No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Machine Learning-Aided Radio Scenario Recognition for Cognitive Radio Networks in Millimeter-Wave Bands
... Wang et al. [107] proposed the use of the AdaBoost algorithm to use path loss and variance of path loss to classify network links in an ultra dense millimetre band network. This approach allows contextual awareness to be applied to cognitive radio by identifying channel conditions or radio scenarios. ...
... This approach assumes that there are no hidden nodes in the network. An alternative approach to cognitive radio is proposed by Wang et al. [107] that does not use PUs and SUs. They proposed the use of the aDaBoost algorithm to use path loss and variance of path loss to classify network links in an ultra dense millimetre band network. ...
Autonomous Vehicles are becoming a reality in places with advanced infrastructure to support their operations. In crowded places, harsh environments, missions that require these vehicles to be aware of the context in which they are operating, and situations requiring continuous coordination with humans such as in disaster relief, Advanced-Vehicle Systems (AVSs) need to be better contextually aware. The vast literature referring to “context-aware systems” is still sparse, focusing on very limited forms of contextual awareness. It requires a structured approach to bring it together to truly realise contextual awareness in AVSs. This paper uses a Human-AVSs (HAVSs) lens to polarise the literature in a coherent form suitable for designing distributed HAVSs. We group the relevant literature into two categories: contextual-awareness related to the vehicle infrastructure itself that enables AVSs to operate, and contextualawareness related to HAVSs. The former category focuses on the communication backbone for AVSs including ad-hoc networks, services, wireless communication, radio systems, and the cyber security and privacy challenges that arise in these contexts. The latter category covers recommender systems, which are used to coordinate the actions that sit at the interface of the human and AVSs, human-machine interaction issues, and the activity recognition systems as the enabling technology for recommender systems to operate autonomously. The structured analysis of the literature has identified a number of open research questions and opportunities for further research in this area.
Scene classification is a fundamental perception task for environmental
understanding in today's robotics. In this paper, we have attempted to exploit
the use of popular machine learning technique of deep learning to enhance scene
understanding, particularly in robotics applications. As scene images have
larger diversity than the iconic object images, it is more challenging for deep
learning methods to automatically learn features from scene images with less
samples. Inspired by human scene understanding based on object knowledge, we
address the problem of scene classification by encouraging deep neural networks
to incorporate object-level information. This is implemented with a
regularization of semantic segmentation. With only 5 thousand training images,
as opposed to 2.5 million images, we show the proposed deep architecture
achieves superior scene classification results to the state-of-the-art on a
publicly available SUN RGB-D dataset. In addition, performance of semantic
segmentation, the regularizer, also reaches a new record with refinement
derived from predicted scene labels. Finally, we apply our SUN RGB-D dataset
trained model to a mobile robot captured images to classify scenes in our
university demonstrating the generalization ability of the proposed algorithm.
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
Latest regulations on TV white space communications and emerging trends of spectrum access through geolocation databases relax the regulatory constraints on Cognitive Radios (CRs). Geolocation databases are designed to store information related to incumbents, and CRs are envisioned to consult this database before spectrum access. Spectrum occupancy and related environment information can be constructed using these geolocation databases. In that regard, Radio Environment Map (REM) is a promising tool that provides a practical means for the realization of cognitive radio networks (CRNs). It constructs a comprehensive map of the CRN by utilizing multi-domain information from geolocation databases, characteristics of spectrum use, geographical terrain models, propagation environment, and regulations. REMs contribute to cognition engines by building long-term knowledge via processing spectrum measurements collected from sensors to estimate the state of locations where there is no measurement data. In addition, REM utilizes feedback from the CRs and can apply various learning tools. The vision is to design CRNs such that CRs, though being simple devices without advanced cognitive functionalities, can become cognitive via REMs and operate in an efficient manner. In this paper, an overview of the REM concept is presented in various dimensions ranging from its architecture and stored information to REM construction techniques as well as REM quality metrics.
A non-line-of-sight (NLOS) mitigation approach is presented for network-based mobile tracking. A distance smoothing method is proposed, which uses online line-of-sight (LOS) and NLOS identification. A technique is proposed to integrate distance, mobile velocity, and heading estimates for position determination through Kalman filtering. Hypothesis testing analysis is performed to provide a guideline for selecting the threshold values. Simulation results demonstrate that the proposed approach significantly improves position accuracy as compared with the existing algorithms.
The Cognitive Radio (CR) technology enables the unlicensed users to share the spectrum with the licensed users on a non-interfering basis. Spectrum sensing is an important function for the unlicensed users to determine availability of a channel in the licensed user's spectrum. However, spectrum sensing consumes considerable energy which can be reduced by employing predictive methods for discovering spectrum holes. Using a reliable prediction scheme, the unlicensed users will sense only those channels which are predicted to be idle. By achieving a low probability of error in predicting the idle channels, the spectrum utilization can also be improved. Since the traffic characteristics of most licensed user systems encountered in real life are not known a priori, we design the spectrum predictor using the neural network model, multilayer perceptron (MLP), which does not require a prior knowledge of the traffic characteristics of the licensed user systems. The performance of the spectrum predictor is analyzed through extensive simulations.
Cognitive radio (CR) is an enabling technology for numerous new capabilities such as dynamic spectrum access, spectrum markets, and self-organizing networks. To realize this diverse set of applications, CR researchers leverage a variety of artificial intelligence (AI) techniques. To help researchers better understand the practical implications of AI to their CR designs, this paper reviews several CR implementations that used the following AI techniques: artificial neural networks (ANNs), metaheuristic algorithms, hidden Markov models (HMMs), rule-based systems, ontology-based systems (OBSs), and case-based systems (CBSs). Factors that influence the choice of AI techniques, such as responsiveness, complexity, security, robustness, and stability, are discussed. To provide readers with a more concrete understanding, these factors are illustrated in an extended discussion of two CR designs.
Channel sensing and spectrum allocation has long been of interest as a prospective addition to cognitive radios for wireless communications systems occupying license-free bands. Conventional approaches to cyclic spectral analysis have been proposed as a method for classifying signals for applications where the carrier frequency and bandwidths are unknown, but is, however, computationally complex and requires a significant amount of observation time for adequate performance. Neural networks have been used for signal classification, but only for situations where the baseband signal is present. By combining these techniques a more efficient and reliable classifier can be developed where a significant amount of processing is performed offline, thus reducing online computation. In this paper we take a renewed look at signal classification using spectral coherence and neural networks, the performance of which is characterized by Monte Carlo simulations
Indoor wireless systems often operate under non-line-of-sight (NLOS) conditions that can cause ranging errors for location-based applications. As such, these applications could benefit greatly from NLOS identification and mitigation techniques. These techniques have been primarily investigated for ultra-wide band (UWB) systems, but little attention has been paid to WiFi systems, which are far more prevalent in practice. In this study, we address the NLOS identification and mitigation problems using multiple received signal strength (RSS) measurements from WiFi signals. Key to our approach is exploiting several statistical features of the RSS time series, which are shown to be particularly effective. We develop and compare two algorithms based on machine learning and a third based on hypothesis testing to separate LOS/NLOS measurements. Extensive experiments in various indoor environments show that our techniques can distinguish between LOS/NLOS conditions with an accuracy of around 95%. Furthermore, the presented techniques improve distance estimation accuracy by 60% as compared to state-of-the-art NLOS mitigation techniques. Finally, improvements in distance estimation accuracy of 50% are achieved even without environment-specific training data, demonstrating the practicality of our approach to real world implementations.
Non line of sight (NLOS) error identification and mitigation is of great importance in ultra wideband (UWB) ranging and localization. Based on the features extracted from the received waveform in practical experiments, a machine learning method is proposed for UWB NLOS identification in this paper. Corresponding NLOS error mitigation method is also given based on the identification results. Compared with the traditional NLOS identification methods, the proposed method is able to achieve better results with less a priori knowledge, which makes it practical in universal applications.
This chapter discusses the strategy of exploiting network support in cognitive radio (CR) systems architectures introducing the radio environment map (REM) as an innovative vehicle of providing network support to CRs. As a systematic top-down approach to providing network support to CRs, the radio environment map is proposed as an integrated database consisting of multi domain information such as geographical features, available services, spectral regulations, locations and activities of radios, policies of the user and/or service provider, and past experience. An radio environment map (REM) can be exploited by a CE to enhance or achieve most of cognitive functionalities such as SA, reasoning, learning, planning, and decision support. Leveraging both internal and external network support through global and local REMs presents a sensible approach to implementing CRs in a reliable, flexible, and cost effective way. Network support can dramatically relax the requirements on a CR device as well as improve the performance of the whole CR network. Considering the dynamic nature of spectral regulation and operation policy, the REM-based CR is flexible and future proof in the sense that it allows regulators or service providers to modify or change their rules or policies simply by updating REMs accordingly.
This article presents empirically-based largescale propagation path loss models for fifthgeneration cellular network planning in the millimeter-wave spectrum, based on real-world measurements at 28 GHz and 38 GHz in New York City and Austin, Texas, respectively. We consider industry-standard path loss models used for today??s microwave bands, and modify them to fit the propagation data measured in these millimeter-wave bands for cellular planning. Network simulations with the proposed models using a commercial planning tool show that roughly three times more base stations are required to accommodate 5G networks (cell radii up to 200 m) compared to existing 3G and 4G systems (cell radii of 500 m to 1 km) when performing path loss simulations based on arbitrary pointing angles of directional antennas. However, when directional antennas are pointed in the single best directions at the base station and mobile, coverage range is substantially improved with little increase in interference, thereby reducing the required number of 5G base stations. Capacity gains for random pointing angles are shown to be 20 times greater than today??s fourth-generation Long Term Evolution networks, and can be further improved when using directional antennas pointed in the strongest transmit and receive directions with the help of beam combining techniques.
We consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update rule of Littlestone and Warmuth [10] can be adapted to this mode yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games and prediction of points in
n
. We also show how the weight-update rule can be used to derive a new boosting algorithm which does not require prior knowledge about the performance of the weak learning algorithm.
Mobile robots could play a significant role in places where it is impossible for the human to work. In such environments, neural networks, instead of traditional methods, are suitable solutions to locally navigate and recognize the environment's subspaces. In order to learn and perform two important functions "environmental recognition " and "local navigation ", multi-layered neural networks are trained to process distance measurements received from a laser range-finder. These neural networks are a major component of the control system of a mobile robot dedicated for industrial applications. This paper will focus on a computer based design and test of a neural system, that includes three neural controllers for local navigation, and two neural networks for environmental recognition, fed off-line by a simulated model of a laser range-finder.
It became a well known technology that a map of complex environment containing low-level geometric primitives (such as laser points) can be generated using a robot with laser scanners. This research is motivated by the need of obtaining semantic knowledge of a large urban outdoor environment after the robot explores and generates a low-level sensing data set. An algorithm is developed with the data represented in a range image, while each pixel can be converted into a 3D coordinate. Using an existing segmentation method that models only geometric homogeneities, the data of a single object of complex geometry, such as people, cars, trees etc., is partitioned into different segments. Such a segmentation result will greatly restrict the capability of object recognition. This research proposes a framework of simultaneous segmentation and classification of range image, where the classification of each segment is conducted based on its geometric properties, and homogeneity of each segment is evaluated conditioned on each object class. Experiments are presented using the data of a large dynamic urban outdoor environment, and performance of the algorithm is evaluated.
In the first part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update Littlestone-Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games, and prediction of points in ℝn. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary finite set or a bounded segment of the real line.