Some pioneer WiFi signal based human activity recognition systems have been proposed. Their key limitation lies in the lack of a model that can quantitatively correlate CSI dynamics and activities. In this paper, we propose CARM, Activity Recognition Monitoring system. CARM has two theoretical underpinnings: CSI-speed model, which quantifies correlation between value movement speeds, CSI-activity speeds different body parts specific activity. By these models, build uses as profiling...

Since human bodies are good reflectors of wireless signals, activities can be recognized by monitoring changes in WiFi signals. However, existing WiFi-based activity recognition systems do not build models that quantify the correlation between signal dynamics and activities. In this paper, we propose a Channel State Information (CSI)-based Activity Recognition Monitoring system (CARM). CARM is based on two theoretical models. First, CSI-speed model quantifies relation CSI movement speeds....

Sensor-based human activity recognition is a fundamental research problem in ubiquitous computing, which uses the rich sensing data from multimodal embedded sensors such as accelerometer and gyroscope to infer activities. The existing approaches either rely on domain knowledge or fail address spatial-temporal dependencies of signals. In this paper, we propose novel attention-based neural network model called AttnSense for recognition. introduce framework combining attention mechanism with...

Radio Frequency IDentification (RFID) technology has attracted much attention due to its variety of applications, e.g., inventory control and object tracking. One important problem in RFID systems is how quickly estimate the number distinct tags without reading each tag individually. This plays a crucial role many real-time monitoring privacy-preserving applications. In this paper, we present an efficient anonymous scheme for population estimation. leverages position first reply from group...

The limited battery capacity of sensor nodes has become one the most critical impediments that stunt deployment wireless networks (WSNs). Recent breakthroughs in energy transfer and rechargeable lithium batteries provide a promising alternative to power WSNs: mobile vehicles/robots carrying high volume serve as chargers periodically deliver nodes. In this paper, we consider how schedule multiple optimize usage effectiveness, such every will not run out energy. We introduce novel charging...

The limited battery capacity of sensor nodes has become the biggest impediment to wireless network (WSN) applications. Two recent breakthroughs in areas energy transfer and rechargeable lithium batteries promise use mobile vehicles, with high volume batteries, as chargers that wirelessly. In this paper, for first time, we envision a novel charging paradigm: collaborative charging, where are allowed charge each other. We investigate problem scheduling multiple chargers, which collaboratively...

Recently, gesture recognition has gained considerable attention in emerging applications (e.g., AR/VR systems) to provide a better user experience for human-computer interaction. Existing solutions usually recognize the gestures based on wearable sensors or specialized signals WiFi, acoustic and visible light), but they are either incurring high energy consumption susceptible ambient environment, which prevents them from efficiently sensing fine-grained finger movements. In this paper, we...

This paper considers a category of rogue access points (APs) that pretend to be legitimate APs lure users connect them. We propose practical timing-based technique allows the user avoid connecting APs. Our detection scheme is client-centric approach employs round trip time between and DNS server independently determine whether an AP without assistance from WLAN operator. implemented our on commercially available wireless cards evaluate their performance. Extensive experiments have...

As tenants take networked virtual machines (VMs) as their requirements, effective placement of VMs is needed to reduce the network cost in cloud data centers. The one major concerns for providers. In addition caused by traffics (N-cost), utilization physical (PM-cost) also non-negligible. this paper, we focus on optimized minimize cost, combination N-cost and PM-cost. We define various functions, according different communication models. formulate problem, prove it be NP-hard. investigate...

Mobile-edge cloud computing is a new paradigm to provide capabilities at the edge of pervasive radio access networks in close proximity mobile users. Aiming provisioning flexible on-demand mobile-edge service, this paper we propose comprehensive framework consisting resource-efficient computation offloading mechanism for users and joint communication (JCC) resource allocation network operator. Specifically, first study problem user, order reduce user's occupation by determining its optimal...

The Multipath TCP (MPTCP) protocol has been standardized by the IETF as an extension of conventional TCP, which enables multi-homed devices to establish multiple paths for simultaneous data transmission. Congestion control is a fundamental mechanism design and implementation MPTCP. Due diverse QoS characteristics heterogeneous links, existing multipath congestion mechanisms suffer from number performance problems such bufferbloat, suboptimal bandwidth usage, etc. In this paper, we propose...

Network virtualization has emerged as a promising approach to overcome the ossification of Internet. A major challenge in network is so-called virtual embedding problem, which deals with efficient networks resource constraints into shared substrate network. number heuristics have been proposed cope NP-hardness this problem; however, all existing proposals reserve fixed resources throughout entire lifetime In paper, we re-examine problem position that time-varying requirements should be taken...

Due to the widespread use of mobile devices, it is essential authenticate users on devices prevent sensitive information leakage. In this paper, we propose TouchID, which combinedly uses touch sensor and inertial for gesture analysis, provide a based user authentication scheme. Specifically, TouchID utilizes analyze on-screen while using device's motion caused by gesture, then combines unique features from authentication. To mitigate intra-class difference reduce inter-class similarity,...

Social psychology and neuroscience had confirmed that emotion state exerts a significant effect on human communication, perception, social behavior decision making. With the wide availability of smartphones equipped with microphone, accelerometer, GPS, other source sensors, it is worthwhile to explore possibility automatic detection via smartphone sensing. Particularly, we focus novel research problem tries detect compound (a set multiple dimensional basic emotions) users. We observe users'...

The booming of Convolutional Neural Networks (CNNs) has empowered lots computer-vision applications. Due to its stringent requirement for computing resources, substantial research been conducted on how optimize deployment and execution resource-constrained devices. However, previous works have several weaknesses, including limited support various CNN structures, fixed scheduling strategies, overlapped computations, high synchronization overheads, etc. In this article, we present DeepSlicing,...

Wireless Sensor Networks (WSNs) are key for various applications that involve long-term and low-cost monitoring actuating. In these applications, sensor nodes use batteries as the sole energy source. Therefore, efficiency becomes critical. We observe many WSN require redundant to achieve fault tolerance Quality of Service (QoS) sensing. However, same redundancy may not be necessary multihop communication because light traffic load stable wireless links. this paper, we present a novel...

The advances of Radio-Frequency Identification (RFID) technology have significantly enhanced the capability capturing data from pervasive space. It becomes a great challenge in information era to effectively understand human behavior, mobility and activity through perceived RFID data. Focusing on management, this article provides an overview current challenges, emerging opportunities recent progresses RFID. In particular, has described analyzed research work three aspects: algorithm,...

Network virtualization provides a promising way to overcome Internet ossification. A major challenge is virtual network mapping, i.e., how embed multiple requests with resource constraints into substrate network, such that physical resources are utilized in an efficient and effective manner. Since this problem known be NP-complete, variety of heuristic algorithms have been proposed. In paper, we re-examine propose mapping framework, ORS TA, which based on Opportunistic Resource Sharing...

Wireless power transfer is a promising technology to extend the lifetime of, and thus enhance usability energy-hungry battery-powered devices. It enables energy be wirelessly transmitted from chargers receiving Existing studies have mainly focused on maximizing network lifetime, optimizing charging efficiency, minimizing delay, etc. Different these works, our objective optimize quality in 2-D target area. Specifically, we consider following charger Placement Power allocation Problem (P <sup...

As an important indicator of autonomic regulation for circulatory function, Heart Rate Variability (HRV) is widely used general health evaluation. Apart from using dedicated devices (e.g, ECG) in a wired manner, current methods search ubiquitous manner by either wearable devices, which suffer low accuracy and limited battery life, or applying wireless techniques (e.g., FMCW), usually utilize USRP) the measurement. To address these issues, we present RF-ECG based on Commercial-Off-The-Shelf...

Wireless power transfer is a promising technology used to extend the lifetime of, and thus enhance usability energy-hungry battery-powered devices. It enables energy be wirelessly transmitted from chargers energy-receiving Existing studies have mainly focused on maximizing network lifetime, optimizing charging efficiency, minimizing delay, etc. In this paper, we consider wireless service provision in two-dimensional target area focus quality, where of each charger adjustable. We first...

Real-time on-device object detection for video analytics fails to meet the accuracy requirement due limited resources of mobile devices while offloading inference edges is time-consuming transference data over edge networks. Based on system with both tracking and edge-assisted analysis, we formulate a non-linear time-coupled program time, maximizing overall by deciding frequency inference, under consideration dynamic networks constrained latency. We then design learning-based online...

Mobile Edge Computing (MEC) has become an attractive solution to enhance the computing and storage capacity of mobile devices by leveraging available resources on edge nodes. In MEC, arrivals tasks are highly dynamic hard predict precisely. It is great importance yet very challenging assign nodes with guaranteed system performance. this article, we aim optimize revenue earned each node optimally offloading We formulate revenue-driven online task (ROTO) problem, which proved be NP-hard. first...