Movie dubbing seeks to synthesize speech from a given script using a specific voice, while ensuring accurate lip synchronization and emotion-prosody alignment with the character’s visual performance. However, existing alignment approaches based on visual features face two key limitations: (1) they rely on complex, handcrafted visual preprocessing pipelines, including facial landmark detection and feature extraction; and (2) they generalize poorly to unseen visual domains, often resulting in degraded alignment and dubbing quality. To address these issues, we propose InstructDubber, a novel instruction-based alignment dubbing method for both robust in-domain and zero-shot movie dubbing. Specifically, we first feed the video, script, and corresponding prompts into a multimodal large language model to generate natural language dubbing instructions regarding the speaking rate and emotion state depicted in the video, which is robust to visual domain variations. Second, we design an instructed duration distilling module to mine discriminative duration cues from speaking rate instructions to predict lip-aligned phoneme-level pronunciation duration. Third, for emotion-prosody alignment, we devise an instructed emotion calibrating module, which fine-tunes an LLM-based instruction analyzer using ground truth dubbing emotion as supervision and predicts prosody based on the calibrated emotion analysis. Finally, the predicted duration and prosody, together with the script, are fed into the audio decoder to generate video-aligned dubbing. Extensive experiments on three major benchmarks demonstrate that InstructDubber outperforms state‑of‑the‑art approaches across both in‑domain and zero‑shot scenarios.

LEO satellite networks are emerging as a global-scale connectivity infrastructure for regions beyond the reach of terrestrial networks. Among them, satellite IoT targets low-power, low-cost IoT applications; however, our real-world measurements reveal that today's commercial satellite IoT still faces substantial challenges in supporting large-volume data transfer for real-world IoT applications. Our results show that a highly-compressed image of only tens of kilobytes typically takes 6–10 hours, extremely exceeding the application time requirements. We find that the bottleneck lies in the direct-to-satellite upload stage, where usable contacts are scarce and underutilized. Moreover, simply adding more nodes does not provide proportional gains, as beacon-triggered upload opportunities remain isolated and exhibit weak correlation. Based on this observation, we propose Co-DtS, a multi-interface upload system that promotes observed beacons into cross-interface coordination signals. Trace-driven evaluation with commercial devices shows that Co-DtS reduces image completion time from 7.62 hours to 0.9 hours.

User authentication is a critical component of IoT environments, serving as the security bridge between users and devices to safeguard data transmission and prevent unauthorized access. While WiFi-based authentication via motion recognition has shown potential in single-user scenarios, its effectiveness diminishes significantly in multi-user environments. Detecting subtle movements, such as breathing, from multiple users simultaneously poses a significant challenge, pushing the capabilities of current WiFi authentication systems to their limits. In this paper, we presentBreathEye, a multi-user authentication system that leverages only a pair of commercial WiFi devices to detect and authenticate the subtle respiratory patterns of multiple individuals simultaneously. The core insight of our approach lies in exploiting the inherent variability in individual breathing patterns, which manifest in short-term energy fluctuations and long-term dependencies within the breathing signals. To this end, we propose a dual-attention fusion mechanism that captures these subtle differences, enabling the effective disentanglement of individual breathing signals from overlapping multi-user data. To further enhance practicality,BreathEyeincorporates a few-shot learning framework to minimize user registration time and reduce system training overhead by analyzing independent breathing signals for authentication. Extensive experiments demonstrate thatBreathEyeachieves authentication accuracies of over 99%, 92%, and 87% in single-, two-, and three-user scenarios, respectively, highlighting the system's effectiveness.

Federated Learning (FL) has emerged as a privacy-preserving paradigm for training machine learning models across distributed edge devices in the Internet of Things (IoT). By keeping data local and coordinating model training through a central server, FL effectively addresses privacy concerns and reduces communication overhead. However, the limited computational power, memory, and bandwidth of IoT edge devices pose significant challenges to the efficiency and scalability of FL, especially when training deep neural networks. Various FL frameworks have been proposed to reduce computation and communication overheads through dropout or layer freezing. However, these approaches often sacrifice accuracy or neglect memory constraints. To this end, in this work, we introduce Federated Learning with Ordered Layer Freezing (FedOLF). FedOLF consistently freezes layers in a predefined order before training, significantly mitigating computation and memory requirements. To further reduce communication and energy costs, we incorporate Tensor Operation Approximation (TOA), a lightweight alternative to conventional quantization that better preserves model accuracy. Experimental results demonstrate that over non-iid data, FedOLF achieves at least 0.3%, 6.4%, 5.81%, 4.4%, 6.27% and 1.29% higher accuracy than existing works respectively on EMNIST (with CNN), CIFAR-10 (with AlexNet), CIFAR-100 (with ResNet20 and ResNet44), and CINIC-10 (with ResNet20 and ResNet44), along with higher energy efficiency and lower memory footprint.

Blood pressure (BP) measurement is an indispensable tool in diagnosing and treating many diseases such as cardiovascular failure and stroke. Traditional direct measurement can be invasive, and wearable-based methods may have limitations of discomfort and inconvenience. Contact-free BP measurement has been recently advocated as a promising alternative. In particular, Millimeter-wave (mmWave) sensing has demonstrated its promising potential, however it is confronted with several challenges including noise and vulnerability to human's tiny motions which may occur intentionally and inevitably. In this paper, we propose mmBP+, a contact-freemmWave-basedBPmeasurement system with high accuracy and motion robustness. Due to the high frequency and short wavelength, mmWave signals received in the time domain are dramatically susceptible to ambient noise, and deteriorating signal quality. To reduce noise,we propose a novel approach to exploit mmWave signal's characteristics and features in the delay-Doppler-fractional Fourier domain to significantly improve signal quality for pulse waveform construction. We also propose a periodic signal feature based functional link adaptive filter leveraging on the periodic and correlation characteristics of pulse waveform signals to alleviate the impact of human's tiny motions. Extensive experiment results achieved by the leave-one-out cross-validation (LOOCV) method demonstrate that mmBP+ achieves the mean errors of 0.65mmHg and 1.31mmHg for systolic blood pressure (SBP) and diastolic blood pressure (DBP), respectively; and the standard deviation errors of 3.92mmHg and 3.99mmHg for SBP and DBP, respectively.

Physical-layer key generation holds significant potential in establishing cryptographic key pairs for emerging LoRa networks. Nevertheless, current key generation solutions may underperform due to critically impaired channel reciprocity, attributed to the low data rate and long range inherent in LoRa networks. In this study, we presentChirpKey, a novel key generation scheme for LoRa networks. We pinpoint the key hurdles as the coarse-grained channel measurement, inefficient quantization methods, and out-of-range device constraints. To capture fine-grained channel information, we introduce a unique, LoRa-specific channel measurement method that focuses on analyzing chirp-level variations in LoRa packets. We also propose a LoRa channel state estimation algorithm to neutralize asynchronous channel sampling. Instead of the traditional quantization approach, we propose an innovative key delivery method based on perturbed compressed sensing, offering enhanced robustness and security. For LoRa devices beyond each other's communication reach, we integrate relay nodes to ensure reliable key generation. To foster secure group communication, we formulate two protocols that facilitate collaborative key generation across both star and chain configurations. Evaluation across diverse real-world scenarios reveals thatChirpKeyenhances the key matching rate by 11.03–26.58% and increases the key generation rate by 27–49× in comparison to existing leading systems. Our security analysis shows thatChirpKeycan effectively withstand a variety of prevalent attacks. Furthermore, we implement aChirpKeyprototype, demonstrating its capability to operate within 0.2 s.

Advances in large language models (LLMs) have opened up new possibilities across various fields, fueling a new wave of interactive AI applications such as DeepSeek and ChatGPT. Inference serving systems play a crucial role in supporting these applications. Recent research indicates that when crossserver parallelization is enabled in inference serving systems, data synchronization overhead can exceed 65% of the total inference delay, making the reduction of communication overhead essential for speeding up inference. While existing systems accelerate cross-server communications by offloading synchronization operations to programmable switches, they often suffer from limited aggregation throughput under bursty traffic conditions, posing challenges for homogeneous network environments. To address these challenges, we propose HeroServe, an innovative inference serving system that leverages heterogeneous networks to accelerate data synchronization in distributed clusters. Our approach enables a fast and scalable inference serving system by employing an offline planner for joint computation allocation and communication scheduling, along with an online scheduler for dynamic traffic management and load balancing. We implement a prototype on a testbed comprising six servers and two programmable switches. Experimental results demonstrate that HeroServe improves scalability by$1.53 \times$while achieving lower latency compared to state-of-the-art solutions.

Low Earth Orbit (LEO) satellites have emerged as a space-based infrastructure to offer networking services anywhere on Earth. Satellite IoTs enable novel Direct-to-Satellite (DtS) connectivity, allowing IoT devices in remote areas to connect to the Internet via LEO satellites using existing terrestrial technologies like LoRa. This paper presents the first-of-its-kind measurement study on satellite IoTs, investigating the practical characteristics of DtS communications and their suitability for IoT applications. We deployed 27 low-cost ground stations across eight locations worldwide to passively measure the network availability of multiple constellations. Our findings reveal a significant gap between the effective durations of DtS connectivity and their theoretical durations, leading to intermittent connections for satellite IoTs. Additionally, we examine the performance of the Tianqi constellation in supporting real-world IoT traffic (agriculture application). We observed longer delays and higher power consumption in satellite IoTs compared to terrestrial IoTs. Our study identifies the bottlenecks and sheds light on potential optimizations for satellite IoTs.

This paper addresses the interference challenges, aiming to improve spatial reuse and optimize spectrum efficiency in LPWANs. We reveal that existing strategies such as interference cancellation and MIMO are ill-suited to the low-cost low-rate characteristics of LPWANs. Our work introduces a novel framework, HydraNet, which leverages the capture effect of LPWAN radios to enable robust concurrent transmissions. HydraNet exempts from strict clock synchronization or accurate channel estimation as required by conventional spatial reuse strategies for interference nulling. We conduct in-depth studies with LoRa radios to uncover their underlying packet reception mechanisms and for the first time characterize their unique capture effect. Based on the new findings, we devise novel strategies to jointly control the timing and power of concurrent LPWAN transmissions. These strategies ensure sufficient power differences between packets and interference at their intended receivers. We prototype HydraNet and integrate with operational LoRaWANs and comprehensively evaluate its performance. Results show that HydraNet achieves higher spectrum utilization with up to 3.6 × throughput improvements over the state-of-the-art.

The recent proliferation of spacecraft in Earth's orbits has ushered in the rise of large-scale satellite constellations. However, this unprecedented growth of constellations has introduced a previously unforeseen challenge: ground track congestion. Specifically, the increasing density of orbital slots forces satellites to share similar orbit planes, causing their nadir-point projections on Earth's surface (i.e., ground tracks) to overlap or remain in close proximity within short time intervals. Such orbit-endowed ground track congestion can degrade constellation performance in remote sensing operations, specified by limited constellation coverage, redundant satellite count, and delayed data delivery.

LoRa technology promises to enable Internet of Things applications over large geographical areas. However, its performance is often hampered by poor channel quality in urban environments, where blockage and multipath effects are prevalent. Our study uncovers that a slight shift in the position or attitude of the receiving antenna can substantially improve the received signal quality. This phenomenon can be attributed to the rich multipath characteristics of wireless signal propagation in urban environments, wherein even small antenna movement can alter the dominant signal path or reduce the polarization angular difference between transceivers. Leveraging these key observations, we propose and implement MoLoRa, an intelligent mobile antenna system designed to enhance LoRa packet reception. At its core, MoLoRa represents the position and attitude of an antenna as a state and employs a statistical optimization method to search for states that offer optimal signal quality efficiently. Through extensive evaluation, we demonstrate that MoLoRa achieves a maximum Signal-to-Noise Ratio (SNR) gain of 13 dB in a few attempts, enabling formerly problematic blind spots to reconnect and strengthening links for other nodes.

Spectrum competition and hardware complexity inherent in communication and radar systems can be alleviated by a dual-function radar communication (DFRC) systems. However, enhancing detection capabilities for maneuvering or weak targets remains a significant challenge, as traditional radar signal accumulation algorithms are not directly applicable to DFRC systems. This article proposes a novel method that integrates signal accumulation and parameter estimation for target detection in DFRC systems. The approach employs an orthogonal frequency division multiplexing (OFDM) waveform within a multiple-input-multiple-output (MIMO) framework, enabling the detection of high-speed or weak targets through a computationally efficient signal accumulation process. The proposed method comprises three key steps: first, the designed signals combined with the multiple signal classification (MUSIC) algorithm for target angle estimation in the spatial domain. Second, a two-step signal accumulation process is introduced, which separately extracts range and velocity information for weak or high-speed targets. Third, acceleration is derived based on velocity information and accumulation time. We present explicit expressions and detailed analyses of various performance metrics, including accumulation output response for high-speed targets, multiple target scenarios, and cases with low-signal-to-noise ratio (SNR). Additionally, Cramér-Rao bounds (CRBs) for azimuth, range cell, and velocity cell estimation in DFRC MIMO-OFDM systems are derived. Simulation results validate the proposed method, demonstrating its superior target detection performance compared to existing techniques.

Dual-function radar-communication (DFRC) systems are key to addressing spectrum congestion and hardware constraints in future 5G/6G networks. Among various DFRC waveform candidates, OFDM stands out for its flexibility, but its high range sidelobes pose challenges for weak target detection in cluttered environments. In this work, we propose a novel waveform optimization framework that jointly minimizes the peak sidelobe level (PSL), maintains a low symbol error rate (SER), and enforces constant envelope constraints. To solve the resulting non-convex, NP-hard problem efficiently, we introduce a Block-wise Majorization-Minimization (BWMM) algorithm that iteratively refines the phase of each OFDM symbol to suppress both auto- and cross-correlation sidelobes. Theoretical analysis and simulation results validate that the proposed BWMM-PSL method significantly enhances radar sensing performance while preserving communication reliability.

Acoustic sensing for heartbeat monitoring has emerged as a prevailing research topic in wireless sensing. However, existing acoustic sensing systems face two limitations: a restricted sensing range and operation limited to a single user, impeding large-scale deployment of its applications. In this paper, we present DF-Sense, aDualForming based multi-user acousticSensingsystem for heartbeat monitoring in home settings. Specifically, we design a novel sensing signal-to-noise ratio (SSNR) enhancement model, namelyDualforming, which leverages constructive superposition across multiple subcarriers and microphones. To facilitateDualforming, we propose a novel MUltiple Subtle SIgnal Classification (MUS2IC) method and a 2-D peak identification scheme to locate and identify multiple subjects with subtle motions. Additionally, we propose a phase change-based method to promptly identify body leaning and adaptively re-localize subjects, thereby avoiding the high computational cost. Finally, we propose an enhanced recursive least squares (RLS) filter to effectively reconstruct high-quality heartbeat waveforms from Channel Frequency Response (CFR) signals affected by limb movements. Experimental results show that DF-Sense achieves high precision measurement of instantaneous heart rates within a range of 10 m, sufficient for most daily space requirements, and can monitor heartbeat for up to 6 subjects in a 2-D space.

LoRa is a promising technology that provides widespread low-power IoT connectivity. With its capabilities for multi-channel communication, orthogonal transmission, and spectrum sharing, LoRaWAN is poised to connect millions of IoT devices across thousands of logical channels. However, current LoRa gateways rely on hardwired Rx chains that cover less than 1% of these channels, restricting the potential for large-scale LoRa communications. This paper introduces XGate, a groundbreaking gateway design that uses a single Rx chain to simultaneously receive packets from all logical channels, enabling scalable LoRa transmission and flexible network access. Unlike the hardwired Rx chains in existing gateway designs, XGate dynamically allocates resources, including software-controlled Rx chains and demodulators, based on the extracted meta-information of incoming packets. XGate overcomes several challenges to efficiently detect incoming packets without prior knowledge of their parameter configurations. Evaluations demonstrate that XGate enhances LoRa concurrent transmissions by$8.4\times $compared to state-of-the-art solutions.

Image super-resolution (SR) is widely used on mobile devices to enhance user experience. However, neural networks used for SR are computationally expensive, posing challenges for mobile devices with limited computing power. A viable solution is to use heterogeneous processors on mobile devices, especially the specialized hardware AI accelerators, for SR computations, but the reduced arithmetic precision on AI accelerators can lead to degraded perceptual quality in upscaled images. To address this limitation, in this paper we present SR For Your Eyes (FYE-SR), a novel image SR technique that enhances the perceptual quality of upscaled images when using heterogeneous processors for SR computations. FYE-SR strategically splits the SR model and dispatches different layers to heterogeneous processors, to meet the time constraint of SR computations while minimizing the impact of AI accelerators on image quality. Experiment results show that FYE-SR outperforms the best baselines, improving perceptual image quality by up to 2×, or reducing SR computing latency by up to 5.6× with on-par image quality.

LoRa is a promising technology that offers ubiquitous low-power IoT connectivity. With the features of multi-channel communication, orthogonal transmission, and spectrum sharing, LoRaWAN is poised to connect millions of IoT devices across thousands of logical channels. However, current LoRa gateways utilize hardwired Rx chains that cover only a small fraction (<1%) of the logical channels, limiting the potential for massive LoRa communications. This paper presents XGate, a novel gateway design that uses a single Rx chain to concurrently receive packets from all logical channels, fundamentally enabling scalable LoRa transmission and flexible network access. Unlike hardwired Rx chains in the current gateway design, XGate allocates resources including software-controlled Rx chains and demodulators based on the extracted meta information of incoming packets. XGate addresses a series of challenges to efficiently detect incoming packets without prior knowledge of their parameter configurations. Evaluations show that XGate boosts LoRa concurrent transmissions by 8.4× than state-of-the-art.

Diverse Wi-Fi-based wireless applications have been proposed, ranging from daily activity recognition to vital sign monitoring. Despite their remarkable sensing accuracy, the high energy consumption and the requirement for customized hardware modification hinder the wide deployment of the existing sensing solutions. In this paper, we propose REHSense, an energy-efficient wireless sensing solution based on Radio-Frequency (RF) energy harvesting. Instead of relying on a power-hungry Wi-Fi receiver, REHSense leverages an RF energy harvester as the sensor and utilizes the voltage signals harvested from the ambient Wi-Fi signals to enable simultaneous context sensing and energy harvesting. We design and implement REHSense using a commercial-off-the-shelf (COTS) RF energy harvester. Extensive evaluation of three fine-grained wireless sensing tasks (i.e., respiration monitoring, human activity recognition, and hand gesture recognition) shows that REHSense can achieve comparable sensing accuracy with conventional Wi-Fi-based solutions while adapting to different sensing environments, reducing the power consumption of sensing by 98.7% and harvesting up to 4.5 mW of power from RF energy.

User authentication is crucial for maintaining privacy. However, most existing methods are designed for single-user scenarios and may not be efficient for multiple users. To address this issue, we propose M-Auth, a Multiuser Authentication system that utilizes a commercial mmWave radar to detect the unique breathing pattern. We exploit the phenomenon that chest movements due to breathing can alter radio frequency signals. To make M-Auth more effective in capturing signals from multiple users, we design an auxiliary rotating gadget to adjust the radar orientation dynamically. By using mmWave’s high directivity, we can isolate individual components from blended RF signals and focus on reflections from different positions. We propose an energy comparison method to filter out irrelevant body movements and retain fine-grained respiration traits. Subsequently, we develop a feature selection pipeline to extract the most informative features and train a machine learning-based classifier to identify each user. M-Auth is practical because it is non-contact and passive, and it is secure because respiration is unique and challenging to forge. Extensive experiments with 37 participants demonstrate that M-Auth is effective in verifying legitimate users and thwarting spoofing attacks, with an authentication accuracy of over 96% and an attack detection rate of over 95%.

Wireless signal analytics in IoT systems can enable various promising wireless sensing applications such as localization, anomaly detection, and human activity recognition. As a matter of fact, there are significant correlations in terms of dimension, spatial and temporal aspects among wireless signals from multiple sensors. However, none of the wireless sensing research currently in use directly incorporates or exploits the signal correlations. Therefore, there is still substantial scope for improvement in regards to accuracy and robustness. We are introducing a novel framework called Signal Correlation Learning (SCL). This framework utilizes a directed graph to explicitly represent the signal correlation across various wireless sensors. We use signal embedding to depict the correlation features of a multi-dimensional sensor that arise from a multi-sensor system. Then, we perform Kullback-Leibler (KL) divergence on embedding vectors of any pair of sensors in the system to construct a subgraph at a given time point, which can measure the spatial signal correlation of sensors. Subsequently, several subgraphs spanning a specific time frame are fused into a coherent universal graph based on the small-world theory. This universal graph represents the three types of signal correlation simultaneously. A signal correlation aggregation structure is utilized to extract the features from the universal graph. These features can be used to address target sensing problems. We implement SCL in real RFID, Bluetooth, WIFI, and Zigbee systems, and evaluate its performance in three common wireless sensing problems including localization, anomaly detection, and human activity recognition. Extensive experiments demonstrate that our SCL framework significantly outperforms state-of-the-art wireless sensing algorithms by increasing$80\%\sim 190\%$in terms of accuracy, and by increasing$160\%\sim 220\%$in terms of robustness.

Indoor intrusion detection is a critical task for home security. Previous works in intrusion detection suffer from the problems such as blind spots in non-line-of-sight (NLOS) areas, restricted device locations, massive offline training required, and privacy concern. In this article, we design and implement an omnidirectional indoor intrusion detection system, named AudioGuard , using only a pair of speaker and microphone. AudioGuard is able to detect both line-of-sight (LOS) and NLOS intrusions. Our observation of acoustic signal propagation in an indoor environment shows that there exist abundant multipath reflections and human movement introduces Doppler shift in echo signals. We hence capture periodical Doppler shift caused by intruder's walking motion to detect intrusion. Specifically, we first extract the Doppler shift embedded in echo signals, and we then propose a periodicity polarization method to cancel out the impact of the change of radial angle and the distance on periodicity of Doppler shift. Finally, we detect intrusion by measuring periodicity of Doppler shift over time. Extensive experiments show that AudioGuard achieves a miss report rate of 0% and 1.75% for LOS and NLOS intrusion, respectively, and a false alarm rate of 4.17%.

With the rapid development of 5G technologies, the demand of quality of service (QoS) from edge users, including high bandwidth and low latency, has increased dramatically. QoS within a mobile edge network is highly dependent on the allocation of edge users. However, the complexity of user movement greatly challenges edge user allocation, leading to privacy leakage. In addition, updating massive data constantly in a dynamic mobile edge network also crucial to ensure efficiency. To address these challenges, this paper proposes a dynamic QoS optimization strategy (MENIFLD_QoS) in mobile edge networks based on incremental learning and federated learning.MENIFLD_QoSoptimizes service cache in edge regions and allocates edge servers to edge users according to the locations of edge servers accessed by edge users in mobile scenarios. While optimizing regional service quality, the system can effectively protect user privacy. In addition, for dynamic incremental data,MENIFLD_QoStrains updated data based on the strategy of incremental learning hence significantly improves optimization speed. Experimental results on an edge QoS dataset show that the proposed strategy achieves global optimization in both multi-variable and multi-peak user allocation scenarios and notably enhances the training efficiency of the regional invocation model.

Fine-grained recognition of human manipulation activities on objects is crucial in the era of human-computer-object integration. However, there is a lack of solutions for simultaneous recognition of human identity, manipulation activities (including drawing and rotation), and manipulated objects. Therefore, we propose an RF-Camera system that combines RFID and computer vision techniques to address this challenge in multi-person and multi-object scenarios. In RF-Camera, we employ a skeleton-assisted method to extract facial images of target individuals, enabling precise recognition of their identities. To identify manipulation activities, we analyze the 3D hand trajectory and fingertip vector angle, differentiating drawing and rotation manipulation activities. Additionally, we model target person?s hand movements to predict phase data of the target tag, enabling the determination of person-object relationships. Implementing RF-Camera using COTS RFID and Kinect devices involves overcoming challenges such as extracting effective data from noisy streams, predicting virtual phase data considering hand-tag offset, and ensuring high tag reading rates in tag-dense scenarios. We conducted experiments involving six participants performing object manipulation activities, including drawing letters/symbols and rotating movements. Extensive experimental results show that RF-Camera achieves over 90% accuracy in recognizing person identity, manipulation activities, and person-object matching in most conditions.

Federated Learning (FL) achieves great popularity in the Internet of Things (IoT) as a powerful interface to offer intelligent services to customers while maintaining data privacy. Under the orchestration of a server, edge devices (also called clients in FL) collaboratively train a global deep-learning model without sharing any local data. Nevertheless, the unequal training contributions among clients have made FL vulnerable, as clients with heavily biased datasets can easily compromise FL by sending malicious or heavily biased parameter updates. Furthermore, the resource shortage issue of the network also becomes a bottleneck. Due to overwhelming computation overheads generated by training deep-learning models on edge devices, and significant communication overheads for transmitting deep-learning models across the network, enormous amounts of resources are consumed in the FL process. This encompasses computation resources like energy and communication resources like bandwidth. To comprehensively address these challenges, in this paper, we present FLrce, an efficient FL framework with arelationship-basedclient selection andearly-stopping strategy. FLrce accelerates the FL process by selecting clients with more significant effects, enabling the global model to converge to a high accuracy in fewer rounds. FLrce also leverages an early stopping mechanism that terminates FL in advance to save communication and computation resources. Experiment results show that, compared with existing efficient FL frameworks, FLrce improves the computation and communication efficiency by at least 30% and 43% respectively.

Recent research has been exploring ways to streamline device pairing by introducingtouch-to-accessthat minimizes user interaction. It generates pairing keys by extracting features from a shared information source to ascertain if two devices are being held by the same person. While these solutions focus on verifying the authenticity of the device, they do not consider the legitimacy and pairing intent of the device holder. Moreover, the pairing keys exchanged over an open wireless link may be susceptible to eavesdropping attacks. In this paper, we propose a secure device pairing mechanism that utilizes the unique electrical responses of the human body to generate and transmit user-specific pairing keys, ensuring both the user's legitimacy and pairing intent while also improving key transmission reliability. We accomplish this by using the device's built-in microphone to capture ambient sound as entropy and converting it into an electrical signal transmitted by the body for device pairing. We have built a prototype and conducted extensive experiments with 31 participants to evaluate its security and usability. The results demonstrate that our proposed mechanism offers a more secure and reliable option for user-specific pairing keys, contributing to the field of device pairing.

In recent years, we have seen efforts made to monitor respiration for multiple users. Existing approaches capture chest movement relying on signals directly reflected from chest or separate breath waves based on breath rate difference between subjects. However, several limitations exist: 1) they may fail when subjects face away from the transceiver or are blocked by obstacles or other subjects; 2) they may fail to separate subjects' breath waves with the same or similar rates (i.e., breath rate differenceMultiResp, a multi-user respiration monitoring system using acoustic signal. By fully leveraging the abundant acoustic signals reflected indirectly from subjects' chest,MultiRespcan robustly capture chest movement even when they face away from the transceiver or are blocked. By extracting fine-grained breath rate and phase difference between different subjects,MultiRespcan separate the breath waves with the same or similar rates and adapt to dynamic change of subject number during monitoring. Extensive experiments show thatMultiRespis able to accurately monitor the respiration of multiple users with a median error of 0.3 bpm in various indoor scenarios, however, it fails when the sound pressure is lower than 55 dB or body movement is happening.

Contactless respiration monitoring using wireless signals has drawn much attention in recent years. Many approaches have been proposed, however, they may not work when there is a lack of signals directly reflected from target's chest, e.g., a target faces away from the transceiver or a target is blocked by furniture. In this paper, we design and implement a novel omnimonitoring system for human respiration,OmniRespMonitor, using a pair of speaker and microphone. Different from Radio Frequency (RF) signal, acoustic signals cannot penetrate through walls and furniture. The multipath reflection in an indoor environment will result in highly abundant acoustic signals. In this case, even though there are lack of acoustic signals directly reflected by a target's chest, indirectly-reflected acoustic signals can still be received by the microphone. We can therefore monitor the target's respiration by extracting this subtle variation of indirectly reflected signals. To achieve this, we model chest movement using truncated System Frequency Response (SFR). We then develop a global search method based on the autocorrelation function to extract minute chest movement from SFR sequences. Finally, we dynamically synthesize the chest movement information to recover the breathing wave in real time. We conduct extensive experiments with both humans and animals (goat), the results show thatOmniResMonitoris able to monitor single target's respiration within 5 meters in indoor environments in various challenging scenarios there are lack of directly-reflected acoustic signals.

Nowadays, to realize the intelligent manufacturing in Industrial Internet of Things (IIoT) scenarios, novel approaches in computer vision are in great demand to tackle the new challenges in IIoT environment. These approaches, which we callIndustrial Vision, are expected to offer customized solutions for intelligent manufacturing in an accurate, time efficient and robust manner. In this paper, we propose a novel approach to industrial vision, calledEdge-Eye, to rectify the edge deviation automatically for Irradiated Cross-linked Polyethylene Foam (IXPE) production with millimeter-level accuracy. IXPE has been one of the most commonly used materials in industry. During the production process of IXPE sheets, their edges need keep aligned strictly, otherwise, they could quickly get out of the border of the rolling plate and cause the huge economic loss. We deploy a commercial camera with mobile edge node in front of the IXPE sheet to continuously detect and rectify the edge deviation. Particularly, to handle the complex production environment when extracting the edge of IXPE sheet, we deploy a pair of reference bars with high-contrast colors to efficiently differentiate the sheet edge from the background. Then, we propose aBi-direction Edge Tracking methodto perform the edge detection from both vertical and horizontal aspects. To realize the rectification using mobile edge nodes with limited computing resources, we reduce the cost of computation by extracting theMinimized Region of Interest, i.e., the edge area overlapped with the higher contrast reference bar on both sides. We further design a negative feedback control system with multi-stage feedback regulation mechanism, keeping the edge deviation withinmillimeter-level. We implementedEdge-Eyeon the ARM64 platform and performed evaluation in the practical IXPE production process. The experimental results show thatEdge-Eyeachieves the average accuracy of 5 mm for the edge deviation rectification, with the average latency of 200 ms for edge deviation detection. During the process of 20-month real deployment for 36 production lines, 66 manpower per day (90% of the overall manpower) has been saved, and the utilization rate of IXPE material increases from 87% to 94%.

This paper presents the design and implementation of HyLink which aims to fill the gap between limited link capacity of LoRa and the diverse bandwidth requirements of IoT systems. At the heart of HyLink is a novel technique named parallel Chirp Spread Spectrum modulation, which tunes the number of modulated symbols to adapt bit-rates according to channel conditions. Over strong link connections, HyLink fully exploits the link capability to transmit more symbols and thus transforms good channel SNRs to high link throughput. While for weak links, it conservatively modulates one symbol and concentrates all transmit power onto the symbol to combat poor channels, which can achieve the same performance as legacy LoRa. HyLink addresses a series of technical challenges on encoding and decoding of multiple payloads in a single packet, aiming at amortizing communication overheads in terms of channel access, radio-on power, transmission air-time, etc. We perform extensive experiments to evaluate the effectiveness of HyLink. Evaluations show that HyLink produces up to$10\times $higher bit rates than LoRa when channel SNRs are higher than$\mathrm {5 dB}$. HyLink inter-operates with legacy LoRa devices and can support new emerging traffic-intensive IoT applications.

A wide range of scenarios, such as warehousing, and smart manufacturing, have used RFID mobile robots for the localization of tagged objects. The state-of-the-art RFID-robot based localization works are based on the premise of stable speed. However, in reality this assumption can hardly be guaranteed because Commercial-Off-The-Shelf (COTS) robots typically have inconsistent moving speeds, and a small speed inconsistency will cause a large localization error. To this end, we propose a Speed Inconsistency-Immune approach to mobile RFID robot Localization (SILoc) system, which accurately locates targets when the robot moving speed varies or is even unknown. We propose an optimized unwrapping method to maximize the use of data, and a lightweight algorithm to calculate the locations in both 2D and 3D spaces. By utilizing the characteristics of tag-antenna distance and combining the phase data from multiple antennas, SILoc can effectively eliminate the side effects of speed inconsistency. To increase the flexibility, we further optimize the system and propose SILoc$+$, which enables the system to achieve localization with part of the data, keeping speed inconsistency-immune. Extensive experiments demonstrate that SILoc and SILoc$+$can achieve a centimeter-level localization accuracy in the scenario with an inconsistent or unknown robot moving speed.

The widespread deployment of unattended LoRa networks poses a growing need to perform Firmware Updates Over-The-Air (FUOTA). However, the FUOTA specifications dedicated by LoRa Alliance fall short of several deficiencies with respect to energy efficiency, transmission reliability, multicast fairness, and security. This article proposes FLoRa+ , energy-efficient, reliable, beamforming-assisted, and secure FUOTA for LoRa networks, which is featured with several techniques, including delta scripting, channel coding, beamforming, and securing mechanisms. Specifically, we first propose a joint differencing and compression algorithm to generate the delta script for processing gain, which unlocks the potential of incremental FUOTA in LoRa networks. Then, we design a concatenated channel coding scheme with outer rateless code and inner error detection to enable reliable transmission for coding gain. Afterward, we develop a beamforming strategy to avoid biased multicast and compromised throughput for power gain. Finally, we present a securing mechanism incorporating progressive hash chain and packet arrival time pattern verification to countermeasure firmware integrity and availability attacks for security gain. Experimental results on a 20-node testbed demonstrate that FLoRa+ improves transmission reliability and energy efficiency by up to 1.51× and 2.65× compared with LoRaWAN. Additionally, FLoRa+ can defend against 100% and 85.4% of spoofing and Denial-of-Service (DoS) attacks.

Sensing in Integrated Sensing and Communications (ISAC) systems with clock asynchronism between the transmitter and receiver poses significant challenges. Understanding the fundamental limits of sensing performance in such setups, which remain largely unknown, is crucial. This paper investigates the sensing performance bounds in the presence of clock asynchronism. In both single-carrier and multi-carrier models, we derive the Cramér-Rao bounds (CRB) for estimating dynamic channel path parameters including angle of arrival, delay, and complex gain sequence (CGS). Through mathematical analyses and numerical simulations, we conduct a comprehensive study on how these bounds depend on various system parameters and the impact of clock asynchronism. Our findings highlight the degradation of parameter estimation performance due to clock asynchronism and reveal low-accuracy zones for CGS estimation in strong-line-of-sight scenarios. Additionally, we observe asymptotic mitigation in performance degradation with larger bandwidth, providing valuable insights for system design and optimization.

Physical-layer key generation is promising in establishing a pair of cryptographic keys for emerging LoRa networks. However, existing key generation systems may perform poorly since the channel reciprocity is critically impaired due to low data rate and long range in LoRa networks. To bridge this gap, this paper proposes a novel key generation system for LoRa networks, named ChirpKey. We reveal that the underlying limitations are coarse-grained channel measurement and inefficient quantization process. To enable fine-grained channel information, we propose a novel LoRa-specific channel measurement method that essentially analyzes the chirp-level changes in LoRa packets. Additionally, we propose a LoRa channel state estimation algorithm to eliminate the effect of asynchronous channel sampling. Instead of using quantization process, we propose a novel perturbed compressed sensing based key delivery method to achieve a high level of robustness and security. Evaluation in different real-world environments shows that ChirpKey improves the key matching rate by 11.03–26.58% and key generation rate by 27–49× compared with the state-of-the-arts. Security analysis demonstrates that ChirpKey is secure against several common attacks. Moreover, we implement a ChirpKey prototype and demonstrate that it can be executed in 0.2 s.

LoRa has emerged as one of the promising long-range and low-power wireless communication technologies for Internet of Things (IoT). With the massive deployment of LoRa networks, the ability to perform Firmware Update Over-The-Air (FUOTA) is becoming a necessity for unattended LoRa devices. LoRa Alliance has recently dedicated the specification for FUOTA, but the existing solution has several drawbacks, such as low energy efficiency, poor transmission reliability, and biased multicast grouping. In this paper, we propose a novel energy-efficient, reliable, and beamforming-assisted FUOTA system for LoRa networks named FLoRa, which is featured with several techniques, including delta scripting, channel coding, and beamforming. In particular, we first propose a novel joint differencing and compression algorithm to generate the delta script for processing gain, which unlocks the potential of incremental FUOTA in LoRa networks. Afterward, we design a concatenated channel coding scheme to enable reliable transmission against dynamic link quality. The proposed scheme uses a rateless code as outer code and an error detection code as inner code to achieve coding gain. Finally, we design a beamforming strategy to avoid biased multicast and compromised throughput for power gain. Experimental results on a 20-node testbed demonstrate that FLoRa improves network transmission reliability by up to 1.51 × and energy efficiency by up to 2.65 × compared with the existing solution in LoRaWAN.

LoRa has emerged as a novel Internet of Things (IoT) communication paradigm, featuring with long-range and low-power transmission capabilities. With the widespread deployment of LoRa networks, the demand to perform Firmware Update Over-The-Air (FUOTA) tasks has become increasingly critical for unattended LoRa devices. However, in practice, three fundamental problems that hinder the performance of FUOTA tasks are revealed, including low energy efficiency, poor transmission reliability, and biased multicast grouping. In this demo, we present a novel FUOTA system, the first work that offers an effective and sustainable solution to achieve energy-efficient and reliable over-the-air firmware updates in LoRa networks. In particular, this system incorporates threefold key modules: delta scripting, channel coding, and beamforming. The delta scripting algorithm unlocks the capability of incremental update, the channel coding scheme ensures the reliability and robustness of large-scale firmware image distribution, and the beamforming strategy as an optional module can further serve the unicast user. Thus, this demo presents a working example of functionality customization to show the efficacy and feasibility of our FUOTA system in LoRa networks.

Facial expression recognition plays a vital role to enable emotional awareness in multimedia Internet of Things applications. Traditional camera or wearable sensor based approaches may compromise user privacy or cause discomfort. Recent device-free approaches open a promising direction by exploring Wi-Fi or ultrasound signals reflected from facial muscle movements, but limitations exist such as poor performance in presence of body motions and not being able to detect multiple targets. To bridge the gap, we propose mmFER, a novel millimeter wave (mmWave) radar based system that extracts facial muscle movements associated with mmWave signals to recognize facial expressions. We propose a novel dual-locating approach based on MIMO that explores spatial information from raw mmWave signals for face localization in space, eliminating ambient noise. In addition, collecting mmWave training data can be very costly in practice, and insufficient training dataset may lead to low accuracy. To overcome, we design a cross-domain transfer pipeline to enable effective and safe model knowledge transformation from image to mmWave. Extensive evaluations demonstrate that mmFER achieves an accuracy of 80.57% on average within a detection range between 0.3m and 2.5m, and it is robust to various real-world settings.

Acoustic sensing for heartbeat monitoring has become a prevailing research topic in wireless sensing. Existing acoustic sensing systems have two limitations---limited sensing range, and heartbeat monitoring for a single user only, hindering the large-scale deployment of applications. In this paper, we present DF-Sense, a Dual Forming based multi-user acoustic Sensing system for heartbeat monitoring in home settings. Specifically, we design a novel sensing signal-to-noise ratio (SSNR) enhancement model, namely Dualforming, based on the constructive superposition across multiple subcarriers and microphones, and further build the quantitative relationship between critical factors and SSNR enhancement to optimize sensing performance. To enable Dualforming, we propose a novel MUltiple Subtle SIgnal Classification (MUS2IC) method to identify multiple subjects with subtle motions. We implement DF-Sense using commercial acoustic devices and conduct extensive experiments in a home setting. Results show that DF-Sense achieves high precision measurement of instantaneous heart rate within the range of 10 m, which is sufficient for most daily space requirements, and is able to monitor heartbeat for up to 6 subjects in a 2-D space simultaneously.

Radio Frequency (RF)-based gait recognition has emerged as a promising technology to authenticate individuals in a pervasive and unobtrusive way. However, a fundamental challenge remains in collecting extensive data of the same user in the same environment. To address this challenge, this paper introduces XGait, a cross-modal gait recognition framework that does not require the prior deployment of RF devices or explicit data collection. The key idea is to leverage the signals of the Inertial Measurement Unit (IMU), which is widely available in modern mobile devices, to simulate the RF signals that would be generated if the same person walked near RF devices. Despite the straightforward idea, several technical challenges need to be addressed due to the diversity of RF devices, the intrinsic difference between IMU signals and RF signals, and the complexity of gait. First, we propose an RF spectrogram generation method to consistently extract essential RF gait data features across different RF signals. Secondly, we propose a generative network-enabled IMU-to-RF translation approach that accurately converts IMU data to RF data. Finally, we design an RF gait spectrogram-specific transformer model to further improve the recognition performance. We conduct a comprehensive evaluation of XGait, involving thirty subjects in three different environments, utilizing three RF devices and seven mobile devices. Experimental results show that XGait consistently achieves over 99% Top-3 accuracy in various scenarios.

Training machine learning (ML) models on mobile and Web-of-Things (WoT) has been widely acknowledged and employed as a promising solution to privacy-preserving ML. However, these end-devices often suffer from constrained resources and fail to accommodate increasingly large ML models that crave great computation power. Offloading ML models partially to the cloud for training strikes a trade-off between privacy preservation and resource requirements. However, device-cloud training creates communication overheads that delay model training tremendously. This paper presents EdgeMove, the first device-edge training scheme that enables fast pipelined model training across edge devices and edge servers. It employs probing-based mechanisms to tackle the new challenges raised by device-edge training. Before training begins, it probes nearby edge servers’ training performance and bootstraps model training by constructing a training pipeline with an approximate model partitioning. During the training process, EdgeMove accommodates user mobility and system dynamics by probing nearby edge servers’ training performance adaptively and adapting the training pipeline proactively. Extensive experiments are conducted with two popular DNN models trained on four datasets for three ML tasks. The results demonstrate that EdgeMove achieves a 1.3 × -2.1 × speedup over the state-of-the-art scheme.

Similar to cloud servers, edge servers running 24/7 in a mobile edge computing (MEC) system consume a large amount of energy, and thus require demand response management. Demand response has been widely employed to reduce energy consumption at data centers. However, existing demand response approaches for data centers are rendered obsolete by the new and unique characteristics of MEC systems: 1) proximity constraint - mobile users can be served by neighbor edge servers only; 2) latency constraint - mobile users' workloads should be processed by their neighbor edge servers to ensure low latency; and 3) capacity constraint - edge servers have limited computing and communication resources to serve mobile users. Demand response for MEC is further complicated by the non-orthogonal multiple access (NOMA) scheme - the emerging radio access scheme for 5G. Communication resources like channels and transmit power must be systematically considered with computing resources like CPU, memory and storage to fulfil mobile users' resource demands. This paper makes the first attempt to tackle this Edge Demand Response (EDR) problem. We first formulate this problem and prove its NP-hardness. Then, we propose a two-phase game-theoretical approach (EDRGame) to solve the EDR problem. Its performance is theoretically analyzed and experimentally evaluated against state-of-the-art approaches on a widely-used real-world dataset.

Voice assistant has been widely used for human-computer interaction and automatic meeting minutes. However, for multiple sound sources, the performance of speech recognition in voice assistant decreases dramatically. Therefore, it is crucial to separate multiple voices efficiently for an effective voice assistant application in multi-user scenarios. In this paper, we present a novel voice separation system using a 2D microphone array in multiple sound source scenarios. Specifically, we propose a spatial filtering-based method to iteratively estimate the Angle of Arrival (AoA) of each sound source and separate the voice signals with adaptive beamforming. We use BeamForming-based cross-Correlation (BF-Correlation) to accurately assess the performance of beamforming and automatically optimize the voice separation in the iterative framework. Different from cross-correlation, BF-Correlation further performs cross-correlation among the after-beamforming voice signals processed with each linear microphone array. In this way, the mutual interference from voice signals out of the specified direction can be effectively suppressed or mitigated via the spatial filtering technique. We implement a prototype system and evaluate its performance in real environments. Experimental results show that the average AoA error is 1.4 degree and the average ratio of automatic speech recognition accuracy is 90.2% in the presence of three sound sources.

Mobile robot-assisted book inventory such as book identification and book order detection has become increasingly popular in smart library, replacing the manual book inventory which is time-consuming and error-prone. The existing systems are either computer vision (CV)-based or RFID-based, however several limitations are inevitable. CV-based systems may not be able to identify books effectively due to low accuracy of detecting texts on book spine. RFID tags attached to books can be used to identify a book uniquely. However, in high tag density scenarios such as library, tag coupling effects of adjacent tags may seriously affect the accuracy of tag reading. To overcome these limitations, this paper presents a novel RFID and CV fusion system for Book Inventory using mobile robot (RC-BI). RFID and CV are first used individually to obtain book order, then the information will be fused by the sequence based matching algorithm to remove ambiguity and improve overall accuracy. Specifically, we address three technical challenges. We design a deep neural network (DNN) model with multiple inputs and mixed data to filter out interference of RFID tags on other tiers, and propose a video information extracting schema to extract book spine information accurately, and use strong link to align and match RFID- and CV-based timestamp vs. book-name sequences to avoid errors during fusion. Extensive experiments indicate that our system achieves an average accuracy of 98.4% for tier filtering and an average accuracy of 98.9% for book order, significantly outperforming the state-of-the-arts.

Irradiated Cross-linked Polyethylene Foam (IXPE) has been one of the most commonly used materials in industry. During the production process of IXPE sheets, their edges need keep aligned strictly, otherwise, they could quickly get out of the border of the rolling plate and cause the huge economic loss. In this paper, we propose a camera-enabled approach, called Edge-Eye, to rectify the edge deviation automatically for IXPE production with millimeter-level accuracy. We deploy a commercial camera with mobile edge node in front of the IXPE sheet to continuously detect and rectify the edge deviation. Particularly, to handle the complex production en-vironment when extracting the edge of IXPE sheet, we deploy a pair of reference bars with high-contrast colors to efficiently differ-entiate the sheet edge from the background. Then, we propose a Bi-direction Edge Tracking method to perform the edge detection from both vertical and horizontal aspects. To realize the rectification using mobile edge nodes with limited computing resources, we reduce the cost of computation by extracting the Minimized Region of Interest, i.e., the edge area overlapped with the higher contrast reference bar on both sides. We further design a negative feedback control system with multi-stage feedback regulation mechanism, keeping the edge deviation within millimeter-level. We implemented Edge-Eye on the ARM64 platform and performed evaluation in the practical IXPE production process. The experimental results show that Edge-Eye achieves the average accuracy of 5mm for the edge deviation rectification, with the average latency of 200ms for edge deviation detection. During the process of 20-month real deployment for 36 production lines, 66 manpower per day (90% of the overall manpower) has been saved, and the utilization rate of IXPE material increases from 87% to 94%.

Recent efforts in reducing user involvement during device pairing have successfully introduced touch-to-access. To detect whether two devices are being held by the same person, existing touch-to-access solutions extract features from a shared information source to generate pairing keys. They focus on validating the device's authenticity by only requiring the user's simple touching of the device, however, ignore the device holder's legitimacy and pairing intent. Moreover, the pairing keys may be vulnerable to eavesdropping attacks since they are exchanged over an open wireless link (e.g., WiFi or Bluetooth). In this paper, we develop a secure device pairing mechanism that essentially uses the human body to generate and transmit user-specific pairing keys, ensuring the user's legitimacy and pairing intent, as well as improving key transmission reliability. Our work is based on the observation that the human body produces a unique response to the electrical signal flowing through it, and different bodies induce distinct responses to the signal. The built-in microphone on devices captures ambient sound as an entropy source and converts it into an electrical signal, which is subsequently processed and transmitted by the human body for device pairing. We build a prototype using off-the-shelf microphones and conduct extensive experiments with 31 participants to evaluate its security performance and usability. The results show that our system achieves a pairing success rate of 97.74% and an equal error rate of 2.28%.

We present a secure device pairing approach, called BiTouch, using the human body as a conductor to generate and transmit user-specific pairing keys for advancing touch-to-access policy. BiTouch is designed based on the observation that the human body responds uniquely to electrical signals flowing through it. Built-in microphones on devices are essentially used to capture ambient sound as entropy and convert it into an electrical signal, which is subsequently transmitted by the body for device pairing. We implement BiTouch using off-the-shelf microphones and evaluate it with 31 participants. The results demonstrate that BiTouch ensures the user's legitimacy and key transmission reliability, and achieves a pairing success rate of 97.74% and an equal error rate of 2.28%.

User authentication is critical to privacy preservation. Most of the existing works focus on single-user authentication, which may not work efficiently and practically in multi-user scenarios. To this end, we present a Multi-user Authentication system (M-Auth) that employs a single COTS mmWave radar to capture the user's unique breathing pattern. It exploits the phenomenon that radio frequency (RF) signals are affected by chest displacements due to breathing. We specifically design an auxiliary rotating gadget to dynamically adjust radar orientation, making it more effective in capturing respiration signals from multiple users. To profile individual components from the entangled RF signals, we leverage mmWave's high directivity to locate each user and separately focus on reflections from different positions. We propose a signal energy comparison method to eliminate the irrelevant body movements for preserving fine-grained respiration traits. Afterward, we develop a feature selection pipeline to elicit the most informative features and train a machine learning-based classifier to identify each user. M-Auth is practical due to its non-contact and passive nature, and it is secure as respiration is unique and difficult-to-forge. Extensive experiments involving 37 participants demonstrate that M-Auth is effective in verifying legitimate users and thwarting spoofing attacks, with an authentication accuracy of over 96 % and an attack detection rate of over 95%.

Blood pressure (BP) measurement is an indispensable tool in diagnosing and treating many diseases such as cardiovascular failure and stroke. Traditional direct measurement can be invasive, and wearable-based methods may have limitations of discomfort and inconvenience. Contact-free BP measurement has been recently advocated as a promising alternative. In particular, Millimetre-wave (mmWave) sensing has demonstrated its promising potential, however it is confronted with several challenges including noise and vulnerability to human's tiny motions which may occur intentionally and inevitably. In this paper, we propose mmBP, a contact-free mmWave-based BP measurement system with high accuracy and motion robustness. Due to the high frequency and short wavelength, mmWave signals received in the time domain are dramatically susceptible to ambient noise, and deteriorating signal quality. To reduce noise, we propose a novel delay-Doppler domain feature transformation method to exploit mmWave signal's characteristics and features in the delay-Doppler domain to significantly improve signal quality for pulse waveform construction. We also propose a temporal referential functional link adaptive filter leveraging on the periodic and correlation characteristics of pulse waveform signals to alleviate the impact of human's tiny motions. Extensive experiment results achieved by the leave-one-out cross-validation (LOOCV) method demonstrate that mmBP achieves the mean errors of 0.87mmHg and 1.55mmHg for systolic blood pressure (SBP) and diastolic blood pressure (DBP), respectively; and the standard deviation errors of 5.01mmHg and 5.27mmHg for SBP and DBP, respectively.

Continuous authentication is crucial for protecting user’s privacy throughout their login session. Existing studies employ wireless sensing technologies to provide device-free and unobtrusive authentication; the user’s behavior is continually assessed without their direct involvement until it deviates from their normal pattern. However, these works primarily concentrate on single-user authentication, which poses challenges in multiuser scenarios, such as smart homes and offices, where more than one user usually exists. In this article, we propose HeartPrint, a continuous multiuser authentication system, that employs a single commodity mmWave radar to capture the unique self-driving heartbeat motions from multiple users. Specifically, HeartPrint leverages the effect of skin surface vibrations caused by heartbeat on radio frequency (RF) transmissions. To profile individual heartbeat signals from the entangled components that are induced by multiple users, we first use a clustering method to position each user in the environment, then focus on the signal reflected from each position separately. The irrelevant body movements are eliminated from the RF signal by using a proposed signal energy comparison method for preserving fine-grained heartbeat traits. We then develop a pipeline to extract the most informative features for characterizing each user and feed them to an elaborated classifier for user authentication. We evaluate HeartPrint with 54 participants and demonstrate that it achieves an average authentication accuracy of over 95%. Additionally, we show that it is resilient against spoofing attacks, with an average attack success rate of less than 3%.

Inattentive driving is one of the high-risk factors that causes a large number of traffic accidents every year. In this article, we aim to detect driver inattention leveraging on large-scale vehicle trajectory data while at the same time explore how do these inattentive events affect driver behaviors and what following reactions they may cause, especially, for commercial vehicles. Specifically, the proposed system targets four most commonly occurring critical inattentive events, including smoking, phone call, turning back, and yawning. By applying a deep convolutional neural network (CNN) (Inception v3) with two data augmentation routines—Mixup and synthetic minority oversampling technique (Smote), we are able to balance the training data distribution and improve the generalization of the classification model. Then, based on the output derived from the inattention detection combining with point of interest (POI) and climate data, a long short-term memory (LSTM)-based model is deployed to predict driver upcoming abnormal operations on road (due to inattention) which may result in potential dangerous driving conditions, such as sudden acceleration/deceleration, aggressive left/right lane change, etc. To evaluate our proposed system, we collect more than 120000 real-world driving traces from over 200 drivers. The experimental results show that our model achieves a weight accuracy (WA) of 92.27% for inattentive driving detection and a WA of 91.67% for abnormal driving prediction, demonstrating its great potential of shaping good driving habits and promoting road safety.

Mobile and wearable devices have become more and more popular. However, the tiny touch screen leads to inefficient interaction with these devices, especially for text input. In this article, we proposeDynaKey, which allows people to type on a virtual keyboard printed on a piece of article or drawn on a desk, for inputting text into a head-mounted camera device (e.g., smart glasses). By using the built-in camera and gyroscope, we capture image frames during typing and detect possible head movements, then track keys, detect fingertips, and locate keystrokes. To track the changes of keys’ coordinates in images caused by natural head (i.e., camera) movements, we introduce perspective transformation to transform keys’ coordinates among different frames. To detect and locate keystrokes, we utilize the variation of fingertip’s coordinates across multiple frames to detect possible keystrokes for localization. To reduce the time cost, we combine gyroscope and camera to adaptively track the keys, and introduce a series of optimizations, such as keypoint detection, frame skipping, multithread processing, etc. Finally, we implement DynaKey on Android-powered devices. The extensive experimental results show that our system can efficiently track and locate the keystrokes in real time. Specifically, the average tracking deviation of the keyboard layout is less than 3 pixels and the Intersection over Union (IoU) of a key in two consecutive images is above 93%. The average keystroke localization accuracy reaches 95.5%.

Edge Computing, extending cloud computing, has emerged as a prospective computing paradigm. It allows a SaaS (Software-as-a-Service) vendor to allocate its users to nearby edge servers to minimize network latency and energy consumption on their devices. From the SaaS vendor’s perspective, a cost-effective SaaS user allocation (SUA) aims to allocate maximum SaaS users on minimum edge servers. However, the allocation of excessive SaaS users to an edge server may result in severe interference and consequently impact SaaS users’ data rates. In this article, we formally model this problem and prove that finding the optimal solution to this problem is NP-hard. Thus, we propose ISUAGame, a game-theoretic approach that formulates the interference-aware SUA (ISUA) problem as a potential game. We analyze the game and show that it admits a Nash equilibrium. Then, we design a novel decentralized algorithm for finding a Nash equilibrium in the game as a solution to the ISUA problem. The performance of this algorithm is theoretically analyzed and experimentally evaluated. The results show that the ISUA problem can be solved effectively and efficiently.

Mobile deep learning (MDL) has emerged as a privacy-preserving learning paradigm for mobile devices. This paradigm offers unique features such as privacy preservation, continual learning and low-latency inference to the building of personal mobile sensing applications. However, squeezing Deep Learning to mobile devices is extremely challenging due to resource constraint. Traditional Deep Neural Networks (DNNs) are usually over-parametered, hence incurring huge resource overhead for on-device learning. In this paper, we present a novel on-device deep learning framework named MDLdroidLite that transforms traditional DNNs into resource-efficient model structures for on-device learning. To minimize resource overhead, we propose a novel release-and-inhibit control (RIC) approach based on Model Predictive Control theory to efficiently grow DNNs from tiny to backbone. We also design agate-basedfast adaptation mechanism for channel-level knowledge transformation to quickly adapt new-born neurons with existing neurons, enabling safe parameter adaptation and fast convergence for on-device training. Our evaluations show that MDLdroidLite boosts on-device training on various PMS datasets with 28× to 50× less model parameters, 4× to 10× less floating number operations than the state-of-the-art model structures while keeping the same accuracy level.

Personal mobile sensing is fast permeating our daily lives to enable activity monitoring, healthcare and rehabilitation. Combined with deep learning, these applications have achieved significant success in recent years. Different from conventional cloud-based paradigms, running deep learning on devices offers several advantages including data privacy preservation and low-latency response for both model inference and update. Since data collection is costly in reality, Google’s Federated Learning offers not only complete data privacy but also better model robustness based on data from multiple users. However, personal mobile sensing applications are mostly user-specific and highly affected by environment. As a result, continuous local changes may seriously affect the performance of a global model generated by Federated Learning. In addition, deploying Federated Learning on a local server, e.g., edge server, may quickly reach the bottleneck due to resource limitation. Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications. To address resource limitation, we propose a ChainSGD-reduce approach which includes a novelchain-directedSynchronous Stochastic Gradient Descent algorithm to effectively reduce overhead among multiple devices. We also design an agent-basedmulti-goalreinforcement learning mechanism to balance resources in a fair and efficient manner. Our evaluations show that our model training on off-the-shelf mobile devices achieves 2x to 3.5x faster than single-device training, and 1.5x faster on average than the existing master-slave approach.

This article presents the design and implementation of PCube, a phase-based parallel packet decoder for concurrent transmissions of LoRa nodes. The key enabling technology behind PCube is a novel air-channel phase measurement technique that is able to extract phase differences of air-channels between LoRa nodes and multiple antennas of a gateway. PCube leverages the reception diversities of multiple receiving antennas of a gateway and scales the concurrent transmissions of a large number of LoRa nodes, even exceeding the number of receiving antennas at a gateway. As a phase-based parallel decoder, PCube provides a new dimension to resolve collisions and supports more concurrent transmissions by complementing time and frequency-based parallel decoders. PCube is implemented and evaluated with synchronized software defined radios and off-the-shelf LoRa nodes in both indoors and outdoors. Results demonstrate that PCube can substantially outperform state-of-the-art works in terms of aggregated throughput by 4.9× and the number of concurrent nodes by up to 5×. More importantly, PCube scales well with the number of receiving antennas of a gateway, which is promising to break the barrier of concurrent transmissions.

Gait rehabilitation is a common method of postoperative recovery after the user sustains an injury or disability. However, traditional gait rehabilitations are usually performed under the supervision of rehabilitation specialists, which implies that the patients cannot receive adequate gait assessment anytime and anywhere. In this article, we propose GaitTracker, a novel system to remotely and continuously perform gait monitoring and analysis by three-dimensional (3D) skeletal tracking in a wearable approach. Specifically, this system consists of four Inertial Measurement Units (IMU), which are attached on the shanks and thighs of the human body. According to the measurements from these IMUs, we can obtain the motion signals of lower limbs during gait rehabilitation. By adaptively synchronizing coordinate systems of different IMUs and building the geometric model of lower limbs, the exact gait movements can be reconstructed, and gait parameters can be extracted without any prior knowledge. GaitTracker offers three key features: (1) a unified 3D skeletal model to depict the precise gait movement and parameters in 3D space, (2) a coordinate system synchronization scheme to perform space synchronization over all the IMU sensors, and (3) an automatic estimation method for the user-specific geometric parameters. In this way, GaitTracker is able to accurately perform 3D skeletal tracking of lower limbs for gait analysis, such as evaluating the gait symmetry and the gait parameters including the swing/stance time. We implemented GaitTracker and evaluated its performance in real applications. The experimental results show that, the average error for skeleton angle estimation, joint displacement estimation, and gait parameter estimation are 3∘, 2.3%, and 3%, respectively, outperforming the state of the art.

Mobile RFID robots have been increasingly used in warehousing and intelligent manufacturing scenarios to pinpoint the locations of tagged objects. The accuracy of state-of-the-art RFID robot localization systems depends much on the stability of robot moving speed. However, in reality this assumption can hardly be guaranteed because a Commercial-Off-The-Shelf (COTS) robot typically has an inconsistent moving speed, and a small speed inconsistency will cause a large localization error. To this end, we propose a Speed Inconsistency-Immune approach to mobile RFID robot Localization (SILoc) system, which can accurately locate RFID tagged targets when the robot moving speed varies or is even unknown. SILoc employs multiple antennas fixed on the mobile robot to collect the phase data of target tags. We propose an optimized unwrapping method to maximize the use of the phase data, and a lightweight algorithm to calculate the locations in both 2D and 3D spaces based on the unwrapped phase profile. By utilizing the characteristics of tag-antenna distance and combining the phase data from multiple antennas, SILoc can effectively eliminate the side effects of moving speed inconsistency. Extensive experimental results demonstrate that SILoc can achieve a centimeter-level localization accuracy in the scenario with an inconsistent or unknown robot moving speed.

With the rapid development of the Internet of Things (IoT), we have seen a larger number of devices deployed with different wireless communication protocols (i.e., WiFi, ZigBee, Bluetooth). Working in the same place opens a new opportunity for these devices to communicate directly with each other, leveraging on Cross-technology Communication (CTC). However, since these devices operate in the same frequency band which results in the competition against each other for network resources, severe interfere may arise. In this paper, we explore pseudo-random sequence (PR sequence) to design a novel CTC protocol that enables low-cost direct communication between WiFi and ZigBee in noisy indoor environments. Pseudorandom sequence offers a unique statistical feature to accomplish both information transmission and synchronization between heterogeneous devices. We design a dynamic synchronous decoding strategy to handle interference coexisted among different wireless protocols. Our system does not require any modification of communication protocol and underlying hardware and firmware. We implement our system on commercial devices (Intel 5300 WiFi NIC and MicaZ CC2420), and conduct extensive experiments to evaluate the system performance in three typical scenarios. The experimental results show that the synchronization time of our approach is lower than 0.5 ms, and the accuracy is greater than 84% while the channel occupancy is as high as 50%.

Recognition of human-object interactions is practically important in various human-centric sensing scenarios such as smart supermarket, factory, and home. This paper proposes an RF-Camera system by fusing RFID and Computer Vision (CV) techniques, which is the first work to recognize the human gestural interactions with physical objects in multi-subject and multi-object scenarios. In RF-Camera, we first propose a dimension reduction method to transform the subject's 3D hand trajectory captured by depth camera to a 2D image, using which the subject's gesture can be recognized. We also propose a method to extract the facial image of target subject from an image that may contain irrelevant subjects, thereby further recognizing his/her identity. Finally, we model the physical movements of the held object's tag and further predict the tag phase data, by comparing which with real phase data of each tag human-object matching can be discovered. When implementing RF-Camera, three technical challenges need to be addressed. (i) To remove noisy data corresponding to irrelevant actions from raw sensing data, we propose a state transition diagram to determine the boundary of effective data. (ii) To predict phase data of the held target tag with unknown hand-tag offset, we quantify target tag trajectory by adding a variable hand-tag vector to captured hand trajectory. (iii) To ensure high reading rates of target tags in tag-dense scenarios, we propose a CV-assisted RFID scheduling method, in which analytics on CV data can help schedule RFID readings. We conduct extensive experiments to evaluate the performance of RF-Camera. Experimental results demonstrate that RF-Camera can recognize the gestural actions, human identity and human-object matching with an average accuracy higher than 90% in most cases.

This paper presents the design and implementation of PCube, a phase-based parallel packet decoder for concurrent transmissions of LoRa nodes. The key enabling technology behind PCube is a novel air-channel phase measurement technique which is able to extract phase differences of air-channels between LoRa nodes and multiple antennas of a gateway. PCube leverages the reception diversities of multiple receiving antennas of a gateway and scales the concurrent transmissions of a large number of LoRa nodes, even exceeding the number of receiving antennas at a gateway. As a phase-based parallel decoder, PCube provides a new dimension to resolve collisions and supports more concurrent transmissions by complementing time and frequency based parallel decoders. PCube is implemented and evaluated with synchronized software defined radios and off-the-shelf LoRa nodes in both indoors and outdoors. Results demonstrate that PCube can substantially outperform state-of-the-art works in terms of aggregated throughput by 4.9× and the number of concurrent nodes by up to 5×. More importantly, PCube scales well with the number of receiving antennas of a gateway, which is promising to break the barrier of concurrent transmissions.

Long range (LoRa) is an attractive low-power wide-area networks (LPWANs) technology for its features of low power, long range, and support for concurrent transmission. Our study reveals LoRa concurrent transmission suffer from the mismatch between the sender’s reception (RX) and gateway’s transmission (TX) window, which leads to the decline of goodput even the throughput is improved. Our experiment shows that goodput only accounts for two-fifths of the throughput in concurrent transmissions with 48 nodes at a duty cycle of 20%. This article presents a window match scheme named Cantor which improves the goodput of LoRa concurrent transmission by controlling the RX window size. Cantor does not require the frequent exchange of controlling information. Instead, it introduces a novel concurrent transmission model to estimate the downlink packet reception rate (PRR) with different network parameters, and a regression model is used to make the result more realistic. Then, we propose a simple optimization algorithm to select optimal RX window sizes in which nodes are able to receive acknowledgments. We implement and evaluate Cantor with commodity LoRa gateway and nodes, and conduct experiments in different scenarios. The experimental results show that Cantor increases the goodput by 70% and reduces energy consumption by 30% in LoRa concurrent transmissions with 48 nodes operate at a duty cycle of 20%.

Sleep monitoring is essential to people's health and wellbeing, which can also assist in the diagnosis and treatment of sleep disorder. Compared with contact-based solutions, contactless sleep monitoring does not attach any device to the human body; hence, it has attracted increasing attention in recent years. Inspired by the recent advances in Wi-Fi-based sensing, this article proposes a low-cost and nonintrusive sleep monitoring system using commodity Wi-Fi devices, namely, WiFi-Sleep. We leverage the fine-grained channel state information from multiple antennas and propose advanced fusion and signal processing methods to extract accurate respiration and body movement information. We introduce a deep learning method combined with clinical sleep medicine prior knowledge to achieve four-stage sleep monitoring with limited data sources (i.e., only respiration and body movement information). We benchmark the performance of WiFi-Sleep with polysomnography, the gold reference standard. Results show that WiFi-Sleep achieves an accuracy of 81.8%, which is comparable to the state-of-the-art sleep stage monitoring using expensive radar devices.

This paper presents LiteNap which improves the energy efficiency of LoRa by enabling LoRa nodes to operate in a downclocked ‘light sleep’ mode for packet reception. A fundamental limit that prevents radio downclocking is the Nyquist sampling theorem which demands the clock-rate being at least twice the bandwidth of LoRa chirps. Our study reveals under-sampled LoRa chirps suffer frequency aliasing and cause ambiguity in symbol demodulation. LiteNap addresses the problem by leveraging an empirical observation that the hardware of LoRa radio can cause phase jitters on modulated chirps, which result in frequency leakage in the time domain. The timing information of phase jitters and frequency leakages can serve as physical fingerprints to uniquely identify modulated chirps. We propose a scheme to reliably extract the fingerprints from under-sampled chirps and resolve ambiguities in symbol demodulation. We update the reception pipeline of LoRa radio to enable reliable packet detection and decoding when operating in downclocked mode. We implement LiteNap on a software defined radio platform and conduct trace-driven evaluation to validate the proposed strategies. Experiment results show that LiteNap can downclock LoRa receiver to sub-Nyquist rates for energy savings (e.g., 1/8 of Nyquist rate), without substantially affecting packet reception performance (e.g., >95% packet reception rate).

Many IoT applications have the requirements of conducting complex IoT events processing (e.g., speech recognition) that are hardly supported by low-end IoT devices due to limited resources. Most existing approaches enable complex IoT event processing on low-end IoT devices by statically allocating tasks to the edge or the cloud. In this article, we present Queec, a QoE-aware edge computing system for complex IoT event processing under dynamic workloads. With Queec, the complex IoT event processing tasks that are relatively computation-intensive for low-end IoT devices can be transparently offloaded to nearby edge nodes at runtime. We formulate the problem of scheduling multi-user tasks to multiple edge nodes as an optimization problem, which minimizes the overall offloading latency of all tasks while avoiding the overloading problem. We implement Queec on low-end IoT devices, edge nodes, and the cloud. We conduct extensive evaluations, and the results show that Queec reduces 56.98% of the offloading latency on average compared with the state-of-the-art under dynamic workloads, while incurring acceptable overhead.

With the increasing relevance of the Internet of Things and large-scale location-based services, LoRa localization has been attractive due to its low-cost, low-power, and long-range properties. However, existing localization approaches based on received signal strength indicators are either easily affected by signal fading of different land-cover types or labor intensive. In this work, we propose SateLoc, a LoRa localization system that utilizes satellite images to generate virtual fingerprints. Specifically, SateLoc first uses high-resolution satellite images to identify land-cover types. With the path loss parameters of each land-cover type, SateLoc can automatically generate a virtual fingerprinting map for each gateway. We then propose a novel multi-gateway combination strategy, which is weighted by the environmental interference of each gateway, to produce a joint likelihood distribution for localization and tracking. We implement SateLoc with commercial LoRa devices without any hardware modification, and evaluate its performance in a 227,500-m urban area. Experimental results show that SateLoc achieves a median localization error of 43.5 m, improving more than 50% compared to state-of-the-art model-based approaches. Moreover, SateLoc can achieve a median tracking error of 37.9 m with the distance constraint of adjacent estimated locations. More importantly, compared to fingerprinting-based approaches, SateLoc does not require the labor-intensive fingerprint acquisition process.

This paper presents LiteNap which improves the energy efficiency of LoRa by enabling LoRa nodes to operate in a downclocked `light sleep' mode for packet reception. A fundamental limit that prevents radio downclocking is the Nyquist sampling theorem which demands the clock-rate being at least twice the bandwidth of LoRa chirps. Our study reveals under-sampled LoRa chirps suffer frequency aliasing and cause ambiguity in symbol demodulation. LiteNap addresses the problem by leveraging an empirical observation that the hardware of LoRa radio can cause phase jitters on modulated chirps, which result in frequency leakage in the time domain. The timing information of phase jitters and frequency leakages can serve as physical fingerprints to uniquely identify modulated chirps. We propose a scheme to reliably extract the fingerprints from under-sampled chirps and resolve ambiguities in symbol demodulation. We implement LiteNap on a software defined radio platform and conduct trace-driven evaluation. Experiment results show that LiteNap can downclock LoRa nodes to sub-Nyquist rates for energy savings (e.g., 1/8 of Nyquist rate), without substantially affecting packet reception performance (e.g., >95% packet reception rate).

With the increasing relevance of the Internet of Things (IoT) and large-scale Location-Based Services (LBS), LoRa localization has been attractive due to its low cost, low power and long range properties. However, existing localization approaches based on Received Signal Strength Indicator (RSSI) are either easily affected by signal fading of different land-cover types or labor-intensive. In this work, we propose SateLoc, a LoRa localization system that utilizes satellite images to generate virtual fingerprints. Specifically, SateLoc first uses high-resolution satellite images to identify land- cover types. With the path loss parameters of each land-cover type, SateLoc can automatically generate a virtual fingerprinting map for each gateway. We then propose a novel multi-gateway combination strategy, which is weighted by the environment interference of each gateway, to produce a joint likelihood distribution for localization. We implement SateLoc with commercial LoRa devices without any hardware modification, and evaluate its performance in a 227,500m2urban area. Experimental results show that SateLoc achieves a median localization error of 47.1m, improving more than 40% compared to the state-of-the-art model-based approaches. More importantly, compared to the fingerprinting-based approach, SateLoc does not require the labor-intensive fingerprint acquisition process.

Personal mobile sensing is fast permeating our daily lives to enable activity monitoring, healthcare and rehabilitation. Combined with deep learning, these applications have achieved significant success in recent years. Different from conventional cloud-based paradigms, running deep learning on devices offers several advantages including data privacy preservation and low-latency response for both model inference and update. Since data collection is costly in reality, Google’s Federated Learning offers not only complete data privacy but also better model robustness based on multiple user data. However, personal mobile sensing applications are mostly user-specific and highly affected by environment. As a result, continuous local changes may seriously affect the performance of a global model generated by Federated Learning. In addition, deploying Federated Learning on a local server, e.g., edge server, may quickly reach the bottleneck due to resource constraint and serious failure by attacks. Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications. To address resource limitation, we propose a ChainSGD-reduce approach which includes a novel chain-directed Synchronous Stochastic Gradient Descent algorithm to effectively reduce overhead among multiple devices. We also design an agent-based multi-goal reinforcement learning mechanism to balance resources in a fair and efficient manner. Our evaluations show that our model training on off-the-shelf mobile devices achieves 2x to 3.5x faster than single-device training, and 1.5x faster than the master-slave approach.

MDLdroid is a novel decentralized mobile deep learning framework, which enables resource-aware on-device collaborative learning for personal mobile sensing applications. To address resource limitation, MDLdroid uses a chain-directed Synchronous Stochastic Gradient Descent (ChainSGD-reduce) approach to effectively reduce overhead among multiple devices. In addition, MDLdroid includes an agent-based multi-goal reinforcement learning mechanism to balance resources in a fair and efficient manner. Real-world experiments demonstrate that our model training on off-the-shelf mobile devices achieves 2× to 3.5× faster than single-device training, and 1.5× faster than the master-slave approach.

Mobile Deep Learning (MDL) has emerged as a privacy-preserving learning paradigm for mobile devices. This paradigm offers unique features such as privacy preservation, continual learning and low-latency inference to the building of personal mobile sensing applications. However, squeezing Deep Learning to mobile devices is extremely challenging due to resource constraint. Traditional Deep Neural Networks (DNNs) are usually over-parametered, hence incurring huge resource overhead for on-device learning. In this paper, we present a novel on-device deep learning framework named MDLdroidLite that transforms traditional DNNs into resource-efficient model structures for on-device learning. To minimize resource overhead, we propose a novel Release-and-Inhibit Control (RIC) approach based on Model Predictive Control theory to efficiently grow DNNs from tiny to backbone. We also design a gate-based fast adaptation mechanism for channel-level knowledge transformation to quickly adapt new-born neurons with existing neurons, enabling safe parameter adaptation and fast convergence for on-device training. Our evaluations show that MDLdroidLite boosts on-device training on various PMS datasets with 28x to 50x less model parameters, 4x to 10x less floating number operations than the state-of-the-art model structures while keeping the same accuracy level.

Biometric authentication involves various technologies to identify individuals by exploiting their unique, measurable physiological and behavioral characteristics. However, traditional biometric authentication systems (e.g., face recognition, iris, retina, voice, and fingerprint) are at increasing risks of being tricked by biometric tools such as anti-surveillance masks, contact lenses, vocoder, or fingerprint films. In this article, we design a multimodal biometric authentication system named DeepKey, which uses both Electroencephalography (EEG) and gait signals to better protect against such risk. DeepKey consists of two key components: an Invalid ID Filter Model to block unauthorized subjects, and an identification model based on attention-based Recurrent Neural Network (RNN) to identify a subject’s EEG IDs and gait IDs in parallel. The subject can only be granted access while all the components produce consistent affirmations to match the user’s proclaimed identity. We implement DeepKey with a live deployment in our university and conduct extensive empirical experiments to study its technical feasibility in practice. DeepKey achieves the False Acceptance Rate (FAR) and the False Rejection Rate (FRR) of 0 and 1.0%, respectively. The preliminary results demonstrate that DeepKey is feasible, shows consistent superior performance compared to a set of methods, and has the potential to be applied to the authentication deployment in real-world settings.

The widespread use of smartphones has brought great convenience to our daily lives, while at the same time we have been increasingly exposed to security threats. Keystroke security is essential to user privacy protection. In this paper, we present GazeRevealer, a novel side-channel based keystroke inference framework to infer sensitive inputs on smartphone from video recordings of victim's eye patterns captured from smartphone front camera. We observe that eye movements typically follow the keystrokes typing on the number-only soft keyboard during password input. By exploiting eye movement patterns, we are able to infer the passwords being entered. We propose a novel algorithm to extract sensitive eye images from video streams, and classify these images with Support Vector Classification. We also propose a novel classification enhancement algorithm to further improve classification accuracy. Compared with prior keystroke detection approaches, GazeRevealer does not require any external auxiliary devices, and it only relies on smartphone front camera. We evaluate the performance of GazeRevealer on several smartphones under different real-life usage scenarios. The results show that GazeRevealer achieves an inference rate of 77.89 percent for single key number and an inference rate of 84.38 percent for 6-digit password in the ideal case.

LoRa has emerged as a promising Low-Power Wide Area Network (LP-WAN) technology to connect a huge number of Internet-of-Things (IoT) devices. The dense deployment and an increasing number of IoT devices lead to intense collisions due to uncoordinated transmissions. However, the current MAC/PHY design of LoRaWAN fails to recover collisions, resulting in degraded performance as the system scales. This article presents FTrack, a novel communication paradigm that enables demodulation of collided LoRa transmissions. FTrack resolves LoRa collisions at the physical layer and thereby supports parallel decoding for LoRa transmissions. We propose a novel technique to separate collided transmissions by jointly considering both the time domain and the frequency domain features. The proposed technique is motivated from two key observations: (1) the symbol edges of the same frame exhibit periodic patterns, while the symbol edges of different frames are usually misaligned in time; (2) the frequency of LoRa signal increases continuously in between the edges of symbol, yet exhibits sudden changes at the symbol edges. We detect the continuity of signal frequency to remove interference and further exploit the time-domain information of symbol edges to recover symbols of all collided frames. We substantially optimize computation-intensive tasks and meet the real-time requirements of parallel LoRa decoding. We implement FTrack on a low-cost software defined radio. Our testbed evaluations show that FTrack demodulates collided LoRa frames with low symbol error rates in diverse SNR conditions. It increases the throughput of LoRaWAN in real usage scenarios by up to 3 times.

Network simulation is a fundamental service for performance testing and protocol design in wireless networks. Due to the wireless dynamics, it is highly challenging to provide repeatable and reliable simulation results that are comparable to the empirical experimental results. To achieve repeatability for simulation, the existing works focus on reproducing the behaviors on individual links. However, as observed in recent works, individual link behaviors alone are far from enough to characterize the protocol-level performance. As a result, even if the link behaviors can be simulated very closely, these works often fail to simulate the protocol performance with high reliability. In this article, we propose a novel performance-aware simulation approach which can preserve not only the link-level behaviors but also the performance-level behaviors. We first combine the spatial-temporal link diversity to devise an accurate performance model. Based on the model, we then propose a Performance Aware Hidden Markov Model (PA-HMM), where the protocol performance is directly fed into the Markov state transitions. Compared to the existing works, PA-HMM is able to simulate both link-level behaviors and high-level protocol performance. We conduct extensive testbed and simulation experiments with broadcast and anycast protocols. The results show that 1) the proposed model is able to accurately characterize communication performance for both broadcast and anycast and 2) the protocol performance is closely simulated as compared to the empirical results and the PA-HMM based simulation is more repeatable compared to the existing works.

LoRa has emerged as a promising Low-Power Wide Area Network (LP-WAN) technology to connect a huge number of Internet-of-Things (IoT) devices. The dense deployment and an increasing number of IoT devices lead to intense collisions due to uncoordinated transmissions. However, the current MAC/PHY design of LoRaWAN fails to recover collisions, resulting in degraded performance as the system scales. This paper presents FTrack, a novel communication paradigm that enables demodulation of collided LoRa transmissions. FTrack resolves LoRa collisions at the physical layer and thereby supports parallel decoding for LoRa transmissions. We propose a novel technique to separate collided transmissions by jointly considering both the time domain and the frequency domain features. The proposed technique is motivated from two key observations: (1) the symbol edges of the same frame exhibit periodic patterns, while the symbol edges of different frames are usually misaligned in time; (2) the frequency of LoRa signal increases continuously in between the edges of symbol, yet exhibits sudden changes at the symbol edges. We detect the continuity of signal frequency to remove interference and further exploit the time-domain information of symbol edges to recover symbols of all collided frames. We implement FTrack on a low-cost software defined radio. Our testbed evaluations show that FTrack demodulates collided LoRa frames with low symbol error rates in diverse SNR conditions. It increases the throughput of LoRaWAN in real usage scenarios by up to 3 times.

Recent years have witnessed advances of Internet of Things technologies and their applications to enable contactless sensing and elderly care in smart homes. Continuous and real-time respiration monitoring is one of the important applications to promote assistive living for elders during sleep and attracted wide attention in both academia and industry. Most of the existing respiration monitoring systems require expensive and specialized devices to sense chest displacement. However, chest displacement is not a direct indicator of breathing and thus false detection may often occur. In this paper, we design and implement a real-time and contactless respiration monitoring system by directly sensing the exhaled airflow from breathing using ultrasound signals with off-the-shelf speaker and microphone. Exhaled airflow from breathing can be regarded as air turbulence, which scatters the sound wave and results in Doppler effect. Our system works as an acoustic radar which transmits sound wave and detects the Doppler effect caused by breathing airflow. We mathematically model the relationship between the Doppler frequency change and the direction of breathing airflow. Based on this model, we design a minimum description length-based algorithm to effectively capture the Doppler effect caused by exhaled airflow. We conduct extensive experiments with 25 participants (7 elders, 2 young kids, and 16 adults, including 11 females and 14 males) in four different rooms. The participants take four different sleep postures (lying on one's back, on right/left side, and on one's stomach) in different positions of the bed. Experiment results show that our system achieves a median error lower than 0.3 breaths/min (2%) for respiration monitoring and can accurately identify Apnea. The results also demonstrate that the system is robust to different respiration styles (shallow, normal, and deep), respiration rate variation, ambient noise, sensing distance variation (within 0.7 m), and transmitted signal frequency variation.

Cross-Technology Interference affects the operation of low-power ZigBee networks, especially under severe WiFi interference. Accurate corruption estimation is very important to improve the resilience of ZigBee transmissions. However, there are many limitations in existing approaches such as low accuracy, high overhead, and requirement of hardware modification. In this paper, we propose an accurate corruption estimation approach, AccuEst, which utilizes per-byte SINR (Signal-to-Interference-and-Noise Ratio) to detect corruption. We combine the use of pilot symbols with per-byte SINR to improve corruption detection accuracy, especially in highly noisy environments (i.e., noise and interference are at the same level). We extract pilot symbols by leveraging protocol signatures. In addition, we design an adaptive pilot instrumentation scheme to strike a good balance between accuracy and overhead. We implement AccuEst on the TinyOS 2.1.1/TelosB platform and evaluate its performance through extensive experiments. Results show that AccuEst improves corruption detection accuracy by 79.4 percent on average compared with state-of-the-art approach (i.e., CARE) in highly noisy environments. In addition, AccuEst reduces pilot overhead by 83.7 percent on average compared to the traditional pilot-based approach. We implement AccuEst in a coding-based transmission protocol, and results show that with AccuEst, the packet delivery ratio is improved by 22.1 percent on average.

Light-to-Camera Communications (LCC) have emerged as a new wireless communication technology with great potential to benefit a broad range of applications. However, the existing LCC systems either require cameras directly facing to the lights or can only communicate over a single link, resulting in low throughputs and being fragile to ambient illuminant interference. We present HYCACO, a novel LCC system, which enables multiple light emitting diodes (LEDs) with an unaltered camera to communicate via the non-line-of-sight (NLoS) links. Different from other NLoS LCC systems, the proposed scheme is resilient to the complex indoor luminous environment. HYCACO can decode the messages by exploring the mixed reflected optical signals transmitted from multiple LEDs. By further exploiting the rolling shutter mechanism, we present the optimal optical frequencies and camera exposure duration selection strategy to achieve the best performance. We built a hardware prototype to demonstrate the efficiency of the proposed scheme under different application scenarios. The experimental results show that the system throughput reaches 4.5 kbps on iPhone 6s with three transmitters. With the robustness, improved system throughput and ease of use, HYCACO has great potentials to be used in a wide range of applications such as advertising, tagging objects, and device certifications.

This paper identifies two energy saving opportunities of Wi-Fi interface emerged during smartphone's screen-off periods. Exploiting the opportunities, we propose a new power saving strategy, BackPSM, for screen-off Wi-Fi communications. BackPSM regulates client to send and receive packets in batches and coordinates multiple clients to communicate at different slots (i.e., beacon interval). The core problem in BackPSM is how to coordinate client without incurring extra traffic overheads. To handle the problem, we propose a novel paradigm, Out-of-Band Communication (OBC), for client-to-client direct communications. OBC exploits the Traffic Indication Map (TIM) field of Wi-Fi Beacon to create a free side-channel between clients. It is based upon the observation that a client may control 1 → 0 appearing on TIM bit by locally regulating packet receiving operations. We adopt this 1 → 0 as the basic signal, and leverage the time length in between two signals to encode information. We demonstrate that OBC can be used to convey coordination information with close to 100% accuracy. We have implemented and evaluated BackPSM on a testbed. The results show that BackPSM can decode the traffic pattern of peers reliably using OBC, and establish collision-free schedules fast to achieve out-ofband coordination of client communications. BackPSM reduces screen-off energy by up to 60% and outperforms the state-ofthe-art strategies by 16%-42%.

Recognizing in-air hand gestures will benefit a wide range of applications such as sign-language recognition, remote control with hand gestures, and “writing” in the air as a new way of text input. This article presents AirContour, which focuses on in-air writing gesture recognition with a wrist-worn device. We propose a novel contour-based gesture model that converts human gestures to contours in 3D space and then recognizes the contours as characters. Different from 2D contours, the 3D contours may have the problems such as contour distortion caused by different viewing angles, contour difference caused by different writing directions, and the contour distribution across different planes. To address the above problem, we introduce Principal Component Analysis (PCA) to detect the principal/writing plane in 3D space, and then tune the projected 2D contour in the principal plane through reversing, rotating, and normalizing operations, to make the 2D contour in right orientation and normalized size under a uniform view. After that, we propose both an online approach, AC-Vec, and an offline approach, AC-CNN, for character recognition. The experimental results show that AC-Vec achieves an accuracy of 91.6% and AC-CNN achieves an accuracy of 94.3% for gesture/character recognition, both outperforming the existing approaches.

Multimodal features play a key role in wearable sensor based human activity recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we propose a “collect fully and select wisely” principle as well as an interpretable parallel recurrent model with convolutional attentions to improve the recognition performance. We first collect modality features and the relations between each pair of features to generate activity frames, and then introduce an attention mechanism to select the most prominent regions from activity frames precisely. The selected frames not only maximize the utilization of valid features but also reduce the number of features to be computed effectively. We further analyze the accuracy and interpretability of the proposed model based on extensive experiments. The results show that our model achieves competitive performance on two benchmarked datasets and works well in real life scenarios.

Wireless network simulation is a fundamental service aiming at providing controlled and repeatable environment for protocol design, performance testing, etc. The existing simulators focus on reproducing the packet behaviors on individual links. However, as observed in some recent works, individual link behaviors alone are not enough to characterize the protocol performance. As a result, while the existing works can mimic the link behaviors very closely, they often fail to simulate protocol level performance. In this paper, we propose a novel performance-aware simulation approach which can preserve not only the link-level behaviors but also the performance-level behaviors. We first devise an accurate performance model by combining link quality and the spatial-temporal link correlation. Based on the performance modeling, we then propose a Performance Aware Hidden Markov Model (PA-HMM), where the protocol performance is directly fed into the Markov state transitions. PA-HMM is able to simulate both link-level behaviors and high-level protocol performance. We conduct extensive testbed and simulation experiments with broadcast and anycast protocols. The results show that compared to the state-of-the-art work, 1) the performance model is able to accurately characterize wireless communication performance and 2) the protocol performance is closely simulated as compared to the empirical results.

The widespread use of smartphones has brought great convenience to our daily lives, while at the same time we have been increasingly exposed to security threats. Keystroke security is an essential element in user privacy protection. In this paper, we present GazeRevealer, a novel side-channel based keystroke inference framework to infer sensitive inputs on smartphone from video recordings of victim's eye patterns captured from smartphone front camera. We observe that eye movements typically follow the keystrokes typing on the number-only soft keyboard during password input. By exploiting eye patterns, we are able to infer the passwords being entered. We propose a novel algorithm to extract sensitive eye pattern images from video streams, and classify different eye patterns with Support Vector Classification. We also propose a novel enhanced method to boost the inference accuracy. Compared with prior keystroke detection approaches, GazeRevealer does not require any external auxiliary devices, and it relies only on smartphone front camera. We evaluate the performance of GazeRevealer with three different types of smartphones, and the result shows that GazeRevealer achieves 77.43% detection accuracy for a single key number and 83.33% inference rate for the 6-digit password in the ideal case.

An electroencephalography (EEG) based Brain Computer Interface (BCI) enables people to communicate with the outside world by interpreting the EEG signals of their brains to interact with devices such as wheelchairs and intelligent robots. More specifically, motor imagery EEG (MI-EEG), which reflects a subject's active intent, is attracting increasing attention for a variety of BCI applications. Accurate classification of MI-EEG signals while essential for effective operation of BCI systems is challenging due to the significant noise inherent in the signals and the lack of informative correlation between the signals and brain activities. In this paper, we propose a novel deep neural network based learning framework that affords perceptive insights into the relationship between the MI-EEG data and brain activities. We design a joint convolutional recurrent neural network that simultaneously learns robust high-level feature presentations through low-dimensional dense embeddings from raw MI-EEG signals. We also employ an Autoencoder layer to eliminate various artifacts such as background activities. The proposed approach has been evaluated extensively on a large-scale public MI-EEG dataset and a limited but easy-to-deploy dataset collected in our lab. The results show that our approach outperforms a series of baselines and the competitive state-of-the-art methods, yielding a classification accuracy of 95.53%. The applicability of our proposed approach is further demonstrated with a practical BCI system for typing.

The on-street parking system is an indispensable part of civic projects, as it provides travelers and shoppers with parking spaces. With the recent in-ground sensors deployed throughout the Melbourne central business district (CBD), there is a significant problem on how to use the sensor data to manage parking violations and issue infringement notices efficiently in a short time-window. In this paper, we use a large realworld dataset with on-street parking sensor data from the local city council, and establish a formulation of the traveling officer problem with a general probability-based model. We propose two solutions using a spatio-temporal probability model for parking officers to maximize the number of infringing cars caught with limited time cost. Using real-world parking sensor data and Google Maps road network information, the experimental results show that our proposed algorithms outperform the existing patrolling routes.

Hand gesture is becoming an increasingly popular means of interacting with consumer electronic devices, such as mobile phones, tablets and laptops. In this paper, we present AudioGest, a device-free gesture recognition system that can accurately sense the hand in-air movement around user's devices. Compared to the state-of-the-art techniques, AudioGest is superior in using only one pair of built-in speaker and microphone, without any extra hardware or infrastructure support and with no training, to achieve multimodal hand detection. Specifically, our system is not only able to accurately recognize various hand gestures, but also reliably estimate the hand in-air duration, average moving speed and waving range. We achieve this by transforming the device into an active sonar system that transmits inaudible audio signal and decodes the echoes of hand's movement at its microphone. We address various challenges including cleaning the noisy reflected sound signal, interpreting the echo spectrogram into hand gestures, decoding the Doppler frequency shifts into the hand waving speed and range, as well as being robust to the environmental motion and signal drifting. We extensively evaluate our system on three electronic devices under four real-world scenarios using overall 3,900 hand gestures collected by five users for more than two weeks. Our results show that AudioGest detects six hand gestures with an accuracy up to 96 percent. By distinguishing the gesture attributions, it can provide more fine-grained control commands for various applications.

Understanding and recognizing human activities is a fundamental research topic for a wide range of important applications such as fall detection and remote health monitoring and intervention. Despite active research in human activity recognition over the past years, existing approaches based on computer vision or wearable sensor technologies present several significant issues such as privacy (e.g., using video camera to monitor the elderly at home) and practicality (e.g., not possible for an older person with dementia to remember wearing devices). In this paper, we present a low-cost, unobtrusive, and robust system that supports independent living of older people. The system interprets what a person is doing by deciphering signal fluctuations using radio-frequency identification (RFID) technology and machine learning algorithms. To deal with noisy, streaming, and unstable RFID signals, we develop a compressive sensing, dictionary-based approach that can learn a set of compact and informative dictionaries of activities using an unsupervised subspace decomposition. In particular, we devise a number of approaches to explore the properties of sparse coefficients of the learned dictionaries for fully utilizing the embodied discriminative information on the activity recognition task. Our approach achieves efficient and robust activity recognition via a more compact and robust representation of activities. Extensive experiments conducted in a real-life residential environment demonstrate that our proposed system offers a good overall performance and shows the promising practical potential to underpin the applications for the independent living of the elderly.

Cross-Technology Interference affects the operation of low-power ZigBee networks, especially under severe WiFi interference. Accurate corruption estimation is very important to improve the resilience of ZigBee transmissions. However, there are many limitations in existing approaches such as low accuracy, high overhead, and requiring hardware modification. In this paper, we propose an accurate corruption estimation approach, AccuEst, which utilizes per-byte SINR (Signal-to-Interference-and-Noise Ratio) to detect corruption. We combine the use of pilot symbols with per-byte SINR to improve corruption detection accuracy, especially in highly noisy environments (i.e., noise and interference are at the same level). In addition, we design an adaptive pilot instrumentation scheme to strike a good balance between accuracy and overhead. We implement AccuEst on the TinyOS 2.1.1/TelosB platform and evaluate its performance through extensive experiments. Results show that AccuEst improves corruption detection accuracy by 78.6% on average compared with state-of-the-art approach (i.e., CARE) in highly noisy environments. In addition, AccuEst reduces pilot overhead by 53.7% on average compared to the traditional pilot-based approach. We implement AccuEst in a coding-based transmission protocol, and results show that with AccuEst, the packet delivery ratio is improved by 20.3% on average.

This paper identifies two energy saving opportunities of Wi-Fi interface emerged during smartphone's screen-off periods. Exploiting the opportunities, we propose a new power saving strategy, BackPSM, for screen-off Wi-Fi communications. BackPSM regulates client to send and receive packets in batches and coordinates multiple clients to communicate at different slots (i.e., beacon interval). The core problem in BackPSM is how to coordinate client without incurring extra traffic overheads. To handle the problem, we propose a novel paradigm, Out-of-Band Communication (OBC), for client-to-client direct communications. OBC exploits the TIM (Traffic Indication Map) field of Wi-Fi Beacon to create a free side-channel between clients. It is based upon the observation that a client may control 1 → 0 appearing on TIM bit by locally regulating packet receiving operations. We adopt this 1 → 0 as the basic signal, and leverage the time length in between two signals to encode information. We demonstrate that OBC can be used to convey coordination information with close to 100% accuracy. We have implemented and evaluated BackPSM on a testbed. The results show that BackPSM reduces screen-off energy by up to 60%, and outperforms state-of-the-art strategies by 16%-42%.

In this paper, we study the problem of pedestrian relative positioning with respect to their walking direction. Existing approaches are mainly based on trajectory information or device proximity detection, and they highly rely on infrastructure or specialized device support. Importantly, most work does not provide relative position information with respect to people's walking direction. To address the above issues, we propose a direction-aware, audio-based solution that only uses daily wearable devices. Based on the fact that pedestrian's arms often swing back and forth during walking, we develop the wrist-body model that formally models the distance change between a user's wrist and his/her walking mate's body when walking together. Based on this model, we design our system by attaching the audio sources to a user's wrists and an audio receiver to the other user's body. We develop key indicators that characterize the received audio signal's Doppler shift induced by arm swing motions and the differences in signal strength. We further propose methods such as cycle segmentation and aggregation to deal with several real-world challenges. The performance of our approach is studied through extensive experiments. Evaluation conducted using real-world data suggests the prototype system achieves 85.9% positioning accuracy, demonstrating its effectiveness.

With the booming of the Internet of Things, enormous number of smart devices/sensors have been deployed in the physical world to monitor our surroundings. Usually those devices generate high-dimensional geo-tagged time-series data. However, these sensor readings are easily missing due to the hardware malfunction, connection errors or data corruption, which severely compromise the back-end data analysis. To solve this problem, in this paper we exploit tensor-based Singular Value Decomposition method to recover the missing sensor readings. The main novelty of this paper lies in that, i) our tensor-based recovery method can well capture the multi-dimensional spatial and temporal features by transforming the irregularly deployed sensors into a sensor-array and folding the periodic temporal patterns into multiple time dimensions, ii) it only requires to tune one key parameter in an unsupervised manner, and iii) Tensor Singular Value Decomposition structure is more efficient on representation of high-dimension sensor data than other tensor recovery methods based on tensor's vectorization or flattening. The experimental results in several real-world one-year air quality and meteorology datasets demonstrate the effectiveness and accuracy of our approach.

An electroencephalography (EEG) based brain activity recognition is a fundamental field of study for a number of significant applications such as intention prediction, appliance control, and neurological disease diagnosis in smart home and smart healthcare domains. Existing techniques mostly focus on binary brain activity recognition for a single person, which limits their deployment in wider and complex practical scenarios. Therefore, multi-person and multi-class brain activity recognition has obtained popularity recently. Another challenge faced by brain activity recognition is the low recognition accuracy due to the massive noises and the low signal-to-noise ratio in EEG signals. Moreover, the feature engineering in EEG processing is time-consuming and highly relies on the expert experience. In this paper, we attempt to solve the above challenges by proposing an approach which has better EEG interpretation ability via raw Electroencephalography (EEG) signal analysis for multi-person and multi-class brain activity recognition. Specifically, we analyze inter-class and inter-person EEG signal characteristics, based on which to capture the discrepancy of inter-class EEG data. Then, we adopt an Autoencoder layer to automatically refine the raw EEG signals by eliminating various artifacts. We evaluate our approach on both a public and a local EEG datasets and conduct extensive experiments to explore the effect of several factors (such as normalization methods, training data size, and Autoencoder hidden neuron size) on the recognition results. The experimental results show that our approach achieves a high accuracy comparing to competitive state-of-the-art methods, indicating its potential in promoting future research on multi-person EEG recognition.

Multi-hop over-the-air reprogramming is essential for remote installation of software patches and upgrades in wireless sensor networks (WSNs). Several recent coding-based reprogramming protocols have been proposed to enable efficient code dissemination in high packet loss environments. An accurate and formal analysis of the performance of these protocols, however, has not been studied sufficiently in the literature. In this paper, we present a novel high-fidelity analytical model based on the shortest path algorithm to measure the completion time by incorporating overhearing and packet coding. This model can be applied to any coding-based reprogramming protocol by substituting the coding part with protocol specific operations. We conduct extensive testbed experiments to evaluate the performance of our proposed model. Based on the analytical and numerical experiments, we find that 1) overhearing causes significant reduction of the completion time in dense wireless sensor networks, particularly, it reduces 50-70 percent of the total completion time when the packet reception rate is 0.896; 2) coding delay plays a key role in the total completion time compared to the communication delay when the packet coding parameters are selected appropriately, for example, the communication delay is about 65 percent of the coding delay when the number of packets per page is 16 for the finite field size 28; 3) the total completion time can be minimized when the number of packets per page is close to 24 and the finite field size is close to 24.

Elderly care is one of the many applications supported by real-time activity recognition systems. Traditional approaches use cameras, body sensor networks, or radio patterns from various sources for activity recognition. However, these approaches are limited due to ease-of-use, coverage, or privacy preserving issues. In this paper, we present a novel wearable Radio Frequency Identification (RFID) system aims at providing an easy-to-use solution with high detection coverage. Our system uses passive tags which are maintenance-free and can be embedded into the clothes to reduce the wearing and maintenance efforts. A small RFID reader is also worn on the user's body to extend the detection coverage as the user moves. We exploit RFID radio patterns and extract both spatial and temporal features to characterize various activities. We also address the issues of false negative of tag readings and tag/antenna calibration, and design a fast online recognition system. Antenna and tag selection is done automatically to explore the minimum number of devices required to achieve target accuracy. We develop a prototype system which consists of a wearable RFID system and a smartphone to demonstrate the working principles, and conduct experimental studies with four subjects over two weeks. The results show that our system achieves a high recognition accuracy of 93.6 percent with a latency of 5 seconds. Additionally, we show that the system only requires two antennas and four tagged body parts to achieve a high recognition accuracy of 85 percent.

The ZigBee communication can be easily and severely interfered by Wi-Fi traffic. Error recovery, as an important means for ZigBee to survive Wi-Fi interference, has been extensively studied in recent years. The existing works add upfront redundancy to in-packet blocks for recovering a certain number of random corruptions. Therefore, the bursty nature of ZigBee in-packet corruptions under Wi-Fi interference is often considered harmful, since some blocks are full of errors which cannot be recovered and some blocks have no errors but are still requiring redundancy. As a result, they often use interleaving to reshape the bursty errors, before applying complex FEC codes to recover the re-shaped random distributed errors. In this paper, we take a different view that burstiness may be helpful. With burstiness, the in-packet corruptions are often consecutive and the requirement for error recovery is reduced as “recovering any k consecutive errors” instead of “recovering any random k errors”. This lowered requirement allows us to design far more efficient code than the existing FEC codes. Motivated by this implication, we exploit the corruption burstiness to design a simple yet effective error recovery code using XOR operations (called ZiXOR). ZiXOR uses XOR code and the delay is significantly reduced. More, ZiXOR uses RSSI-hinted approach to detect in packet corruptions without CRC, incurring almost no extra transmission overhead. The testbed evaluation results show that ZiXOR outperforms the state-of-the-art works in terms of the throughput (by 47 percent) and latency (by 22 percent).

Data dissemination is a fundamental service offered by low-power wireless networks. Sender selection is the key to the dissemination performance and has been extensively studied. Sender impact metric plays a significant role in sender selection, since it determines which senders are selected for transmission. Recent studies have shown that spatial link diversity has a significant impact on the efficiency of broadcast. However, the existing metrics overlook such impact. Besides, they consider only gains but ignore the costs of sender candidates. As a result, existing works cannot achieve accurate estimation of the sender impact. Moreover, they cannot well support data dissemination with network coding, which is commonly used for lossy environments. In this paper, we first propose a novel sender impact metric, namely, γ, which jointly exploits link quality and spatial link diversity to calculate the gain/cost ratio of the sender candidates. Then, we develop a generic sender selection scheme based on the γ metric (called γ-component) that can generally support both types of dissemination using native packets and network coding. Extensive evaluations are conducted through real testbed experiments and large-scale simulations. The performance results and analysis show that γ achieves far more accurate impact estimation than the existing works. In addition, the dissemination protocols based on γ-component outperform the existing protocols in terms of completion time and transmissions (by 20.5% and 23.1%, respectively).

In this paper, we investigate the problem of energy balanced data collection in wireless sensor networks, aiming to balance energy consumption among all sensor nodes during the data propagation process. Energy balanced data collection can potentially save energy consumption and prolong network lifetime, and hence, it has many practical implications for sensor network design and deployment. The traditional hop-by-hop transmission model allows a sensor node to propagate its packets in a hop-by-hop manner toward the sink, resulting in poor energy balancing for the entire network. To address the problem, we apply a slice-based energy model, and divide the problem into inter-slice and intra-slice energy balancing problems. We then propose a probability-based strategy named inter-slice mixed transmission protocol and an intra-slice forwarding technique to address each of the problems. We propose an energy-balanced transmission protocol by combining both techniques to achieve total energy balancing. In addition, we study the condition of switching between inter-slice transmission and intra-slice transmission, and the limitation of hops in an intra-slice transmission. Through our extensive simulation studies, we demonstrate that the proposed protocols achieve energy balancing, prolong network lifespan, and decrease network delay, compared with the hop-by-hop transmission and a cluster-based routing protocol under various parameter settings.

This paper presents ScaPSM (i.e., Scalable Power-Saving Mode Scheduler), a design that enables scalable competing background traffic scheduling in crowd event 802.11 deployments with Power-Saving Mode (PSM) radio operation. ScaPSM prevents the packet delay proliferation of previous study, if applied in the crowd events scenario, by introducing a new strategy of adequate competition among multiple PSM clients to optimize overall energy saving without degrading packet delay performance. The key novelty behind ScaPSM is that it exploits delay-aware load balance to control judiciously the qualification and the number of competing PSM clients before every beacon frame’s transmission, which helps to mitigate congestion at the peak period with increasing the number of PSM clients. With ScaPSM, the average packet delay is bounded and fairness among PSM clients is simultaneously achieved. ScaPSM is incrementally deployable due to only AP-side changes and does not require any modification to the 802.11 protocol or the clients. We theoretically analyze the performance of ScaPSM. Our experimental results show that the proposed design is practical, effective, and featuring with significantly improved scalability for crowd events.

It is still challenging in telecommunication (telco) industry to accurately locate mobile devices (MDs) at city-scale using the measurement report (MR) data, which measure parameters of radio signal strengths when MDs connect with base stations (BSs) in telco networks for making/receiving calls or mobile broadband (MBB) services. In this paper, we find that the widely-used location based services (LBSs) have accumulated lots of over-the-top (OTT) global positioning system (GPS) data in telco networks, which can be automatically used as training labels for learning accurate MR-based positioning systems. Benefiting from these telco big data, we deploy a context-aware coarse-to-fine regression (CCR) model in Spark/Hadoop-based telco big data platform for city-scale localization of MDs with two novel contributions. First, we design map-matching and interpolation algorithms to encode contextual information of road networks. Second, we build a two-layer regression model to capture coarse-to-fine contextual features in a short time window for improved localization performance. In our experiments, we collect 108 GPS-associated MR records in the centroid of Shanghai city with 12 x 11 square kilometers for 30 days, and measure four important properties of real-world MR data related to localization errors: stability, sensitivity, uncertainty and missing values. The proposed CCR works well under different properties of MR data and achieves a mean error of 110m and a median error of $80m$, outperforming the state-of-art range-based and fingerprinting localization methods.

Hand gesture is becoming an increasingly popular means of interacting with consumer electronic devices, such as mobile phones, tablets and laptops. In this paper, we present AudioGest, a device-free gesture recognition system that can accurately sense the hand in-air movement around user's devices. Compared to the state-of-the-art, AudioGest is superior in using only one pair of built-in speaker and microphone, without any extra hardware or infrastructure support and with no training, to achieve fine-grained hand detection. Our system is able to accurately recognize various hand gestures, estimate the hand in-air time, as well as average moving speed and waving range. We achieve this by transforming the device into an active sonar system that transmits inaudible audio signal and decodes the echoes of hand at its microphone. We address various challenges including cleaning the noisy reflected sound signal, interpreting the echo spectrogram into hand gestures, decoding the Doppler frequency shifts into the hand waving speed and range, as well as being robust to the environmental motion and signal drifting. We implement the proof-of-concept prototype in three different electronic devices and extensively evaluate the system in four real-world scenarios using 3,900 hand gestures that collected by five users for more than two weeks. Our results show that AudioGest can detect six hand gestures with an accuracy up to 96%, and by distinguishing the gesture attributions, it can provide up to 162 control commands for various applications.

Recent research has demonstrated the feasibility of detecting human respiration rate non-intrusively leveraging commodity WiFi devices. However, is it always possible to sense human respiration no matter where the subject stays and faces? What affects human respiration sensing and what's the theory behind? In this paper, we first introduce the Fresnel model in free space, then verify the Fresnel model for WiFi radio propagation in indoor environment. Leveraging the Fresnel model and WiFi radio propagation properties derived, we investigate the impact of human respiration on the receiving RF signals and develop the theory to relate one's breathing depth, location and orientation to the detectability of respiration. With the developed theory, not only when and why human respiration is detectable using WiFi devices become clear, it also sheds lights on understanding the physical limit and foundation of WiFi-based sensing systems. Intensive evaluations validate the developed theory and case studies demonstrate how to apply the theory to the respiration monitoring system design.

Despite the active research into, and the development of, human activity recognition over the decades, existing techniques still have several limitations, in particular, poor performance due to insufficient ground-truth data and little support of intra-class variability of activities (i.e., the same activity may be performed in different ways by different individuals, or even by the same individuals with different time frames). Aiming to tackle these two issues, in this paper, we present a robust activity recognition approach by extracting the intrinsic shared structures from activities to handle intra-class variability, and the approach is embedded into a semi-supervised learning framework by utilizing the learned correlations from both labeled and easily-obtained unlabeled data simultaneously. We use l2,1 minimization on both loss function and regularizations to effectively resist outliers in noisy sensor data and improve recognition accuracy by discerning underlying commonalities from activities. Extensive experimental evaluations on four community-contributed public datasets indicate that with little training samples, our proposed approach outperforms a set of classical supervised learning methods as well as those recently proposed semi-supervised approaches.

Energy balance is a critical issue in wireless sensor networks. Several mixed data transmission (MDT) schemes have been proposed to achieve energy balance. However, most existing works are lack of theoretical study, especially understanding the relationship between network-wide energy balancing and lifetime optimization. In this paper, we conduct comprehensive theoretical analysis to the two-level based MDT scheme when applying to network-wide energy balancing, and eventually to maximize the network lifetime. We propose a novel network model, named energy balance area (EBA), and formally analyze its characteristics under the two-level based MDT scheme. To maximize the network lifetime, we convert the transmission probability allocation problem in the MDT scheme into an EBA partitioning (EBA-PT) problem, which is shown to be NP-hard. We then propose a heuristic approximation algorithm to determine the optimal configuration of EBAs, which is proven in this paper to be the key for maximizing the network lifetime. In this way, we obtain a near-optimal result. Our experimental studies show that network lifetime can be further improved as compared the hop-by-hop and the two-level based MDT schemes.

Smartphone based personal tracking is very important for people to find their destination in large complex buildings (e.g. shopping malls, airports and museums). Such applications are highly demanded in both industries and research organizations. One critical issue for these applications is lack of mature technologies for highly accurate indoor location tracking. In this paper, a new Wi-Fi and magnetic field based smartphone tracking system, named WMLoc, was introduced. The system is a part of a collaborative project between the RMIT University and a famous Australian software company. A number of tracking algorithms such as K nearest neighbor (KNN), artificial neural network (ANN) and back tracing (BT) have been developed or adopted for the system in order to obtain a real-time precise location of the smartphone user. The integration of Wi-Fi and magnetic field includes physical floor analysis, label pattern creation using ANN and BT for enhancing the tracking reliability and improving positioning accuracy. The WMLoc system was tested in two buildings at the RMIT University, Australia. The preliminary results showed that the average root-mean-square (RMS) error of the WMLoc system was less than 2.6 m.

Smoking behavior detection has attracted much research interest for its significant impact on smokers' physical and mental health. Existing research has shown the potential of using wearable devices for fine-grained smoking puff and session detection by detecting a smoker's content of breathing, lighter usage, breathing, and gesture patterns. However, the existing systems are complex, and they are usually vulnerable to confounding activities and diversity of smoking behavior. To address these limitations, this paper proposes the design and implementation of a simple and compact smart neckband device for smoking detection. The device is equipped with both passive and active acoustic sensors to detect smoking sessions and puffs. We propose a hierarchical processing framework in which the lower-layer detects the sub-movements, i.e., lighter usage, hand-to-mouth gesture and deep breathing, from perceived audio data; and the higher-layer, based on the lower-layerąŕs detection results, detects smoking puffs and sessions using temporal sequence analysis techniques. Real-world experiments suggest our system can accurately detect smoking puffs and sessions with F1 score of respectively 93.59% and 92.96% in complex environments with the presence of confounding activities and diverse ways of smoking.

Traffic congestion is a major concern in many cities around the world. Previous work mainly focuses on the prediction of congestion and analysis of traffic flows, while the congestion correlation between road segments has not been studied yet. In this paper, we propose a three-phase framework to study the congestion correlation between road segments from multiple real world data. In the first phase, we extract congestion information on each road segment from GPS trajectories of over 10,000 taxis, define congestion correlation and propose a corresponding mining algorithm to find out all the existing correlations. In the second phase, we extract various features on each pair of road segments from road network and POI data. In the last phase, the results of the first two phases are input into several classifiers to predict congestion correlation. We further analyze the important features and evaluate the results of the trained classifiers. We found some important patterns that lead to a high/low congestion correlation, and they can facilitate building various transportation applications. The proposed techniques in our framework are general, and can be applied to other pairwise correlation analysis.

Device-free indoor localization aims to localize people without requiring them to carry any devices or being actively involved in the localizing process. It underpins a wide range of applications including older people surveillance, intruder detection and indoor navigation. However, in a cluttered environment such as a residential home, the Received Signal Strength Indicator (RSSI) is heavily obstructed by furniture or metallic appliances, thus reducing the localization accuracy. This environment is important to observe as human-object interaction (HOI) events, detected by pervasive sensors, can potentially reveal people's interleaved locations during daily living activities, such as watching TV, opening the fridge door. This paper aims to enhance the performance of commercial off-the-shelf (COTS) RFID-based localization system by leveraging HOI contexts in a furnished home. Specifically, we propose a general Bayesian probabilistic framework to integrate both RSSI signals and HOI events to infer the most likely location and trajectory. Experiments conducted in a residential house demonstrate the effectiveness of our proposed method, in which we can localize a resident with average 95% accuracy and track a moving subject with 0.58m mean error distance.

Parkinson's disease (PD) is one of the typical movement disorder diseases among elderly people, which has a serious impact on their daily lives. In this article, we propose a novel computation framework to recognize gait patterns in patients with PD. The key idea of our approach is to distinguish gait patterns in PD patients from healthy individuals by accurately extracting gait features that capture all three aspects of movement functions, that is, stability, symmetry, and harmony. The proposed framework contains three steps: gait phase discrimination, feature extraction and selection, and pattern classification. In the first step, we put forward a sliding window--based method to discriminate four gait phases from plantar pressure data. Based on the gait phases, we extract and select gait features that characterize stability, symmetry, and harmony of movement functions. Finally, we recognize PD gait patterns by applying a hybrid classification model. We evaluate the framework using an open dataset that contains real plantar pressure data of 93 PD patients and 72 healthy individuals. Experimental results demonstrate that our framework significantly outperforms the four baseline approaches.

Using magnetic field data as fingerprints for smartphone indoor positioning has become popular in recent years. Particle filter is often used to improve accuracy. However, most of existing particle filter based approaches either are heavily affected by motion estimation errors, which result in unreliable systems, or impose strong restrictions on smartphone such as fixed phone orientation, which are not practical for real-life use. In this paper, we present a novel indoor positioning system for smartphones, which is built on our proposed reliability-augmented particle filter. We create several innovations on the motion model, the measurement model, and the resampling model to enhance the basic particle filter. To minimize errors in motion estimation and improve the robustness of the basic particle filter, we propose a dynamic step length estimation algorithm and a heuristic particle resampling algorithm. We use a hybrid measurement model, combining a new magnetic fingerprinting model and the existing magnitude fingerprinting model, to improve system performance, and importantly avoid calibrating magnetometers for different smartphones. In addition, we propose an adaptive sampling algorithm to reduce computation overhead, which in turn improves overall usability tremendously. Finally, we also analyze the “Kidnapped Robot Problem” and present a practical solution. We conduct comprehensive experimental studies, and the results show that our system achieves an accuracy of 1~2 m on average in a large building.

Abstract Traditional fingerprint‐based localization techniques mainly rely on infrastructure support such as GSM and Wi‐Fi. They require war‐driving, which is both time‐consuming and labor‐intensive. With recent advances of smartphone sensors, sensor‐assisted localization techniques are emerging. However, they often need user‐specific training and more power intensive sensing, resulting in infeasible solutions for real deployment. In this paper, we present Barometer‐based floor Localization system (B‐Loc), a novel floor localization system to identify the floor level in a multi‐floor building on which a mobile user is located. It makes use of the barometer on smartphone. B‐Loc does not rely on any Wi‐Fi infrastructure and requires neither war‐driving nor prior knowledge of the buildings. Leveraging on crowdsourcing, B‐Loc builds the barometer fingerprint map, which contains the barometric pressure value for each floor level to locate users' floor levels. We conduct both simulation and field studies to demonstrate the accuracy, scalability, and robustness of B‐Loc. Our simulation shows that B‐Loc can locate the user fast and the field study in a 10‐floor building shows that B‐Loc achieves an accuracy of over 98%. Copyright © 2016 John Wiley & Sons, Ltd.

The newly emerging event-based social networks (EBSNs) extend social interaction from online to offline, providing an appealing platform for people to organize and participate realworld social events. In this paper, we investigate how to select potential participants in EBSNs from an event host's point of view. We formulate the problem as mining influential and preferable invitee set, considering from two complementary aspects. The first aspect concerns users' preference with respect to the event. The second aspect is influence maximization, which aims to influence the largest number of users to participate the event. In particular, we propose a novel Credit Distribution-User Influence Preference (CD-UIP) algorithm to find the most influential and preferable followers as the invitees. We collect a real-world dataset from a popular EBSNs called "Douban Events", and the experimental results on the dataset demonstrate the proposed algorithm outperforms the state-of-the-art prediction methods.

Understanding and recognizing the activities performed by people is a fundamental research topic for a wide range of important applications such as fall detection of elderly people. In this paper, we present the technical details behind Freedom, a low-cost, unobtrusive system that supports independent livingof the older people. The Freedom system interprets what aperson is doing by leveraging machine learning algorithmsand radio-frequency identification (RFID) technology. To dealwith noisy, streaming, unstable RFID signals, we particularlydevelop a dictionary-based approach that can learn dictionariesfor activities using an unsupervised sparse coding algorithm. Our approach achieves efficient and robust activity recognitionvia a more compact representation of the activities. Extensiveexperiments conducted in a real-life residential environmentdemonstrate that our proposed system offers a good overallperformance (e.g., achieving over 96% accuracy in recognizing23 activities) and has the potential to be further developed tosupport the independent living of elderly people.

This paper investigates the suboptimal problem of existing state-of-the-art routing protocols when they are applied to heterogeneous duty-cycled wireless sensor networks (WSNs). In particular, we discover that the selected optimal routes with the least cost based their routing metric may not always lead to the least transmission cost. The key reason is that the existing routing metrics used do not sufficiently capture packet transmission cost in heterogeneous duty-cycled WSNs. To address this issue, we propose a novel routing metric, namely expected transmission cost (ETC), which efficiently captures packet transmission cost in heterogeneous duty-cycled WSNs by estimating both expected rendezvous cost and communication cost. Based on ETC, we design an opportunistic routing protocol (EoR) which is proved to select optimal routes with the least packet transmission cost. Our experimental results show that EoR outperforms the state-of-the-art protocols in terms of energy efficiency, latency, and packet delivery ratio.

Wireless link correlation can greatly affect the performance of wireless protocols such as flooding, and opportunistic routing. Researchers have proposed a variety of approaches to optimize existing protocols exploiting link correlation. Most existing works directly measure link correlation using packet-level transmissions and receptions. Measurement alone is insufficient because it lacks predictive power and scalability. In this paper, we present CorModel, a model for predicting link correlation in low-power wireless networks. Based on the underlying causes of link correlation, we explore four easily measurable parameters for our modeling. Besides PHY-layer parameters that previous studies have explored, we find that network-layer parameters can also have significant impact on link correlation. We validate our model and illustrate its usefulness by integrating it into existing protocols for more accurate correlation estimation. Experimental results show that our model can significantly increase the accuracy of wireless link estimation, resulting in better protocol performance.

Falls are among the leading causes of hospitalization for the elderly and illness individuals. Considering that the elderly often live alone and receive only irregular visits, it is essential to develop such a system that can effectively detect a fall or abnormal activities. However, previous fall detection systems either require to wear sensors or are able to detect a fall but fail to provide fine-grained contextual information (e.g., what is the person doing before falling, falling directions). In this paper, we propose a device-free, fine-grained fall detection system based on pure passive UHF RFID tags, which not only is capable of sensing regular actions and fall events simultaneously, but also provide caregivers the contexts of fall orientations. We first augment the Angle-based Outlier Detection Method (ABOD) to classify normal actions (e.g., standing, sitting, lying and walking) and detect a fall event. Once a fall event is detected, we first segment a fix-length RSSI data stream generated by the fall and then utilize Dynamic Time Warping (DTW) based kNN to distinguish the falling direction. The experimental results demonstrate that our proposed approach can distinguish the living status before fall happening, as well as the fall orientations with a high accuracy. The experiments also show that our device-free, fine-grained fall detection system offers a good overall performance and has the potential to better support the assisted living of older people.

Leveraging the regularities of people's trajectories, mobility prediction can help forecast social interaction opportunities. In this paper, in order to facilitate real-world social interaction, we aim to predict “serendipitous” social interactions, which are defined as unplanned encounters and interaction opportunities and regarded as emerging social interactions. We collected GPS trajectory data from people' daily life on campus and use it as empirical mobility traces to generate decision trees and model trees to predict next venues, arrival times, and user encounter. Mobility regularities are mainly considered in these prediction models, and mobility contexts (e.g., time, location, and speed) act as decision nodes in the classification trees. Experimental results using collected GPS data showed that our system achieves 90% accuracy for predicting a user's next venue using a decision tree algorithm, with minute-level (around 5 min) prediction error for arrival time using the model tree algorithm. Two prototype applications were developed to support serendipitous social interaction on campus, and the feedback from a user study with 25 users demonstrated the usability of these two applications.

Software update in wireless sensor networks requires the ability of disseminating bulk data to specified sensors of a network with low latency in an energy efficient manner. This paper proposes a target-aware, transmission power-adaptive, and collision-free data dissemination protocol to fulfill these requirements. This protocol disseminates data to sensors of a network by first constructing a connected dominating set (CDS) in the network. We propose a target-aware CDS construction to exclude many unnecessary non-target sensors from the data dissemination process. By allowing some dominators of the CDS to increase their transmission power to disseminate data to more dominatees, the protocol efficiently reduces the total energy consumption. In addition, we propose a collision-based channel assignment strategy to eliminate communication collisions among dominators so as to reduce latency. We have implemented the protocol and evaluated it through simulations and a real application scenario. Our experimental results show that the proposed protocol at most reduces non-target sensors by 75.3%, total energy consumption by 57.1%, and latency by 39.8% compared to existing dissemination protocols.

Using magnetic field data as fingerprints for localization in indoor environment has become popular in recent years. Particle filter is often used to improve accuracy. However, most of existing particle filter based approaches either are heavily affected by motion estimation errors, which makes the system unreliable, or impose strong restrictions on smartphone such as fixed phone orientation, which is not practical for real-life use. In this paper, we present an indoor localization system named MaLoc, built on our proposed augmented particle filter. We create several innovations on the motion model, the measurement model and the resampling model to enhance the traditional particle filter. To minimize errors in motion estimation and improve the robustness of particle filter, we augment the particle filter with a dynamic step length estimation algorithm and a heuristic particle resampling algorithm. We use a hybrid measurement model which combines a new magnetic fingerprinting model and the existing magnitude fingerprinting model to improve the system performance and avoid calibrating different smartphone magnetometers. In addition, we present a novel localization quality estimation method and a localization failure detection method to address the "Kidnapped Robot Problem" and improve the overall usability. Our experimental studies show that MaLoc achieves a localization accuracy of 1~2.8m on average in a large building.

Traditional fingerprint based localization techniques mainly rely on infrastructure support such as GSM, Wi-Fi or GPS. They work by war-driving the entire indoor spaces which is both time-consuming and labor-intensive. With recent advances of smartphone and sensing technologies, sensor-assisted localization techniques leveraging on mobile phone sensing are emerging. However, sensors are inherently noisy, making this technique challenging for real deployment. In this paper, we present F-Loc, a novel floor localization system to identify the floor level in a multi-floor building on which a mobile user is located. It does not need to war-drive the entire building. Leveraging on crowdsourcing and mobile phone sensing, we collect users' Wi-Fi traces and accelerometer readings. Through advanced clustering and cluster manipulating techniques, we are able to build the Wi-Fi map of the entire building, which can then be used for floor localization. We conduct both simulation and field studies to demonstrate the accuracy, scalability, and robustness of F-Loc. Our field study in a 10-floor building shows that F-Loc achieves an accuracy of over 98%.

Traditional fingerprint based localization techniques mainly rely on infrastructure support such as GSM and Wi-Fi. They require war-driving which is both time-consuming and labor-intensive. With recent advances of smartphone sensors, sensor-assisted localization techniques are emerging. However, they often need user-specific training and more power intensive sensing, resulting in infeasible solutions for real deployment. In this paper, we present B-Loc, a novel floor localization system to identify the floor level in a multi-floor building on which a mobile user is located. It makes use of the barometer on smartphone only. B-Loc does not rely on any Wi-Fi infrastructure and requires neither war-driving nor prior knowledge of the buildings. Leveraging on crowd sourcing, B-Loc builds the barometer fingerprint map which contains the barometric pressure value for each floor level to locate users' floor levels. We conduct both simulation and field studies to demonstrate the accuracy, scalability, and robustness of B-Loc. Our field study in a 10-floor building shows that B-Loc achieves an accuracy of over 98%.

We have seen increasingly popularity in embedding barometer into smartphone today. A barometer measures the barometric pressure, and it can be used for a variety of applications. For example, in localization techniques, it is used to detect the altitude or altitude change of a user. Unfortunately, t

Bulk data dissemination is a basic building block for enabling software update and reprogramming in wireless sensor networks. The recent structure based approach looks promising for efficient dissemination since it facilitates transmission and sleep scheduling. However, a number of limitations exist in existing structured protocols. In this paper, we propose a correlated core based solution for efficient bulk data dissemination in wireless sensor networks. We propose an efficient backbone node selection algorithm to construct the core structure by exploiting link correlation. We also design a novel negotiation mechanism which greatly reduces the control message overhead as compared to the existing structured protocols. We conduct both simulation and testbed experiments, and the results show that our proposed solution outperforms the state-of-the-art in terms of both the number of transmissions and the completion time.

Traditional fingerprint based localization techniques mainly rely on infrastructure support such as RFID, Wi-Fi or GPS. They operate by war-driving the entire space which is both time-consuming and labor-intensive. In this paper, we present M-Loc, a novel infrastructure-free localization system to locate mobile users in a metro line. It does not rely on any Wi-Fi infrastructure, and does not need to war-drive the metro line. Leveraging crowdsourcing, we collect accelerometer, magnetometer and barometer readings on smartphones, and analyze these sensor data to extract patterns. Through advanced data manipulating techniques, we build the pattern map for the entire metro line, which can then be used for localization. We conduct field studies to demonstrate the accuracy, scalability, and robustness of M-Loc. The results of our field studies in 3 metro lines with 55 stations show that M-Loc achieves an accuracy of 93% when travelling 3 stations, 98% when travelling 5 stations.

Efficiently operating on relevant data for users in large-scale online social network (OSN) systems is a challenging problem. Storage systems used by popular OSN systems often rely on key-value stores, where randomly partitioning the data of users among servers across the data centers is the defacto standard. Although by using DHTs, the random partition scheme is highly scalable for hosting a large number of users, it leads to costly inter-server communications across data centers due to the complexity of interconnection and interaction between OSN users. In this paper, we explore how to reduce the inter-server communications by retaining the simple and robust nature of OSNs. We propose a data placement solution atop OSN systems to divide users among servers according to the interaction-locality-based structure. Our approach exploits a simple, yet powerful principle of OSN interactions, self-similarity, which reveals that the inter-server communication cost is minimized under such intrinsic structure. Our algorithm avoids a significant amount of inter-server traffic as well as achieves load balance among servers across the data centers. We demonstrate the existence of self-similarity in large-scale Facebook traces including 10 million Facebook users and 24 million interaction events. We conduct comprehensive trace-driven simulations to evaluate this design exploiting the unique feature of self-similarity. Results show that our scheme significantly reduces the traffic and latency of the existing schemes.

In this paper, we investigate the energy balanced data collection problem in WSNs, aiming to balance the energy consumption among all the sensor nodes in the data propagation process. Energy balanced data collection can potentially save energy consumption and prolong the network lifetime, and hence it has many practical implications for WSN design and deployment. The traditional hop-by-hop transmission model allows a sensor node to propagate its packets in a hop-by-hop manner towards the sink, resulting in poor energy balance for the entire network. To address the problem, we apply a slice based energy model, and divide the energy balanced data collection problem into inter- and intra-slice energy balance problems. We then propose a novel Inter-slice Mixed Transmission strategy and an Intra-slice Forwarding technique to address each of the problems. Finally, we design an Energy-balanced Transmission Protocol (ETP) to combine both techniques to achieve total energy balance in data collection. Through extensive simulation studies, we demonstrate that, while ETP achieves energy balanced data collection, the network lifespan is increased by 10 times and the network delay is decreased by more than 70% compared to the hop-by-hop transmission in a general square area WSN.

Using mobile devices, people can easily obtain their location information, and access a wide range of location based services (LBSs). Many existing LBSs rely in accurate, continuous, and real-time streams of location information to provide quality of service guarantees. In this case, even if an user accesses LBSs anonymously, the identity of the user can still be revealed by analyzing the mobility trace. To protect user privacy, existing work sacrifice the quality of LBSs by degrading spatial and temporal accuracy. To achieve a better tradeoff between user privacy and the quality of service, we present a novel approach, Complete Bipartite Anonymity (CBA), to confuse the paths of nearby users by connecting different users' real traces with fake ones. CBA protects user privacy as users become indistinguishable after their paths are confused, the quality of service of LBSs is also guaranteed since users are able to report their accurate locations. We evaluate CBA by comparing the system and privacy performance with existing techniques such as Path Confusion or Query Obfuscation using a real-world data set, the results show that our scheme increases the chance for a user joining an anonymity group by 10 times in low user density areas, and reduces the resources consumed by about 90% for achieving the same anonymity degree.

Audio represents one of the most appealing yet least exploited modalities in wireless sensor networks, due to the potentially extremely large data volumes and limited wireless capacity. Therefore, how to effectively collect audio sensing information remains a challenging problem. In this paper, we propose a new paradigm of audio information collection based on the concept of audio-on-demand. We consider a sink-free environment targeting for disaster management, where audio chunks are stored inside the network for retrieval. The difficulty is to guarantee a high search success rate without infrastructure support. To solve the problem, we design a novel replication algorithm that deploys an optimal number of O(√n) replicas across the sensor network. We prove the optimality of the energy consumption of the algorithm, and use real testbed experiments and extensive simulations to evaluate the performance and efficiency of our design. The experimental results show that our design can provide satisfactory quality of audio-on-demand service with short startup latency and slight playback jitter. Extensive simulation results show that this design achieves a search success rate of 98% while reducing the search energy consumption by an order of magnitude compared with existing schemes.

Mobile phone localization plays a key role in the fast-growing Location Based Applications domain. Most of the existing localization schemes rely on infrastructure support such as GSM, WiFi or GPS. In this paper, we present FTrack, a novel floor localization system to identify the floor level in a multi-floor building on which a mobile user is located. FTrack uses the mobile phone's accelerometer only without any infrastructure support. It does not require any prior knowledge of the building such as floor height. By capturing user encounters and analyzing user trails, FTrack finds the mapping from the traveling time (when taking the elevator) or the step counts (when walking on the stairs) between any two floors to the number of floor levels. The mapping can then be used for mobile users to pinpoint their current floor levels. We conduct both simulation and field studies to demonstrate the effectiveness of FTrack. Our field trial in a 10-floor building shows that FTrack achieves an accuracy of over 90% after two hours in our experiment.

Efficient and effective full-text retrieval in unstructured peer-to-peer networks remains a challenge in the research community. First, it is difficult, if not impossible, for unstructured P2P systems to effectively locate items with guaranteed recall. Second, existing schemes to improve search success rate often rely on replicating a large number of item replicas across the wide area network, incurring a large amount of communication and storage costs. In this paper, we propose BloomCast, an efficient and effective full-text retrieval scheme, in unstructured P2P networks. By leveraging a hybrid P2P protocol, BloomCast replicates the items uniformly at random across the P2P networks, achieving a guaranteed recall at a communication cost of O(√N), where N is the size of the network. Furthermore, by casting Bloom Filters instead of the raw documents across the network, BloomCast significantly reduces the communication and storage costs for replication. We demonstrate the power of BloomCast design through both mathematical proof and comprehensive simulations based on the query logs from a major commercial search engine and NIST TREC WT10G data collection. Results show that BloomCast achieves an average query recall of 91 percent, which outperforms the existing WP algorithm by 18 percent, while BloomCast greatly reduces the search latency for query processing by 57 percent.

Prior work on anti-collision for Radio Frequency IDentification (RFID) systems usually schedule adjacent readers to exclusively interrogate tags for avoiding reader collisions. Although such a pattern can effectively deal with collisions, the lack of readers' collaboration wastes numerous time on the scheduling process and dramatically degrades the throughput of identification. Even worse, the tags within the overlapped interrogation regions of adjacent readers (termed as contentious tags), even if the number of such tags is very small, introduce a significant delay to the identification process. In this paper, we propose a new strategy for collision resolution. First, we shelve the collisions and identify the tags that do not involve reader collisions. Second, we perform a joint identification, in which adjacent readers collaboratively identify the contentious tags. In particular, we find that neighboring readers can cause a new type of collisions, cross-tag-collision, which may impede the joint identification. We propose a protocol stack, named Season, to undertake the tasks in two phases and solve the cross-tag-collision. We conduct extensive simulations and preliminary implementation to demonstrate the efficiency of our scheme. The results show that our scheme can achieve above 6 times improvement on the identification throughput in a large-scale dense reader environment.

Recognizing human activities from sensor readings has recently attracted much research interest in pervasive computing due to its potential in many applications, such as assistive living and healthcare. This task is particularly challenging because human activities are often performed in not only a simple (i.e., sequential), but also a complex (i.e., interleaved or concurrent) manner in real life. Little work has been done in addressing complex issues in such a situation. The existing models of interleaved and concurrent activities are typically learning-based. Such models lack of flexibility in real life because activities can be interleaved and performed concurrently in many different ways. In this paper, we propose a novel pattern mining approach to recognize sequential, interleaved, and concurrent activities in a unified framework. We exploit Emerging Pattern-a discriminative pattern that describes significant changes between classes of data-to identify sensor features for classifying activities. Different from existing learning-based approaches which require different training data sets for building activity models, our activity models are built upon the sequential activity trace only and can be applied to recognize both simple and complex activities. We conduct our empirical studies by collecting real-world traces, evaluating the performance of our algorithm, and comparing our algorithm with static and temporal models. Our results demonstrate that, with a time slice of 15 seconds, we achieve an accuracy of 90.96 percent for sequential activity, 88.1 percent for interleaved activity, and 82.53 percent for concurrent activity.

The advances of wireless networking and sensor technology open up an interesting opportunity to infer human activities in a smart home environment. Existing work in this paradigm focuses mainly on recognizing activities of single user. In this work, we focus on the fundamental problem of recognizing activities of multiple users using a wireless body sensor network, and propose a scalable pattern mining approach to recognize both single- and multiuser activities in a unified framework. We exploit Emerging Pattern-a discriminative knowledge pattern which describes significant changes among activity classes of data-for building activity models and design a scalable, noise-resistant, Emerging Pattern-based Multiuser Activity Recognizer (epMAR) to recognize both single- and multiuser activities. We develop a multimodal, wireless body sensor network for collecting real-world traces in a smart home environment, and conduct comprehensive empirical studies to evaluate our system. Results show that epMAR outperforms existing schemes in terms of accuracy, scalability, and robustness.

The emerging participatory sensing applications have brought a privacy risk where users expose their location information. Most of the existing solutions preserve location privacy by generalizing a precise user location to a coarse-grained location, and hence they cannot be applied in those applications requiring fine-grained location information. To address this issue, in this paper we propose a novel method to preserve location privacy by anonymizing coarse-grained locations and retaining fine-grained locations using Attribute Based Encryption (ABE). In addition, we do not assume the service provider is an trustworthy entity, making our solution more feasible to practical applications. We present and analyze our security model, and evaluate the performance and scalability of our system.

Real-time activity recognition using body sensor networks is an important and challenging task and it has many potential applications. In this paper, we propose a real time, hierarchical model to recognize both simple gestures and complex activities using a wireless body sensor network. In this model, we first use a fast, lightweight template matching algorithm to detect gestures at the sensor node level, and then use a discriminative pattern based real-time algorithm to recognize high-level activities at the portable device level. We evaluate our algorithms over a real-world dataset. The results show that the proposed system not only achieves good performance (an average precision of 94.9%, an average recall of 82.5%, and an average real-time delay of 5.7 seconds), but also significantly reduces the network communication cost by 60.2%.

Understanding and recognizing human activities from sensor readings is an important task in pervasive computing. Existing work on activity recognition mainly focuses on recognizing activities for a single user in a smart home environment. However, in real life, there are often multiple inhabitants l

Recognizing human activities from sensor readings has recently attracted much research interest in pervasive computing. This task is particularly challenging because human activities are often performed in not only a simple (i.e., sequential), but also a complex (i.e., interleaved and concurrent) manner in real life. In this paper, we propose a novel emerging patterns based approach to sequential, interleaved and concurrent activity recognition (epSICAR). We exploit emerging patterns as powerful discriminators to differentiate activities. Different from other learning-based models built upon the training dataset for complex activities, we build our activity models by mining a set of emerging patterns from the sequential activity trace only and apply these models in recognizing sequential, interleaved and concurrent activities. We conduct our empirical studies in a real smart home, and the evaluation results demonstrate that with a time slice of 15 seconds, we achieve an accuracy of 90.96% for sequential activity, 87.98% for interleaved activity and 78.58% for concurrent activity.

The growing aging population faces a number of challenges, including rising medical cost, inadequate number of medical doctors and healthcare professionals, as well as higher incidence of misdiagnosis. There is an increasing demand for a better healthcare support for the elderly and one promising solution is the development of a context-aware middleware infrastructure for pervasive health/wellness-care. This allows the accurate and timely delivery of health/medical information among the patients, doctors and healthcare workers through a widespread deployment of wireless sensor networks and mobile devices. In this paper, we present our design and implementation of such a context-aware middleware for pervasive homecare (CAMPH). The middleware offers several key-enabling system services that consist of P2P-based context query processing, context reasoning for activity recognition and context-aware service management. It can be used to support the development and deployment of various homecare services for the elderly such as patient monitoring, location-based emergency response, anomalous daily activity detection, pervasive access to medical data and social networking. We have developed a prototype of the middleware and demonstrated the concept of providing a continuing-care to an elderly with the collaborative interactions spanning multiple physical spaces: person, home, office and clinic. The results of the prototype show that our middleware approach achieves good efficiency of context query processing and good accuracy of activity recognition.

We envisage future context-aware applications will dynamically adapt their behaviors to various context data from sources in wide-area networks, such as the Internet. Facing the changing context and the sheer number of context sources, a data management system that supports effective source organization and efficient data lookup becomes crucial to the easy development of context-aware applications. In this paper, we propose the design of a new context data management system that is equipped with query processing capabilities. We encapsulate the context sources into physical spaces belonging to different context spaces and organize them as peers in semantic overlay networks. Initial evaluation results of an experimental system prototype demonstrate the effectiveness of our design.

Context-aware computing is a key paradigm of ubiquitous computing in which applications automatically adapt their operations to dynamic context data from multiple sources. Managing a number of distributed sources, a middleware that facilitates the development of context-aware applications must provide a uniform view of all these sources to the applications. Local schemas of context data from individual sources need to be matched into a set of global schemas in the middleware, upon which applications can issue context queries to acquire data. In this paper, we study this problem of schema matching for context-aware computing. We propose a multi-criteria algorithm to determine candidate attribute matches between two schemas. The algorithm adaptively adjusts the priorities of different criteria based on previous matching results to improve the efficiency and accuracy of succeeding operations. We further develop an algorithm to categorize a new local schema into one of the global schemas whenever possible via a shared attribute dictionary. Our results based on schemas from real-world websites demonstrate the good matching accuracy achieved by our algorithms.

In this paper, we propose two RFID identification and authentication schemes based on the previously proposed triggered hash chain scheme by Henrici and Muller. The schemes are designed to mitigate the shortcomings observed in the triggered hash chain scheme and to ensure privacy preserving identification, tag-reader mutual authentication, as well as forward-privacy in the case of RFID tags that have been compromised. The first scheme uses a challenge-response mechanism to defend against an obvious weakness of the triggered hash chain scheme. The second scheme uses an authenticated monotonic counter to defend against a session linking attack that the first scheme is vulnerable to. We compare the level of security offered by our proposed schemes against other previous schemes and find that the schemes perform well, while keeping within reasonable overheads in terms of computational, storage and communication requirements.

In this paper, we propose a peer-to-peer approach to derive and obtain additional context data from low-level context data that may be spread over multiple domains in pervasive computing environments. In this system, peers are self-organized into a semantic peer- to-peer network as the underlying communication substrate. Context reasoning is done in a distributed fashion through logical reasoning according to a set of user-defined rules. Both pull and push services are supported in the system to enable message exchange during the reasoning process. We present our design concepts, and prove the effectiveness of our system through the prototype evaluation.

This paper proposes a two-tier semantic peer-to-peer network that facilitates efficient search for context information in wide-area networks. Context data with the same semantics are grouped together into a one-dimensional semantic ring space in the upper-tier network. This is achieved by applying an ontology-based semantic clustering technique and dedicating part of node identifiers to correspond to their data semantics. In the lower-tier network, peers in each semantic cluster are organized as Chord identifier space. Thus, all the nodes in the same semantic cluster know which node is responsible for storing context data triples they are looking for, and context queries can be efficiently routed to those nodes. Through the simulation studies, we demonstrate the effectiveness of our proposed scheme.

Building large-scale smart environments is one of the long-term goals of ubiquitous computing. The widespread of context information in such environments necessitates an effective context retrieval mechanism. This paper proposes a novel context retrieval method based on applications' query patterns. We propose high dimensional vector to model contexts from applications' perspective, and apply the normalized inner product of high dimensional vectors to measure context distance. Contexts with similar query patterns are clustered into the same group. To improve the performance of context retrieval, we build distributed indices on each node to speed up a local search, and create shortcuts based on clustering results to facilitate query routing. We show how our proposed methods can be applied to existing context retrieval mechanisms. Our experimental results show that our method can significantly reduce retrieval cost.

Conference and social events provides an opportunity for people to interact and develop formal contacts with various groups of individuals. In this paper, we propose an efficient interaction mechanism in a pervasive computing environment that provide recommendation to users of suitable locations within a conference or expo hall to meet and interact with individuals of similar interests. The proposed solution is based on evaluation of context information to deduce each user's interests as well as bioinspired self-organisation mechanism to direct users towards appropriate locations. Simulation results have also been provided to validate our proposed solution.

This paper proposes a formal approach for protocol information modeling and validation leveraging on ontological techniques. We demonstrate the advantage of our approach through prototyping a protocol management system for representation of communication protocols and composition of protocol stacks. The prototype has an ontology-based model to describe meta-data of protocols and protocol stacks in a systematic way. Consequently, the retrieval of protocols and the validation of protocol stacks are realized by corresponding operations on the ontology model. Owing to the better expressiveness of RDFS, the ontology model can describe protocols with higher fidelity. Our experimental results show that the ontology-based protocol management system is operable and provides expressive knowledge modeling without compromising the performance

The widespread use of context information necessitates an efficient wide-area lookup service in pervasive computing. In this paper, we present semantic context space (SCS), a semantic overlay network that facilitates efficient search for context information in distributed environments. Peers in SCS are grouped based on the semantics of their local data and self-organized into a one-dimensional ring space. Context search requests are only routed to the appropriate semantic clusters, reducing unnecessary search cost on peers that have irrelevant context data, and increasing the chances that the context data will be found quickly. By exploring parallelism in a semantic cluster, search request can be found quickly. Our simulation studies demonstrate the effectiveness of SCS.

As computing technology moves towards pervasive computing, many applications are beginning to make use of context information to adapt to and respond appropriately to their environments. Such a trend necessitates efficient search for context information in wide-area networks. In this paper, we propose a semantic P2P context lookup system. Peers are grouped based on the semantics of their local data which are extracted according to a set of schemas and are self-organized as a semantic overlay network. Context search requests are only routed to the appropriate nodes that have relevant data, reducing unnecessary query traffic and increasing the chances that the context data will be found quickly. To reduce maintenance overheads incurred by high-dimensional semantic overlay networks, we propose a one-dimensional ring space to construct peers and facilitate efficient query routing. Our simulation studies demonstrate the effectiveness of our proposed routing techniques.

Service discovery has been drawing much attention from researchers and practitioners. The existing service discovery systems, like SLP, Jini, UPnP and Salutation, provide basic infrastructures where services can announce their presence and users can locate these services across the network. However there are several key issues which are partially solved or have not been well addressed - such as scalability, availability, dynamics and support for multiple matching mechanisms. In this paper, we propose a design for a service locating manager (SLM) system which addresses some of these issues. The SLM system adopts a dynamic hierarchical tree structure and service aggregation for scalability, availability and dynamics, and introduces multiple matching mechanisms which contain an attribute-based and a semantic matching engine. It provides a scalable, distributed, dynamic and robust solution to establish a flexible service discovery architecture. We describe our concepts, architecture and implementation, and present a performance study for our prototype.