No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
FreeDetector: Device-Free Occupancy Detection with Commodity WiFi
... 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. ...
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.
... Accurate human sensing is essential for context-awareness to improve the building management system (BMS) and design of impact building. It also plays an important role in many e-Healthcare applications, such as infant monitoring at room, elder monitoring at home, patient monitoring in hospital, and safety management in office [1]- [6]. Traditional approaches for indoor context-awareness include vision [7], RFID [8], environment sensors [9] and Passive Infra-Red (PIR) [10]. ...
... With the widely deployment of WiFi infrastructure in residential, commercial and industrial buildings, WiFi has become the primary resources for non-invasive human sensing [1,2,12,19]. There are a number of WiFi-based approach for context-awareness applications such as indoor localization [1,11], activity recognition [12], and writing recognition [13]. ...
... With the widely deployment of WiFi infrastructure in residential, commercial and industrial buildings, WiFi has become the primary resources for non-invasive human sensing [1,2,12,19]. There are a number of WiFi-based approach for context-awareness applications such as indoor localization [1,11], activity recognition [12], and writing recognition [13]. The basic principle behind WiFi sensing is to measure the variations of WiFi signal intrusive by human motion. ...
Human presence detection and activity event classification are of importance to a variety of context-awareness applications such as e-Healthcare, security and low impact building. However, existing Radio Frequency IDentification (RFID) tags, wearables and passive infrared (PIR) approaches require the user to carry dedicated electronic devices, suffer low detection accuracy and false alarm problems. This paper proposes a novel system for non-invasive human sensing by analyzing the Doppler information contained in the human reflections of WiFi signal. Doppler information is insensitive to the stationary objects, thus no requirement on scenario-specific calibration that makes it ideal for human sensing. We also introduce the time-frequency domain feature vectors of WiFi Doppler information for the Support Vector Machine (SVM) classifier towards activity event recognition. The proposed methodology is evaluated on a Software Defined Radio (SDR) system together with experiment of five different events. The results indicate that the proposed system is sufficient for indoor context-awareness with 95.3% overall accuracy for event classification and 93.3% accuracy for human presence detection, which outperforms the traditional Received Signal Strength (RSS)
approach 69.3% for event classification and 83.3% for human presence detection.
... The most comparable work to ours is the one recently published by Zou et al. [103], which uses modified COTS WiFi routers to observe changes in the channel state information (CSI). Aside from using electromagnetic signals (WiFi) in comparison to mechanical signals (ultrasound), the main differentiation from our work is that they observe the change in the CSI over frequency subcarriers by using OFDM packets. ...
... We compare the results of our proposed system to the work of Zou et al. [103]. In their work, they used two routers placed at 5 meters from each other. ...
As human beings, we rely on audible sounds as one way to communicate between each other and to infer information about our surrounding environment. Similarly, ultrasounds are used by some species in the animal kingdom to sense objects around them and get relevant information about their environment. In this thesis, we build on the inherent characteristics of ultrasounds and explore their application in occupancy sensing of indoor spaces, as ultrasounds exhibit interesting advantages compared to other technologies. Specifically, we design methods and algorithms to generate and process ultrasonic signals and infer the room occupancy, and we develop systems to evaluate their performance. Throughout the work, we address the implementation of our methods using commodity hardware, we pay attention to design algorithms that are computationally efficient, and we evaluate their time and space complexity. We focus on the reusability aspects in our designs, with the aim of bringing the technology to a wide range of existing and potential commercial devices, that would be able to implement our methods and algorithms seamlessly, and offer insights for new applications (like improving users' experience, enhancing home automation, etc.).
... 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. ...
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.
... Wearable sensors [3], [4] solve these problems to some extent but human being do not necessarily carry them in daily life. Recently, WiFi-based approaches [5], [6] are proposed based on the analysis of multi-path distortions in WiFi signals caused by human activities. They preserve user privacy and perform better robustness against vision-based and sensor-based method. ...
... where B y is the background sample for pixel y and the calculation of probability estimation can be achieved by Equation (5). Then the upper bound restriction of P N is able to eliminate some false detections by small motions. ...
... In this situation, by analyzing the historical activity patterns of each occupant captured by WinOSS, we could predict and infer their activities and then confirm with them through the interface to ensure correct occupancy information are obtained and feedback to BMS. WiFi-based device-free occupancy sensing system[54]can be integrated with WinOSS to compensate the performance when occupants forget to carry their MDs. Other special case is when one individual carries multiple MDs, such as one phone and one tablet, in buildings and WinOSS will assume that two occupants are detected. ...
Buildings accounted for half of global electricity consumption in recent years. Accurate occupancy information could improve the energy efficiency and reduce the energy consumption in built environments. Although prior studies have explored various sensing techniques for occupancy sensing, these solutions still suffer from serious drawbacks, e.g. their estimated occupancy information is coarse, extra infrastructure is required, and the privacy of occupants is exposed. In this paper, we present the design and implementation of a novel and practical occupancy sensing system, WinOSS, which is able to provide fine-grained occupancy information thoroughly by leveraging existing commodity WiFi infrastructure along with the WiFi-enabled mobile devices carried by occupants. We have implemented WinOSS in a 1500 m² built environment for four weeks to validate its performance. Extensive experimental results demonstrate that WinOSS outperforms existing occupancy sensing techniques, and provides comprehensive fine-grained occupancy information (including occupancy detection, counting and tracking) in an accurate, reliable, cost-effective and non-intrusive manner.
... The Channel State Information (CSI) metric has become a popular localization metric over RSSI as it is more immune to the adverse effects of multipath propagation [32] and outperforms RSSI based methods [33]. Since CSI offers more fine-grained information than RSSI, it has been extensively utilized in machine learning based DFL approaches including shapelet learning [34], SVM [9,35], Random Forest [36], HMM [37], and Deep Learning [38]. A shortcoming of CSI is that it is currently only accessible using modified drivers in legacy Intel 5300 [11,39], Atheros ath9k [12] based devices, or by using Software Defined Radio (SDR) platforms like USRP [40] or WARP [41]. ...
Device-free Localization (DFL) algorithms using the Received Signal Strength Indicator (RSSI) metric, have become a popular research focus in recent years as they allow for location-based service using Commercial-off-the-shelf (COTS) wireless equipment. However, most existing DFL approaches have limited applicability in realistic smart home environments as they typically require extensive offline calibration, large node densities or use technology that is not readily available in commercial smart homes. In this paper, we introduce SpringLoc, a DFL algorithm that relies on simple parameter tuning and does not require offline measurements. It localizes and tracks an entity using an adaptive spring relaxation approach. The anchor points of the artificial springs are placed in regions containing the links that are affected by the entity. The affected links are determined by comparing the kernel-based histogram distance of successive RSSI values. SpringLoc is benchmarked against existing algorithms in two diverse and realistic environments, showing significant improvement over the state-of-the-art, especially in situations with low node deployment density.
... The motivation for using SVM classifier was that it has been used in various previous baseline works. It would be interesting to measure the accuracy using other methods such as Extreme Learning Machine [36] which has lower training time, Random forest [37] which operates by constructing a multitude of decision trees at the training time. Artificial Neural Network [38] is another method which seems quite promising. ...
Wi-Fi based activity recognition serves a multitude of applications in fields such as smart homes, health care, and security. The property of the channel state information to provide fine-grained information has been utilized in the above-mentioned fields. However, we wanted to diversify the use of channel state information to even broader areas and that’s why used it to detect the water flow and differentiate between different water patterns. Given the huge scarcity of water in the current world our work tends to serve a practical purpose. The basic idea is to utilize the signal variation caused due to the water flow pattern. The static objects such as furniture, still human causes reflection of signal whereas dynamic or moving objects causes additional propagation paths. These additional propagation paths can be observed by measuring the channel state information amplitude between the two routers.
There have been a number of challenges on the way which needed to be figured out before we can get a satisfactory result. Some of them include removing the background noise from the CSI data collected, selecting a classifier which can accurately differentiate between the different patterns of the water flow. We performed various signal processing techniques to reduce the noise and to get a much better representation of the CSI waveform. The Multi-class SVM classifier was modeled and trained to predict the accuracy of different labels collected. Our model achieved 90.35 % accuracy in classifying different labels. Considering this as base work for the detection of water flow pattern, accuracy can be improved later on with some additional functionalities.
... 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]. ...
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%.
... 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. ...
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.
... RSSI-based methods, such as PAWS [8], WiSee [31], WiGest [32], are effective ways to detect human activity but the accuracy is not satisfactory due to the restriction of resolution of RSSI. CSI is more fine-grained that has been utilized for various applications such as occupancy detection [33], activity recognition [22], [23], [34], [35] (E-eyes, CARM, DeepSense and FALAR), sedentary behavior monitoring [36], falling detection [37] (WiFall), crowd counting [38], indoor localization [17], [39], [40] and person identification [41]- [43] These methods realize fine-grained recognition of human activity, but they are deficient in availability due to the lack of scalable platform. Our innovative CSI-enable IoT platform fills the gap and provide a chance to promote these applications for practical usage. ...
Intelligent occupancy sensing is becoming a vital underpinning for various emerging applications in smart homes, such as security surveillance and human behavior analysis. However, prevailing approaches mainly rely on video camera, ambient sensors or wearable devices, which either requires arduous deployment or arouses privacy concerns. In this paper, we present a novel real-time, device-free and privacy-preserving WiFi-enabled IoT platform for occupancy sensing, which can promote a myriad of emerging applications. It is designed to achieve an optimal tradeoff between performance and scalability. Our system empowers commercial off-the-shelf (COTS) WiFi routers to collect Channel State Information (CSI) measurements and provides an efficient cloud server for computing via a lightweight communication protocol. To demonstrate the usefulness of our platform, an occupancy detection system is developed by exploiting the CSI curve of human presence. Furthermore, we also design an innovative activity recognition system based on our platform and machine learning techniques with high availability and extensibility. In the evaluation, the experimental results show that our platform enables these applications efficiently, with the accuracy of 96.8% and 90.6% in terms of occupancy detection and recognition respectively.
... 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. ...
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.
... 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. ...
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.
... 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. ...
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.
... 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]. ...
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.
... 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]. ...
... 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. ...
Manuscript draft of a privacy-preserving system for detecting and predicting occupancy in a building, deployed in a real application
... This is different from other approaches which look at the WiFi signal's interactions with the surrounding area. In [14] the authors examine the channel state information between 2 WiFi routers to determine occupancy, while the authors in [15] off the shelf components and achieve similar results by using the Received Signal Strength (RSS) of the WiFi router. One can also probe the traffic or connect directly to the WiFi router itself to determine the number of number of active devices if privacy is ignored. ...
Presence and occupancy detection in residential and office environments is used to predict movement of people, detect intruders and manage electric power consumption. Specifically, we are developing methods to improve demand side electrical power management by reducing electrical power waste in unoccupied spaces. In this work we conduct an extensive analysis on the applicability of using a WiFi router’s electrical power consumption in different types of environments to determinate the number or people present in a space. We show the importance of a moving average filter for electrical load time series data, confirm the correlation between control packets and increased minimal router power consumption and present our results on the accuracy of our approach. We conclude that a WiFi router’s power consumption can improve presence detection in home environments and occupancy estimation in office environments, and where possible, should be analysed separately from the aggregated power consumption.
... 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]. ...
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.
... 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. ...
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.
... In a typical indoor environment, WiFi signals propagate through multiple paths from TX to RX due to reflection, scattering and diffraction introduced by walls, doors, furniture, as well as the presence and movements of occupants [13]. Nowadays, most of the COTS WiFi devices are equipped with multiple antennas for multiple input, multiple output (MIMO) communication and at the physical layer adopt OFDM that supports IEEE 802.11n/ac standard. ...
... In the future, we plan to include more riding behaviors and optimize the energy consumption of BikeMate. In addition, we consider to extend the capability of commodity WIFI device to tracking the user's riding behavior [33] and even group behiviors [17] of riders. Finally, we will investigate to utilize BikeMate on more types of bike-ways such as one-way bike-ways and single-lane bike-ways. ...
Detecting dangerous riding behaviors is of great importance toimprove bicycling safety. Existing bike safety precautionary mea-sures rely on dedicated infrastructures that incur high installationcosts. In this work, we propose BikeMate, a ubiquitous bicyclingbehavior monitoring system with smartphones. BikeMate invokessmartphone sensors to infer dangerous riding behaviors includ-ing lane weaving, standing pedalling and wrong-way riding. Foreasy adoption, BikeMate leverages transfer learning to reduce theoverhead of training models for different users, and applies crowd-sourcing to infer legal riding directions without prior knowledge.Experiments with 12 participants show that BikeMate achieves anoverall accuracy of 86.8% for lane weaving and standing pedallingdetection, and yields a detection accuracy of 90% for wrong-wayriding using crowdsourced GPS traces.
... 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. ...
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.
... Occupant's movements change the signal paths, affect the transmission channel and lead to high variation of CSI. [17] built a device-free occupancy detection system using CSI and achieve detection accuracy 94%. A CSI-based device-free crowd counting scheme has been proposed in [18]. ...
... 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. ...
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.
... In this case, we plan to analyze the historical activity patterns of each occupant captured by WinLight and identify which MD is the most frequently used personal device to present the occupant. WiFi-based device-free occupancy sensing system [82] can be integrated with WinLight to compensate the performance when occupants forget to carry their MDs. Other sensing modalities, such as PIR occupancy sensor or cameras, can be integrated with WinLight to ensure the correct occupancy information are obtained and feedback to BMS. ...
Artificial lighting accounts for a significant proportion (19%) of energy consumption in building environments. This large contribution calls for the creation of energy-efficient lighting control schemes. In this article, we present WinLight, a novel occupancy-driven lighting control system that aims to reduce energy consumption while simultaneously preserving the lighting comfort of occupants. By leveraging the fine-grained occupancy information estimated by existing WiFi infrastructure in a non-intrusive manner, WinLight computes an appropriate dimming command for each lamp based on a novel lighting control algorithm. A centralized lighting control system assigns these commands to a zonal gateway, and occupancy-driven lighting control is achieved by actuating the brightness adjustment with a local controller integrated within each lamp. Moreover, a WinLight App is designed to enable occupants to customize their luminance preferences and to control nearby lamps using their mobile devices. We implemented WinLight in a 1500 m2 multi-functional office in Singapore and conducted an experiment during 24 weeks. The experimental results demonstrate that WinLight achieves 93.09% and 80.27% energy savings compared to static scheduling lighting control scheme and PIR sensor based lighting control scheme while guaranteeing the personalized lighting comfort of each occupant.
Sedentary Behavior (SB) has been proved to be important risk factor for poor health, such as blood pressure and even cancer. However, existing sensor and vision-based SB detection approaches have limitations on practical usage and privacy concerns respectively. In this paper, we take the first attempt to develop a device-free SB monitoring and recommendation system namely CareFi, which leverages tremendous information behind WiFi signals to monitor the indoor environment and identify series of activities in SB. We deeply investigate the properties of channel state information and various activities in SB. According to different characteristics of static and dynamic activities, we design a foreground detection method to separate two categories and then adopt discriminative features of wireless signals in frequency and time domain to recognize them. Besides, we propose an update strategy to overcome the mutability of environment. We implement CareFi on Commercial The-Shelf (COTS) WiFi routers and evaluate its performance in both office and home environments. Experimental results demonstrate the robustness and accuracy of our method.
Detecting dangerous riding behaviors is of great importance to improve bicycling safety. Existing bike safety precautionary measures rely on dedicated infrastructures that incur high installation costs. In this work, we propose BikeMate, a ubiquitous bicycling behavior monitoring system with smartphones. BikeMate invokes smartphone sensors to infer dangerous riding behaviors including lane weaving, standing pedalling and wrong-way riding. For easy adoption, BikeMate leverages transfer learning to reduce the overhead of training models for different users, and applies crowdsourcing to infer legal riding directions without prior knowledge. Experiments with 12 participants show that BikeMate achieves an overall accuracy of 86.8% for lane weaving and standing pedalling detection, and yields a detection accuracy of 90% for wrong-way riding using crowdsourced GPS traces.
In the research of smart buildings, human activity recognition is an important cornerstone for numerous emerging applications. Although several sensing techniques have been proposed for human activity identification, they require either the user instrumentation or additional infrastructure, that are inconvenient, privacy-intrusive and expensive. To address these issues, a WiFi-enabled device-free human activity recognition system, namely SmartSense, is proposed in this paper. By upgrading commercial WiFi routers with our designed firmware, fine-grained Channel State Information (CSI) from PHY layer can be directly extracted from the existing WiFi traffic. In this paper, we propose SmartSense, a device-free human activity recognition system that only leverages existing commercial off-the-shelf (COTS) WiFi routers. By exploiting the prevalence of WiFi infrastructure in buildings, we developed a novel CSI-enabled Internet of things (IoT) platform to collect the CSI measurements from regular data frames. To identify different human activities, a novel machine learning tool, namely multiple kernel semi-representation learning (MKSRL) method is established. MKSRL allows the input of expert domain knowledge in a flexible way and conducts automatic and effective multi-kernel representation learning for the activity recognition task. Each stage of MKSRL is computationally efficient and theoretically guaranteed, and they can be integrated seamlessly within the reproducing kernel framework for the overall information extraction, representation, and fusion. We conducted experiments to comprehensively evaluate the performance of SmartSense in 3 common indoor environments. Experimental results validate that SmartSense can provide an activity recognition accuracy of 98%, which achieves significant performance gain over the existing methods.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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
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.
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%.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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 (PMU) data for power distribution network event detection. A novel datadriven 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 (PDOP), is established through its equivalence to a concave programming. Finally, the proposed method is validated on an actual distribution feeder with installed PMUs, and the result justifies the effectiveness of the learning-based event detection framework, as well as its potential to serve as one
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 $0.95m$.
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.
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.
Parametric dual maximization for non-convex learning problems
- Y Zhou
- Z Kang
- C J Spanos
Y. Zhou, Z. Kang, and C. J. Spanos, "Parametric dual maximization for
non-convex learning problems," in Thirty-First AAAI Conference, AAAI,
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.