arXiv subjects

Chau Yuen

Publications and source records attributed to Chau Yuen.

At least 415 records · Page 23Linked to original sources

arXiv2020

Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications

Even though the Convolutional Neural Networks (CNN) has shown superior results in the field of computer vision, it is still a challenging task to implement computer vision algorithms in real-time at the edge, especially using a low-cost IoT device due to high memory consumption and computation complexities in a CNN. Network compression methodologies such as weight pruning, filter pruning, and quantization are used to overcome the above mentioned problem. Even though filter pruning methodology has shown better performances compared to other techniques, irregularity of the number of filters pruned across different layers of a CNN might not comply with majority of the neural computing hardware architectures. In this paper, a novel greedy approach called cluster pruning has been proposed, which provides a structured way of removing filters in a CNN by considering the importance of filters and the underlying hardware architecture. The proposed methodology is compared with the conventional filter pruning algorithm on Pascal-VOC open dataset, and Head-Counting dataset, which is our own dataset developed to detect and count people entering a room. We benchmark our proposed method on three hardware architectures, namely CPU, GPU, and Intel Movidius Neural Computer Stick (NCS) using the popular SSD-MobileNet and SSD-SqueezeNet neural network architectures used for edge-AI vision applications. Results demonstrate that our method outperforms the conventional filter pruning methodology, using both datasets on above mentioned hardware architectures. Furthermore, a low cost IoT hardware setup consisting of an Intel Movidius-NCS is proposed to deploy an edge-AI application using our proposed pruning methodology.

cs.CV↗

arXiv2020

Intelligent Reflecting Surface: Practical Phase Shift Model and Beamforming Optimization

Intelligent reflecting surface (IRS) that enables the control of the wireless propagation environment has been looked upon as a promising technology for boosting the spectrum and energy efficiency in future wireless communication systems. Prior works on IRS are mainly based on the ideal phase shift model assuming the full signal reflection by each of the elements regardless of its phase shift, which, however, is practically difficult to realize. In contrast, we propose in this paper a practical phase shift model that captures the phase-dependent amplitude variation in the element-wise reflection coefficient. Applying this new model to an IRS-aided wireless system, we formulate a problem to maximize its achievable rate by jointly optimizing the transmit beamforming and the IRS reflect beamforming. The formulated problem is non-convex and difficult to be optimally solved in general, for which we propose a low-complexity suboptimal solution based on the alternating optimization (AO) technique. Simulation results unveil a substantial performance gain achieved by the joint beamforming optimization based on the proposed phase shift model as compared to the conventional ideal model.

eess.SP↗

arXiv2020

Intelligent Reflecting Surface: Practical Phase Shift Model and Beamforming Optimization

Intelligent reflecting surface (IRS) that enables the control of wireless propagation environment has recently emerged as a promising cost-effective technology for boosting the spectrum and energy efficiency in future wireless communication systems. Prior works on IRS are mainly based on the ideal phase shift model assuming the full signal reflection by each of the elements regardless of its phase shift, which, however, is practically difficult to realize. In contrast, we propose in this paper the practical phase shift model that captures the phase-dependent amplitude variation in the element-wise reflection coefficient. Based on the proposed model and considering an IRS-aided multiuser system with an IRS deployed to assist in the downlink communications from a multi-antenna access point (AP) to multiple single-antenna users, we formulate an optimization problem to minimize the total transmit power at the AP by jointly designing the AP transmit beamforming and the IRS reflect beamforming, subject to the users' individual signal-to-interference-plus-noise ratio (SINR) constraints. Iterative algorithms are proposed to find suboptimal solutions to this problem efficiently by utilizing the alternating optimization (AO) or penalty-based optimization technique. Moreover, we analyze the asymptotic performance loss of the IRS-aided system that employs practical phase shifters but assumes the ideal phase shift model for beamforming optimization, as the number of IRS elements goes to infinity. Simulation results unveil substantial performance gains achieved by the proposed beamforming optimization based on the practical phase shift model as compared to the conventional ideal model.

cs.IT↗

arXiv2020

Reconfigurable Intelligent Surface Assisted Multiuser MISO Systems Exploiting Deep Reinforcement Learning

Recently, the reconfigurable intelligent surface (RIS), benefited from the breakthrough on the fabrication of programmable meta-material, has been speculated as one of the key enabling technologies for the future six generation (6G) wireless communication systems scaled up beyond massive multiple input multiple output (Massive-MIMO) technology to achieve smart radio environments. Employed as reflecting arrays, RIS is able to assist MIMO transmissions without the need of radio frequency chains resulting in considerable reduction in power consumption. In this paper, we investigate the joint design of transmit beamforming matrix at the base station and the phase shift matrix at the RIS, by leveraging recent advances in deep reinforcement learning (DRL). We first develop a DRL based algorithm, in which the joint design is obtained through trial-and-error interactions with the environment by observing predefined rewards, in the context of continuous state and action. Unlike the most reported works utilizing the alternating optimization techniques to alternatively obtain the transmit beamforming and phase shifts, the proposed DRL based algorithm obtains the joint design simultaneously as the output of the DRL neural network. Simulation results show that the proposed algorithm is not only able to learn from the environment and gradually improve its behavior, but also obtains the comparable performance compared with two state-of-the-art benchmarks. It is also observed that, appropriate neural network parameter settings will improve significantly the performance and convergence rate of the proposed algorithm.

cs.IT↗

arXiv2020

Understanding Crowd Behaviors in a Social Event by Passive WiFi Sensing and Data Mining

Understanding crowd behaviors in a large social event is crucial for event management. Passive WiFi sensing, by collecting WiFi probe requests sent from mobile devices, provides a better way to monitor crowds compared with people counters and cameras in terms of free interference, larger coverage, lower cost, and more information on people's movement. In existing studies, however, not enough attention has been paid to the thorough analysis and mining of collected data. Especially, the power of machine learning has not been fully exploited. In this paper, therefore, we propose a comprehensive data analysis framework to fully analyze the collected probe requests to extract three types of patterns related to crowd behaviors in a large social event, with the help of statistics, visualization, and unsupervised machine learning. First, trajectories of the mobile devices are extracted from probe requests and analyzed to reveal the spatial patterns of the crowds' movement. Hierarchical agglomerative clustering is adopted to find the interconnections between different locations. Next, k-means and k-shape clustering algorithms are applied to extract temporal visiting patterns of the crowds by days and locations, respectively. Finally, by combining with time, trajectories are transformed into spatiotemporal patterns, which reveal how trajectory duration changes over the length and how the overall trends of crowd movement change over time. The proposed data analysis framework is fully demonstrated using real-world data collected in a large social event. Results show that one can extract comprehensive patterns from data collected by a network of passive WiFi sensors.

cs.SI↗

arXiv2020

Intelligent Reflecting Surface Meets Mobile Edge Computing: Enhancing Wireless Communications for Computation Offloading

We consider computation offloading for edge computing in a wireless network equipped with intelligent reflecting surfaces (IRSs). IRS is an emerging technology and has recently received great attention since they can improve the wireless propagation environment in a configurable manner and enhance the connections between mobile devices (MDs) and access points (APs). At this point not many papers consider edge computing in the novel context of wireless communications aided by IRS. In our studied setting, each MD offloads computation tasks to the edge server located at the AP to reduce the associated comprehensive cost, which is a weighted sum of time and energy. The edge server adjusts the IRS to maximize its earning while maintaining MDs' incentives for offloading and guaranteeing each MD a customized information rate. This problem can be formulated into a difficult optimization problem, which has a sum-of-ratio objective function as well as a bunch of nonconvex constraints. To solve this problem, we first develop an iterative evaluation procedure to identify the feasibility of the problem when confronting an arbitrary set of information rate requirement. This method serves as a sufficient condition for the problem being feasible and provides a feasible solution. Based on that we develop an algorithm to optimize the objective function. Our numerical results show that the presence of IRS enables the AP to guarantee higher information rate to all MDs and at the same time improve the earning of the edge server.

eess.SP↗

arXiv2020

Parallel Factor Decomposition Channel Estimation in RIS-Assisted Multi-User MISO Communication

Reconfigurable Intelligent Surfaces (RISs) have been recently considered as an energy-efficient solution for future wireless networks due to their fast and low power configuration enabling massive connectivity and low latency communications. Channel estimation in RIS-based systems is one of the most critical challenges due to the large number of reflecting unit elements and their distinctive hardware constraints. In this paper, we focus on the downlink of a RIS-assisted multi-user Multiple Input Single Output (MISO) communication system and present a method based on the PARAllel FACtor (PARAFAC) decomposition to unfold the resulting cascaded channel model. The proposed method includes an alternating least squares algorithm to iteratively estimate the channel between the base station and RIS, as well as the channels between RIS and users. Our selective simulation results show that the proposed iterative channel estimation method outperforms a benchmark scheme using genie-aided information. We also provide insights on the impact of different RIS settings on the proposed algorithm.

cs.IT↗

arXiv2020

Peer-to-Peer Trading in Electricity Networks: An Overview

Peer-to-peer trading is a next-generation energy management technique that economically benefits proactive consumers (prosumers) transacting their energy as goods and services. At the same time, peer-to-peer energy trading is also expected to help the grid by reducing peak demand, lowering reserve requirements, and curtailing network loss. However, large-scale deployment of peer-to-peer trading in electricity networks poses a number of challenges in modeling transactions in both the virtual and physical layers of the network. As such, this article provides a comprehensive review of the state-of-the-art in research on peer-to-peer energy trading techniques. By doing so, we provide an overview of the key features of peer-to-peer trading and its benefits of relevance to the grid and prosumers. Then, we systematically classify the existing research in terms of the challenges that the studies address in the virtual and the physical layers. We then further identify and discuss those technical approaches that have been extensively used to address the challenges in peer-to-peer transactions. Finally, the paper is concluded with potential future research directions.

cs.MA↗

arXiv2019

A Coalition Formation Game Framework for Peer-to-Peer Energy Trading

This paper studies social cooperation backed peer-to-peer energy trading technique by which prosumers can decide how they can use their batteries opportunistically for participating in the peer-to-peer trading. The objective is to achieve a solution in which the ultimate beneficiaries are the prosumers, i.e., a prosumer-centric solution. To do so, a coalition formation game is designed, which enables a prosumer to compare its benefit of participating in the peer-to-peer trading with and without using its battery and thus, allows the prosumer to form suitable social coalition groups with other similar prosumers in the network for conducting peer-to-peer trading. The properties of the formed coalitions are studied, and it is shown that 1) the coalition structure that stems from the social cooperation between participating prosumers at each time slot is both stable and optimal, and 2) the outcomes of the proposed peer- to-peer trading scheme is prosumer-centric. Case studies are conducted based on real household energy usage and solar generation data to highlight how the proposed scheme can benefit prosumers through exhibiting prosumer-centric properties.

eess.SP↗

arXiv2019

PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block

In many real-time applications, the deployment of deep neural networks is constrained by high computational cost and efficient lightweight neural networks are widely concerned. In this paper, we propose that depthwise convolution (DWC) is used to expand the number of channels in a bottleneck block, which is more efficient than 1 x 1 convolution. The proposed Pointwise-Standard-Depthwise network (PSDNet) based on channel expansion with DWC has fewer number of parameters, less computational cost and higher accuracy than corresponding ResNet on CIFAR datasets. To design more efficient lightweight concolutional neural netwok, Depthwise-Pointwise-Depthwise inverted bottleneck block (DPD block) is proposed and DPDNet is designed by stacking DPD block. Meanwhile, the number of parameters of DPDNet is only about 60% of that of MobileNetV2 for networks with the same number of layers, but can achieve approximated accuracy. Additionally, two hyperparameters of DPDNet can make the trade-off between accuracy and computational cost, which makes DPDNet suitable for diverse tasks. Furthermore, we find the networks with more DWC layers outperform the networks with more 1x1 convolution layers, which indicates that extracting spatial information is more important than combining channel information.

cs.CV↗

arXiv2019

Collaborative SLAM based on Wifi Fingerprint Similarity and Motion Information

Simultaneous localization and mapping (SLAM) has been extensively researched in past years particularly with regard to range-based or visual-based sensors. Instead of deploying dedicated devices that use visual features, it is more pragmatic to exploit the radio features to achieve this task, due to their ubiquitous nature and the widespread deployment of Wi-Fi wireless network. This paper presents a novel approach for collaborative simultaneous localization and radio fingerprint mapping (C-SLAM-RF) in large unknown indoor environments. The proposed system uses received signal strengths (RSS) from Wi-Fi access points (AP) in the existing infrastructure and pedestrian dead reckoning (PDR) from a smart phone, without a prior knowledge about map or distribution of AP in the environment. We claim a loop closure based on the similarity of the two radio fingerprints. To further improve the performance, we incorporate the turning motion and assign a small uncertainty value to a loop closure if a matched turning is identified. The experiment was done in an area of 130 meters by 70 meters and the results show that our proposed system is capable of estimating the tracks of four users with an accuracy of 0.6 meters with Tango-based PDR and 4.76 meters with a step counter-based PDR.

cs.NI↗

arXiv2019

Joint Unicast and Multi-group Multicast Transmission in Massive MIMO Systems

We study the joint unicast and multi-group multicast transmission in massive multiple-input-multiple-output (MIMO) systems. We consider a system model that accounts for channel estimation and pilot contamination, and derive achievable spectral efficiencies (SEs) for unicast and multicast user terminals (UTs), under maximum ratio transmission and zero-forcing precoding. For unicast transmission, our objective is to maximize the weighted sum SE of the unicast UTs, and for the multicast transmission, our objective is to maximize the minimum SE of the multicast UTs. These two objectives are coupled in a conflicting manner, due to their shared power resource. Therefore, we formulate a multiobjective optimization problem (MOOP) for the two conflicting objectives. We derive the Pareto boundary of the MOOP analytically. As each Pareto optimal point describes a particular efficient trade-off between the two objectives of the system, we determine the values of the system parameters (uplink training powers, downlink transmission powers, etc.) to achieve any desired Pareto optimal point. Moreover, we prove that the Pareto region is convex, hence the system should serve the unicast and multicast UTs at the same time-frequency resource. Finally, we validate our results using numerical simulations.

cs.IT↗

arXiv2019

Resource Allocation in Mobility-Aware Federated Learning Networks: A Deep Reinforcement Learning Approach

Federated learning allows mobile devices, i.e., workers, to use their local data to collaboratively train a global model required by the model owner. Federated learning thus addresses the privacy issues of traditional machine learning. However, federated learning faces the energy constraints of the workers and the high network resource cost due to the fact that a number of global model transmissions may be required to achieve the target accuracy. To address the energy constraint, a power beacon can be used that recharges energy to the workers. However, the model owner may need to pay an energy cost to the power beacon for the energy recharge. To address the high network resource cost, the model owner can use a WiFi channel, called default channel, for the global model transmissions. However, communication interruptions may occur due to the instability of the default channel quality. For this, special channels such as LTE channels can be used, but this incurs channel cost. As such, the problem of the model owner is to decide amounts of energy recharged to the workers and to choose channels used to transmit its global model to the workers to maximize the number of global model transmissions while minimizing the energy and channel costs. This is challenging for the model owner under the uncertainty of the channel, energy and mobility states of the workers. In this paper, we thus propose to employ the Deep Q-Network (DQN) that enables the model owner to find the optimal decisions on the energy and the channels without any a priori network knowledge. Simulation results show that the proposed DQN always achieves better performance compared to the conventional algorithms.

cs.NI↗

arXiv2019

DNN-Aided Block Sparse Bayesian Learning for User Activity Detection and Channel Estimation in Grant-Free Non-Orthogonal Random Access

In the upcoming Internet-of-Things (IoT) era, the communication is often featured by massive connection, sporadic transmission, and small-sized data packets, which poses new requirements on the delay expectation and resource allocation efficiency of the Random Access (RA) mechanisms of the IoT communication stack. A grant-free non-orthogonal random access (NORA) system is considered in this paper, which could simultaneously reduce the access delay and support more Machine Type Communication (MTC) devices with limited resources. In order to address the joint user activity detection (UAD) and channel estimation (CE) problem in the grant-free NORA system, we propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm. In the DNN-MP-BSBL algorithm, the iterative message passing process is transferred from a factor graph to a deep neural network (DNN). Weights are imposed on the messages in the DNN and trained to minimize the estimation error. It is shown that the trained weights could alleviate the convergence problem of the MP-BSBL algorithm, especially on crowded RA scenarios. Simulation results show that the proposed DNN-MP-BSBL algorithm could improve the UAD and CE accuracy with a smaller number of iterations, indicating its advantages for low-latency grant-free NORA systems.

cs.IT↗

arXiv2019

Benchmarking air-conditioning energy performance of residential rooms based on regression and clustering techniques

Air conditioning (AC) accounts for a critical portion of the global energy consumption. To improve its energy performance, it is important to fairly benchmark its energy performance and provide the evaluation feedback to users. However, this task has not been well tackled in the residential sector. In this paper, we propose a data-driven approach to fairly benchmark the AC energy performance of residential rooms. First, regression model is built for each benchmarked room so that its power consumption can be predicted given different weather conditions and AC settings. Then, all the rooms are clustered based on their areas and usual AC temperature set points. Lastly, within each cluster, rooms are benchmarked based on their predicted power consumption under uniform weather conditions and AC settings. A real-world case study was conducted with data collected from 44 residential rooms. Results show that the constructed regression models have an average prediction accuracy of 85.1% in cross-validation tests, and support vector regression with Gaussian kernel is the overall most suitable model structure for building the regression model. In the clustering step, 44 rooms are successfully clustered into seven clusters. By comparing the benchmarking scores generated by the proposed approach with two sets of scores computed from historical power consumption data, we demonstrate that the proposed approach is able to eliminate the influences of room areas, weather conditions, and AC settings on the benchmarking results. Therefore, the proposed benchmarking approach is valid and fair. As a by-product, the approach is also shown to be useful to investigate how room areas, weather conditions, and AC settings affect the AC power consumption of rooms in real life.

eess.SY↗

arXiv2019

DNN-Aided Message Passing Based Block Sparse Bayesian Learning for Joint User Activity Detection and Channel Estimation

Faced with the massive connection, sporadic transmission, and small-sized data packets in future cellular communication, a grant-free non-orthogonal random access (NORA) system is considered in this paper, which could reduce the access delay and support more devices. In order to address the joint user activity detection (UAD) and channel estimation (CE) problem in the grant-free NORA system, we propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm. In this algorithm, the message passing process is transferred from a factor graph to a deep neural network (DNN). Weights are imposed on the messages in the DNN and trained to minimize the estimation error. It is shown that the weights could alleviate the convergence problem of the MP-BSBL algorithm. Simulation results show that the proposed DNN-MP-BSBL algorithm could improve the UAD and CE accuracy with a smaller number of iterations.

cs.IT↗

arXiv2019

Blockchain Technologies for Smart Energy Systems: Fundamentals, Challenges and Solutions

In this paper, we discuss the integration of blockchain in smart energy systems. We present various blockchain technology solutions, review important blockchain platforms, and several blockchain based smart energy projects in different smart energy domains. The majority of blockchain platforms with embedded combination of blockchain technology solutions are computing- and resource- intensive, and hence not entirely suitable for smart energy applications. We consider the requirements of smart energy systems and accordingly identify appropriate blockchain technology solutions for smart energy applications. Our analysis can help in the development of flexible blockchain platforms for smart energy systems.

cs.CY↗

arXiv2019

Doppler Invariant Demodulation for Shallow Water Acoustic Communications Using Deep Belief Networks

Shallow water environments create a challenging channel for communications. In this paper, we focus on the challenges posed by the frequency-selective signal distortion called the Doppler effect. We explore the design and performance of machine learning (ML) based demodulation methods --- (1) Deep Belief Network-feed forward Neural Network (DBN-NN) and (2) Deep Belief Network-Convolutional Neural Network (DBN-CNN) in the physical layer of Shallow Water Acoustic Communication (SWAC). The proposed method comprises of a ML based feature extraction method and classification technique. First, the feature extraction converts the received signals to feature images. Next, the classification model correlates the images to a corresponding binary representative. An analysis of the ML based proposed demodulation shows that despite the presence of instantaneous frequencies, the performance of the algorithm shows an invariance with a small 2dB error margin in terms of bit error rate (BER).

eess.SP↗