With the booming development of Internet-of-Things (IoT) and communication technologies such as 5G, our future world is envisioned an interconnected entity where billions devices will provide uninterrupted service to daily lives industry. Meanwhile, these generate massive amounts valuable data at network edge, calling for not only instant processing but also intelligent analysis in order fully unleash potential edge big data. Both traditional cloud computing on-device cannot sufficiently...

This paper presents a systematic in-depth study on the existence, importance, and application of stable nodes in peer- to-peer live video streaming. Using traces from real large-scale system as well analytical models, we show that, while number is small throughout whole session, their longer lifespans make them constitute significant portion per-snapshot view peer-to-peer overlay. As result, they have substantially affected performance overall system. Inspired by this, propose tiered overlay...

The deeply penetrated WiFi signals not only provide fundamental communications for the massive Internet of Things devices but also enable cognitive sensing ability in many other applications, such as human activity recognition. State-of-the-art WiFi-based device-free systems leverage correlations between signal changes and body movements They have demonstrated reasonably good recognition results with a properly placed transceiver pair, or, words, when is within certain sweet zone....

Today's explosively growing Internet video traffics and viewers' ever-increasing quality of experience (QoE) demands for streaming bring tremendous pressures to the backbone network. As a new network paradigm, mobile edge caching provides promising alternative by pushing content closer at rather than remote CDN servers so as reduce both access latency redundant traffic. However, our large-scale trace analysis shows that different from based caching, environment is much more complicated with...

The Internet of Things (IoT) is widely regarded as a key component the future and thereby has drawn significant interests in recent years. IoT consists billions intelligent communicating "things", which further extend borders world with physical virtual entities. Such ubiquitous smart things produce massive data every day, posing urgent demands on quick analysis various mobile devices. Fortunately, breakthroughs deep learning have enabled us to address problem an elegant way. Deep models can...

Recent years have seen booming development and great success in interactive crowdsourced livecast (i.e., crowdcast). Different from traditional services, crowdcast is featured with tremendous video contents at the broadcaster side, highly diverse viewer side content watching environments/preferences as well viewers' personalized quality of experience (QoE) demands (e.g., individual preferences for streaming delays, channel switching latencies bitrates). This imposes unprecedented key...

Recent years have witnessed an explosive growth of online shopping, which has posted unprecedented pressure on the logistics industry, especially last mile parcel delivery. Existing solutions mostly rely dedicated couriers, suffer from high cost and low elasticity when dealing with a massive amount local addresses. Advances in Internet Things, however, enabled vehicle information to be readily accessible anytime anywhere, forming Vehicles (IoV), further enables intelligent scheduling...

The advent of high-accuracy and resource-intensive deep neural networks (DNNs) has fulled the development live video analytics, where camera videos need to be streamed over network edge or cloud servers with sufficient computational resources. Although it is promising strike a balance between available bandwidth server-side DNN inference accuracy by adjusting encoding configurations, influences fine-grained content dynamics on configuration performance should addressed. In this paper, we...

As one of the most important manifestations virtual reality (VR), 360° panoramic videos in recent years have experienced booming development due to desire for immersive and interactive experiences. Compared traditional videos, are featured with uncertain user Field View (FoV), more sensitive delay tolerance, much higher bandwidth requirement, bringing unprecedented challenges video streaming. Meanwhile, 5G mobile edge computing starts pave way high-bandwidth low-latency Some preliminary...

Volumetric video (VV) recently emerges as a new form of application providing photorealistic immersive 3D viewing experience with 6 degree-of-freedom (DoF), which empowers many applications such VR, AR, and Metaverse. A key problem therein is how to stream the enormous size VV through network limited bandwidth. Existing works mostly focused on predicting viewport for tiling-based adaptive streaming, however only has quite effect resource saving. We argue that content repeatability in can be...

Federated learning (FL) offers a privacy-centric distributed framework, enabling model training on individual clients and central aggregation without necessitating data exchange. Nonetheless, FL implementations often suffer from non-i.i.d. long-tailed class distributions across mobile applications, e.g., autonomous vehicles, which leads models to overfitting as local may converge sub-optimal. In our study, we explore the impact of heterogeneity bias introduce an innovative personalized...

WiFi-based human activity recognition explores the correlations between body movement and reflected WiFi signals to classify different activities. State-of-the-art solutions mostly work on a single channel hence are quite sensitive quality of particular channel. Co-channel interference in an indoor environment can seriously undermine accuracy. In this paper, we for first time explore wideband information with advanced deep learning toward more accurate robust recognition. We present...

Cognitive communication and computing have seen deep penetration in many networking areas the past decades. With recent advances big data analysis learning, we great potential toward exploring cognitive intelligence for a wide range of applications. A notable example therein is human activity recognition, especially through RFID. Existing RFID identification solutions are mostly designed static or slowly moving targets, rendering them far from satisfactory. More importantly, observe that...

In-car human activity recognition is playing a critical role in detecting distracted driving and improving human-car interaction. Among multiple sensing technologies, WiFi-based in-car exhibits unique advantages since it does not rely on visible light, avoids privacy leaks cost-efficient with integrated WiFi signals cars. Existing systems mostly focus the relatively stable indoor space, which only yield reasonably good performance limited situations. Based our field studies, recognition,...

In-car human activity recognition opens a new opportunity toward intelligent driving behavior detection and touchless human-car interaction. Among the many sensing technologies (e.g., using cameras wearable sensors), radio frequency identification (RFID) exhibits unique advantages given its low cost, easy deployment, less privacy concerns. Existing RFID-based solutions for are mostly confined to working in stable indoor spaces. The inside space of car however is much more compact complex,...

Federated learning (FL) emerges as a new distributed machine (ML) paradigm that enables thousands of mobile devices to collaboratively train ML models using local data without compromising user privacy. However, the FL quality highly relies on contribution from devices. Therefore, well-designed incentive mechanism with effectiveness, fairness, and reciprocity is in urgent need guarantee stable participation users. In this article, we propose federated auction bandit ( <monospace...

Point cloud video (PCV) offers watching experiences in photorealistic 3D scenes with six-degree-of-freedom (6-DoF), enabling a variety of VR and AR applications. The user's Field View (FoV) is more fickle 6-DoF movement than 3-DoF 360-degree video. PCV streaming extremely bandwidth-intensive. However, current systems require hundreds Mbps bandwidth, exceeding the bandwidth capabilities commodity devices. To save FoV-adaptive predicts FoV only downloads point data falling predicted FoV. But...

The explosion of online shopping brings great challenges to traditional logistics industry, where the massive parcels and tight delivery deadline impose a large cost on process, in particular last mile parcel delivery. On other hand, modern cities never lack transportation resources such as private car trips. Motivated by these observations, we propose novel effective mechanism through trip sharing, leverage available trips incidentally deliver during their original To achieve this, major...

Volumetric video emerges as a new attractive paradigm in recent years since it provides an immersive and interactive 3D viewing experience with six degree-of-freedom (DoF). Unlike traditional 2D or panoramic videos, volumetric videos require dense point clouds, voxels, meshes, huge neural models to depict scenes, which results prohibitively high bandwidth burden for delivery. Users' behavior analysis, especially the viewport gaze then plays significant role prioritizing content streaming...

With the deep penetration of mobile devices, more and learning applications have been widely used in daily life. However, since tasks are computationally intensive, limited computation resource on devices cannot execute application effectively. The common approaches transmitting data from offloading to cloud. This brings another issue that high transmission delay may become bottleneck performance. In this paper, we explore a new rising concept, edge computing, into applications. Comparing...

Today's anywhere and anytime broadband connection audio/video capture have boosted the deployment of crowdsourced livecast services (or <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">crowdcast</i> ). Bridging a massive amount geo-distributed broadcasters their fellow viewers, such representatives as Twitch.tv, Youtube Gaming, Inke.tv, greatly changed generation distribution landscape streaming content. They also enable rich online...