Improving Human Activity Monitoring by Imputation of Missing Sensory Data: Experimental Study

A Portable Smart Fitness Suite for Real-Time Exercise Monitoring and Posture Correction

Fitness and sport have drawn significant attention in wearable and persuasive computing. Physical activities are worthwhile for health, well-being, improved fitness levels, lower mental pressure and tension levels. Nonetheless, during high-power and commanding workouts, there is a high likelihood that physical fitness is seriously influenced. Jarring motions and improper posture during workouts can lead to temporary or permanent disability. With the advent of technological advances, activity acknowledgment dependent on wearable sensors has pulled in countless studies. Still, a fully portable smart fitness suite is not industrialized, which is the central need of today's time, especially in the Covid-19 pandemic. Considering the effectiveness of this issue, we proposed a fully portable smart fitness suite for the household to carry on their routine exercises without any physical gym trainer and gym environment. The proposed system considers two exercises, i.e., T-bar and bicep curl with the assistance of the virtual real-time android application, acting as a gym trainer overall. The proposed fitness suite is embedded with a gyroscope and EMG sensory modules for performing the above two exercises. It provided alerts on unhealthy, wrong posture movements over an android app and is guided to the best possible posture based on sensor values. The KNN classification model is used for prediction and guidance for the user while performing a particular exercise with the help of an android application-based virtual gym trainer through a text-to-speech module. The proposed system attained 89% accuracy, which is quite effective with portability and a virtually assisted gym trainer feature.

Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data

Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).

Comparison of machine learning techniques for the identification of human activities from inertial sensors available in a mobile device after the application of data imputation techniques

Human activity recognition (HAR) is a significant research area due to its wide range of applications in intelligent health systems, security, and entertainment games. Over the past few years, many studies have recognized human daily living activities using different machine learning approaches. However, the performance of a machine learning algorithm varies based on the sensing device type, the number of sensors in that device, and the position of the underlying sensing device. Moreover, the incomplete activities (i.e., data captures) in a dataset also play a crucial role in the performance of machine learning algorithms. Therefore, we perform a comparative analysis of eight commonly used machine learning algorithms in different sensor combinations in this work. We used a publicly available mobile sensors dataset and applied the k-Nearest Neighbors (KNN) data imputation technique for extrapolating the missing samples. Afterward, we performed a couple of experiments to figure out which algorithm performs best at which sensors' data combination. The experimental analysis reveals that the AdaBoost algorithm outperformed all machine learning algorithms for recognizing five different human daily living activities with both single and multi-sensor combinations. Furthermore, the experimental results show that AdaBoost is capable to correctly identify all the activities presented in the dataset with 100% classification accuracy.

A Framework for Malicious Traffic Detection in IoT Healthcare Environment

The Internet of things (IoT) has emerged as a topic of intense interest among the research and industrial community as it has had a revolutionary impact on human life. The rapid growth of IoT technology has revolutionized human life by inaugurating the concept of smart devices, smart healthcare, smart industry, smart city, smart grid, among others. IoT devices' security has become a serious concern nowadays, especially for the healthcare domain, where recent attacks exposed damaging IoT security vulnerabilities. Traditional network security solutions are well established. However, due to the resource constraint property of IoT devices and the distinct behavior of IoT protocols, the existing security mechanisms cannot be deployed directly for securing the IoT devices and network from the cyber-attacks. To enhance the level of security for IoT, researchers need IoT-specific tools, methods, and datasets. To address the mentioned problem, we provide a framework for developing IoT context-aware security solutions to detect malicious traffic in IoT use cases. The proposed framework consists of a newly created, open-source IoT data generator tool named IoT-Flock. The IoT-Flock tool allows researchers to develop an IoT use-case comprised of both normal and malicious IoT devices and generate traffic. Additionally, the proposed framework provides an open-source utility for converting the captured traffic generated by IoT-Flock into an IoT dataset. Using the proposed framework in this research, we first generated an IoT healthcare dataset which comprises both normal and IoT attack traffic. Afterwards, we applied different machine learning techniques to the generated dataset to detect the cyber-attacks and protect the healthcare system from cyber-attacks. The proposed framework will help in developing the context-aware IoT security solutions, especially for a sensitive use case like IoT healthcare environment.

An Experimental Study on the Validity and Reliability of a Smartphone Application to Acquire Temporal Variables during the Single Sit-to-Stand Test with Older Adults

Smartphone sensors have often been proposed as pervasive measurement systems to assess mobility in older adults due to their ease of use and low-cost. This study analyzes a smartphone-based application’s validity and reliability to quantify temporal variables during the single sit-to-stand test with institutionalized older adults. Forty older adults (20 women and 20 men; 78.9 ± 8.6 years) volunteered to participate in this study. All participants performed the single sit-to-stand test. Each sit-to-stand repetition was performed after an acoustic signal was emitted by the smartphone app. All data were acquired simultaneously with a smartphone and a digital video camera. The measured temporal variables were stand-up time and total time. The relative reliability and systematic bias inter-device were assessed using the intraclass correlation coefficient (ICC) and Bland-Altman plots. In contrast, absolute reliability was assessed using the standard error of measurement and coefficient of variation (CV). Inter-device concurrent validity was assessed through correlation analysis. The absolute percent error (APE) and the accuracy were also calculated. The results showed excellent reliability (ICC = 0.92–0.97; CV = 1.85–3.03) and very strong relationships inter-devices for the stand-up time (r = 0.94) and the total time (r = 0.98). The APE was lower than 6%, and the accuracy was higher than 94%. Based on our data, the findings suggest that the smartphone application is valid and reliable to collect the stand-up time and total time during the single sit-to-stand test with older adults.

Biometric User Identification Based on Human Activity Recognition Using Wearable Sensors: An Experiment Using Deep Learning Models

Currently, a significant amount of interest is focused on research in the field of Human Activity Recognition (HAR) as a result of the wide variety of its practical uses in real-world applications, such as biometric user identification, health monitoring of the elderly, and surveillance by authorities. The widespread use of wearable sensor devices and the Internet of Things (IoT) has led the topic of HAR to become a significant subject in areas of mobile and ubiquitous computing. In recent years, the most widely-used inference and problem-solving approach in the HAR system has been deep learning. Nevertheless, major challenges exist with regard to the application of HAR for problems in biometric user identification in which various human behaviors can be regarded as types of biometric qualities and used for identifying people. In this research study, a novel framework for multi-class wearable user identification, with a basis in the recognition of human behavior through the use of deep learning models, is presented. In order to obtain advanced information regarding users during the performance of various activities, sensory data from tri-axial gyroscopes and tri-axial accelerometers of the wearable devices are applied. Additionally, a set of experiments were shown to validate this work, and the proposed framework’s effectiveness was demonstrated. The results for the two basic models, namely, the Convolutional Neural Network (CNN) and the Long Short-Term Memory (LSTM) deep learning, showed that the highest accuracy for all users was 91.77% and 92.43%, respectively. With regard to the biometric user identification, these are both acceptable levels.

Homogeneous Data Normalization and Deep Learning: A Case Study in Human Activity Classification

One class of applications for human activity recognition methods is found in mobile devices for monitoring older adults and people with special needs. Recently, many studies were performed to create intelligent methods for the recognition of human activities. However, the different mobile devices in the market acquire the data from sensors at different frequencies. This paper focuses on implementing four data normalization techniques, i.e., MaxAbsScaler, MinMaxScaler, RobustScaler, and Z-Score. Subsequently, we evaluate the impact of the normalization algorithms with deep neural networks (DNN) for the classification of the human activities. The impact of the data normalization was counterintuitive, resulting in a degradation of performance. Namely, when using the accelerometer data, the accuracy dropped from about 79% to only 53% for the best normalization approach. Similarly, for the gyroscope data, the accuracy without normalization was about 81.5%, whereas with the best normalization, it was only 60%. It can be concluded that data normalization techniques are not helpful in classification problems with homogeneous data.