Search

The quest for efficient and non-intrusive human activity recognition (HAR) in indoor environments has led to the burgeoning field of WiFi-based HAR. This method promises applications from healthcare monitoring to elderly care due to its cost-effectiveness and ease of deployment compared to traditional sensor-based systems. However, WiFi-based HAR faces significant challenges in maintaining performance across diverse environments and subjects, largely due to WiFi signal variability. Addressing this issue necessitates training models on extensive datasets. Recent studies have utilized conventional models, including Convolutional Neural Networks (CNNs), and sequence-to-sequence (Seq2Seq) models such as LSTM, GRU, or Transformer. Despite their precision, these models are computationally intensive and require more training data. To tackle these limitations, we propose a novel approach that leverages a Temporal Convolutional Network with Augmentations and Attention, referred to as TCN-AA. This model enhances computational efficiency and accuracy in the face of dataset variability by combining temporal convolutional layers with data augmentation strategies and an attention mechanism to focus on critical features. Our method is computationally efficient and significantly improves accuracy, even with a threefold increase in data size through augmentation techniques. Experiments on a public dataset indicate our approach outperforms state-of-the-art methods, achieving 99.42% accuracy. This work represents a significant step forward in the practical application of WiFi-based HAR, paving the way for broader adoption in critical areas like healthcare and security.

The aim of this study is to examine the long-term effects of prenatal and early-life WIFI signal exposure on neurodevelopment and behaviors as well as biochemical alterations of Wistar rats. On the first day of pregnancy (E0), expectant rats were allocated into two groups: the control group (n = 12) and the WiFi-exposed group (WiFi group, n = 12). WiFi group was exposed to turn on WiFi for 24 h/day from E0 to postnatal day (PND) 42. The control group was exposed to turn-off WiFi at the same time. On PND7-42, we evaluated the development and behavior of the offspring, including body weight, pain threshold, and swimming ability, spatial learning, and memory among others. Also, levels of proteins involved in apoptosis were analyzed histologically in the hippocampus in response to oxidative stress. The results showed that WiFi signal exposure in utero and early life (1) increased the body weight of WiFi + M (WiFi + male) group; (2) no change in neuro-behavioral development was observed in WiFi group; (3) increased learning and memory function in WiFi + M group; (4) enhanced comparative levels of BDNF and p-CREB proteins in the hippocampus of WiFi + M group; (5) no neuronal loss or degeneration was detected, and neuronal numbers in hippocampal CA1 were no evidently differences in each group; (6) no change in the apoptosis-related proteins (caspase-3 and Bax) levels; and (7) no difference in GSH-PX and SOD activities in the hippocampus. Prenatal WiFi exposure has no effects on hippocampal CA1 neurons, oxidative equilibrium in brain, and neurodevelopment of rats. Some effects of prenatal WiFi exposure are sex dependent. Prenatal WiFi exposure increased the body weight, improved the spatial memory and learning function, and induced behavioral hyperactivity of male rats. [ABSTRACT FROM AUTHOR]

High-precision indoor localization is growing extremely quickly, especially for multi-floor scenarios. The data on existing indoor positioning schemes, mainly, come from wireless, visual, or lidar means, which are limited to a single sensor. With the massive deployment of WiFi access points and low-cost cameras, it is possible to combine the above three methods to achieve more accurate, complete, and reliable location results. However, the existing SLAM rapidly advances, so hybrid visual and wireless approaches take advantage of this, in a straightforward manner, without exploring their interactions. In this paper, a high-precision multi-floor indoor positioning method, based on vision, wireless signal characteristics, and lidar is proposed. In the joint scheme, we, first, use the positioning data output in lidar SLAM as the theoretical reference position for visual images; then, use a WiFi signal to estimate the rough area, with likelihood probability; and, finally, use the visual image to fine-tune the floor-estimation and location results. Based on the numerical results, we show that the proposed joint localization scheme can achieve 0.62 m of 3D localization accuracy, on average, and a 1.24-m MSE for two-dimensional tracking trajectories, with an estimation accuracy for the floor equal to 89.22%. Meanwhile, the localization process takes less than 0.25 s, which is of great importance for practical implementation. [ABSTRACT FROM AUTHOR]

Indoor localization algorithms in smart cities often use Wi‐Fi fingerprints as a database of Received Signal Strength (RSS) and its corresponding position coordinate for position estimation. However, the issue of fingerprinting is the use of different platform‐devices. To this end, we propose a Long Short‐Term Memory (LSTM)‐based novel indoor positioning mechanism in smart city environment. We used LSTM, a type of recurrent neural network to process sequential data of users trajectory in indoor buildings. The proposed approach first utilizes a database of normalizing fingerprint landmarks to calculate WiFi Access Points (WAPs) RSS values to mitigate the fluctuation issue and then apply the normalization parameters on the RSS values during the online phase. Afterwards, we constructed a transfer model to adapt the RSS values during the offline phase and then applying it on the RSS values from the different smartphones during the online phase. Thorough simulation results confirm that the proposed approach can obtain 1.5 to 2 meters positioning accuracy for indoor environments, which is 60% higher than traditional approaches. [ABSTRACT FROM AUTHOR]

High-precision indoor localization is growing extremely quickly, especially for multi-floor scenarios. The data on existing indoor positioning schemes, mainly, come from wireless, visual, or lidar means, which are limited to a single sensor. With the massive deployment of WiFi access points and low-cost cameras, it is possible to combine the above three methods to achieve more accurate, complete, and reliable location results. However, the existing SLAM rapidly advances, so hybrid visual and wireless approaches take advantage of this, in a straightforward manner, without exploring their interactions. In this paper, a high-precision multi-floor indoor positioning method, based on vision, wireless signal characteristics, and lidar is proposed. In the joint scheme, we, first, use the positioning data output in lidar SLAM as the theoretical reference position for visual images; then, use a WiFi signal to estimate the rough area, with likelihood probability; and, finally, use the visual image to fine-tune the floor-estimation and location results. Based on the numerical results, we show that the proposed joint localization scheme can achieve 0.62 m of 3D localization accuracy, on average, and a 1.24-m MSE for two-dimensional tracking trajectories, with an estimation accuracy for the floor equal to 89.22%. Meanwhile, the localization process takes less than 0.25 s, which is of great importance for practical implementation.

Copyright of Journal of Fuzhou University is the property of Journal of Fuzhou University, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Continuous activity recognition (CAR) plays an important role in human daily indoor activity monitoring and can be widely used in smart home, human-computer interaction and user authentication. Due to the privacy issue and limited coverage of video signals, RF-based CAR has attracted more and more attention in recent years. This paper focuses on three key problems in RF-based CAR: denoising, segmentation and recognition. We present the design and implementation of a contactless and sensorless continuous activity recognition system, namely WiCheck. Our basic idea is to utilize the temporal correlation between two adjacent actions in continuous activity to eliminate the cumulative error in continuous activity segmentation. Firstly, the multi-layer optimized noise elimination method is used to decrease the environment interference. Secondly, a method based on dual-swing window is proposed to reduce the cumulative error of continuous activity segmentation. Finally, WiCheck is implemented in different indoor environments, and 6 continuous activity sequences are designed to evaluate and analyze the influencing factors. The continuous activity recognition accuracy of WiCheck to two actions and three actions can approach 90% and 75%, respectively. [ABSTRACT FROM AUTHOR]

With the sustainable development of mobile communication technology and the increasing demand for indoor services, Location-based Service (LBS) is attracting more and more attention. Determining the mobile target's location is a core problem of LBS. The traditional WiFi signal fingerprint-based positioning technology mainly determines the location information of the mobile target by received RSS, which has high real-time positioning but low positioning accuracy. The fingerprint-based positioning technology using image mainly determines the location information of the mobile target by matching the features of the foreground images, which has the high positioning accuracy but low real-time positioning. This paper presents an indoor positioning method fusing information of the WiFi signal and RGB image to improve the positioning performance. The WiFi signal is transformed into the W-image according to indoor space and correction radius parameters, then the W-image and RGB image information are fused with LBP feature by the uniform-LBP algorithm. A fusion positioning model based on the sparse representation is established and solved using Lasso and BPDN positioning method. The positioning methods are tested in manufacturing workshop, and the experimental results show that the proposed method can reduce the complexity of the positioning method and achieve the higher positioning accuracy under same conditions. [ABSTRACT FROM AUTHOR]

As a fundamental research step for subsurface target imaging by passive ground penetrating radar, some simulation and experimental results of passive bistatic radar imaging for short-range targets by using IEEE 802.11 Wireless Fidelity (WiFi) wave as the source of illumination have been presented. As the WiFi signal only penetrates shallow layers and yet lacks bandwidth for high resolution subsurface structure mapping, the interrogation of cooperative targets with the passive bistatic radar approach is demonstrated. This strategy is achieved by inserting surface acoustic wave (SAW) delay lines acting as dedicated reflectors allowing for subsurface tagging (identification) or sensing (temperature measurement) through the fine measurement of echo delays. Experimental results show that short-range targets, such as cars and metallic plates located within 10 m, can effectively be detected and imaged. The response of the SAW delay lines can also be well probed.

As a fundamental research step for subsurface target imaging by passive ground penetrating radar, some simulation and experimental results of passive bistatic radar imaging for short-range targets by using IEEE 802.11 Wireless Fidelity (WiFi) wave as the source of illumination have been presented. As the WiFi signal only penetrates shallow layers and yet lacks bandwidth for high resolution subsurface structure mapping, the interrogation of cooperative targets with the passive bistatic radar approach is demonstrated. This strategy is achieved by inserting surface acoustic wave (SAW) delay lines acting as dedicated reflectors allowing for subsurface tagging (identification) or sensing (temperature measurement) through the fine measurement of echo delays. Experimental results show that short-range targets, such as cars and metallic plates located within 10 m, can effectively be detected and imaged. The response of the SAW delay lines can also be well probed. [ABSTRACT FROM AUTHOR]

Radiofrequency fields are usually measured in order to be compared with electromagnetic exposure limits defined by international standardization organizations with the aim of preserving the human health. However, in the case of WiFi technology, accurate measurement of the radiation coming from user terminals and access points is a great challenge due to the nature of these emissions, which are noncontinuous signals transmitted in the form of pulses of short duration. Most of the methodologies defined up to now for determining WiFi exposure levels use or take as reference exposimeters, broadband probes, and spectrum analyzers without taking into account that WiFi signals are not continuously transmitted. This leads to an overestimation of the radiation level that cannot be considered negligible when data of the actual exposure are needed. To avoid this, other procedures apply empirical weighting factors that account for the actual duration of burst transmissions. However, this implies the implementation of additional measurements for calculating the weighting factors, and thus, increases the complexity of the work. According to this, it was still necessary to define the frequency domain measurement setup that is optimal for obtaining realistic WiFi signal values, without requiring the performance of additional recordings. Thus, the definition of an appropriate methodology to achieve this goal was established as the main objective of this paper. The set of tasks carried out to identify such a configuration, as well as the limitations obtained for other measurement settings, are deeply explained in this paper. [ABSTRACT FROM AUTHOR]

Detection of human presence and activity event classification are of importance to a variety of context‐awareness applications such as e‐Healthcare, security, and low impact building. However, existing radio frequency identification tags, wearables, and passive infrared approaches require the user to carry dedicated electronic devices that suffer from problems of low detection accuracy and false alarms. This study proposes a novel system for non‐invasive human sensing by analysing the Doppler information contained in the human reflections of WiFi signal. Doppler information is insensitive to stationary objects, thus there is no need for any scenario‐specific calibration which makes it ideal for human sensing. We also introduce the time‐frequency domain feature vectors of WiFi Doppler information for the support vector machine classifier towards activity event recognition. The proposed methodology is evaluated on a software defined radio system together with the experiment of five different events. The results indicate that the proposed system is sufficient for indoor context awareness, with 95.3% overall accuracy for event classification and 93.3% accuracy for human presence detection, which outperforms the traditional received signal strength approach where accuracy is 69.3% for event classification and 83.3% for human presence detection. [ABSTRACT FROM AUTHOR]

In this paper, estimation of mobility using received signal strength (RSS) is presented. In contrast to standard methods, speed can be estimated without the use of any additional hardware like accelerometer, gyroscope or position estimator. The pattern of mobility can be inferred using any hand-held device such as mobile phone, tablet or smart watch and source of RSS. The strength of Wireless Fidelity (WiFi) signal is considered herein to compute the time-domain features such as mean, minimum, maximum, and autocorrelation of signal strength. The experiments are carried out in different environments like academic area, residential area and in open space. The experimental results indicate that the average accuracy in the estimated speed is 88% using the maximum RSS model with limited data set. The accuracy can be further increased by carrying out the training with a larger dataset. The proposed method is cost-effective and having linear complexity with reasonable accuracy. Additionally, the proposed method is scalable that is the performance is not affected in a multi-smartphones scenario in a WiFi or cellular environment. [ABSTRACT FROM AUTHOR]

Today, due to technology development and aversive events of daily life, Human exposure to both radiofrequency and stress is unavoidable. This study investigated the co-exposure to repeated restraint stress and WiFi signal on cognitive function and oxidative stress in brain of male rats. Animals were divided into four groups: Control, WiFi-exposed, restrained and both WiFi-exposed and restrained groups. Each of WiFi exposure and restraint stress occurred 2 h (h)/day during 20 days. Subsequently, various tests were carried out for each group, such as anxiety in elevated plus maze, spatial learning abilities in the water maze, cerebral oxidative stress response and cholinesterase activity in brain and serum. Results showed that WiFi exposure and restraint stress, alone and especially if combined, induced an anxiety-like behavior without impairing spatial learning and memory abilities in rats. At cerebral level, we found an oxidative stress response triggered by WiFi and restraint, per se and especially when combined as well as WiFi-induced increase in acetylcholinesterase activity. Our results reveal that there is an impact of WiFi signal and restraint stress on the brain and cognitive processes especially in elevated plus maze task. In contrast, there are no synergistic effects between WiFi signal and restraint stress on the brain. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach that applies WiFi-based IQ data and time–frequency images to classify human activities automatically and accurately. The proposed strategy first uses the Choi–Williams distribution transform and the Margenau–Hill spectrogram transform to obtain the time–frequency images, followed by the offset and principal component analysis (PCA) feature extraction. The offset features were extracted from the IQ data and several spectra with maximum energy values in the time domain, and the PCA features were extracted via the whole images and several image slices on them with rich unit information. Finally, a traditional supervised learning classifier was used to label various activities. With twelve-thousand experimental samples from four categories of WiFi signals, the experimental data validated our proposed method. The results showed that our method was more robust to varying image slices or PCA numbers over the measured dataset. Our method with the random forest (RF) classifier surpassed the method with alternative classifiers on classification performance and finally obtained a 91.78% average sensitivity, 91.74% average precision, 91.73% average F1-score, 97.26% average specificity, and 95.89% average accuracy. [ABSTRACT FROM AUTHOR]