Device‐Free Human Activity Recognition Based on Dual‐Channel Transformer Using WiFi Signals

Deep learning techniques for human activity recognition are gaining popularity due to their effectiveness in identifying intricate tasks and their cost-effectiveness compared to conventional machine learning methods. Human Activity Recognition (HAR) is a research domain concerned with detecting the everyday activities performed by individuals using time-series data captured by sensors. HAR encompasses a wide range of applications, including surveillance, baby monitoring, elderly healthcare, and smart driving. This article provides a brief introduction to the application of deep learning in HAR. It covers the fundamental concepts of CNNs and LSTMs, their strengths in capturing spatial and temporal features, and their integration for enhanced activity recognition. Different approaches are employed in HAR to address problems with efficiency and precision. Conventional human activity recognition (HAR) systems rely on wearable devices like IMUs and stretch sensors to identify different activities. These systems have proven to be effective in recognizing simple user actions like sitting, standing, and walking. However, when it comes to more intricate activities like running, jumping, wrestling, and swinging, sensor-based HAR systems encounter greater misclassification rates due to inaccuracies in sensor readings. These errors significantly impact the accuracy of the HAR system, resulting in suboptimal classification outcomes. In contrast, employing vision-based HAR systems enables improved accuracy in identifying complex activities, leading to enhanced overall performance.

Modern monostatic radar-based human activity recognition (HAR) systems perform very well as long as the direction of human activities is either towards or away from the radar. The monostatic single-input single-output (SISO) and monostatic multiple-input multiple-output (MIMO) radar systems cannot detect motion of an object that moves perpendicularly to the radar’s boresight axis. Due to this physical layer limitation, today’s radar-based HAR systems fail to classify multi-directional human activities. In this paper, we resolve this typical but critical physical layer problem of contemporary HAR systems. We propose a HAR system underlying a distributed MIMO radar configuration, where multiple antennas of a millimeter wave MIMO radar system (Ancortek SDR-KIT 2400T2R4) are distributed in an indoor environment. In our proposed HAR system, we have two independent and identical monostatic radar subsystems that irradiate and capture the multi-directional human movement from two perspectives, which allows to compute two distinct time-variant radial velocity distributions. A feature extraction network extracts numerous features from the measured time-variant radial velocity distributions, which are then fused by a multiclass classifier to detect five types of human activities. The proposed multi-perspective MIMO-radar-based HAR system achieves a classification accuracy of 98.52%, which surpasses the accuracy of SISO radar-based HAR system by more than 9%. Our approach resolves the physical layer limitations of modern HAR systems that are based on either monostatic SISO or monostatic MIMO radar systems.

Human Activity Recognition (HAR) systems are designed to read sensor data and analyse it to classify any detected movement and respond accordingly. However, there is a need for more responsive and near real-time systems to distinguish between false and true alarms. To accurately determine alarm triggers, the motion pattern of legitimate users need to be stored over a certain period and used to train the system to recognise features associated with their movements. This training process is followed by a testing cycle that uses actual data of different patterns of activity that are either similar or different to the training data set. This paper evaluates the use of a combined Convolutional Neural Network (CNN) and Naive Bayes for accuracy and robustness to correctly identify true alarm triggers in the form of a buzzer sound for example. It shows that pattern recognition can be achieved using either of the two approaches, even when a partial motion pattern is derived as a subset out of a full-motion path.

The conventional Human Activity Recognition (HAR) systems use smartwatches, smartphones, and other wearable devices to autonomously derive consumer physical activities. However, implementing real-time HAR in resource-constrained applications is challenging. Computational offloading approaches must address network reliance, latency, and data privacy, which affect system performance. The present study proposes a low-cost, wearable HAR device that collects and transmits the Inertial Measurement Unit (IMU) telemetry signals to smartphones, enabling real-time on-device activity detection. Human actions are subjective and affected by physiological, environmental, and behavioural factors, complicating HAR systems' performance in personalized contexts. Generalized methods for existing systems reduce performance for new consumers or due to alterations in consumer locomotive signatures. Thus, our second goal is to enable the on-device personalization of wearable HAR models with minimum customer calibration. The HAR device, which is in the form of a smart-band, transfers data to and fro smartphones through Bluetooth Low Energy (BLE). A lightweight 1D convolutional neural network (CNN) is built and, using transfer learning, the network model is fine-tuned from real-time sensed data. On-device HAR inferences ensure real-time processing on smartphones without computational offloading. Smartphone-based on-device training for fine-tuning the model allows the HAR system to get customized without compromising privacy or computational costs. The experimental results show that the personalized classification achieves on average 98% accuracy when assessed using four benchmark datasets.

Since human bodies are good reflectors of wireless signals, human activities can be recognized by monitoring changes in WiFi signals. However, existing WiFi-based human activity recognition systems do not build models that can quantify the correlation between WiFi signal dynamics and human activities. In this paper, we propose a Channel State Information (CSI)-based human Activity Recognition and Monitoring system (CARM). CARM is based on two theoretical models. First, we propose a CSI-speed model that quantifies the relation between CSI dynamics and human movement speeds. Second, we propose a CSI-activity model that quantifies the relation between human movement speeds and human activities. Based on these two models, we implemented the CARM on commercial WiFi devices. Our experimental results show that the CARM achieves recognition accuracy of 96% and is robust to environmental changes.

In this work, we propose a Human Activity Prediction (HAP) system using activity sequence spanning trees constructed from a life-log created by a video sensor-based daily Human Activity Recognition (HAR) system using time-sequential Independent Component (IC)-based depth silhouette features with Hidden Markov Models (HMMs). In the daily HAR system, the IC features are extracted from the collection of the depth silhouettes containing various daily human activities such as walking, sitting, lying, cooking, eating etc. Using these features, HMMs are used to model the time sequential features and recognize various human activities. The depth silhouette-based human activity recognition system is used to recognize daily human activities automatically in real time, which creates a life-log of daily activity events. In this work, we propose a method for human activity prediction using fixed-length activity sequence spanning trees based on the life-log. Utilizing the consecutive activities recorded in an activity sequence database (i.e. life-log) for a specific period of time of each day over a period such as a month, the fixed-length spanning trees can be constructed for the sequences starting with each activity where the leaf nodes contain the frequency of the fixed-length consecutive activity sequences. Once the trees are constructed, to predict an activity after a sequence of activities, we traverse the spanning trees until a path up to the previous node of the leaf nodes is matched with the testing pattern. Finally, we can predict the next activity based on the highest frequency of the leaf nodes along the matched path. The prediction experiments over the computer simulated data which is based on the daily logs show satisfactory results. Our video sensor-based human activity recognition and prediction systems can be utilized for practical applications such as smart and proactive healthcare.

PurposeTo find a successful human action recognition system (HAR) for the unmanned environments.Design/methodology/approachThis paper describes the key technology of an efficient HAR system. In this paper, the advancements for three key steps of the HAR system are presented to improve the accuracy of the existing HAR systems. The key steps are feature extraction, feature descriptor and action classification, which are implemented and analyzed. The usage of the implemented HAR system in the self-driving car is summarized. Finally, the results of the HAR system and other existing action recognition systems are compared.FindingsThis paper exhibits the proposed modification and improvements in the HAR system, namely the skeleton-based spatiotemporal interest points (STIP) feature and the improved discriminative sparse descriptor for the identified feature and the linear action classification.Research limitations/implicationsThe experiments are carried out on captured benchmark data sets and need to be analyzed in a real-time environment.Practical implicationsThe middleware support between the proposed HAR system and the self-driven car system provides several other challenging opportunities in research.Social implicationsThe authors’ work provides the way to go a step ahead in machine vision especially in self-driving cars.Originality/valueThe method for extracting the new feature and constructing an improved discriminative sparse feature descriptor has been introduced.

Human activity recognition is becoming the vital underpinning for a myriad of emerging applications in the field of human-computer interaction, mobile computing, and smart grid. Besides the utilization of up-to-date sensing techniques, modern activity recognition systems also require a machine learning (ML) algorithm that leverages the sensory data for identification purposes. In view of the unique characteristics of the measurement data and the ML challenges thereof, we propose a non-intrusive human activity recognition system that only uses existing commodity WiFi routers. The core of our system is a novel multiple kernel representation learning (MKRL) framework that automatically extracts and combines informative patterns from the Channel State Information (CSI) measurements. The MKRL firstly learns a kernel string representation from time, frequency, wavelet, and shape domains with an efficient greedy algorithm. Then it performs information fusion from diverse perspectives based on multi-view kernel learning. Moreover, different stages of MKRL can be seamlessly integrated into a multiple kernel learning framework to build up a robust and comprehensive activity classifier. Extensive experiments are conducted in typical indoor environments and the experimental results demonstrate that the proposed system outperforms existing methods and achieves a 98\% activity recognition accuracy.

In recent years, Channel State Information (CSI)-based Human activity recognition (HAR) has received extensive attention for its low cost and privacy protection property. Existing CSI-based HAR systems utilize single classifier to accomplish recognition, which results in poor robustness and relatively low recognition accuracy. In this paper, a random subspace classifier ensemble method is proposed for classification, which utilizes the frequency domain feature instead of the time domain feature and each kind of feature is selected in the same amount. We evaluate its performance both in typical indoor and outdoor environment. Our results show, the recognition accuracy can reach 91.2% and 90.2% in outdoor and indoor environment, respectively.

Human motion detection and activity recognition are becoming vital for the applications in smart homes. Traditional Human Activity Recognition (HAR) mechanisms use special devices to track human motions, such as cameras (vision-based) and various types of sensors (sensor-based). These mechanisms are applied in different applications, such as home security, Human–Computer Interaction (HCI), gaming, and healthcare. However, traditional HAR methods require heavy installation, and can only work under strict conditions. Recently, wireless signals have been utilized to track human motion and HAR in indoor environments. The motion of an object in the test environment causes fluctuations and changes in the Wi-Fi signal reflections at the receiver, which result in variations in received signals. These fluctuations can be used to track object (i.e., a human) motion in indoor environments. This phenomenon can be improved and leveraged in the future to improve the internet of things (IoT) and smart home devices. The main Wi-Fi sensing methods can be broadly categorized as Received Signal Strength Indicator (RSSI), Wi-Fi radar (by using Software Defined Radio (SDR)) and Channel State Information (CSI). CSI and RSSI can be considered as device-free mechanisms because they do not require cumbersome installation, whereas the Wi-Fi radar mechanism requires special devices (i.e., Universal Software Radio Peripheral (USRP)). Recent studies demonstrate that CSI outperforms RSSI in sensing accuracy due to its stability and rich information. This paper presents a comprehensive survey of recent advances in the CSI-based sensing mechanism and illustrates the drawbacks, discusses challenges, and presents some suggestions for the future of device-free sensing technology.

Recognition of hand activities of daily living (hand-ADL) is useful in the areas of human–computer interactions, lifelogging, and healthcare applications. However, developing a reliable human activity recognition (HAR) system for hand-ADL with only a single wearable sensor is still a challenge due to hand movements that are typically transient and sporadic. Approaches based on deep learning methodologies to reduce noise and extract relevant features directly from raw data are becoming more promising for implementing such HAR systems. In this work, we present an ARMA-based deep autoencoder and a deep recurrent network (RNN) using Gated Recurrent Unit (GRU) for recognition of hand-ADL using signals from a single IMU wearable sensor. The integrated ARMA-based autoencoder denoises raw time-series signals of hand activities, such that better representation of human hand activities can be made. Then, our deep RNN-GRU recognizes seven hand-ADL based upon the output of the autoencoder: namely, Open Door, Close Door, Open Refrigerator, Close Refrigerator, Open Drawer, Close Drawer, and Drink from Cup. The proposed methodology using RNN-GRU with autoencoder achieves a mean accuracy of 84.94% and F1-score of 83.05% outperforming conventional classifiers such as RNN-LSTM, BRNN-LSTM, CNN, and Hybrid-RNNs by 4–10% higher in both accuracy and F1-score. The experimental results also showed the use of the autoencoder improves both the accuracy and F1-score of each conventional classifier by 12.8% in RNN-LSTM, 4.37% in BRNN-LSTM, 15.45% CNN, 14.6% Hybrid RNN, and 12.4% for the proposed RNN-GRU.

When developing a fully automatic system for evaluating motor activities performed by a person, it is necessary to segment and recognize the different activities in order to focus the analysis. This process must be carried out by a Human Activity Recognition (HAR) system. This paper proposes a user adaptation technique for improving a HAR system based on Hidden Markov Models (HMMs). This system segments and recognizes six different physical activities (walking, walking upstairs, walking downstairs, sitting, standing and lying down) using inertial signals from a smartphone. The system is composed of a feature extractor for obtaining the most relevant characteristics from the inertial signals, a module for training the six HMMs (one per activity), and the last module for segmenting new activity sequences using these models. The user adaptation technique consists of a Maximum A Posteriori (MAP) approach that adapts the activity HMMs to the user, using some activity examples from this specific user. The main results on a public dataset have reported a significant relative error rate reduction of more than 30%. In conclusion, adapting a HAR system to the user who is performing the physical activities provides significant improvement in the system’s performance.

Human activity recognition (HAR) is an important technology for a wide range of applications including elderly people monitoring, ambient assisted living, sport and fitness activities. The aim of this paper is to address the HAR task directly on a wearable device, implementing a recurrent neural network (RNN) on a low cost, low power microcontroller, ensuring the required performance in terms of accuracy and low complexity. To reach this goal we first develop a lightweight RNN on the Human Activity Recognition Using Smartphones dataset in order to accurately detect human activity and then we port the RNN to the embedded device Cloud-JAM L4, based on an STM32 microcontroller. Experimental results show that this HAR RNN-based detector can be effectively implemented on the chosen constrained-resource system, achieving an accuracy of about 90.50% with a very low memory cost (40.883 KB) and inference time (67.131 ms), allowing the design of a wearable embedded system for human activity recognition.

Human Activity Recognition (HAR) is the automatic detection and understanding of human motion behavior based on data extracted from video camera, ambient sensors or wearable sensors which particularly has recently attracted increased attention from both researchers and industry. However, for running practical HAR systems on wearable devices, there are some requirements such as design and development of small, lightweight, powerful, and low-cost smart sensors. In this context, data must be continuously collected, and edge computing is a viable solution, which is an energy-efficient technique, offering real-time response and privacy requirements for HAR applications. Rather than sending data to the cloud, edge computing is a local process that minimizes the data transmission time and responds with low latency. Recently, HAR system designers have adopted deep learning techniques inspired by their outstanding performance in many application areas and achieved relevant gain in activity recognition performance, however, these techniques were not demonstrated suitable for running on resource constrained devices. Thus, designing energy-efficient deep learning models is critical for realizing efficient HAR for mobile applications. In this work, we present a lightweight framework for the deployment of low-power but accurate HAR systems for these devices. We also implement and run the system in a microcontroller and analyze computational cost and energy consumption, and how different system configurations and deep learning model complexity influence on that.

There are several large datasets available that are captured from motion tracking systems which could be useful to train wearable human activity recognition (HAR) systems, if only their spatial data could be mapped into the equivalent inertial measurement unit (IMU) data that would be sensed on the body. In this paper, we describe a mapping from 3D Vicon motion tracking data to data collected from a BlueSense on-body IMU. We characterise the error incurred in order to discern the extent to which it is possible to generate useful training data for a wearable activity recognition system from data collected with a motion capture system. We analyse this by mapping Vicon motion tracking data to rotational velocity and linear acceleration at the head, and compare this to actual gyroscope and accelerometer data collected by an IMU mounted on the head. In a 15 min dataset comprising three static activities—sitting, standing and lying down—we find that 95% of the reconstructed gyroscope data is within an error of [−7.25;+7.46] \(deg \cdot s^{-1}\), while 95% of the reconstructed accelerometer data was contained within [−96.1;+72.9] \(m \cdot G\). However, when we introduce more movement by including data collected while walking this increases to [−19.0;+18.2] \(deg \cdot s^{-1}\) for the gyroscope and [−208;+186] \(m \cdot G\) for the accelerometer. We conclude that generating accurate IMU data from motion capture datasets is possible and could be useful in providing larger volumes of data for activity recognition tasks and in helping enable advanced, data-hungry techniques such as deep learning to be employed on a larger scale within the domain of human activity recognition.