Human Activity Recognition Research Articles

Deep Learning for Skeleton-Based Human Activity Segmentation: An Autoencoder Approach

Automatic segmentation is essential for enhancing human activity recognition, especially given the limitations of publicly available datasets that often lack diversity in daily activities. This study introduces a novel segmentation method that utilizes skeleton data for a more accurate and efficient analysis of human actions. By employing an autoencoder, this method extracts representative features and reconstructs the dataset, using the discrepancies between the original and reconstructed data to establish a segmentation threshold. This innovative approach allows for the automatic segmentation of activity datasets into distinct segments. Rigorous evaluations against ground truth across three publicly available datasets demonstrate the method’s effectiveness, achieving impressive average annotation error, precision, recall, and F1-score values of 3.6, 90%, 87%, and 88%, respectively. This illustrates the robustness of the proposed method in accurately identifying change points and segmenting continuous skeleton-based activities as compared to two other state-of-the-art techniques: one based on deep learning and another using the classical time-series segmentation algorithm. Additionally, the dynamic thresholding mechanism enhances the adaptability of the segmentation process to different activity dynamics improving overall segmentation accuracy. This performance highlights the potential of the proposed method to significantly advance the field of human activity recognition by improving the accuracy and efficiency of identifying and categorizing human movements.

A Comparative Analysis of XGBoost and LightGBM Approaches for Human Activity Recognition: Speed and Accuracy Evaluation

A Comparative Analysis of XGBoost and LightGBM Approaches for Human Activity Recognition: Speed and Accuracy Evaluation

Enhanced Depth Motion Maps for Improved Human Action Recognition from Depth Action Sequences

Enhanced Depth Motion Maps for Improved Human Action Recognition from Depth Action Sequences

Prediction of Human Physiological States by Using an Enhanced Recursive Feature Elimination Method

Human Action Recognition (HAR) is a vital part of the healthcare sector. Medical practitioners are experiencing difficulty in recognizing human physiological conditions due to the enormous quantity of sensory stimulation. Machine learning techniques help to predict human physiological conditions, providing medical practitioners to work more efficiently. Feature selection is an essential part of discovering new knowledge in the majority of real-world problems when there are a lot of features. Feature selection is extremely useful because it speeds up decisions and enhances classification performance. The importance of feature selection in machine learning is dimension reduction in a massive multivariate data collection. This paper presents an effective feature selection method known as the Enhanced Recursive Feature Elimination (EFRE) for selecting key features from the data set for HAR prediction. The experimental results reveal that the ERFE technique selects the most suitable features for HAR prediction. The performance of the proposed ERFE approach is tested using different performance evaluation metrics. The performance analysis shows that the ERFE method outperforms existing feature selection methods with 88% accuracy.

HARWE: A multi-modal large-scale dataset for context-aware human activity recognition in smart working environments

In recent years, deep neural networks (DNNs) have provided high performances for various tasks, such as human activity recognition (HAR), in view of their end-to-end training process between the input data and output labels. However, the performances of the DNNs are highly dependent on the availability of large-scale data for their training processes. In this paper, we propose a novel dataset for the task of HAR, in which the labels are specified for the working environments (WE). Our proposed dataset, namely HARWE, considers multiple signal modalities, including visual signal, audio signal, inertial sensor signals, and biological signals, that are acquired using four different electronic devices. Furthermore, our HARWE dataset is acquired from a large number of participants while considering the realistic disturbances that can occur in the wild. Our HARWE data is context-driven, which means there exist a number of labels in it that even though they are correlated with each other, they have contextual differences. A deep conventional multi-modal neural network provides an accuracy of 99.06% and 68.60%, for the cases of the easy and difficult settings of our dataset, respectively, which indicates its applicability for the task of human activity recognition.

A Spatio-temporal Graph Transformer driven model for recognizing fine-grained data human activity

Human activity recognition(HAR) is an important research focus in ubiquitous computing. It has been widely applied in various domains, such as smart homes, healthcare assistance, and sports training. Accurate human activity recognition directly impacts the performance of downstream tasks. Existing methods for human activity recognition primarily rely on extracting temporal or spatial features from the data. These features are used for the task of human activity recognition. The existing methods mainly use CNN or RNN models to model the Euclidean correlations among spatially adjacent sensors or channels. However, non-Euclidean pairwise correlations among all sensors or channels are even critical for accurate classification, which has been ignored by the existing methods. In this paper, we incorporate fine-grained spatial structural data into the model to overcome these limitations. A novel deep learning model for human activity recognition is proposed, which is called the fine-grained data-oriented Spatial-Temporal Graph Transformer network (STGT). The introduction of the STGT model can eliminate the limitations of existing spatial feature extraction methods by leveraging a novel data organization approach proposed in this study. This model enhances the spatial features within the time feature extraction module for effective spatio-temporal feature extraction. We conducted experiments on four large-scale real-world HAR datasets to evaluate its performance. The experimental results demonstrate the superiority of our method over state-of-the-art approaches.

Robust explainer recommendation for time series classification

Time series classification is a task which deals with temporal sequences, a prevalent data type common in domains such as human activity recognition, sports analytics and general sensing. In this area, interest in explanability has been growing as explanation is key to understand the data and the model better. Recently, a great variety of techniques (e.g., LIME, SHAP, CAM) have been proposed and adapted for time series to provide explanation in the form of saliency maps, where the importance of each data point in the time series is quantified with a numerical value. However, the saliency maps can and often disagree, so it is unclear which one to use. This paper provides a novel framework to quantitatively evaluate and rank explanation methods for time series classification. We show how to robustly evaluate the informativeness of a given explanation method (i.e., relevance for the classification task), and how to compare explanations side-by-side. The goal is to recommend the best explainer for a given time series classification dataset. We propose AMEE, a Model-Agnostic Explanation Evaluation framework, for recommending saliency-based explanations for time series classification. In this approach, data perturbation is added to the input time series guided by each explanation. Our results show that perturbing discriminative parts of the time series leads to significant changes in classification accuracy, which can be used to evaluate each explanation. To be robust to different types of perturbations and different types of classifiers, we aggregate the accuracy loss across perturbations and classifiers. This novel approach allows us to recommend the best explainer among a set of different explainers, including random and oracle explainers. We provide a quantitative and qualitative analysis for synthetic datasets, a variety of time-series datasets, as well as a real-world case study with known expert ground truth.

A hybrid deep approach to recognizing student activity and monitoring health physique based on accelerometer data from smartphones

Smartphone sensors have gained considerable traction in Human Activity Recognition (HAR), drawing attention for their diverse applications. Accelerometer data monitoring holds promise in understanding students’ physical activities, fostering healthier lifestyles. This technology tracks exercise routines, sedentary behavior, and overall fitness levels, potentially encouraging better habits, preempting health issues, and bolstering students’ well-being. Traditionally, HAR involved analyzing signals linked to physical activities using handcrafted features. However, recent years have witnessed the integration of deep learning into HAR tasks, leveraging digital physiological signals from smartwatches and learning features automatically from raw sensory data. The Long Short-Term Memory (LSTM) network stands out as a potent algorithm for analyzing physiological signals, promising improved accuracy and scalability in automated signal analysis. In this article, we propose a feature analysis framework for recognizing student activity and monitoring health based on smartphone accelerometer data through an edge computing platform. Our objective is to boost HAR performance by accounting for the dynamic nature of human behavior. Nonetheless, the current LSTM network’s presetting of hidden units and initial learning rate relies on prior knowledge, potentially leading to suboptimal states. To counter this, we employ Bidirectional LSTM (BiLSTM), enhancing sequence processing models. Furthermore, Bayesian optimization aids in fine-tuning the BiLSTM model architecture. Through fivefold cross-validation on training and testing datasets, our model showcases a classification accuracy of 97.5% on the tested dataset. Moreover, edge computing offers real-time processing, reduced latency, enhanced privacy, bandwidth efficiency, offline capabilities, energy efficiency, personalization, and scalability. Extensive experimental results validate that our proposed approach surpasses state-of-the-art methodologies in recognizing human activities and monitoring health based on smartphone accelerometer data.

Using Graphs to Perform Effective Sensor-Based Human Activity Recognition in Smart Homes.

There has been a resurgence of applications focused on human activity recognition (HAR) in smart homes, especially in the field of ambient intelligence and assisted-living technologies. However, such applications present numerous significant challenges to any automated analysis system operating in the real world, such as variability, sparsity, and noise in sensor measurements. Although state-of-the-art HAR systems have made considerable strides in addressing some of these challenges, they suffer from a practical limitation: they require successful pre-segmentation of continuous sensor data streams prior to automated recognition, i.e., they assume that an oracle is present during deployment, and that it is capable of identifying time windows of interest across discrete sensor events. To overcome this limitation, we propose a novel graph-guided neural network approach that performs activity recognition by learning explicit co-firing relationships between sensors. We accomplish this by learning a more expressive graph structure representing the sensor network in a smart home in a data-driven manner. Our approach maps discrete input sensor measurements to a feature space through the application of attention mechanisms and hierarchical pooling of node embeddings. We demonstrate the effectiveness of our proposed approach by conducting several experiments on CASAS datasets, showing that the resulting graph-guided neural network outperforms the state-of-the-art method for HAR in smart homes across multiple datasets and by large margins. These results are promising because they push HAR for smart homes closer to real-world applications.

Efficient human activity recognition: A deep convolutional transformer-based contrastive self-supervised approach using wearable sensors

Artificial intelligence has advanced the applications of sensor-based human motion capture and recognition technology in various engineering fields, such as human–robot collaboration and health monitoring. Deep learning methods can achieve satisfactory recognition results when provided with sufficient labeled data. However, labeling a large dataset is expensive and time-consuming in practical applications. To address this issue, this paper proposes a deep convolutional transformer-based contrastive self-supervised (DCTCSS) model under the bootstrap your own latent (BYOL) framework. The DCTCSS model aims to achieve reliable activity recognition using only a small amount of labeled data. Firstly, a deep convolutional transformer (DCT) model is proposed as the backbone of DCTCSS model, to learn high-level feature representations from unlabeled data in pre-training period. Subsequently, a simple linear classifier is trained with supervised fine-tuning using a limited amount of labeled data to recognize activities. In addition, this paper experimentally formulates a random data augmentation strategy to increase the diversity of input data. The performance of the DCTCSS model is evaluated and compared with several state-of-the-art algorithms on three datasets widely used in daily life, medical monitoring, and intelligent manufacturing. Experimental results show that the DCTCSS model achieves mean F1 scores of 95.64%, 88.39%, and 98.40% on the UCI-HAR, Skoda, and Mhealth datasets, respectively, using only 10% of the labeled data. These results outperform both supervised and unsupervised baseline models. Consequently, the DCTCSS model demonstrates its effectiveness in reducing the dependence on large amounts of labeled data while still achieving competitive activity recognition performance.

Optimizing HAR Systems: Comparative Analysis of Enhanced SVM and k-NN Classifiers

This research addresses the accuracy issues in IoT-based human activity recognition (HAR) applications, essential for health monitoring, elderly care, gait analysis, security, and Industry 5.0. This study uses 12 machine learning approaches, split equally between support vector machine (SVM) and k-nearest neighbor (k-NN) models. Data from 102 individuals, aged 18–43, were used to train and test these models. The researchers aimed to detect twelve daily activities, such as sitting, walking, and cycling. Results showed k-NN models achieved slightly higher accuracy (97.08%) compared to SVM models (95.88%), though SVM had faster processing times. The improved machine learning approaches proved effective in accurately classifying daily activities, with k-NN models outperforming SVM models marginally. The paper provides significant contributions to the field of HAR by enhancing the performance of SVM and k-NN classifiers, optimizing them for higher accuracy and faster processing. Through robust testing with samples of real-world data, the study provides a detailed comparative analysis that highlights strengths and weaknesses of each classifier model, specifically within IoT-based systems. This work not only advances the theoretical understanding and practical applications of HAR systems in areas, such as healthcare and industrial automation, but also sets the stage for future research that could explore hybrid models or further enhancements, consequently improving the efficiency and functionality of IoT devices based on activity recognition.

SenseMLP: a parallel MLP architecture for sensor-based human activity recognition

SenseMLP: a parallel MLP architecture for sensor-based human activity recognition

Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition.

Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person's ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully in-the-wild environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using in-the-wild data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world.

Real-Time Sensor-Based Human Activity Recognition for eFitness and eHealth Platforms

Human Activity Recognition (HAR) plays an important role in the automation of various tasks related to activity tracking in such areas as healthcare and eldercare (telerehabilitation, telemonitoring), security, ergonomics, entertainment (fitness, sports promotion, human–computer interaction, video games), and intelligent environments. This paper tackles the problem of real-time recognition and repetition counting of 12 types of exercises performed during athletic workouts. Our approach is based on the deep neural network model fed by the signal from a 9-axis motion sensor (IMU) placed on the chest. The model can be run on mobile platforms (iOS, Android). We discuss design requirements for the system and their impact on data collection protocols. We present architecture based on an encoder pretrained with contrastive learning. Compared to end-to-end training, the presented approach significantly improves the developed model’s quality in terms of accuracy (F1 score, MAPE) and robustness (false-positive rate) during background activity. We make the AIDLAB-HAR dataset publicly available to encourage further research.

Modality Consistency-Guided Contrastive Learning for Wearable-Based Human Activity Recognition

Modality Consistency-Guided Contrastive Learning for Wearable-Based Human Activity Recognition

GANCDE: Neural networks based on graphs and attention neural control differential equations for human activity recognition

GANCDE: Neural networks based on graphs and attention neural control differential equations for human activity recognition

Artificial Intelligence-Based Algorithms and Healthcare Applications of Respiratory Inductance Plethysmography: A Systematic Review

Respiratory Inductance Plethysmography (RIP) is a non-invasive method for the measurement of respiratory rates and lung volumes. Accurate detection of respiratory rates and volumes is crucial for the diagnosis and monitoring of prognosis of lung diseases, for which spirometry is classically used in clinical applications. RIP has been studied as an alternative to spirometry and shown promising results. Moreover, RIP data can be analyzed through machine learning (ML)-based approaches for some other purposes, i.e., detection of apneas, work of breathing (WoB) measurement, and recognition of human activity based on breathing patterns. The goal of this study is to provide an in-depth systematic review of the scope of usage of RIP and current RIP device developments, as well as to evaluate the performance, usability, and reliability of ML-based data analysis techniques within its designated scope while adhering to the PRISMA guidelines. This work also identifies research gaps in the field and highlights the potential scope for future work. The IEEE Explore, Springer, PLoS One, Science Direct, and Google Scholar databases were examined, and 40 publications were included in this work through a structured screening and quality assessment procedure. Studies with conclusive experimentation on RIP published between 2012 and 2023 were included, while unvalidated studies were excluded. The findings indicate that RIP is an effective method to a certain extent for testing and monitoring respiratory functions, though its accuracy is lacking in some settings. However, RIP possesses some advantages over spirometry due to its non-invasive nature and functionality for both stationary and ambulatory uses. RIP also demonstrates its capabilities in ML-based applications, such as detection of breathing asynchrony, classification of apnea, identification of sleep stage, and human activity recognition (HAR). It is our conclusion that, though RIP is not yet ready to replace spirometry and other established methods, it can provide crucial insights into subjects’ condition associated to respiratory illnesses. The implementation of artificial intelligence (AI) could play a potential role in improving the overall effectiveness of RIP, as suggested in some of the selected studies.

Human Joint Angle Estimation Using Deep Learning-Based Three-Dimensional Human Pose Estimation for Application in a Real Environment.

Human pose estimation (HPE) is a technique used in computer vision and artificial intelligence to detect and track human body parts and poses using images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods that employ monocular cameras are highly versatile and applicable to standard videos and CCTV footage. These methods have evolved from two-dimensional (2D) to three-dimensional (3D) pose estimation. However, in real-world environments, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges, such as limited training data, depth ambiguity, left/right switching, and issues with occlusions. In this study, four 3D HPE methods were compared based on their strengths and weaknesses using real-world videos. Joint position correction techniques were proposed to eliminate and correct anomalies such as left/right inversion and false detections of joint positions in daily life motions. Joint angle trajectories were obtained for intuitive and informative human activity recognition using an optimization method based on a 3D humanoid simulator, with the joint position corrected by the proposed technique as the input. The efficacy of the proposed method was verified by applying it to three types of freehand gymnastic exercises and comparing the joint angle trajectories during motion.

TCN-Inception: Temporal Convolutional Network and Inception modules for sensor-based Human Activity Recognition

The field of Human Activity Recognition (HAR) has experienced a significant surge in interest due to its essential role across numerous areas, including human–computer interaction (HCI), healthcare, smart homes, and various Internet of Things (IoT) applications. The power of deep learning methods in performing various classification tasks, including HAR, has been well-demonstrated. In light of this, our paper presents an efficient HAR system developed using a unique deep-learning architecture called TCN-Inception, which is designed for multivariate time series tasks like HAR data, by combining Temporal Convolutional Network (TCN) and Inception modules. The network starts with an Inception module that uses parallel convolution layers with various kernel sizes for feature extraction. It then includes a TCN module with dilated convolutions to grasp extended temporal patterns. Features are merged from different channels, and the use of residual connections and batch normalization improves training and deepens the architecture. We use four public datasets, UCI-HAR, MobiAct, Daphnet, and DSADS to assess the performance of the TCN-Inception model, and it obtains an average accuracy of 96.15%, 98.86%, 92.63%, and 99.50% for each dataset, respectively. Moreover, we compare the TCN-Inception to several deep learning frameworks to verify its performance. Finally, we implement an ablation study using several architectural configurations of the TCN-Inception model.

Application of Human Activity Recognition in Supermarkets with Human Pose Estimation

Human Activity Recognition is the ability to interpret human body movements or movements through sensors and to determine human activities or actions. Most everyday human tasks can be simplified or automated if they can be identified through an activity management system. The introduction of human activities in supermarkets has many benefits in its development, such as Just Walk Out technologies such as Amazon Go and the prevention of theft of goods. Proposed research with the theme of human activity recognition that has a focus on supermarkets. The methods that will be used in this research are Human Pose Estimation and Random Forest Classifier with data collected from the internet. The designed application will first detect skeletons with Blazepose from human objects, which will then be classified by the Random Forest Classifier. Activities that can be classified by the designed application are standing, walking, and fetching. The output of the application is a classification of activities carried out in real-time with the camera. The test results on the training data get an accuracy value of 100%, precision of 100%, recall of 100%, and F1-Score of 100%. Using the test data produces a confusion matrix which shows that the model being trained has an accuracy value of 100%, precision of 100%, recall of 100%, and an F1-Score of 100%.