, our student model amends the feature learning to be domain-invariant, then being our objective model running in the edge device. Our approach is evaluated on a challenging IoT-based WiFi gesture recognition scenario, and three classic visual adaptation benchmarks. The empirical studies corroborate the effectiveness of distillation for domain transfer, and the overall results show that our model achieves state-of-the-art performance merely using a simple network.
... There is prior work on presence detection using CSI. The FreeDetector system [22] achieves occupancy detection by computing the temporal similarity of CSIs across frequencies; however, it can only detect walking across line of sight between the transmitter and the receiver. The PADS and R-TTWD systems in [23] and [26] utilize support vector machine (SVM) to detect motion; the inputs to the SVM come from CSI time series after dimensionality reduction through principal component analysis. ...
Preprint
This paper explores the use of ambient radio frequency (RF) signals for human presence detection through deep learning. Using WiFi signal as an example, we demonstrate that the channel state information (CSI) obtained at the receiver contains rich information about the propagation environment. Through judicious pre-processing of the estimated CSI followed by deep learning, reliable presence detection can be achieved. Several challenges in passive RF sensing are addressed. With presence detection, how to collect training data with human presence can have a significant impact on the performance. This is in contrast to activity detection when a specific motion pattern is of interest. A second challenge is that RF signals are complex-valued. Handling complex-valued input in deep learning requires careful data representation and network architecture design. Finally, human presence affects CSI variation along multiple dimensions; such variation, however, is often masked by system impediments such as timing or frequency offset. Addressing these challenges, the proposed learning system uses pre-processing to preserve human motion induced channel variation while insulating against other impairments. A convolutional neural network (CNN) properly trained with both magnitude and phase information is then designed to achieve reliable presence detection. Extensive experiments are conducted. Using off-the-shelf WiFi devices, the proposed deep learning based RF sensing achieves near perfect presence detection during multiple extended periods of test and exhibits superior performance compared with leading edge passive infrared sensors. The learning based passive RF sensing thus provides a viable and promising alternative for presence or occupancy detection.
... They report thermal load savings up to 14.16% compared with actual occupancy at 50% humidity and 25 • C temperature. From the same family with K-NN models, the Random Forest (RF) models were applied and returned promising results for occupancy tasks [20], [21]. ...
... In the recent years, numerous wireless technology-based solutions have been proposed and reported in the literature. They utilized Radio Tomographic Imaging (RTI) [3][4][5][6], energy minimization [7,8], and machine learning approaches (including: Support Vector Machines (SVM) [9,10], Random Forest [11], Hidden Markov Models (HMM) [12], and Deep Learning [13]) to mention a few. These approaches are commonly implemented using either the received signal strength indicator (RSSI) metric, or the Wi-Fi channel state information (CSI) metric. ...
Article
Device-free or passive localization techniques allow positioning of targets, without requiring them to carry any form of transceiver or tag. In this paper, a novel device-free visible light positioning technique is proposed. It exploits the variation of the ambient light levels caused by a moving entity. The target is localized by employing a system of artificial potential fields associated with a set of photodiodes embedded into an indoor environment. The system does not require the existing lighting infrastructure to be modified. It also employs a novel calibration procedure that does not require labelled training data, thus significantly reducing the calibration cost. The developed prototype system is installed in three typical indoor environments consisting of a corridor, foyer, and laboratory and was able to attain median errors of 0.68m, 1.20m and 0.84m respectively. Through experimental results, the proposed VLP technique is benchmarked against an existing wireless RSSI-based device-free localization approach, and was able to attain a median error 0.63m lower than the wireless technique.
... Recent literature has witnessed many successful employments of CSI measurements for various applications, such as device-free indoor localization [9], human activity recognition [20], [21] and crowd counting [22], [23]. E-eyes [24] employs the similarity of CSI waves and dynamic time warping to recognize human activities. ...
Article
Full-text available
We propose a gesture recognition system that leverages existing WiFi infrastructures and learns gestures from Channel State Information (CSI) measurements. Having developed an innovative OpenWrt-based platform for commercial WiFi devices to extract CSI data, we propose a novel deep Siamese representation learning architecture for one-shot gesture recognition. Technically, our model extends the capacity of spatio-temporal patterns learning for the standard Siamese structure by incorporating convolutional and bidirectional recurrent neural networks. More importantly, the representation learning is ameliorated by our Siamese framework and transferable pairwise loss which helps to remove structured noise such as individual heterogeneity and various measurement conditions during domain-different training. Meanwhile, our Siamese model also enables one-shot learning for higher availability in reality. We prototype our system on commercial WiFi routers. The experiments demonstrate that our model outperforms state-of-the-art solutions for temporal-spatial representation learning and achieves satisfactory results under one-shot conditions.
... Table 2 summarizes and compares these approaches. All of them need more or less calibration before use: some, e.g., E-eyes [22], CARM [20], TR-BREATH [5] and Omni-PHD [32], need to build a database storing the CSIs for the normal state and motion is detected as long as the incoming CSI is very dissimilar to the stored CSIs; others, e.g., DeMan [23], PADS [15], FreeSense [27], FreeDetector [34] and SIED [12], investigate intrinsic features of the CSI in the presence of human motion yet need a training phase to tune system parameters in order to balance the false positive rate and false negative rate. Basically, most of the existing works apply a data-driven approach and try to extract features from CSIs to distinguish between motion and non-motion scenarios. ...
Article
Full-text available
Motion detection acts as a key component for a range of applications such as home security, occupancy and activity monitoring, retail analytics, etc. Most existing solutions, however, require special installation and calibration and suffer from frequent false alarms with very limited coverage. In this paper, we propose WiDetect, a highly accurate, robust, and calibration-free wireless motion detector that achieves almost zero false alarm rate and large through-the-wall coverage. Different from previous approaches that either extract data-driven features or assume a few reflection multipaths, we model the problem from a perspective of statistical electromagnetic (EM) by accounting for all multipaths indoors. By exploiting the statistical theory of EM waves, we establish a connection between the autocorrelation function of the physical layer channel state information (CSI) and target motion in the environment. On this basis, we devise a novel motion statistic that is independent of environment, location, orientation, and subjects, and then perform a hypothesis testing for motion detection. By harnessing abundant multipaths indoors, WiDetect can detect arbitrary motion, be it in Line-Of-Sight vicinity or behind multiple walls, providing sufficient whole-home coverage for typical apartments and houses using a single link on commodity WiFi. We conduct extensive experiments in a typical office, an apartment, and a single house with different users for an overall period of more than 5 weeks. The results show that WiDetect achieves a remarkable detection accuracy of 99.68% with a zero false rate, significantly outperforming the state-of-the-art solutions and setting up the stage for ubiquitous motion sensing in practice.
... Daniel Konings is with the Department of Mechanical & Electrical Engineering, Massey University, Auckland 0632, New Zealand (email: d.konings@massey.ac.nz). grained features than the competing Received Signal Strength Indicator (RSSI) metric, recent machine learning approaches have largely focused on CSI-based DFL using: shapelet learning [17], Support-vector machines (SVM) [6,18], Random Forest [19], Hidden Markov Models (HMM) [20], and Deep Learning [21]. Though CSI is routinely used in recent literature, it can only currently be implemented using SDR or legacy Wi-Fi radios with modified drivers [22][23][24][25]. ...
Article
Device-free localization (DFL) systems that that rely on the wireless received signal strength indicator (RSSI) metric have been reported in literature for almost a decade. Histogram Distance based DFL (HD-DFL) techniques that operate by constructing RSSI histograms are highly effective as they can localize stationary and moving people in both outdoor and complex indoor environments. A key step in the histogram approaches is the estimation of the difference between the “long-term” and “short-term” histograms. Existing HD-DFL methods use either Kullback-Leibler or the subsequent improvement, Kernel distance, to measure this difference. This paper is the first known work to compare an extensive range of histogram distance metrics within a DFL context and demonstrate how a judicious selection of a distance metric can significantly increase the performance of an HD-DFL system. Results from practical implementation in two different environments show that some distance metrics perform considerably better than Kernel distance when used for existing DFL techniques like Radio Tomographic Imaging (RTI) and SpringLoc, with the overall median tracking error reducing by up to 25%.
Article
Comprehensive occupancy information in smart buildings has become more imperative in order to develop new control strategies in energy management systems. Several techniques can be used to collect occupancy information considering accurate sensing techniques, such as passive infrared (PIR), carbon dioxide (CO2) and different types of cameras (i.e., thermal, or optical cameras). Recent studies show the usefulness of integrating occupancy information into energy management systems to reduce energy consumption while maintaining the occupants’ comfort. The purpose of this work is to elaborate a comprehensive review on occupancy detection systems in smart buildings. This study presents a set of comparison standards including methods, occupancy resolution, type of buildings and sensors. A classification of different approaches, which can be implemented and integrated into the building management system for detecting indoor occupancy, is introduced. Summary and discussions are given by highlighting the usefulness of machine learning for enabling predictive control of active systems in smart buildings.
Article
This paper presents a novel approach for multimodal data fusion based on the Vector-Quantized Variational Autoencoder (VQVAE) architecture. The proposed method is simple yet effective in achieving excellent reconstruction performance on paired MNIST-SVHN data and WiFi spectrogram data. Additionally, the multimodal VQVAE model is extended to the 5G communication scenario, where an end-to-end Channel State Information (CSI) feedback system is implemented to compress data transmitted between the base-station (eNodeB) and User Equipment (UE), without significant loss of performance. The proposed model learns a discriminative compressed feature space for various types of input data (CSI, spectrograms, natural images, etc), making it a suitable solution for applications with limited computational resources.
Article
Wi-Fi sensing technology has shown superiority in smart homes among various sensors for its cost-effective and privacy-preserving merits. It is empowered by channel state information (CSI) extracted from Wi-Fi signals and advanced machine learning models to analyze motion patterns in CSI. Many learning-based models have been proposed for kinds of applications, but they severely suffer from environmental dependency. Though domain adaptation methods have been proposed to tackle this issue, it is not practical to collect high-quality, well-segmented, and balanced CSI samples in a new environment for adaptation algorithms, but randomly captured CSI samples can be easily collected. In this article, we first explore how to learn a robust model from these low-quality CSI samples, and propose AutoFi, an annotation-efficient Wi-Fi sensing model based on a novel geometric self-supervised learning algorithm. The AutoFi fully utilizes unlabeled low-quality CSI samples that are captured randomly, and then transfers the knowledge to specific tasks defined by users, which is the first work to achieve cross-task transfer in Wi-Fi sensing. The AutoFi is implemented on a pair of Atheros Wi-Fi APs for evaluation. The AutoFi transfers knowledge from randomly collected CSI samples into human gait recognition and achieves state-of-the-art performance. Furthermore, we simulate cross-task transfer using public data sets to further demonstrate its capacity for cross-task learning. For the UT-HAR and Widar data sets, the AutoFi achieves satisfactory results on activity recognition and gesture recognition without any prior training. We believe that AutoFi takes a huge step toward automatic Wi-Fi sensing without any developer engagement. Our codes have been included in https://github.com/xyanchen/Wi-Fi-CSI-Sensing-Benchmark .
Article
Device-free activity recognition plays a crucial role in smart building, security, and human–computer interaction, which shows its strength in its convenience and cost-efficiency. Traditional machine learning has made significant progress by heuristic hand-crafted features and statistical models, but it suffers from the limitation of manual feature design. Deep learning overcomes such issues by automatic high-level feature extraction, but its performance degrades due to the requirement of massive annotated data and cross-site issues. To deal with these problems, transfer learning helps to transfer knowledge from existing datasets while dealing with the negative effect of background dynamics. This paper surveys the recent progress of deep learning and transfer learning for device-free activity recognition. We begin with the motivation of deep learning and transfer learning, and then introduce the major sensor modalities. Then the deep and transfer learning techniques for device-free human activity recognition are introduced. Eventually, insights on existing works and grand challenges are summarized and presented to promote future research.
Article
As an important biomarker for human identification, human gait can be collected at a distance by passive sensors without subject cooperation, which plays an essential role in crime prevention, security detection and other human identification applications. At present, most research works are based on cameras and computer vision techniques to perform gait recognition. However, vision-based methods are not reliable when confronting poor illuminations, leading to degrading performances. In this paper, we propose a novel multimodal gait recognition method, namely GaitFi, which leverages WiFi signals and videos for human identification. In GaitFi, Channel State Information (CSI) that reflects the multi-path propagation of WiFi is collected to capture human gaits, while videos are captured by cameras. To learn robust gait information, we propose a Lightweight Residual Convolution Network (LRCN) as the backbone network, and further propose the two-stream GaitFi by integrating WiFi and vision features for the gait retrieval task. The GaitFi is trained by the triplet loss and classification loss on different levels of features. Extensive experiments are conducted in the real world, which demonstrates that the GaitFi outperforms state-of-the-art gait recognition methods based on single WiFi or camera, achieving 94.2% for human identification tasks of 12 subjects.
Article
Existing channel-state information (CSI)-based human authentication systems in the literature require a large amount of CSI data to train deep neural network (DNN) models and are ineffective for unknown intruder detection. To address this issue, we propose a CSI-based human authentication system (CAUTION) which is able to learn distinctive gait features of different users through CSI data to perform human authentication in this article. By taking advantage of few-shot learning, CAUTION is able to construct an accurate user identification model with a very limited number of CSI training data. By converting the CSI samples into low-dimensional representations on the feature plane, it computes central points for different users as their CSI profiles and introduces an intruder threshold to measure whether the CSI data matches one of the user classes by a margin. The intruder threshold is able to be optimized without any intruders’ data. CAUTION does not require a large number of training data and provides an effective way to train the system for unknown intruder detection. We have tested CAUTION at different places and compared it with state-of-the-art CSI-based authentication systems. The experimental results demonstrate that CAUTION is able to perform accurate human authentication with a limited amount of CSI training data (one-fifth of data needed by compared systems) and outperforms the compared human authentication systems.
Article
WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access. Recently, besides network services, WiFi sensing is appealing in smart homes since it is device-free, cost-effective and privacy-preserving. Though numerous WiFi sensing methods have been developed, most of them only consider single smart home scenario. Without the connection of powerful cloud server and massive users, large-scale WiFi sensing is still difficult. In this paper, we firstly analyze and summarize these obstacles, and propose an efficient large-scale WiFi sensing framework, namely EfficientFi. The EfficientFi works with edge computing at WiFi APs and cloud computing at center servers. It consists of a novel deep neural network that can compress fine-grained WiFi Channel State Information (CSI) at edge, restore CSI at cloud, and perform sensing tasks simultaneously. A quantized auto-encoder and a joint classifier are designed to achieve these goals in an end-to-end fashion. To the best of our knowledge, the EfficientFi is the first IoT-cloud-enabled WiFi sensing framework that significantly reduces communication overhead while realizing sensing tasks accurately. We utilized human activity recognition and identification via WiFi sensing as two case studies, and conduct extensive experiments to evaluate the EfficientFi. The results show that it compresses CSI data from 1.368Mb/s to 0.768Kb/s with extremely low error of data reconstruction and achieves over 98% accuracy for human activity recognition.
Article
Full-text available
Electricity usage of buildings (including offices, malls, and residential apartments) represents a significant portion of a nation's energy expenditure and carbon footprint. In the United States, the buildings' appliances consume 72% of the total produced electricity approximately. In this regard, cyber-physical system (CPS) researchers have put forth associated research questions to reduce cyber-physical building environment energy consumption by minimizing the energy dissipation while securing occupants' comfort. Some of the questions in CPS building include finding the optimal HVAC control, monitoring appliances' energy usage, detecting insulation problems, estimating the occupants' number and activities, managing thermal comfort, intelligently interacting with the smart grid. Various machine learning (ML) applications have been studied in recent CPS researches to improve building energy efficiency by addressing these questions. In this paper, we comprehensively review and report on the contemporary applications of ML algorithms such as deep learning, transfer learning, active learning, reinforcement learning, and other emerging techniques that propose and envision to address the above challenges in the CPS building environment. Finally, we conclude this article by discussing diverse existing open questions and prospective future directions in the CPS building environment research. This article is categorized under: • Technologies > Machine Learning • Technologies > Reinforcement Learning Abstract Content and scope of this paper.
Article
This article explores the use of ambient radio frequency (RF) signals for human presence detection through deep learning. Using Wi-Fi signal as an example, we demonstrate that the channel state information (CSI) obtained at the receiver contains rich information about the propagation environment. Through judicious preprocessing of the estimated CSI followed by deep learning, reliable presence detection can be achieved. Several challenges in passive RF sensing are addressed. With presence detection, how to collect training data with human presence can have a significant impact on the performance. This is in contrast to activity detection when a specific motion pattern is of interest. A second challenge is that RF signals are complex-valued. Handling complex-valued input in deep learning requires careful data representation and network architecture design. Finally, human presence affects CSI variation along multiple dimensions; such variation, however, is often masked by system impediments, such as timing or frequency offset. Addressing these challenges, the proposed learning system uses preprocessing to preserve human motion-induced channel variation while insulating against other impairments. A convolutional neural network (CNN) properly trained with both magnitude and phase information is then designed to achieve reliable presence detection. Extensive experiments are conducted. Using off-the-shelf Wi-Fi devices, the proposed deep-learning-based RF sensing achieves near-perfect presence detection during multiple extended periods of test and exhibits superior performance compared with leading edge passive infrared sensors. A comparison with existing RF-based human presence detection also demonstrates its robustness in performance, especially when deployed in a completely new environment. The learning-based passive RF sensing thus provides a viable and promising alternative for presence or occupancy detection.
Article
Human mobility information is widely needed by many sectors in smart cities. This work designs lightweight algorithms to perform stop detection, passenger flow tracking, and passenger estimation in an automated train. The on-board learning and detection algorithms are running on an edge node that is integrated with Wi-Fi sniffing technology, a GPS sensor, and an IMU sensor. The stop detection algorithm determines if the automated train is static at which train station based on GPS and IMU data. When the train is moving, the correlations between statistical properties extracted from Wi-Fi probes and the actual number of passengers change. The passenger flow tracking algorithm analyzes the number of incoming and outgoing passengers in the train. The passenger estimation algorithm approximates the number of passengers inside the train based on a multidimensional regression model created by statistical properties extracted from different device brands. The prototype is deployed in an automated train to conduct real-world experiments. The experimental results indicate that the passenger flow tracking algorithm reduces the average errors of 62.5% and 70% compared against two clustering algorithms. Compared with two counting-based approaches, the passenger estimation algorithm results in lower errors with a mean of 3.15 and a variance of 9.29.
Article
Full-text available
In the era of the Internet of Things (IoT), billions of smart devices connect, interact, and exchange data with each other. As “things" get connected together, intelligent systems and technologies have been developed to exploit the rich information in the collected data, perceive what is happening in the surroundings, and finally take actions to maximize their own utility. Thanks to the ubiquitous wireless signals and the prevalence of wireless devices, wireless sensing becomes more popular among the various approaches that have been adopted in the IoT to measure the surrounding environment. Because human activities interact with wireless signals and introduce distinct patterns to the propagation, analyzing how wireless channel state information (CSI) responds to human activities enables many IoT applications. Recently, radio analytics has been proposed as a promising technique that exploits multipath as virtual antennas, extracts various features from wireless signals, and reveals rich environmental information. As automobiles continue to play an important role nowadays, manufacturers have been seeking emerging techniques for IoT applications that support drivers and enhance safety. The interior of an automobile can be viewed as a special indoor environment where most of the multipaths are restricted inside by the metal exterior. In this article, we introduce the concept of wireless artificial intelligence (AI) and demonstrate its concept in a smart car scenario where information about drivers and passengers is collected by commercial Wi-Fi devices deployed in the car. The proposed wireless AI system is capable of identifying authorized drivers based on radio biometric information. Vital signals of human introduce periodic patterns to the wireless CSI. By extracting the vital sign from wireless signals, the proposed wireless AI system can monitor the driver’s state, count number of people in the car, and detect a child left in an unattended car.
Conference Paper
Full-text available
More than half of the commercial building stock in the United States was built before 1980 prior to the increased focus on energy efficiency. In the current age of Smart and Green buildings, owners incorporating expensive sensor infrastructure to reduce building energy consumption and improve the building occupants' satisfaction, efficiency, and comfort levels. The success of these automated building systems is influenced by the ability to estimate building occupancy. Recently, researchers shifted their focus towards exploring different occupancy estimation techniques with both dedicated sensors and existing infrastructure (e.g. CO2 sensors, Smart meters, temperature and humidity sensors, and wi-fi networks). However, there are concerns about the cost effectiveness, computational effort, accuracy and privacy protection for these techniques. This study explores the usage wi-fi router data to generate the of number of IP addresses connected to the router to estimate the occupancy within a building. To this end, occupancy patterns in a thirty-year-old university building are estimated using existing wi-fi infrastructure and compared and calibrated to ground data obtained manually and from dedicated occupancy estimating sensors to evaluate the accuracy. The estimated occupancy data patterns using existing wi-fi network represent a cost-effective method of occupancy estimation with less computational processing and reduced privacy concerns, that could assist owners in the decision-making process towards investing into smart and energy efficient technologies.
Article
Full-text available
Commercial and residential buildings consume about 27% of total energy used in the US, out of which nearly half is consumed by commercial building sector and it expected to grow in the next 30-year period. Literature suggests that occupancy data may improve the energy consumption of the buildings, especially in HVAC operation. In the past few years studies came up with various frameworks based on existing infrastructure to estimate occupancy, out of which commodity WiFi gained popularity in detecting, estimating, and tracking occupants within buildings. However, there are concerns with those frameworks such as added infrastructure and computational efforts, upgrades to existing infrastructure, and privacy of occupants. This paper presents a simplistic framework based on commodity WiFi to estimate real time occupancy data without any added infrastructure or upgrades, while protecting the occupant privacy and can produce significant energy reduction in HVAC operation. The framework is tested on a large lecture hall in an institutional building that has multiple classes scheduled. The initial tests showed that the WiFi based occupancy had a 0.96 correlation with the established ground truth. Additionally, the WiFi based occupancy schedule resulted in at least 50% savings in HVAC energy consumption over static schedule.
Conference Paper
Commercial and residential buildings consume about 27% of total energy used in the US, out of which nearly half is consumed by commercial building sector and it expected to grow in the next 30-year period. Literature suggests that occupancy data may improve the energy consumption of the buildings, especially in HVAC operation. In the past few years studies came up with various frameworks based on existing infrastructure to estimate occupancy, out of which commodity WiFi gained popularity in detecting, estimating, and tracking occupants within buildings. However, there are concerns with those frameworks such as added infrastructure and computational efforts, upgrades to existing infrastructure, and privacy of occupants. This paper presents a simplistic framework based on commodity WiFi to estimate real time occupancy data without any added infrastructure or upgrades, while protecting the occupant privacy and can produce significant energy reduction in HVAC operation. The framework is tested on a large lecture hall in an institutional building that has multiple classes scheduled. The initial tests showed that the WiFi based occupancy had a 0.96 correlation with the established ground truth. Additionally, the WiFi based occupancy schedule resulted in at least 50% savings in HVAC energy consumption over static schedule.
Conference Paper
Full-text available
Blood glucose concentration plays an important role in personal health. Hyperglycemia results in diabetes, leading to health risks such as pancreatic function failure, immunity reduce and ocular fundus diseases [6]. Meanwhile, hypoglycemia also brings complications such as confusion, shakiness, anxiety, and if not treated in time, coma or death [2]. People with diabetes need tight control of their blood glucose concentration to avoid both short-term and long-term physiological complications. In this work, we design BGMonitor, the first personalized smartphone-based non-invasive blood glucose monitoring system that detects abnormal blood glucose events by jointly tracking meal, drugs and insulin intake, physical activity and sleep quality. When BGMonitor detects an abnormal blood glucose event, it reminds the user to double-check by finger pricking or using clinical CGM devices.
Article
Full-text available
Experiments show that operation efficiency and reliability of buildings can greatly benefit from rich and relevant datasets. More specifically, data can be analyzed to detect and diagnose system and component failures that undermine energy efficiency. Among the huge quantity of information, some features are more correlated with the failures than others. However there has been little research to date focusing on determining the types of data that can optimally support Fault Detection and Diagnosis (FDD). This paper presents a novel optimal feature selection method, named Information Greedy Feature Filter (IGFF), to select essential features that benefit building FDD. On one hand, the selection results can serve as reference for configuring sensors in the data collection stage, especially when the measurement resource is limited. On the other hand, with the most informative features selected by IGFF, the performance of building FDD could be improved and theoretically justified. A case study on Air Handling Unit (AHU) is conducted based on the dataset of the ASHRAE Research Project 1312. Numerical results show that, compared with several baselines, the FDD performances of conventional classification methods are greatly enhanced by IGFF.
Conference Paper
Full-text available
Power system has been incorporating increasing amount of unconventional generations and loads such as renewable resources, electric vehicles, and controllable loads. The induced short term and stochastic power flow requires high resolution monitoring technology and agile decision support techniques for system diagnosis and control. In this paper, we discuss the application of micro-phasor measurement unit (μPMU) for power distribution network monitoring, and study learning based data-driven methods for abnormal event detection. We first resolve the challenging problem of information representation for the multiple streams of high resolution μPMU data, by proposing a pooling-picking scheme. With that, a kernel Principle Component Analysis (kPCA) is adopted to build statistical models for nominal state and detect possible anomalies. To distinguish event types, we propose a novel discriminative method that only requires partial expert knowledge for training. Finally, our methods are tested on an actual distribution network with μPMUs, and the results justifies the effectiveness of the data driven event detection framework, as well as its potentials to serve as one of the core algorithms to ensure power system security and reliability.
Conference Paper
Full-text available
Device-free localization without any device attached to the target is playing a critical role in many emerging applications. This paper presents an accurate model-based device-free localization system LiFS, implemented on cheap commercial off-the-shelf Wi-Fi devices. Unlike previous work, LiFS is able to localize a target accurately without offline training. The basic idea is simple: channel state information (CSI) is sensitive to a target's location and by modelling the CSI measurements of multiple wireless links as a set of power fading based equations, the target location can be determined. However, due to rich multipaths indoors, the received signal strength (RSS) or even the fine-grained CSI can not be easily modelled. We observe that even in a rich multipath environment, not all subcarriers are affected equally by multipaths. Our novel pre-processing scheme tries to identify the subcarriers not affected by multipath. Thus, CSIs on the identified ``clean'' subcarriers can be input into the proposed model for localization. We design, implement and evaluate LiFS with extensive experiments in three different scenes. Without knowing the majority transceivers' locations, LiFS achieves a median accuracy of 0.5~m and 1.1~m in Line-of-Sight and Non-Line-of-Sight scenarios respectively, outperforming the state-of-the-art systems. Besides single target localization, LiFS is able to differentiate two sparsely-located targets and localize each of them at a high accuracy.
Conference Paper
Full-text available
We propose Veto-Consensus Multiple Kernel Learning (VCMKL), a novel way of combining multiple kernels such that one class of samples is described by the logical intersection (consensus) of base kernelized decision rules, whereas the other classes by the union (veto) of their complements. The proposed configuration is a natural fit for domain description and learning with hidden subgroups. We first provide generalization risk bound in terms of the Rademacher complexity of the classifier, and then a large margin multi-ν learning objective with tunable training error bound is formulated. Seeing that the corresponding optimization is non-convex and existing methods severely suffer from local minima, we establish a new algorithm, namely Parametric Dual Descent Procedure (PDDP) that can approach global optimum with guarantees. The bases of PDDP are two theorems that reveal the global convexity and local explicitness of the parameterized dual optimum, for which a series of new techniques for parametric program have been developed. The proposed method is evaluated on extensive set of experiments, and the results show significant improvement over the state-of-the-art approaches.
Conference Paper
Full-text available
Recently diverse variations of large margin learning formalism have been proposed to improve the flexibility and the performance of classic discriminative models such as SVM. However, extra difficulties do arise in optimizing non-convex learning objectives and selecting multiple hyperparameters. Observing that many variations of large margin learning could be reformulated as jointly minimizing a parameterized quadratic objective, in this paper we propose a novel optimization framework, namely Parametric Dual sub-Gradient Descent Procedure (PDGDP), that produces a globally optimal training algorithm and an efficient model selection algorithm for two classes of large margin learning variations. The theoretical bases are a series of new results for parametric program, which characterize the unique local and global structure of the dual optimum. The proposed algorithms are evaluated on two representative applications, i.e., the training of latent SVM and the model selection of cost sensitive feature re-scaling SVM. The results show that PDGDP based training and model selection achieves significant improvement over the state-of-the-art approaches.
Article
Full-text available
The location and contextual status (indoor or outdoor) is fundamental and critical information for upper-layer applications, such as activity recognition and location-based services (LBS) for individuals. In addition, optimizations of building management systems (BMS), such as the pre-cooling or heating process of the air-conditioning system according to the human traffic entering or exiting a building, can utilize the information, as well. The emerging mobile devices, which are equipped with various sensors, become a feasible and flexible platform to perform indoor-outdoor (IO) detection. However, power-hungry sensors, such as GPS and WiFi, should be used with caution due to the constrained battery storage on mobile device. We propose BlueDetect: an accurate, fast response and energy-efficient scheme for IO detection and seamless LBS running on the mobile device based on the emerging low-power iBeacon technology. By~leveraging the on-broad Bluetooth module and our proposed algorithms, BlueDetect provides a precise IO detection service that can turn on/off on-board power-hungry sensors smartly and automatically, optimize their performances and reduce the power consumption of mobile devices simultaneously. Moreover, seamless positioning and navigation services can be realized by it, especially in a semi-outdoor environment, which cannot be achieved by GPS or an indoor positioning system (IPS) easily. We~prototype BlueDetect on Android mobile devices and evaluate its performance comprehensively. The~experimental results have validated the superiority of BlueDetect in terms of IO detection accuracy, localization accuracy and energy consumption.
Article
Full-text available
Sleep quality plays a significant role in personal health. A great deal of effort has been paid to design sleep quality monitoring systems, providing services ranging from bedtime monitoring to sleep activity detection. However, as sleep quality is closely related to the distribution of sleep duration over different sleep stages, neither the bedtime nor the intensity of sleep activities is able to reflect sleep quality precisely. To this end, we present Sleep Hunter, a mobile service that provides a fine-grained detection of sleep stage transition for sleep quality monitoring and intelligent wake-up call. The rationale is that each sleep stage is accompanied by specific yet distinguishable body movements and acoustic signals. Leveraging the built-in sensors on smartphones, Sleep Hunter integrates these physical activities with sleep environment, inherent temporal relation and personal factors by a statistical model for a fine-grained sleep stage detection. Based on the duration of each sleep stage, Sleep Hunter further provides sleep quality report and smart call service for users. Experimental results from over 30 sets of nocturnal sleep data show that our system is superior to existing actigraphy-based sleep quality monitoring systems, and achieves satisfying detection accuracy compared with dedicated polysomnography-based devices. Copyright
Article
Full-text available
Indoor Positioning System (IPS) has become one of the most attractive research fields due to the increasing demands on Location Based Services (LBSs) in indoor environments. Various IPSs have been developed under different circumstances, and most of them adopt the fingerprinting technique to mitigate pervasive indoor multipath effects. However, the performance of the fingerprinting technique severely suffers from device heterogeneity existing across commercial off-the-shelf mobile devices (e.g. smart phones, tablet computers, etc.) and indoor environmental changes (e.g. the number, distribution and activities of people, the placement of furniture, etc.). In this paper, we transform the Received Signal Strength (RSS) to a standardized location fingerprint based on the Procrustes analysis, and introduce a similarity metric, termed Signal Tendency Index (STI), for matching standardized fingerprints. An analysis on the capability of the proposed STI in handling device heterogeneity and environmental changes is presented. We further develop a robust and precise IPS by integrating the merits of both the STI and Weighted Extreme Learning Machine (WELM). Finally, extensive experiments are carried out and a performance comparison with existing solutions verifies the superiority of the proposed IPS in terms of robustness to device heterogeneity.
Article
Full-text available
Non-invasive human sensing based on radio signals has attracted numerous research interests and fostered a broad range of innovative applications of localization, gesture recognition, smart health-care, etc, for which a primary primitive is to detect human presence. Previous works have studied to detect moving humans via signal variations caused by human movements. For stationary people, however, existing approaches often employ a prerequisite scenario-tailored calibration of channel profile in human-free environments. Based on in-depth understanding of human motion induced signal attenuation reflected by PHY layer channel state information (CSI), we propose DeMan, a unified scheme for non-invasive detection of moving and stationary human on commodity WiFi devices. DeMan takes advantages of both amplitude and phase information of CSI to detect moving targets. In addition, DeMan considers human breathing as an intrinsic indicator of stationary human presence and adopts sophisticated mechanisms to detect particular signal patterns caused by minute chest motions, which could be destroyed by significant whole-body motion or hidden by environmental noises. By doing this, DeMan is capable of simultaneously detecting moving and stationary people with only a small number of prior measurements for model parameter determination, yet without the cumbersome scenario-specific calibration. Extensive experimental evaluation in typical indoor environments validates the great performance of DeMan in case of various human poses and locations and diverse channel conditions. Particularly, DeMan provides detection rate of around 95% for both moving and stationary people, while identifies human-free scenarios by 96%, all of which outperforms existing methods by about 30%.
Article
Full-text available
The increasing demands of location-based services have spurred the rapid development of indoor positioning system and indoor localization system interchangeably (IPSs). However, the performance of IPSs suffers from noisy measurements. In this paper, two kinds of robust extreme learning machines (RELMs), corresponding to the close-to-mean constraint, and the small-residual constraint, have been proposed to address the issue of noisy measurements in IPSs. Based on whether the feature mapping in extreme learning machine is explicit, we respectively provide random-hidden-nodes and kernelized formulations of RELMs by second order cone programming. Furthermore, the computation of the covariance in feature space is discussed. Simulations and real-world indoor localization experiments are extensively carried out and the results demonstrate that the proposed algorithms can not only improve the accuracy and repeatability, but also reduce the deviation and worst case error of IPSs compared with other baseline algorithms.
Conference Paper
Full-text available
We present the results, experiences and lessons learned from comparing a diverse set of technical approaches to indoor localization during the 2014 Microsoft Indoor Localization Competition. 22 different solutions to indoor localization from different teams around the world were put to test in the same unfamiliar space over the course of 2 days, allowing us to directly compare the accuracy and overhead of various technologies. In this paper, we provide a detailed analysis of the evaluation study's results, discuss the current state-of-the-art in indoor localization, and highlight the areas that, based on our experience from organizing this event, need to be improved to enable the adoption of indoor location services.
Article
Full-text available
Nowadays, developing indoor positioning systems (IPSs) has become an attractive research topic due to the increasing demands on location-based service (LBS) in indoor environments. WiFi technology has been studied and explored to provide indoor positioning service for years in view of the wide deployment and availability of existing WiFi infrastructures in indoor environments. A large body of WiFi-based IPSs adopt fingerprinting approaches for localization. However, these IPSs suffer from two major problems: the intensive costs of manpower and time for offline site survey and the inflexibility to environmental dynamics. In this paper, we propose an indoor localization algorithm based on an online sequential extreme learning machine (OS-ELM) to address the above problems accordingly. The fast learning speed of OS-ELM can reduce the time and manpower costs for the offline site survey. Meanwhile, its online sequential learning ability enables the proposed localization algorithm to adapt in a timely manner to environmental dynamics. Experiments under specific environmental changes, such as variations of occupancy distribution and events of opening or closing of doors, are conducted to evaluate the performance of OS-ELM. The simulation and experimental results show that the proposed localization algorithm can provide higher localization accuracy than traditional approaches, due to its fast adaptation to various environmental dynamics.
Article
Full-text available
Location-based services (LBS) have attracted a great deal of attention recently. Outdoor localization can be solved by the GPS technique, but how to accurately and efficiently localize pedestrians in indoor environments is still a challenging problem. Recent techniques based on WiFi or pedestrian dead reckoning (PDR) have several limiting problems, such as the variation of WiFi signals and the drift of PDR. An auxiliary tool for indoor localization is landmarks, which can be easily identified based on specific sensor patterns in the environment, and this will be exploited in our proposed approach. In this work, we propose a sensor fusion framework for combining WiFi, PDR and landmarks. Since the whole system is running on a smartphone, which is resource limited, we formulate the sensor fusion problem in a linear perspective, then a Kalman filter is applied instead of a particle filter, which is widely used in the literature. Furthermore, novel techniques to enhance the accuracy of individual approaches are adopted. In the experiments, an Android app is developed for real-time indoor localization and navigation. A comparison has been made between our proposed approach and individual approaches. The results show significant improvement using our proposed framework. Our proposed system can provide an average localization accuracy of 1 m.
Article
Full-text available
In recent years, developing Indoor Positioning System (IPS) has become an attractive research topic due to the increasing demands on Location-Based Service (LBS) in indoor environment. Several advantages of Radio Frequency Identification (RFID) Technology, such as anti-interference, small, light and portable size of RFID tags, and its unique identification of different objects, make it superior to other wireless communication technologies for indoor positioning. However, certain drawbacks of existing RFID-based IPSs, such as high cost of RFID readers and active tags, as well as heavy dependence on the density of reference tags to provide the LBS, largely limit the application of RFID-based IPS. In order to overcome these drawbacks, we develop a cost-efficient RFID-based IPS by using cheaper active RFID tags and sensors. Furthermore, we also proposed three localization algorithms: Weighted Path Loss (WPL), Extreme Learning Machine (ELM) and integrated WPL-ELM. WPL is a centralized model-based approach which does not require any reference tags and provides accurate location estimation of the target effectively. ELM is a machine learning fingerprinting-based localization algorithm which can provide higher localization accuracy than other existing fingerprinting-based approaches. The integrated WPL-ELM approach combines the fast estimation of WPL and the high localization accuracy of ELM. Based on the experimental results, this integrated approach provides a higher localization efficiency and accuracy than existing approaches, e.g., the LANDMARC approach and the support vector machine for regression (SVR) approach.
Conference Paper
Full-text available
Developing Indoor Positioning System (IPS) has become an attractive research topic due to the increasing demands on Location Based Service (LBS) in indoor environment recently. WiFi technology has been studied and explored to provide indoor positioning service for years since existing WiFi infrastructures in indoor environment can be used to greatly reduce the deployment costs. A large body of WiFi based IPSs adopt the fingerprinting approach as the localization algorithm. However, these WiFi based IPSs suffer from two major problems: the intensive costs on manpower and time for offline site survey and the inflexibility to environmental dynamics. In this paper, we propose an indoor localization algorithm based on online sequential extreme learning machine (OS-ELM) to address these problems accordingly. The fast learning speed of OS-ELM can reduce the time and manpower costs for the offline site survey, and more importantly, its online sequential learning ability enables the proposed localization algorithm to automatically and timely adapt to the environmental dynamics. The experimental results show that the proposed localization algorithm can provide higher localization accuracy than traditional approaches due to its fast adaptation to various environmental changes.
Article
Full-text available
We present results from a set of experiments in this pilot study to investigate the causal influence of user activity on various environmental parameters monitored by occupant carried multi-purpose sensors. Hypotheses with respect to each type of measurements are verified, including temperature, humidity, and light level collected during eight typical activities: sitting in lab / cubicle, indoor walking / running, resting after physical activity, climbing stairs, taking elevators, and outdoor walking. Our main contribution is the development of features for activity and location recognition based on environmental measurements, which exploit location- and activity-specific characteristics and capture the trends resulted from the underlying physiological process. The features are statistically shown to have good separability and are also information-rich. Fusing environmental sensing together with acceleration is shown to achieve classification accuracy as high as 99.13%. For building applications, this study motivates a sensor fusion paradigm for learning individualized activity, location, and environmental preferences for energy management and user comfort.
Conference Paper
Full-text available
Buildings are known to be the largest consumers of electricity in the United States, and often times the dominant energy consumer is the HVAC system. Despite this fact, in most buildings the HVAC system is run using primitive static control algorithms based on fixed work schedules causing wasted energy during periods of low occupancy. In this paper we present a novel control architecture that uses occupancy sensing to guide the operation of a building HVAC system. We show how we can enable aggressive duty-cycling of building HVAC systems - that is, turn them ON or OFF - to save energy while meeting building performance requirements using inexpensive sensing and control methods. We have deployed our occupancy sensor network across an entire floor of a university building and our data shows several periods of low occupancy with significant opportunities to save energy over normal HVAC schedules. Furthermore, by interfacing with the building Energy Management System (EMS) directly and using real-time occupancy data collected by our occupancy nodes, we measure electrical energy savings of 9.54% to 15.73% and thermal energy savings of 7.59% to 12.85% for the HVAC system by controlling just one floor of our four floor building.
Article
Full-text available
We are pleased to announce the release of a tool that records detailed measurements of the wireless channel along with received 802.11 packet traces. It runs on a commodity 802.11n NIC, and records Channel State Information (CSI) based on the 802.11 standard. Unlike Receive Signal Strength Indicator (RSSI) values, which merely capture the total power received at the listener, the CSI contains information about the channel between sender and receiver at the level of individual data subcarriers, for each pair of transmit and receive antennas. Our toolkit uses the Intel WiFi Link 5300 wireless NIC with 3 antennas. It works on up-to-date Linux operating systems: in our testbed we use Ubuntu 10.04 LTS with the 2.6.36 kernel. The measurement setup comprises our customized versions of Intel's close-source firmware and open-source iwlwifi wireless driver, userspace tools to enable these measurements, access point functionality for controlling both ends of the link, and Matlab (or Octave) scripts for data analysis. We are releasing the binary of the modified firmware, and the source code to all the other components.
Article
We consider a class of non-convex learning problems that can be formulated as jointly optimizing regularized hinge loss and a set of auxiliary variables. Such problems encompass but are not limited to various versions of semi-supervised learning,learning with hidden structures, robust learning, etc. Existing methods either suffer from local minima or have to invoke anon-scalable combinatorial search. In this paper, we propose a novel learning procedure, namely Parametric Dual Maximization(PDM), that can approach global optimality efficiently with user specified approximation levels. The building blocks of PDM are two new results: (1) The equivalent convex maximization reformulation derived by parametric analysis.(2) The improvement of local solutions based on a necessary and sufficient condition for global optimality. Experimental results on two representative applications demonstrate the effectiveness of PDM compared to other approaches.
Article
Occupancy detection for buildings is crucial to improving energy efficiency, user comfort, and space utility. However, existing methods require dedicated system setup, continuous calibration, and frequent maintenance. With the instrumentation of electricity meters in millions of homes and offices, however, power measurement presents a unique opportunity for a non-intrusive and cost-effective way to detect occupant presence. This study develops solutions to the problems when no data or limited data is available for training, as motivated by difficulties in ground truth collection. Experimental evaluations on data from both residential and commercial buildings indicate that the proposed methods for binary occupancy detection are nearly as accurate as models learned with sufficient data, with accuracies of approximately 78 to 93% for residences and 90% for offices. This study shows that power usage contains valuable and sensitive user information, demonstrating a virtual occupancy sensing approach with minimal system calibration and setup.
Article
The power system has been incorporating increasing amount of unconventional generations and loads, such as distributed renewable resources, electric vehicles, and controllable loads. The induced dynamic and stochastic power flow require high-resolution monitoring technology and agile decision support techniques for system diagnosis and control. This paper discusses the application of micro-phasor measurement unit (μPMU) data for power distribution network event detection. A novel data-driven event detection method, namely hidden structure semi-supervised machine (HS 3 M), is established. HS 3 M only requires partial expert knowledge: it combines unlabeled data and partly labeled data in a large margin learning objective to bridge the gap between supervised learning, semi-supervised learning, and learning with hidden structures. To optimize the non-convex learning objective, a novel global optimization algorithm, namely parametric dual optimization procedure, is established through its equivalence to a concave programming. Finally, the proposed method is validated on an actual distribution feeder with installed μPMUs, and the result justifies the effectiveness of the learning-based event detection framework, as well as its potential to serve as one of the core algorithms for power system security and reliability.
Conference Paper
Power delay profiles characterize multipath channel features, which are widely used in motion- or localization-based applications. Recent studies show that the power delay profile may be derived from the CSI traces collected from commodity WiFi devices, but the performance is limited by two dominating factors. The resolution of the derived power delay profile is determined by the channel bandwidth, which is however limited on commodity WiFi. The collected CSI reflects the signal distortions due to both the channel attenuation and the hardware imperfection. A direct derivation of power delay profiles using raw CSI measures, as has been done in the literature, results in significant inaccuracy. In this paper, we present Splicer, a software-based system that derives high-resolution power delay profiles by splicing the CSI measurements from multiple WiFi frequency bands. We propose a set of key techniques to separate the mixed hardware errors from the collected CSI measurements. Splicer adapts its computations within stringent channel coherence time and thus can perform well in presence of mobility. Our experiments with commodity WiFi NICs show that Splicer substantially improves the accuracy in profiling multipath characteristics, reducing the errors of multipath distance estimation to be less than 2m. Splicer can immediately benefit upper-layer applications. Our case study with recent single-AP localization achieves a median localization error of 0.95m.
Article
Heating, cooling and ventilation accounts for 35% energy usage in the United States. Currently,mostmodern buildings still condition rooms assuming maximum occupancy rather than actual usage. As a result, rooms are often over-conditioned needlessly. Thus, in order to achieve efficient conditioning, we require knowledge of occupancy. This article shows how real time occupancy data from a wireless sensor network can be used to create occupancy models, which in turn can be integrated into building conditioning system for usage-based demand control conditioning strategies. Using strategies based on sensor network occupancy model predictions, we show that it is possible to achieve 42% annual energy savings while still maintaining American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) comfort standards.
Conference Paper
Despite of several years of innovative research, indoor localization is still not mainstream. Existing techniques either employ cumbersome fingerprinting, or rely upon the deployment of additional infrastructure. Towards a solution that is easier to adopt, we propose CUPID, which is free from these restrictions, yet is comparable in accuracy. While existing WiFi based solutions are highly susceptible to indoor multipath, CUPID utilizes physical layer (PHY) information to extract the signal strength and the angle of only the direct path, successfully avoiding the effect of multipath reflections. Our main observation is that natural human mobility, when combined with PHY layer information, can help in accurately estimating the angle and distance of a mobile device from an wireless access point (AP). Real-world indoor experiments using off-the-shelf wireless chipsets confirm the feasibility of CUPID. In addition, while previous approaches rely on multiple APs, CUPID is able to localize a device when only a single AP is present. When a few more APs are available, CUPID can improve the median localization error to 2.7m, which is comparable to schemes that rely on expensive fingerprinting or additional infrastructure.
Statistical Learning for Sparse Sensing and Agile Operation
  • Y Zhou
Y. Zhou, Statistical Learning for Sparse Sensing and Agile Operation. PhD thesis, EECS Department, University of California, Berkeley, May 2017.
Intelligent sleep stage mining service with smartphones
  • W Gu
  • Z Yang
  • L Shangguan
  • W Sun
  • K Jin
  • Y Liu
W. Gu, Z. Yang, L. Shangguan, W. Sun, K. Jin, and Y. Liu, "Intelligent sleep stage mining service with smartphones," in Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 649-660, ACM, 2014.
Environmental sensing by wearable device for indoor activity and location estimation
  • M Jin
  • H Zou
  • K Weekly
  • R Jia
  • A M Bayen
  • C J Spanos
M. Jin, H. Zou, K. Weekly, R. Jia, A. M. Bayen, and C. J. Spanos, "Environmental sensing by wearable device for indoor activity and location estimation," in Industrial Electronics Society, IECON 2014-40th Annual Conference of the IEEE, pp. 5369-5375, IEEE, 2014.
From rssi to csi: Indoor localization via channel response
  • Z Yang
  • Z Zhou
  • Y Liu
Z. Yang, Z. Zhou, and Y. Liu, "From rssi to csi: Indoor localization via channel response," ACM Computing Surveys (CSUR), vol. 46, no. 2, p. 25, 2013.