In recent years, long-range human presence detection has become increasingly important, especially in complex and non-line-of-sight (NLoS) environments such as urban warfare and disaster response. Existing vision-based and wireless sensing methods suffer from limited range, environmental interference, and degraded performance in challenging scenarios. These limitations are particularly severe for static targets, where subtle micro-motions such as respiration are easily buried in noise. To address this issue, we propose a LoRa-based micro-motion sensing framework for long-range static human presence detection that leverages the extended coverage and interference resilience of LoRa links. A dedicated signal preprocessing pipeline based on channel ratioing and multi-angle rotation mitigates static-path dominance and enhances motion-related components, while a CNN backbone with multi-scale 1D Inception blocks and dual (channel-temporal) attention focuses on informative micro-motion patterns. On top of this, a supervised contrastive learning strategy is introduced to suppress environment-specific biases and improve cross-scene and cross-user generalization. Experiments on a real-world indoor dataset with line-of-sight (LoS) and NLoS scenarios show that the proposed method achieves higher detection accuracy and more robust generalization than representative baselines, demonstrating its potential as a practical solution for low-power long-range human presence sensing.

Narrowband Internet of Things (NB-IoT) is an low-power wide area network based on cellar architecture. The repetition scheme is a key solution to achieve enhanced coverage with low complexity in the uplink. However, the impact of the current repetition scheme on energy consumption and coverage performance of NB-IoT are still unclear. In this paper, we conduct field measurements of the repetition scheme in terms of energy efficiency. We find that most of repetition values configured by the eNodeB lead to non-optimal energy efficiency. Then we propose an adaptive repetition scheme based on a regression block delivery rate (BDR) model which can be derived from a theoretical model and a small number of measurements. We conduct simulations based on real-world measurement data. The results show that the proposed adaptive repetition scheme outperforms the default repetition scheme in both energy efficiency and data transmission rate.

Improving the transferability of adversarial examples for the purpose of attacking unknown black-box models has been intensively studied. In particular, feature-level transfer-based attacks, which destroy the intermediate feature outputs of source models, are proven to generate more transferable adversarial examples. However, existing state-of-the-art feature-level attacks only destroy a single intermediate layer, this severely limits the transferability of adversarial examples. And all of these attacks have a vague distinction between positive and negative features. By contrast, we propose the Multi-layer Feature Division Attack (MFDA), which aggregates multi-layer feature information on the basis of feature division to attack. Extensive experimental evaluation demonstrates that MFDA can significantly boost the adversarial transferability and quantitatively distinguish the effects of positive and negative features on transferability. Compared to the state-of-the-art feature-level attacks, our improvement methods with MFDA increase the average success rate by 2.8% against normally trained models and 3.0% against adversarially trained models.

Crowd counting, which counts or estimates the number of people within a region, is critical in many applications, such as guided tours and disaster rescue. Several RF-based contact-free crowd counting techniques have been proposed in recent years, including WiFi, RFID, and millimeter wave radar. While promising in many aspects, one key limitation of current techniques is the small sensing range. However, many applications of crowd counting do require long-range sensing capability. In this work, we propose LoCount to significantly increase the sensing range of crowd counting using LoRa, which is a new wireless technology for long range communications among IoT devices. In particular, to solve the system performance degradation caused by different environments, we try to remove the components representing surrounding environments from the signal and use adversarial domain adaptation to extract environment-independent features. Considering that we may have multiple different source domains, for the target domain data, we comprehensively think over its similarity to each source domain and the prediction results to get the final result. We test LoCount in multiple large-scale scenes, and the results show that LoCount can achieve an average accuracy of 97.0% in the target domain without labeled data.

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources being limited. In such a situation, training data and models are exposed to the public. As a result, attackers can manipulate the training process to inject some triggers into the model, which is called backdoor attack. Backdoor attack is quite stealthy and difficult to be detected because it has little inferior influence on the model’s performance for the clean samples. To get a precise grasp and understanding of this problem, in this paper, we conduct a comprehensive review of backdoor attacks and defenses in the field of NLP. Besides, we summarize benchmark datasets and point out the open issues to design credible systems to defend against backdoor attacks.

Narrowband Internet of Things (NB-IoT) standardized by the 3GPP has attracted significant attention since its appearance. It provides extended coverage, high capacity, reduced device processing complexity, and low-power consumption to meet the requirements of a wide range of IoT applications. In particular, NB-IoT is expected to bring IoT devices prolonged lifetime up to ten years. Radio access (RA) plays a key role in the total power consumption of NB-IoT devices. Specifically, the enhanced coverage levels (ECLs) configure the user equipment (UE) with different random-access resources and power consumption during packet transmissions. In this article, we examine the ECL selection strategies for reducing the power consumption of NB-IoT. We develop two testbeds to conduct extensive field measurements related to ECL selection. Based on the measurement results, we analyze the key issues in the ECL selection process. Then, we propose an adaptive RA approach for UE, which includes two novel strategies for predictive ECL selection and opportunistic packet transmission. Evaluations show that, with the configuration of ECL selected by our adaptive approach, the UE can reduce the radio power consumption up to 36% while maintaining the same block error rate (BLER) during uploading under real-world settings.

Recent years have witnessed the increasing penetration of wireless charging base stations in the workplace and public areas, such as airports and cafeterias. Such an emerging wireless charging infrastructure has presented opportunities for new indoor localization and identification services for mobile users. In this paper, we present QID, the first system that can identify a Qi-compliant mobile device during wireless charging in real-time. QID extracts features from the clock oscillator and control scheme of the power receiver and employs light-weight algorithms to classify the device. QID adopts a 2-dimensional motion unit to emulate a variety of multi-coil designs of Qi, which allows for fine-grained device fingerprinting. Our results show that QID achieves high recognition accuracy. With the prevalence of public wireless charging stations, our results also have important implications for mobile user privacy.

Narrowband-Internet of Things (NB-IoT) is an emerging cellular communication technology designed for low-power wide-area applications. Cell selection determines the channel of user device and hence is an important issue in cellular networks. In this article, we make the first attempt to examine and optimize the cell selection in NB-IoT networks by field measurement. We conduct measurements at 30 different locations which involve five typical application scenarios of NB-IoT. Two kinds of NB-IoT modules and two network operators are also involved in the measurements. We find four potential issues on the cell selection of the User Equipment (UE) through the measurements. We propose an adaptive cell selection approach to optimize the cell selection of UE. The simulation test based on real-world measurement data shows that the cell selected by the adaptive approach can improve the coverage level and reduce the power consumption for UE.

Continuous and accurate respiratory volume monitoring is crucial in many healthcare-related applications. Traditional respiratory volume monitoring approaches involve obtrusive devices that are uncomfortable for long-term monitoring, while unobtrusive approaches mainly focus on sensing the respiratory rate, which is insufficient for many healthcare-related applications. In this article, we present radio-frequency respiratory volume monitoring (RF-RVM), an unobtrusive system to sense the respiratory volume based on commercial off-the-shelf (COTS) RFID devices. Specifically, RF-RVM continuously collects the temporal phase information from tags attached to the chest and abdomen to extract the chest displacement and abdomen displacement caused by respiration. Then, we assess the respiratory volume by training a backpropagation neural network model to correlate chest and abdomen displacements and respiratory volume. We use a reference tag attached under the user's neck to eliminate the noise caused by slight movements of the upper body during respiration. We implement and evaluate RF-RVM based on COTS RFID devices. The experimental results show that RF-RVM can continuously monitor user's respiratory volume with an average accuracy of 94.52% for leave-one-session-out cross-validation and 91.96% for leave-one-record-out cross-validation based on a data set sampled from 20 volunteers.

Recent years have seen a widespread deployment of NB-IoT networks for massive machine-to-machine communication in the emerging 5G era. Unfortunately, the key aspects of NB-IoT networks, such as radio access performance and power consumption have not been well-understood due to lack of effective tools and closed nature of operational cellular infrastructure. In this paper, we develop NB-Scope - the first hardware NB-IoT diagnostic tool that supports fine-grained fusion of power and protocol traces. We then conduct a large-scale field measurement study consisting of 30 nodes deployed at over 1,200 locations in 4 regions during a period of three months. Our in-depth analysis of the collected 49 GB traces showed that NB-IoT nodes yield significantly imbalanced energy consumption in the wild, up to a ratio of 75:1, which may lead to short battery lifetime and frequent network partition. Such a high performance variance can be attributed to several key factors including diverse network coverage levels, long tail power profile, and excessive control message repetitions. We then explore the optimization of NB-IoT base station settings on a software-defined eNodeB testbed, and suggest several important design aspects that can be considered by future NB-IoT specifications and chipsets.

Heart rate (HR) estimation based on photoplethysmography (PPG) signals has been widely adopted in wrist-worn devices. However, the motion artifacts caused by the user’s physical activities make it difficult to get the accurate HR estimation from contaminated PPG signals. Although many signal processing methods have been proposed to address this challenge, they are often highly optimized for specific scenarios, making them impractical in real-world settings where a user may perform a wide range of physical activities. In this article, we propose DeepHeart, a new HR estimation approach that features deep-learning-based denoising and spectrum-analysis-based calibration. DeepHeart generates clean PPG signals from electrocardiogram signals based on a training data set. Then a set of denoising convolutional neural networks (DCNNs) are trained with the contaminated PPG signals and their corresponding clean PPG signals. Contaminated PPG signals are then denoised by an ensemble of DCNNs and a spectrum-analysis-based calibration is performed to estimate the final HR. We evaluate DeepHeart on the IEEE Signal Processing Cup training data set with 12 records collected during various physical activities. DeepHeart achieves an average absolute error of 1.61 beats per minute (bpm), outperforming a state-of-the-art deep learning approach (4 bpm) and a classical signal processing approach (2.34 bpm).

Narrowband-Internet of Things (NB-IoT) is an emerging cellular communication technology designed for low power wide area applications. Cell selection determines the channel of user device and hence is an important issue in cellular networks. In this paper, we take the first attempt to examine and optimize the the cell selection in NB-IoT networks by field measurement. We conduct measurements at 30 different locations which involve 5 typical application scenarios of NB-IoT. Two kinds of NB-IoT modules and two network operators are also involved in the measurements. We find three potential issues on the cell selection of the User Equipment (UE) through the measurements. We propose an adaptive cell selection approach to optimize the cell selection of UE. The simulation test based on real-world measurement data shows that the cell selected by the adaptive approach can improve the coverage level and reduce the power consumption for UE.

Recent years have seen a widespread deployment of NB-IoT networks for massive machine-to-machine communication in the emerging 5G era. Unfortunately, the key aspects of NB-IoT networks, such as radio access performance and power consumption have not been well-understood due to lack of effective tools and closed nature of operational cellular infrastructure. In this paper, we develop NB-Scope - the first hardware NB-IoT diagnostic tool that supports fine-grained fusion of power and protocol traces. We then conduct a large-scale field measurement study consisting of 30 nodes deployed at over 1,200 locations in 3 regions during a period of three months. Our in-depth analysis of the collected 49 GB traces showed that NB-IoT nodes yield significantly imbalanced energy consumption in the wild, up to a ratio of 75:1, which may lead to short battery lifetime and frequent network partition. Such a high performance variance can be attributed to several key factors including diverse network coverage levels, long tail power profile, and excessive control message repetitions. We then explore the optimization of NB-IoT base station settings on a software-defined eNodeB testbed, and suggest several important design aspects that can be considered by future NB-IoT specifications and chipsets.

The identification of wood is an important problem both in industrial manufacturing and in people's daily life. Traditional methods based on experts are laborious. New technologies based on computer visions rely on high-quality cross section images. In this paper, we take the first attempt to identify the wood type based on commodity RFID devices. A system named RF-WTI is proposed. The main idea of RF-WTI is that different wood types result in different signal changes when RF signals pass through the wood. Specifically, after collecting the changes of Received Signal Strength (RSS) and phase when RFID signals pass through the wood, a feature that is unique for the wood is derived. Then RF-WTI applies a Bayesian neural network to identify wood types. Experimental results show that RF-WTI achieves 92.33% average accuracy for identifying 12 different types of wood.

By learning from the existing family mealtime activities, family members can be motivated to make the positive changes towards better relationships, which are important for the physical and mental health of children. Moreover, the details of family mealtime activities provide rich information for study in sociology and culture. This paper presents FamilyLog - a practical system to log family mealtime activities using smartphones and smartwatches. FamilyLog automatically detects and logs details of activities during the mealtime, including occurrence and duration of meal, conversations, participants, TV viewing, etc., in an unobtrusive manner. Based on the sensor data collected from real families, we carefully design robust yet lightweight signal features from a set of complex activities during the meal, including clattering sound, arm gestures of eating, human voice, TV sound, etc. Moreover, FamilyLog opportunistically fuses data from built-in sensors of multiple mobile devices available in a family with a CRFs-based classifier. To evaluate the real-world performance of FamilyLog, we perform extensive experiments that consist of 77 days of sensor data from 37 subjects in 8 families with children. FamilyLog can detect those events with high accuracy across different families and home environments.

The quality of sleep is an important factor in maintaining a healthy life style. A great deal of work has been done for designing sleep monitoring systems. However, most of existing solutions bring invasion to users more or less due to the exploration of the accelerometer sensor inside the device. This article presents iSleep—a practical system to monitor people’s sleep quality using off-the-shelf smartphone. iSleep uses the built-in microphone of the smartphone to detect the events that are closely related to sleep quality, and infers quantitative measures of sleep quality. iSleep adopts a lightweight decision-tree-based algorithm to classify various events. For two-user scenario, iSleep differentiates the events of two users either when two phones can collaborate with each other or when two phones cannot communicate with each other. The experimental results show that iSleep achieves consistently above 90% accuracy for event classification in a variety of different settings in one-user scenario and above 92% accuracy for distinguishing users in two-user scenario. By providing a fine-grained sleep profile that depicts details of sleep-related events, iSleep allows the user to track the sleep efficiency over time and relate irregular sleep patterns to possible causes.

PPG-based heart rate estimation has been widely adopted in wrist-worn devices. However, the motion artifacts caused by the user's physical activities make it difficult to get the accurate HR estimation from contaminated PPG signals. Although many signal processing methods have been proposed to address this challenge, they are often highly optimized for specific scenarios (e.g., running or biking), making them impractical in real-world settings where a user may perform a wide range of physical activities. In this paper, we propose DeepHeart, a new HR estimation approach that features deep-learning-based denoising and spectrum-analysis-based calibration. DeepHeart generates clean PPG signals from ECG signals based on a training data set. Then a denoising convolutional neural network (DnCNN) is trained with the contaminated PPG signals and their corresponding clean PPG signals. Contaminated PPG signals are then denoised by the DnCNN and a spectrum-analysis-based calibration is performed to estimate the final HR. We evaluate DeepHeart on the IEEE Signal Processing Cup (SPC) training data set with 12 records collected during various physical activities. DeepHeart achieves an average absolute error of 1.98 bpm, outperforming two state-of-the-art methods TROIKA and Deep PPG.

The continuous demand for content-rich multimedia is pushing for high-speed and secure transmission approaches. In recent years, linear network coding (LNC) has been shown to be a promising technology to improve network throughput, transmission reliability, and information security. In this paper, we study the optimal transmission topology construction and LNC design for a secure multiple-source multicast to deliver the same content with integral link rates, which can be equivalent to the secure multicast problem with a virtual source, i.e., the integer secure virtual-source multicast (ISVM) problem. The objectives of the ISVM problem include the following: 1) satisfy the weakly secure requirements, 2) maximize the secure multicast rate (SMR), and 3) minimize the transmission cost when the SMR is maximized. First, we analyze the necessary and sufficient condition that there exist a transmission topology with integral link rates and a secure LNC that can achieve a given SMR$R$. Then, we model the ISVM problem as an integer linear programming based on the theoretical analysis and design an efficient transmission topology construction algorithm to solve the ISVM problem by utilizing the Lagrangian relaxation and subgradient method. We also analyze the size of finite field required to construct thedeterministic LNCfor a secure virtual-source multicast and the probability that the virtual-source multicast is weakly secure when usingrandom LNCin the ISVM problem. Finally, we design upper and lower bounds for the ISVM problem and conduct extensive simulations to compare the performance of the proposed algorithms with these two bounds.

Monitoring aquatic debris is of great interest to the ecosystems, marine life, human health, and water transport. This paper presents the design and implementation of SOAR-a vision-based surveillance robot system that integrates an off-the-shelf Android smartphone and a gliding robotic fish for debris monitoring in relatively calm waters. SOAR features real-time debris detection and coverage-based rotation scheduling algorithms. The image processing algorithms for debris detection are specifically designed to address the unique challenges in aquatic environments. The rotation scheduling algorithm provides effective coverage for sporadic debris arrivals despite camera's limited angular view. Moreover, SOAR is able to dynamically offload compute-intensive processing tasks to the cloud for battery power conservation. We have implemented a SOAR prototype and conducted extensive experimental evaluation. The results show that SOAR can accurately detect debris in the presence of various environment and system dynamics, and the rotation scheduling algorithm enables SOAR to capture debris arrivals with reduced energy consumption.

Wireless sensor networks (WSNs) are increasingly deployed for mission-critical applications such as emergency management and health care, which impose stringent requirements on the communication performance of WSNs. To support these applications, it is crucial to model and measure the effect of wireless interference, which is the major factor that limits WSN performance. Accurate modeling and measurement of interference faces two key challenges. First, as shown in our experimental results, interference yields considerable spatial and temporal variations of WSN performance, which poses a major challenge for measurement at rum-time. Second, in the unlicensed band, the communication of WSN is interfered by coexisting wireless devices such as smartphones and laptops equipped with 802.11 radios, which lead to cross-technology interference that are difficult to characterize due to the heterogeneous PHY. To tackle these challenges, this paper presents a novel accuracy-aware approach to interference modeling and measurement for WSNs. First, we propose a new regression-based interference model and analytically characterize its accuracy based on statistics theory. Second, we develop a novel protocol called accuracy-aware interference measurement for measuring the proposed interference model with assured accuracy at run time. Third, building on interference modeling, we propose an algorithm that accurately forecasts the performance of WSNs in the presence of cross-technology interference. Our extensive experiments on a testbed of 17 TelosB motes show that the proposed approaches achieve high accuracy of interference modeling and WSN performance forecasting with significantly lower overhead than state-of-the-art approaches.

Mission-critical target detection imposes stringent performance requirements for wireless sensor networks, such as high detection probabilities and low false alarm rates. Data fusion has been shown as an effective technique for improving system detection performance by enabling efficient collaboration among sensors with limited sensing capability. Due to the high cost of network deployment, it is desirable to place sensors at optimal locations to achieve maximum detection performance. However, for sensor networks employing data fusion, optimal sensor placement is a nonlinear and nonconvex optimization problem with prohibitively high computational complexity. In this paper, we present fast sensor placement algorithms based on a probabilistic data fusion model. Simulation results show that our algorithms can meet the desired detection performance with a small number of sensors while achieving up to seven-fold speedup over the optimal algorithm.

In recent years network coding has attracted significant attention in telecommunication. The benefits of network coding to a communication network include the increased throughput as well as secure data transmission. The purpose of this work is to design secure linear network coding against wiretap attack. The problem is to maximize the transmission data rate of multiple unicast streams between a pair of source and destination nodes, under the condition of satisfying the weakly secure requirements. Different from most existing research on network coding that designs the network coding scheme based on a given network topology, we will consider the integrated network topology design and network coding design. Such an integrated approach has not been reported by other researchers. In this paper, we formally introduce the problem, prove the problem is computational intractable, and then develop efficient heuristic algorithms. We first try to find the transmission topology that is suitable for network coding. Based on the topology, we design linear network coding scheme that is weakly secure. We conduct simulations to show that the proposed algorithms can achieve good performance.

Many wireless sensor networks require sufficient sensing coverage over long periods of time. To conserve energy, a coverage maintenance protocol achieves desired coverage by activating only a subset of nodes, while allowing the others to sleep. Existing coverage maintenance protocols are often designed based on simplistic sensing models that do not capture the stochastic nature of distributed sensing. We propose a new sensing coverage model based on the distributed detection theory, which captures two important characteristics of sensor networks, i.e., probabilistic detection by individual sensors and data fusion among sensors. We then present three coverage maintenance protocols that can meet the specified event detection probability and false alarm rate. The centralized protocol only activates a small number of sensors, but introduces extremely long coverage configuration delay. The Se-Grid protocol reduces the configuration time by dividing the network into separate fusion groups, but increases the number of active sensors due to the lack of collaboration among sensors in different groups. In contrast, by coordinating overlapping fusion groups, the Co-Grid protocol can effectively reduce the number of active sensors and the coverage configuration time. The advantages of Co-Grid have been validated through simulations and benchmark results on Mica2 motes.