Human activity recognition (HAR) plays a critical role in a wide range of real-world applications, and it is traditionally achieved via wearable sensing. Recently, to avoid the burden and discomfort caused by wearable devices, device-free approaches exploiting radio-frequency (RF) signals arise as a promising alternative for HAR. Most of the latest device-free approaches require training a large deep neural network model in either time or frequency domain, entailing extensive storage to contain the model and intensive computations to infer human activities. Consequently, even with some major advances on device-free HAR, current device-free approaches are still far from practical in real-world scenarios where the computation and storage resources possessed by, for example, edge devices, are limited. To overcome these weaknesses, we introduce HAR-SAnet which is a novel RF-based HAR framework. It adopts an original signal adapted convolutional neural network architecture: instead of feeding the handcraft features of RF signals into a classifier, HAR-SAnet fuses them adaptively from both time and frequency domains to design an end-to-end neural network model. We apply point-wise grouped convolution and depth-wise separable convolutions to confine the model scale and to speed up the inference execution time. The experiment results show that the recognition accuracy of HAR-SAnet substantially outperforms the state-of-the-art algorithms and systems.

With the proliferation of Internet-of-Things (IoT) devices, acoustic sensing attracts significant attention in recent years. It exploits acoustic transceivers such as microphones and speakers beyond their primary functions, namely recording and playing, to enable novel applications and new user experiences. In this paper, we present the first systematic survey on recent advances in ubiquitous acoustic sensing using commodity IoT hardware with a frequency range below 24 kHz. We propose a general framework that categorizes main building blocks of acoustic sensing systems. This framework encompasses three layers, i.e., device, core technique, and application. The device layer includes basic hardware components, acoustic platforms, as well as the air-borne and structure-borne channel characteristics. The core technique layer encompasses key mechanisms to generate acoustic signals (waveforms) and to extract useful temporal, spatial, and spectral information from received signals. The application layer builds upon the functions offered by the core techniques to realize different acoustic sensing applications. We highlight unique challenges due to the limitations of physical devices and acoustic channels and how they are mitigated or overcame by core processing techniques and application-specific solutions. Finally, research opportunities and future directions are discussed to spawn further in-depth investigation on IoTenabled ubiquitous acoustic sensing.

Microservices as an emerging architecture are creating new opportunities to enable superior network services in Mobile Edge Computing (MEC). In the presence of huge amounts of user requests, the massive communications among microservices have become notoriously complicated. Due to the intricate data dependencies of the microservices, the overall performance of large-scale MEC applications simultaneously depends on both service deployment and request routing. However, most existing work ignores the interdependencies of microservices and studies the deployment and routing as two isolated problems. In this case, this paper investigates the joint optimization of service deployment and request routing in edge computing. We first formulate a delay minimization problem via mixed integer linear programming and queuing analysis, and then provide a hardness proof on the problem. In addition, this paper presents a 2-approximation algorithm, followed with rigorous mathematical proofs to demonstrate the approximation ratio. The proposed two-phase algorithm consists of rounding based service deployment and adaptive-scaling-based request routing policies, which employ fine grained joint optimization to minimize service response delay. Finally, we illustrate the near-optimal performance of the proposed algorithm via comprehensive experiments.

The most basic requirement for autonomous vehicles is accurate environmental perception. However, the lack of onboard computing resources makes it difficult for such a vehicle to process all environmental information. Through the edge computing technology and 6G networks, vehicles can offload computing tasks to edge servers for execution, which alleviates the problem of insufficient onboard resources. The environmental perception task offloading problem for autonomous vehicles is studied. The purpose is to improve the environmental perception quality through reasonable task offloading. After assigning dynamic priorities to tasks generated by autonomous vehicles, the multi-vehicle and multi-server task offloading process is abstracted as a Markov decision process, and an offloading decision algorithm based on deep reinforcement learning is designed to select edge nodes for task execution to obtain better long-term benefits. The earliest deadline first algorithm is improved to consider the deadline and priority of each task, allowing the edge node to complete more high-priority tasks within the specified time. Experimental results show that the proposed method can guarantee the basic environmental perception requirements of every vehicle, and performs better than existing methods in terms of the total priority of the discarded tasks in each scheduling period and the completion rate of key tasks.

The emerging low earth orbit (LEO) broadband satellite networks are creating new opportunities to enable superior video distribution. With numerous satellites deployed, broadband constellations are capable of distributing videos across the globe by efficient multicasting techniques. However, existing work only studied IP multicast for broadband constellations, which suffer from limited scalability and tree performance. With recent breakthroughs in software defined networking, novel software defined multicasting (SDM) techniques manage to achieve efficient data transfer through intelligent and granular management, outperforming traditional IP Multicast. This paper leverages software defined multicasting in the promising broadband constellations to empower satellite-based Internet video distribution. Based on rectilinear Steiner trees, this paper proposes a novel software defined multicasting framework for broadband satellite networks. In addition, this paper designs simple, agile, and scalable multicast segment routing protocols implementing source routing and equal cost multipath routing. The proposed protocols also adapt to frequent member updates and network failures with efficient tree recovery and local rerouting mechanisms. Comprehensive experiments demonstrate the effectiveness and efficiency of our approach when compared with traditional algorithms.

Recently, acoustic-based indoor localization has attracted much attention due to its affordable infrastructure costs and high localization accuracy. However, previous work is infeasible in mobile target tracking for its long latency in obtaining sufficient beacon messages. In addition, the performance can further deteriorate due to device diversity, varying channel gains, and background noises. To this end, we propose an asynchronous acoustic localization and tracking system (AALTS), which utilizes distributed acoustic anchor nodes to locate passive off-the-shelf mobile devices. In AALTS, we propose an orthogonal chirp spread spectrum (OCSS) modulation technique, which doubles the data rate and thus mitigates the latency. We design a more robust method to capture acoustic signals which embody timestamps for localization, accounting for device diversity, varying channel gains, and the multipath effect. Finally, we incorporate an acoustic Doppler speed estimation module with a path-based particle filter framework to accurately track the moving targets. We have evaluated AALTS in an indoor testbed of size 8×12 m ² with commodity mobile phones and customized acoustic anchors. Our evaluation results demonstrate remarkable performance: AALTS achieves 90-percentile tracking errors of 0.49 m for mobile targets and a median of 0.12 m for stationary ones with only four anchor nodes.