Wi-CCFAR: Wi-Fi CSI-Based Controllable False Alarm Rate Human Presence Detector With Normalizing Flow

WiFi-based human activity recognition (HAR) has been extensively studied due to its far-reaching applications in health domains, including elderly monitoring, exercise supervision and rehabilitation monitoring, etc. Although existing supervised deep learning techniques have achieved remarkable performances for these tasks, they are however data-hungry and hence are notoriously difficult due to the privacy and incomprehensibility of WiFi-based HAR data. Existing contrastive learning models, mainly designed for computer vision, cannot guarantee their performance on channel state information (CSI) data. To this end, we propose a new dual-stream contrastive learning model that can process and learn the raw WiFi CSI data in a self-supervised manner. More specifically, our proposed method, coined as DualConFi, takes raw WiFI CSI data as input and incorporates channel and temporal streams to learn highly-discriminative spatiotemporal features under a mutual information constraint using unlabeled data. We exhibit the effectiveness of our model on three publicly available CSI data sets in various experiment settings, including linear evaluation, semi-supervised, and transfer learning. We show that DualConFi is able to perform favourably against challenging baselines in each setting. Moreover, by studying the effects of different transform functions on CSI data, we finally verify the effectiveness of highly-discriminative features.

Falls pose a serious health risk for the elderly, particular for those who are living alone. The utilization of WiFi-based fall detection, employing Channel State Information (CSI), emerges as a promising solution due to its non-intrusive nature and privacy preservation. Despite these advantages, the challenge lies in optimizing cross-individual performance for CSI-based methods. This study aimed to develop a resilient real-time fall detection system across individuals utilizing CSI, named TCS-Fall. This method was designed to offer continuous monitoring of activities over an extended timeframe, ensuring accurate and prompt detection of falls. Extensive CSI data on 1800 falls and 2400 daily activities was collected from 20 volunteers. The grouped coefficient of variation of CSI amplitudes were utilized as input features. These features capture signal fluctuations and are input to a convolutional neural network classifier. Cross-individual performance was extensively evaluated using various train/test participant splits. Additionally, a user-friendly CSI data collection and detection tool was developed using PyQT. To achieve real-time performance, data parsing and pre-processing computations were optimized using Numba's just-in-time compilation. The proposed TCS-Fall method achieved excellent performance in cross-individual fall detection. On the test set, AUC reached 0.999, no error warning ratio score reached 0. 955 and correct warning ratio score reached of 0.975 when trained with data from only two volunteers. Performance can be further improved to 1.00 when 10 volunteers were included in training data. The optimized data parsing/pre-processing achieved over 20× speedup compared to previous method. The PyQT tool parsed and detected the fall within 100 ms. TCS-Fall method enables excellent real-time cross-individual fall detection utilizing WiFi CSI, promising swift alerts and timely assistance to elderly. Additionally, the optimized data processing led to a significant speedup. These results highlight the potential of our approach in enhancing real-time fall detection systems.

Wi-Fi sensing for gesture recognition systems is a fascinating and challenging research topic. We propose a multitask sign language recognition framework called Wi-SignFi, which accounts for gestures in the real world associated with various objects, actions, or scenes. The proposed framework comprises a convolutional neural network (CNN) and K-nearest neighbor (KNN) module. It is evaluated on the public SignFi dataset and achieves 98.91%, 86.67%, and 99.99% average gesture recognition accuracies on 276/150 activities, five users, and two environments, respectively. The experimental results show that the proposed gesture recognition method outperforms previous methods. Instead of converting the channel state information (CSI) data of multiple antennas into three-dimensional matrices (i.e., color images) as in the existing literature, we found that the CSI data can be converted into matrices (i.e., grayscale images) by concatenating different channels, allowing the Wi-SignFi model to balance between speed and accuracy. This finding facilitates deploying Wi-SignFi on Nvidia’s Jetson Nano edge embedded devices. We expect this work to promote the integration of Wi-Fi sensing and the Internet of Things (IoT) and improve the quality of life of the deaf community.

The development of tools for automated analysis of data collected for mine countermeasures (MCM) search, classify and map (SCM) has predominantly focused on automated target recognition for individual mines. As MCM target detection becomes more automated, detecting spatial patterns in the positioning of mines should follow. Natural restrictions on mine deployment such as depth and bottom contour as well as mine deployment methodology and protocol effectively create mine line patterns that are typical to coastal areas. We have developed a mine line detection algorithm that uses nonparametric spatial analysis to identify mine-like contacts (MLCs) that fit into mine line patterns dictated by standard mine laying protocol in coastal regions. In general, a set of MLCs reported from a mine detection sensor will consist of both actual mines and false alarms; the algorithm classifies every MLC in this set into one of three classes: fixed — the MLCψfits into a mine line pattern with fixed mine spacing; random -the MLCψfits into a mine line pattern with random mine spacing; or false alarm-ψ-the MLCψdoes not fit into a mine line pattern and is subsequently not considered a mine. The latest version of the algorithm utilizes nonparametric techniques and requires no knowledge of either the detection sensor's probability of detection (P d ) or probability of false alarm (P fa ). A nonparametric anomaly detector first identifies regions with unusually high MLC density for more detailed analysis. Suspected regions are subsequently analyzed for unusually regular patterns of MLCs. The probabilities that the observed target densities and target patterns could occur simply by chance are estimated by comparison with results from nearby areas using basic information about mine deployment. To ensure that a mine line's full extent is captured, the algorithm attempts to grow a line after it is detected. And a more detailed probability analysis distinguishes random mine lines from fixed-spaced mine lines. Extensive Matlab simulations characterize the algorithm's performance across a wide range of operating environments and simulated minefield configurations. In total, ten replications each of 1,367 different configurations have been evaluated. These configurations include three different water depths (10 ft., 6 ft. and 200 ft.), six false notional alarm rates (1, 2,5,10,15 and 20 false alarms per sq. NM), three false alarm distributions (uniform, sloped, and striped), three sensor probabilities of detections (0.4, 0.6 and 0.9), three target confidence scores (0.6,0.8 and 1.0) and four false alarm confidence scores (0.5, 0.6, 0.8 and 1.0). The range of simulation parameters was selected in part as an attempt to push the algorithm past its acceptable performance limits. However, the algorithm performed remarkably well even under the worst conditions. For MLC sets with false alarm rates as high as 20 per square nautical mile, the algorithm correctly classifies over 98% of the MLCs as mines and detects 97% of the mine lines. Furthermore, it reduces the false alarm rate from 20 to 0.2 per square nautical mile with a false mine line rate of 0.14 false lines per square nautical mile. The algorithm achieves even lower false alarm rates when the initial false alarm rate is less than 20. The automated mine line detection discovers many obscure lines that are virtually undetectable to the naked eye.

Since channel state information (CSI) data can be utilized to sense the subtle changes in the environment, such as chest movement, we provide the analysis of CSI amplitude and phase as a basis for estimating breathing rates. In this paper, a breathing rate monitoring system is proposed, in which CSI data is collected with Intel Wi-Fi Link 5300 wireless network interface card (NIC) and Linux 802.11n CSI Tool [1]. To this end, an antenna and subcarrier selection method is proposed to select those CSIs which are sensitive to respiratory thoracic changes. Furthermore, multiple signal classification (MUSIC) is applied as our research method in the estimation of breathing rates. Extensive experiments are conducted to validate the effectiveness of the proposed system. Our experimental results demonstrate that the proposed system can not only effectively distinguish the breathing state differences of fast, slow, and apnea but also achieve a certain accuracy in the calculation of the breathing rates.

A robust and unobtrusive human activity recognition system is essential to a multitude of applications, such as health care, active assisted living, robotics, sports, and tele-immersion. Existing well-performing activity recognition methods are either vision- or wearable sensor-based. However, they are not fully passive. In this paper, we develop WiHAR-an unobtrusive Wi-Fi-based activity recognition system. WiHAR uses the Wi-Fi network interface card to capture the channel state information (CSI) data. These CSI data are effectively processed, and then amplitude and phase information is used to obtain the spectrogram. In the subsequent step, the time-variant mean Doppler shift (MDS) caused by the human body movements in the radio signals before their arrival at the receiver is estimated. The MDS is used to extract time and frequency domain features that are needed to train the supervised learning algorithms (i.e., decision tree, linear discriminant analysis, and support vector machines (SVM)) to assess the performance of the WiHAR. Our results show that WiHAR combined with SVM achieves 96.2% recognition accuracy on the data set consisting of 9 participants where each participant performed four activities including: walking, falling, picking up an object from the ground, and sitting on a chair.

Indoor occupancy detection (IOD) via Wi-Fi sensing capitalizes on the varying patterns in CSI (Channel State Information) to estimate the number of people in a given area. However, the precision of such systems heavily depends on the quality of the CSI data, which can be degraded by noise and environmental factors. To address this issue, In this paper, we present a CSI preprocessing method to improve the accuracy of IOD systems using Wi-Fi sensing. Unlike existing preprocessing methods that use computationally complex signal processing or statistical techniques, we expand the dimension of CSI amplitude data into a three-channel vector through nonlinear transformation to amplify subtle differences between CSI data belonging to a different number of people. By drawing clearer boundaries between CSI data distributions belonging to a different number of people in a monitored area, our method improves the people-counting accuracy of a Wi-Fi sensing system. To ensure temporal consistency and improve data quality, we discretize the CSI measurements based on their transmission periods and aggregate consecutive measurements over a given time interval. These samples are then fed into a Convolutional Neural Network (CNN) specifically trained for the IOD task. Experimental results in diverse real-world scenarios verify that compared to the traditional methods, the enhanced feature representation capability of our approach leads to more accurate and robust sensing outcomes even in the most resource-constrained environment, where a commercial off-the-shelf CSI capture machine with only one antenna is used when a Wi-Fi sender with one transmit antenna sends packets periodically to the channel with the smallest Wi-Fi channel bandwidth.

Fine-grained occupant activity monitoring with Wi-Fi channel state information: Practical implementation of multiple receiver settings

This study proposes a new deep learning method for reconstructing depth images of moving objects within a specific area using Wi-Fi channel state information (CSI). The Wi-Fibased depth imaging technique has novel applications in domains such as security and elder care. However, reconstructing depth images from CSI is challenging because it is difficult to learn the mapping function between CSI and depth images, both of high-dimensionalities. To address the challenge, we propose Wi-Depth. The main idea behind the design of Wi-Depth is that a depth image of a moving object can be decomposed into three core components: the shape, depth, and position of the target. Therefore, in the depth-image reconstruction task, Wi-Depth simultaneously estimates the three core pieces of information as auxiliary tasks in our proposed VAE-based teacher-student architecture, enabling it to output images with the consistency of a correct shape, depth, and position. In addition, the design of Wi-Depth is based on our idea that this decomposition efficiently takes advantage of the fact that shape, depth, and position relate to primitive information inferred from CSI such as angle-of-arrival, time-of-flight, and Doppler frequency shift.

Recent advances in Internet of Things (IoT) technologies require a new type of IoT security environment. Various heterogeneous smart devices have easy access to IoT environment, and as the number of users increases, they are exposed to various threats such as malicious attacks on IoT devices and IoT infrastructure, and data tampering by malicious code. Malware detection in IoT requires data and models for continuous and changing learning of smart devices. Methods/Statistical analysis: To minimize these security threats, various malware detection techniques in the field of IoT security have been studied. Malware detection in IoT environment is important for data derivation and learning model required for continuous and changing learning of smart devices. The metadata of malware detection can be normalized by the value of device id, time, behavior, location and state. This paper proposes behavior-based malware detection using deep learning (BMD-DL). Findings: BMD-DL was able to collect metadata about behavior-based malicious behavior and learn and detect malicious codes through deep learning. In addition, through the learned model, IoT Security is provided by disconnecting malicious devices that cause malicious behavior in the IoT environment. Improvements/Applications: BMD-DL collects behavioral data generated from multiple devices in the IoT and applies the results learned through deep learning to detect persistent malware.

The proliferation of Internet of Things (IoT) devices continues to expand the network attack surface while introducing stringent privacy requirements that challenge effective intrusion detection. Federated learning enables collaborative model training without centralizing raw network telemetry. However, existing federated intrusion detection approaches often degrade under statistical heterogeneity and remain vulnerable to zero-day attacks when they rely on labeled data or reconstruction-based objectives. This work proposes Fed-DTCN (Federated Dual Temporal Contrastive Network), an unsupervised federated framework for zero-day anomaly detection in IoT environments. Fed-DTCN learns robust representations of benign IoT traffic using contrastive learning with semantic-preserving augmentations. A dual-encoder architecture disentangles globally shared features from client-specific patterns, improving generalization under heterogeneous federated deployments. Personalization and privacy are preserved by selectively aggregating only the shared encoder parameters. The framework employs a compact temporal convolutional backbone together with a soft-weighted contrastive objective to constrain benign representations, thereby enabling reliable detection of out-of-distribution threats. Extensive experiments on the TON_IoT and CSE-CIC-IDS2018 benchmarks show that Fed-DTCN matches or surpasses a state-of-the-art supervised baseline on standard attacks, achieving an F1-score of 99.99% on TON_IoT. In a zero-day evaluation where the Botnet class is withheld during training, Fed-DTCN attains an F1-score of 96%, compared to 0.52% for the supervised baseline. Ablation studies validate the effectiveness of the proposed augmentations, while evaluations under heterogeneous client partitions demonstrate reduced inter-client variance and consistent per-client improvements, indicating suitability for realistic IoT deployments.

In this paper, a novel indoor localization system with channel state information (CSI) fingerprints is proposed, which learns the spatial and frequency features of CSI in the fifth-generation (5G) cellular network by a Siamese convolution neural network. In particular, considering that the CSI continuously collected by a moving target possesses the implicit spatial association, we locate the target by the successive CSI data gathered within a time interval which can be regarded as an information subspace of the fingerprint database. Therefore, the fingerprint localization can be modeled as a subspace matching problem and solved by the Siamese network-based similarity learning. In the proposed system, we design a structure of CSI fingerprint which includes the information from multiple base stations in spatial and frequency domains. Then, the proposed Siamese architecture extracts the CSI feature and estimates the location of the target by feature similarity comparison. Compared with the existing algorithms, it can increase the positioning accuracy significantly by the feature relevance among the CSI data collected at different positions. The field tests indicate that compared to other CSI fingerprint-based positioning methods, our proposed algorithm can effectively reduce the localization error.

This paper presents a new approach for recognizing human activities that involve two humans, referred to as human-human interactions, using Wi-Fi signals. The proposed approach utilizes the Channel State Information (CSI) metric of the Wi-Fi signals to characterize the performed interactions in indoor environment. Specifically, the proposed approach analyzes the CSI data and extracts a set of time-domain and frequency-domain features that comprise salient information to distinguish between the performed interactions. The extracted features are used to construct a multi-class support vector machine classifier that can recognize the classes of the interactions comprised within the CSI data. The performance of the proposed approach was evaluated using our publicly available human-human interaction CSI dataset that contains the CSI data recorded for 40 pairs of participants while performing 13 interactions. The experimental results indicate that our proposed approach achieved an average recognition accuracy of 69.78% computed overall the 13 interactions. The reported results for each pair of participants demonstrate the feasibility of our proposed approach to recognize human-human interactions using the CSI metric of the Wi-Fi signals.

The Internet of Things (IoT) is a new technology paradigm that refers to distributed physical devices that are connected to the Internet. The large amount of data generated by these devices is considered to be a challenging issue. This data suffers from anomalies or abnormal behaviour for a number of reasons, such as sensor faults or attack issues. However, the data collected from IoT devices is usually unlabelled, which means that the normal or anomaly classes are unknown. This study proposes TCMD, a two-tier classification model for anomaly detection in IoT. In addition, it describes the validation methods used for the model to evaluate the quality of the clustering and the performance of the classification. TCMD firstly employs hierarchical affinity propagation (HAP) clustering to group the data into normal and anomaly clusters. Secondly, the labelled data obtained from the clustering is used to train decision trees (DTs). The results show that the TCMD is able to label the data which can be helpful to reduce human intervention. In addition, in terms of false positive rate (FPR), TCMD performs well compared with the DTs on the original dataset and outperforms the state-of-the-art model.

We develop a novel deep learning technique for human fall detection using WiFi Channel State Information (CSI) of a WiFi transmitter and receiver. Different motions in the environment generate distinct features in CSI, which can be fed to a supervised learning machine learning algorithm for training. However, the CSI varies from one environment to another, requiring the collection of environment-specific training data. To overcome this challenge, we propose 1-d convolutional neural network using domain adaptation technique. By adapting to un-labeled data from a new environment, we significantly improve precision and recall, making activity recognition accurate in new environments.