Search

Background: The ActiPASS software was developed from the open-source Acti4 activity classification algorithm for thigh-worn accelerometry. However, the original algorithm has not been validated in children or compared with a child-specific set of algorithm thresholds. This study aims to evaluate the accuracy of ActiPASS in classifying activity types in children using 2 published sets of Acti4 thresholds. Methods: Laboratory and free-living data from 2 previous studies were used. The laboratory condition included 41 school-aged children (11.0 [4.8] y; 46.5% male), and the free-living condition included 15 children (10.0 [2.6] y; 66.6% male). Participants wore a single accelerometer on the dominant thigh, and annotated video recordings were used as a reference. Postures and activity types were classified with ActiPASS using the original adult thresholds and a child-specific set of thresholds. Results: Using the original adult thresholds, the mean balanced accuracy (95% CI) for the laboratory condition ranged from 0.62 (0.56–0.67) for lying to 0.97 (0.94–0.99) for running. For the free-living condition, accuracy ranged from 0.61 (0.48–0.75) for lying to 0.96 (0.92–0.99) for cycling. Mean balanced accuracy for overall sedentary behavior (sitting and lying) was ≥0.97 (0.95–0.99) across all thresholds and conditions. No meaningful differences were found between the 2 sets of thresholds, except for superior balanced accuracy of the adult thresholds for walking under laboratory conditions. Conclusions: The results indicate that ActiPASS can accurately classify different basic types of physical activity and sedentary behavior in children using thigh-worn accelerometer data. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) have attained human-level performance for object categorization and exhibited representation alignment between network layers and brain regions. Does such representation alignment naturally extend to other visual tasks beyond recognizing objects in static images? In this study, we expanded the exploration to the recognition of human actions from videos and assessed the representation capabilities and alignment of two-stream DCNNs in comparison with brain regions situated along ventral and dorsal pathways. Using decoding analysis and representational similarity analysis, we show that DCNN models do not show hierarchical representation alignment to human brain across visual regions when processing action videos. Instead, later layers of DCNN models demonstrate greater representation similarities to the human visual cortex. These findings were revealed for two display formats: photorealistic avatars with full-body information and simplified stimuli in the point-light display. The discrepancies in representation alignment suggest fundamental differences in how DCNNs and the human brain represent dynamic visual information related to actions. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) is a highly promising research area meant to automatically identify and interpret human behaviour using data received from sensors in various contexts. The potential uses of HAR are many, among them health care, sports coaching or monitoring the elderly or disabled. Nonetheless, there are numerous hurdles to be circumvented for HAR's precision and usefulness to be improved. One of the challenges is that there is no uniformity in data collection and annotation making it difficult to compare findings among different studies. Furthermore, more comprehensive datasets are necessary so as to include a wider range of human activities in different contexts while complex activities, which consist of multiple sub‐activities, are still a challenge for recognition systems. Researchers have proposed new frontiers such as multi‐modal sensor data fusion and deep learning approaches for enhancing HAR accuracy while addressing these issues. Also, we are seeing more non‐traditional applications such as robotics and virtual reality/augmented world going forward with their use cases of HAR. This article offers an extensive review on the recent advances in HAR and highlights the major challenges facing this field as well as future opportunities for further researches. [ABSTRACT FROM AUTHOR]

Over the past few decades, numerous studies have focused on identifying and recognizing human actions using machine learning and computer vision techniques. Video-based human action recognition (HAR) aims to detect actions from video sequences automatically. This can cover simple gestures to complex actions involving multiple people interacting with objects. Actions in team sports exhibit a different nature compared to other sports, since they tend to occur at a faster pace and involve more human-human interactions. As a result, research has typically not focused on the challenges of HAR in team sports. This paper comprehensively summarises HAR-related research and applications with specific focus on team sports such as football (soccer), basketball and Australian rules football. Key datasets used for HAR-related team sports research are explored. Finally, common challenges and future work are discussed, and possible research directions identified. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) remains a challenging problem in computer vision due to the unpredictable nature of human activities. In recent years, researchers have proposed various hybrid models for HAR, focusing on spatial, temporal, or both aspects. The spatial and temporal feature-based models have limitations in fully capturing the features and exhibit low accuracy during the training and testing. Addressing these challenges, we present a TriFusion hybrid model that integrates spatial, temporal, and high-level features to enhance accuracy in HAR. In this paper, different from previous fusion methods, we propose a novel approach by combining three deep learning model architectures. Specifically, VGG16 spatial features are fed into BiGRU for temporal feature extraction and also directly connected to TriFusion, alongside the BiGRU output, while transfer learning (ResNet18) is also connected to TriFusion. Our TriFusion model achieved an average accuracy of 99.92% on the UCF101 dataset and 99.78% on the HMDB51 dataset, demonstrating its suitability for real-time deployment in HAR applications. Our TriFusion model, designed for HAR tasks, exhibits promising applications across various AI domains, including human-computer interaction and diverse classification tasks. The code of TriFusion is publicly accessible at https://github.com/TripleTheGreatDali/TriFusionHAR. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) serves as a fundamental component for the various applications of smart homes. However, although existing methods can extract temporal features of sensor event sequences, they do not consider the activation time, location specificity, and long-term dependence of sensor events. This article proposes a new HAR approach based on RGB activity images and a deep convolutional attention network (DCAN). First, the raw data is segmented according to the activity labels after preprocessing. Subsequently, a sliding window is utilized to partition the segmented activity instances into several fixed-length parts. Next, the windowed part is converted into an RGB activity image, where the x-coordinate represents the event sequence, the y-coordinate represents the sensor pattern, and the pixel value is a triplet composed of the event's start time, end time, and duration. Then DCAN is used to extract features and classify these RGB activity images. We test the proposed method on the Aruba dataset and the weighted F1 scores of 10-fold cross-validation for 10 and 8 activities are 0.953 and 0.992, respectively, indicating that our proposed RGB activity image effectively improves classification and our DCAN classifier outperforms existing methods. [ABSTRACT FROM AUTHOR]

Many scientific studies on tennis stroke recognition are based on datasets, that have been developed for particular studies, using video or motion capture techniques. The importance of such datasets has been increasing due to the athlete performance evaluation needs. The primary contribution of this study is to present a state-of-the-art 3DTennisDS storing four tennis moves: backhand, forehand, volley backhand as well as volley forehand. The strokes were registered using the Vicon optical motion capture and contain a 39 – marker player and a 7 – marker tennis racket models. The potential and quality of this unique dataset has been verified using spatial-temporal graph neural networks, because this type of network topology matches to the human body structure. The presented 3DTennisDS has been compared with two well-known datasets: the THETIS and the Tennis-Mocap. They contain tennis movements in a form of motion capture data, registered using markerless and marker-based systems. The classification of tennis movements has been performed to verify how different types of data acquisition (marker-based and marker-less ones) as well as the structure of the data affect the accuracy of human action recognition. In this study ONI files from THETIS, bvh from Tennis-Mocap and c3d data from 3DTennisDS were considered. Moreover, the impact of input data fuzzification was examined. The obtained results showed that the classification using 3DTennisDS achieved the best results, both for fuzzy and non-fuzzy inputs. These outcomes indicate that the way of capturing data, its preparation and structure have great influence on classification accuracy. The developed 3DTennisDS has a great potential in further motion capture analysis. [ABSTRACT FROM AUTHOR]

In this study, we focus on human activity recognition, particularly aiming to distinguish the activity of praying (salat) from other daily activities. To achieve this goal, we have created a new dataset named HAR-P (Human activity recognition for Praying), which includes eight different activities: walking, running, sitting, standing, walking upstairs, walking downstairs, typing with a keyboard, and praying (salat). The HAR-P dataset was collected from 50 male individuals, who wore smartwatches on their dominant wrists. We compare the activity classification performance using three state-of-the-art algorithms from the literature: Long Short-Term Memory, Convolutional Long Short-Term Memory, and Convolutional Neural Network—Long Short-Term Memory. To assess the influence of sensors, data from accelerometer, gyroscope, linear acceleration sensor, and magnetic field sensor were utilized. The impact of individual sensor data as well as combinations thereof was investigated. The highest classification accuracy within single sensor groups, reaching 95.7%, was achieved using the accelerometer data with the Convolutional Long Short-Term Memory method. Combining two sensor groups resulted in an increase in accuracy of up to 9%. The highest accuracy of 96.4% was obtained by utilizing three sensor groups together with the Convolutional Neural Network—Long Short-Term Memory method. Furthermore, the evaluation of sensor and model performance was conducted using the stratified k-fold cross-validation method with 5-folds. These findings contribute significantly to evaluating the performance of sensor combinations and different algorithms in activity classification. This study may provide an effective foundation for the automatic recognition and tracking of human activities and offer an applicable model, particularly for the recognition of religious practices such as praying. [ABSTRACT FROM AUTHOR]

Impulse radio ultra-wideband (IR-UWB) radar, operating in the low-frequency band, can penetrate walls and utilize its high range resolution to recognize different human activities. Complex deep neural networks have demonstrated significant performance advantages in classifying radar spectrograms of various actions, but at the cost of a substantial computational overhead. In response, this paper proposes a lightweight model named TG2-CAFNet. First, clutter suppression and time–frequency analysis are used to obtain range–time and micro-Doppler feature maps of human activities. Then, leveraging GhostV2 convolution, a lightweight feature extraction module, TG2, suitable for radar spectrograms is constructed. Using a parallel structure, the features of the two spectrograms are extracted separately. Finally, to further explore the correlation between the two spectrograms and enhance the feature representation capabilities, an improved nonlinear fusion method called coordinate attention fusion (CAF) is proposed based on attention feature fusion (AFF). This method extends the adaptive weighting fusion of AFF to a spatial distribution, effectively capturing the subtle spatial relationships between the two radar spectrograms. Experiments showed that the proposed method achieved a high degree of model lightweightness, while also achieving a recognition accuracy of 99.1%. [ABSTRACT FROM AUTHOR]

Human activity recognition is known as the backbone of the development of interactive systems, such as computer games. This process is usually performed by either vision-based or depth sensors. So far, various solutions have been developed for this purpose; however, all the challenges of this process have not been completely resolved. In this paper, a solution based on pattern recognition has been developed for labeling and scoring physical exercises performed in front of the Kinect sensor. Extracting the features from human skeletal joints and then generating relative descriptors among them is the first step of our method. This has led to quantification of the meaningful relationships between different parts of the skeletal joints during exercise performance. In this method, the discriminating descriptors of each exercise motion are used to identify the adaptive kernels of the Constrained Energy Minimization method as a target detector operator. The results indicated an accuracy of 95.9% in the labeling process of physical exercise motions. Scoring the exercise motions was the second step after the labeling process, in which a geometric method was used to interpolate numerical quantities extracted from descriptor vectors to transform into semantic scores. The results demonstrated the scoring process coincided with the scores derived by the sports coach by a 99.5 grade in the R2 index. [ABSTRACT FROM AUTHOR]

Existing activity tracker datasets for human activity recognition are typically obtained by having participants perform predefined activities in an enclosed environment under supervision. This results in small datasets with a limited number of activities and heterogeneity, lacking the mixed and nuanced movements normally found in free-living scenarios. As such, models trained on laboratory-style datasets may not generalise out of sample. To address this problem, we introduce a new dataset involving wrist-worn accelerometers, wearable cameras, and sleep diaries, enabling data collection for over 24 hours in a free-living setting. The result is CAPTURE-24, a large activity tracker dataset collected in the wild from 151 participants, amounting to 3883 hours of accelerometer data, of which 2562 hours are annotated. CAPTURE-24 is two to three orders of magnitude larger than existing publicly available datasets, which is critical to developing accurate human activity recognition models. [ABSTRACT FROM AUTHOR]

Accurately understanding the travel demand of urban rail transit (URT) systems is crucial for effective operational management. Despite the recognition that the diversity in human activity patterns results in different travel demands, few studies have thoroughly investigated the heterogeneity among passengers and its impact on URT ridership. This study utilizes smart card data collected from the Beijing Subway to categorize passengers into four groups: tourist passengers, flexible commuters, regular commuters, and life‐oriented passengers, based on their spatiotemporal travel patterns. Furthermore, a Multiscale Geographically Weighted Regression (MGWR) model is employed to examine the relationship between station‐level ridership of URT and its determinants, including the built environment and station properties, for each passenger group. The results indicate that the influence of these determinants on station‐level ridership varies across passenger groups and spatial scales. For instance, regular commuters exhibit lower sensitivity to accessibility on workdays, whereas those unfamiliar with the URT network are more concerned about the bus accessibility in pedestrian‐ or bicycle‐unfriendly areas. Notably, for tourist and life‐oriented passengers, the stations significantly affected by population density are concentrated in areas with a higher proportion of elderly individuals. Conversely, for flexible and regular commuters, these stations are predominantly situated in areas associated with internet technology and scientific research. These findings are valuable for policymakers in designing strategies tailored to different passenger groups to balance trip demand and capacity, thereby improving URT services and promoting a sustainable urban environment. [ABSTRACT FROM AUTHOR]

Abnormal behavior methods have attempted to reduce execution time, computational complexity, efficiency, robustness against pixel occlusion, and generalizability. This research proposed a novel method in human activity-based anomaly detection and recognition by surveillance video utilizing DL methods. Input is collected as video and processed for noise removal and smoothening. Then kernel local component analysis extracts these video features for human activity monitoring. Then the extracted features are classified using Bayesian network-based spatiotemporal neural networks. The classified output shows the anomaly activities of the selected input surveillance video dataset. The simulation results are obtained for various crowd datasets regarding the mean average error, mean square error, training accuracy, validation accuracy, specificity, and F_measure. The proposed technique attained an MAE of 58%, MSE of 63%, specificity of 89%, and F-measure of 68%. training and validation accuracy of 92% and 96% respectively. [ABSTRACT FROM AUTHOR]

The advancements in intelligent action recognition can be instrumental in developing autonomous robotic systems capable of analyzing complex human activities in real-time, contributing to the growing field of robotics that operates in dynamic environments. The precise recognition of basketball players' actions using artificial intelligence technology can provide valuable assistance and guidance to athletes, coaches, and analysts, and can help referees make fairer decisions during games. However, unlike action recognition in simpler scenarios, the background in basketball is similar and complex, the differences between various actions are subtle, and lighting conditions are inconsistent, making action recognition in basketball a challenging task. To address this problem, an Adaptive Context-Aware Network (ACA-Net) for basketball player action recognition is proposed in this paper. It contains a Long Short-term Adaptive (LSTA)module and a Triplet Spatial-Channel Interaction (TSCI)module to extract effective features at the temporal, spatial, and channel levels. The LSTA module adaptively learns global and local temporal features of the video. The TSCI module enhances the feature representation by learning the interaction features between space and channels. We conducted extensive experiments on the popular basketball action recognition datasets SpaceJam and Basketball-51. The results show that ACA-Net outperforms the current mainstream methods, achieving 89.26% and 92.05% in terms of classification accuracy on the two datasets, respectively. ACA-Net's adaptable architecture also holds potential for real-world applications in autonomous robotics, where accurate recognition of complex human actions in unstructured environments is crucial for tasks such as automated game analysis, player performance evaluation, and enhanced interactive broadcasting experiences. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) and brain-machine interface (BMI) are two emerging technologies that can enhance human-robot collaboration (HRC) in domains such as industry or healthcare. HAR uses sensors or cameras to capture and analyze the movements and actions of humans, while BMI uses human brain signals to decode action intentions. Both technologies face challenges impacting accuracy, reliability, and usability. In this article, we review the state-of-the-art techniques and methods for HAR and BMI and highlight their strengths and limitations. We then propose a hybrid framework that fuses HAR and BMI data, which can integrate the complementary information from the brain and body motion signals and improve the performance of human state decoding. We also discuss our hybrid method's potential benefits and implications for HRC. [ABSTRACT FROM AUTHOR]

Physical activity recognition using accelerometry is a rapidly advancing field with significant implications for healthcare, sports science, and wearable technology. This research presents an interesting approach for classifying physical activities using solely accelerometry data, signals that were taken from the available "MHEALTH dataset" and processed through artificial neural networks (ANNs). The methodology involves data acquisition, preprocessing, feature extraction, and the application of deep learning algorithms to accurately identify activity patterns. A major innovation in this study is the incorporation of a new feature derived from the radius of curvature. This time-domain feature is computed by segmenting accelerometry signals into windows, conducting double integration to derive positional data, and subsequently estimating a circumference based on the positional data obtained within each window. This characteristic is computed across the three movement planes, providing a robust and comprehensive feature for activity classification. The integration of the radius of curvature into the ANN models significantly enhances their accuracy, achieving over 95%. In comparison with other methodologies, our proposed approach, which utilizes a feedforward neural network (FFNN), demonstrates superior performance. This outperforms previous methods such as logistic regression, which achieved 93%, KNN models with 90%, and the InceptTime model with 88%. The findings demonstrate the potential of this model to improve the precision and reliability of physical activity recognition in wearable health monitoring systems. [ABSTRACT FROM AUTHOR]

Recently, the research community has taken great interest in human activity recognition (HAR) due to its wide range of applications in different fields of life, including medicine, security, and gaming. The use of sensory data for HAR systems is most common because the sensory data are collected from a person's wearable device sensors, thus overcoming the privacy issues being faced in data collection through video cameras. Numerous systems have been proposed to recognize some common activities of daily living (ADLs) using different machine learning, image processing, and deep learning techniques. However, the existing techniques are computationally expensive, limited to recognizing short-term activities, or require large datasets for training purposes. Since an ADL is made up of a sequence of smaller actions, recognizing them directly from raw sensory data is challenging. In this paper, we present a computationally efficient two-level hierarchical framework for recognizing long-term (composite) activities, which does not require a very large dataset for training purposes. First, the short-term (atomic) activities are recognized from raw sensory data, and the probabilistic atomic score of each atomic activity is calculated relative to the composite activities. In the second step, the optimal features are selected based on atomic scores for each composite activity and passed to the two classification algorithms: random forest (RF) and support vector machine (SVM) due to their well-documented effectiveness for human activity recognition. The proposed method was evaluated on the publicly available CogAge dataset that contains 890 instances of 7 composite and 9700 instances of 61 atomic activities. The data were collected from eight sensors of three wearable devices: a smartphone, a smartwatch, and smart glasses. The proposed method achieved the accuracy of 96.61% and 94.1% by random forest and SVM classifiers, respectively, which shows a remarkable increase in the classification accuracy of existing HAR systems for this dataset. [ABSTRACT FROM AUTHOR]

The integration of different Mobile Edge Computing (MEC) applications has significantly enhanced the realm of security and surveillance, with Human Activity Recognition (HAR) standing out as a crucial application. The diverse sensors found in smartphones have made it convenient for monitoring applications to gather and analyze data, rendering them valuable for HAR purposes. Moreover, MEC can be employed to automate surveillance, allowing intelligent monitoring of restricted areas to identify and respond to unwanted or suspicious activities. This research develops a system using motion sensors in smartphones to identify unusual human activities. People's smartphones were employed to monitor both suspicious and regular activities. Information was collected for various actions categorized as either suspicious or regular. When a person performs a certain action, the smartphone records a series of sensory data, analyse important patterns from the basic data, and then determines what the person is doing by combining information from different sensors. To prepare the data, information from different sensors was aligned to a shared timeline. In this study, we used a sliding window approach on synchronized data to feed sequences into LSTM and CNN models. These models, which include initial layers of LSTM and CNN, automatically find important patterns in the order of human activities. We combined SVM with the features extracted by the shallow Neural Network to make a mixed model that predicts suspicious activities. Lastly, we compared LSTM, CNN, and our new shallow mixed neural network using a new real‐time dataset. The mixed model of CNN and SVM achieved an accuracy of 94.43%. Additionally, the sliding window method's effectiveness was confirmed with a 4.28% improvement in accuracy. [ABSTRACT FROM AUTHOR]

The article discusses the use of artificial intelligence in radiotherapy treatment planning and dose optimization, particularly focusing on Head and Neck Cancer (HNC). Artificial intelligence systems can enhance treatment accuracy, efficiency, and outcomes by automating treatment planning, determining appropriate doses, and reducing human errors. While there are challenges and concerns, such as negative perceptions, the integration of artificial intelligence in cancer radiotherapy shows promise for improving treatment outcomes and efficiency. Continued research and development in this field are crucial for unlocking the full potential of AI in cancer radiotherapy. [Extracted from the article]

Featured Application: Applications can be found in industries, services, and other areas of human activity where products are designed to be brought out to the market. The proposed methodology requires information technologies because the methods are data-driven. This paper describes procedures that can be adopted during product development, so that there is a higher chance that new products are properly designed before being placed on the market. To implement the suggested procedures, market data are first obtained, then processed in a specified way for the new products to reflect relevant market information. This means putting into use suitable data-processing algorithms and information technologies, based on the type of collected information. The text deals with two information scenarios in this regard, the first assuming that not much is known about customers' desires and the second working with larger amounts of more specific customer data. While the former requires a more sophisticated approach to product design, theoretically speaking, the latter is simpler to handle from the theoretical point of view, but potentially less so from a practical perspective, given the amounts of data. These theoretical and practical problems are discussed in what follows, and their possible solutions are presented. [ABSTRACT FROM AUTHOR]

To create an effective Ambient Assisted Living (AAL) system that supports the daily activities of patients or the elderly, it is crucial to accurately detect and differentiate user actions to determine the necessary assistance. Traditional intrusive methods, such as wearable or object-attached devices, can interfere with the natural behavior of patients and may lead to resistance. Furthermore, non-intrusive systems that rely on video or sound data processed by servers or the cloud can generate excessive data traffic and raise concerns about the security of personal information. In this study, we developed an edge-based real-time system for detecting Activities of Daily Living (ADL) using ambient noise. Additionally, we introduced an online post-processing method to enhance classification performance and extract activity events from noisy sound in resource-constrained environments. The system, tested with data collected in a living space, achieved high accuracy in classifying ADL-related behaviors in continuous events and successfully generated user activity logs from time-series sound data, enabling further analyses such as ADL assessments. Future work will focus on enhancing detection accuracy and expanding the range of detectable behaviors by integrating the activity logs generated in this study with additional data sources beyond sound. [ABSTRACT FROM AUTHOR]

This paper investigates the feasibility of cross-domain recognition for human activities captured using low-resolution 8 × 8 infrared sensors in indoor environments. To achieve this, a novel prototype recurrent convolutional network (PRCN) was evaluated using a few-shot learning strategy, classifying up to eleven activity classes in scenarios where one or two individuals engaged in daily tasks. The model was tested on two independent datasets, with real-world measurements. Initially, three different networks were compared as feature extractors within the prototype network. Following this, a cross-domain evaluation was conducted between the real datasets. The results demonstrated the model's effectiveness, showing that it performed well regardless of the diversity of samples in the training dataset. [ABSTRACT FROM AUTHOR]

Human Interaction Recognition (HIR) was one of the challenging issues in computer vision research due to the involvement of multiple individuals and their mutual interactions within video frames generated from their movements. HIR requires more sophisticated analysis than Human Action Recognition (HAR) since HAR focuses solely on individual activities like walking or running, while HIR involves the interactions between people. This research aims to develop a robust system for recognizing five common human interactions, such as hugging, kicking, pushing, pointing, and no interaction, from video sequences using multiple cameras. In this study, a hybrid Deep Learning (DL) and Machine Learning (ML) model was employed to improve classification accuracy and generalizability. The dataset was collected in an indoor environment with four-channel cameras capturing the five types of interactions among 13 participants. The data was processed using a DL model with a fine-tuned ResNet (Residual Networks) architecture based on 2D Convolutional Neural Network (CNN) layers for feature extraction. Subsequently, machine learning models were trained and utilized for interaction classification using six commonly used ML algorithms, including SVM, KNN, RF, DT, NB, and XGBoost. The results demonstrate a high accuracy of 95.45% in classifying human interactions. The hybrid approach enabled effective learning, resulting in highly accurate performance across different interaction types. Future work will explore more complex scenarios involving multiple individuals based on the application of this architecture. [ABSTRACT FROM AUTHOR]

Analyzing physical activities through wearable devices is a promising research area for improving health assessment. This research focuses on the development of an affordable and real-time Human Activity Recognition (HAR) system designed to operate on low-performance microcontrollers. The system utilizes data from a body-worn accelerometer to recognize and classify human activities, providing a cost-effective, easy-to-use, and highly accurate solution. A key challenge addressed in this study is the execution of efficient motion recognition within a resource-constrained environment. The system employs a Random Forest (RF) classifier, which outperforms Gradient Boosting Decision Trees (GBDT), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) in terms of accuracy and computational efficiency. The proposed features Average absolute deviation (AAD), Standard deviation (STD), Interquartile range (IQR), Range, and Root mean square (RMS). The research has conducted numerous experiments and comparisons to establish optimal parameters for ensuring system effectiveness, including setting a sampling frequency of 50 Hz and selecting an 8-s window size with a 40% overlap between windows. Validation was conducted on both the WISDM public dataset and a self-collected dataset, focusing on five fundamental daily activities: Standing, Sitting, Jogging, Walking, and Walking the stairs. The results demonstrated high recognition accuracy, with the system achieving 96.7% on the WISDM dataset and 97.13% on the collected dataset. This research confirms the feasibility of deploying HAR systems on low-performance microcontrollers and highlights the system’s potential applications in patient support, rehabilitation, and elderly care. [ABSTRACT FROM AUTHOR]

As the proportion of elderly individuals in developed countries continues to rise globally, addressing their healthcare needs, particularly in preserving their autonomy, is of paramount concern. A growing body of research focuses on Ambient Assisted Living (AAL) systems, aimed at alleviating concerns related to the independent living of the elderly. This systematic review examines the literature pertaining to fall detection and Human Activity Recognition (HAR) for the elderly, two critical tasks for ensuring their safety when living alone. Specifically, this review emphasizes the utilization of Deep Learning (DL) approaches on computer vision data, reflecting current trends in the field. A comprehensive search yielded 2,616 works from five distinct sources, spanning the years 2019 to 2023 (inclusive). From this pool, 151 relevant works were selected for detailed analysis. The review scrutinizes the employed DL models, datasets, and hardware configurations, with particular emphasis on aspects such as privacy preservation and real-world deployment. The main contribution of this study lies in the synthesis of recent advancements in DL-based fall detection and HAR for the elderly, providing insights into the state-of-the-art techniques and identifying areas for further improvement. Given the increasing importance of AAL systems in enhancing the quality of life for the elderly, this review serves as a valuable resource for researchers, practitioners, and policymakers involved in developing and implementing such technologies. [ABSTRACT FROM AUTHOR]

Automating tasks through human activity recognition in video data has become increasingly vital. Deep learning has yielded versatile activity recognition systems applicable in surveillance, healthcare analysis, sports, and human–computer interaction. Despite various proposed video-based activity recognition techniques over the years, the reliance over RGB frames, accompanied by other modalities like joint locations and depth maps, often proves less effective compared to multimodal methods. In response to this challenge, our paper introduces a competitive approach for identifying human activity in video frames. Leveraging a Convolutional Long Short-Term Memory (Conv-LSTM) network and a novel pre-processing step involving a Human Segmentation network, our method accentuates human subjects in each frame using segmentation maps. These highlighted frames undergo further processing through Convolutional Neural Networks (CNNs) to learn feature vectors, without including other modalities with RGB frames directly. The learned features are then subjected to Long Short-Term Memory (LSTM) units for comprehending sequential video data and drawing meaningful inferences. The proposed methodology undergoes rigorous testing on three publicly available datasets—KARD, MSR Daily Activity, and SBU-Interactions. Remarkably, our approach outperforms similar state-of-the-art methods, achieving benchmark accuracy scores exceeding 98% on MSR Daily Activity and 99% on KARD and SBU-Interactions datasets. In essence, our method not only provides a competitive solution for human activity recognition in video frames but also contributes to advancing the field by integrating Conv-LSTM networks and innovative pre-processing techniques. The comprehensive evaluation on multiple datasets underlines the robustness and superior performance of our proposed approach. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is a technology that infers current user activities by using the available sensory data network. Research on activity recognition is considered extremely important, particularly when it comes to delivering sensitive services such as healthcare services and live tracking assistance and autonomy. For this purpose, many researchers have proposed a knowledge-driven approach or data-driven reasoning for identification techniques. However, there are multiple limitations associated with these approaches and the resulting models are typically not complete enough to capture all types of human activities. Thus, recent works have suggested combining these techniques through a hybrid model. This paper's goal is to give a brief overview of activity recognition implementation approaches by looking at various sensing technologies used to gather data from internet of things (IoT) gadgets, looking at preprocessing and feature extraction approaches, and then comparing methods used to identify human activities in smart homes, and highlighting their strengths and weaknesses across various fields. Numerous pertinent works were located, and their accomplishments were assessed. [ABSTRACT FROM AUTHOR]

The success of human activity recognition relies on the extraction of effective features, which can provide richer information for subsequent downstream tasks after embedding spatial fusion. However, due to the disruption of the original temporal relationships when integrating features from different variables, existing methods exert pressure on capturing temporal characteristics. In response to this issue, we propose a deep learning-based multi-channel architecture that combines two stages graph neural network and stacked attentional neural control differential equation method, named GANCDE. First, an adaptive graph architecture is employed to calculate similarity weights between different variables. Then, to obtain global information, multi-channel features are squeezed, and attention weights are calculated to overcome the drawbacks of graph convolution operations. This enables a more precise graph structure while eliminating redundant information. Next, the expression of the derivative of the temporal attention weight curve is obtained using tricubic interpolation and multi-scale convolution. Finally, the downstream task is completed using an N-layer convolutional architecture. Extensive experiments prove that GANCDE not only alleviates the issue of motion and non-motion features becoming similar caused by graph convolution, but also produces attention weight curves that better adhere to the continuity of actions. As a result, GANCDE achieves state-of-the-art performance in human activity recognition tasks. Specifically, on datasets such as WISDM, UCIHAR, and PAMAP2, the accuracy can reach 94.75, 93.50, and 96.37%, respectively. [ABSTRACT FROM AUTHOR]

Perception is difficult in video surveillance applications because of the presence of dynamic objects and constant environmental changes. This problem worsens when bad weather, including snow, rain, fog, dark nights, and bright daylight, interferes with the quality of perception. The proposed work aims to enhance the accuracy of camera-based perception for human activity detection in video surveillance during adverse weather conditions. To identify primary human activities, including walking on the road during severe weather, transfer learning from many adverse conditions using realtime images or videos has been proposed as an improvement for you look only once v8 (YOLOv8)-based human activity recognition in poor weather conditions. We collected and sorted training rates into frames from videos depicting human walking activity, their combined forms, and other subgroups, such as running and standing, based on their characteristics. The assessment of the detection efficiency of the previously described images and subgroups led to a comparison of the training weights. The use of realtime activity images for training greatly enhanced the detection performance when comparing the proposed test results to the existing YOLO base weights. Furthermore, a notable improvement in human activity efficiency was obtained by utilizing extra images and feature-related combinations of data techniques. [ABSTRACT FROM AUTHOR]

Human behavior recognition is the process of automatically identifying and analyzing multiple human behaviors using modern technology. From previous studies, we find that redundant features not only slow down the model training process and increase the structural complexity but also degrade the overall performance of the model. To overcome this problem, this paper investigates a temporal convolutional neural network (TCN) model based on improved sparrow search algorithm random forest (SSARF) feature selection to accurately identify human behavioral traits based on wearable devices. The model is based on the TCN classification model and incorporates a random forest with the sparrow optimization algorithm to perform dimensionality reduction on the original features, which is used to remove poorly correlated and unimportant features and retain effective features with a certain contribution rate to generate the optimal feature subset. In order to verify the reliability of the method, the performance of the model was evaluated on two public datasets, UCI Human Activity Recognition and WISDM, respectively, and 98.54% and 97.83% recognition accuracies were obtained, which were improved by 0.47% and 1.04% compared to the prefeature selection, but the number of features was reduced by 84.31% and 32.50% compared to the original feature set. In addition, we compared the TCN classification model with other deep learning models in terms of evaluation metrics such as F1 score, recall, precision, and accuracy, and the results showed that the TCN model outperformed the other control models in all four metrics. Meanwhile, it also outperforms the existing recognition methods in terms of accuracy and other aspects, which have some practical application value. [ABSTRACT FROM AUTHOR]

Human Activity Recognition models have potential to contribute to valuable and detailed knowledge of habitual physical activity for typically developing children and children with Cerebral Palsy. The main objective of the present study was to develop and validate two Human Activity Recognition models. One trained on data from typically developing children (n = 63), the second also including data from children with Cerebral Palsy (n = 16), engaging in standardised activities and free play. Our data was collected using accelerometers and ground truth was established with video annotations. Additionally, we aimed to investigate the influence of window settings on model performance. Utilizing the Extreme gradient boost (XGBoost) classifier, twelve sub-models were created, with 1-,3- and 5-seconds windows, with and without overlap. Both Human Activity Recognition models demonstrated excellent predictive capabilities (>92%) for standardised activities for both typically developing and Cerebral Palsy. From all window sizes, the 1-second window performed best for all test groups. Accuracy was slightly lower (>75%) for the Cerebral Palsy test group performing free play activities. The impact of window size and overlap varied depending on activity. In summary both Human Activity Recognition models effectively predict standardised activities, surpassing prior models for typically developing and children with Cerebral Palsy. Notably, the model trained on combined typically developing children and Cerebral Palsy data performed exemplary across all test groups. Researchers should select window settings aligned with their specific research objectives. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) deals with the automatic recognition of physical activities and plays a crucial role in healthcare and sports where wearable sensors and intelligent computational techniques are used. We propose a HAR algorithm that uses the smartphones accelerometer data for human activity recognition. In particular, we present a recurrent convolutional neural network-based HAR algorithm that combines a Convolutional Neural Network (CNN) to extract temporal features from the sensor data, a Fuzzy C-Means (FCM) clustering algorithm to cluster the features extracted by the CNN, and a Long Short-Term Memory (LSTM) network to learn the temporal dependencies between the features. We evaluate the proposed methodology on two distinct datasets: the MotionSense dataset and the WISDM dataset. We evaluate the proposed CNN-FCM-LSTM model on the publicly available MotionSense dataset to classify ten activity types: 1) walking upstairs, 2) walking downstairs, 3) jogging, 4) sitting, 5) standing, 6) level ground walking, 7) jumping jacks, 8) brushing teeth, 9) writing, and 10) eating. Next, we evaluate the model's performance on the WISDM dataset to assess its ability to generalize to unseen data. On the MotionSense test dataset, CNN-FCM-LSTM achieves a classification accuracy of 99.69%, a sensitivity of 99.62%, a specificity of 99.63%, and a false positive rate per hour (FPR/h) of 0.37%. Meanwhile, it achieves a classification accuracy of 97.27% on the WISDM dataset. The CNN-FCM-LSTM model's capability to classify a diverse range of activities within a single architecture is noteworthy. The results suggest that the proposed CNN-FCM-LSTM model using smartphone inputs is more accurate, reliable, and robust in detecting and classifying activities than the state-of-the-art models. It should be noted that activity recognition technology has the potential to aid in studying the underpinnings of physical activity, designing more effective training regimens, and simulating the rigors of competition in sports. [ABSTRACT FROM AUTHOR]

Public space is usually conceived as where people live, perceive, and interact with other people. The environment affects people in several different ways as well. The impact of environmental problems on humans is significant, affecting all human activities, including health and socio-economic development. Thus, there is a need to rethink how space is used. Dealing with the important needs raised by climate emergency, pandemic and digitization, the contributions of this paper consist in the creation of opportunities for developing generative approaches to space design and utilization. It is proposed GREEN PATH, an intelligent expert system for space planning. GREEN PATH uses human trajectories and deep learning methods to analyse and understand human behaviour for offering insights to layout designers. In particular, a Generative Adversarial Imitation Learning (GAIL) framework hybridised with classical reinforcement learning methods is proposed. An example of the classical reinforcement learning method used is continuous penalties, which allow us to model the shape of the trajectories and insert a bias, which is necessary for the generation, into the training. The structure of the framework and the formalisation of the problem to be solved allow for the evaluation of the results in terms of generation and prediction. The use case is a chosen retail domain that will serve as a demonstrator for optimising the layout environment and improving the shopping experience. Experiments were assessed on shoppers' trajectories obtained from four different stores, considering two years. [ABSTRACT FROM AUTHOR]

Since digital media has become increasingly popular, video processing has expanded in recent years. Video processing systems require high levels of processing, which is one of the challenges in this field. Various approaches, such as hardware upgrades, algorithmic optimizations, and removing unnecessary information, have been suggested to solve this problem. This study proposes a video saliency map based method that identifies the critical parts of the video and improves the system's overall performance. Using an image registration algorithm, the proposed method first removes the camera's motion. Subsequently, each video frame's color, edge, and gradient information are used to obtain a spatial saliency map. Combining spatial saliency with motion information derived from optical flow and color-based segmentation can produce a saliency map containing both motion and spatial data. A nonlinear function is suggested to properly combine the temporal and spatial saliency maps, which was optimized using a multi-objective genetic algorithm. The proposed saliency map method was added as a preprocessing step in several Human Action Recognition (HAR) systems based on deep learning, and its performance was evaluated. Furthermore, the proposed method was compared with similar methods based on saliency maps, and the superiority of the proposed method was confirmed. The results show that the proposed method can improve HAR efficiency by up to 6.5% relative to HAR methods with no preprocessing step and 3.9% compared to the HAR method containing a temporal saliency map. [ABSTRACT FROM AUTHOR]

This study examines the impact of sensor placement and multimodal sensor fusion on the performance of a Long Short-Term Memory (LSTM)-based model for human activity classification taking place in an agricultural harvesting scenario involving human-robot collaboration. Data were collected from twenty participants performing six distinct activities using five wearable inertial measurement units placed at various anatomical locations. The signals collected from the sensors were first processed to eliminate noise and then input into an LSTM neural network for recognizing features in sequential time-dependent data. Results indicated that the chest-mounted sensor provided the highest F1-score of 0.939, representing superior performance over other placements and combinations of them. Moreover, the magnetometer surpassed the accelerometer and gyroscope, highlighting its superior ability to capture crucial orientation and motion data related to the investigated activities. However, multimodal fusion of accelerometer, gyroscope, and magnetometer data showed the benefit of integrating data from different sensor types to improve classification accuracy. The study emphasizes the effectiveness of strategic sensor placement and fusion in optimizing human activity recognition, thus minimizing data requirements and computational expenses, and resulting in a cost-optimal system configuration. Overall, this research contributes to the development of more intelligent, safe, cost-effective adaptive synergistic systems that can be integrated into a variety of applications. [ABSTRACT FROM AUTHOR]

Obtaining discriminative joint features is crucial for skeleton-based human action recognition. Current models mainly focus on the research of skeleton topology encoding. However, their predefined topology is the same and fixed for all action samples, making it challenging to obtain discriminative joint features. Although some studies have considered the complex non-natural connection relationships between joints, the existing methods cannot fully capture this complexity by using high-order adjacency matrices or adding trainable parameters and instead increase the computation parameters. Therefore, this study constructs a novel adaptive channel-enhanced graph convolution (ACE-GCN) model for human action recognition. The model generates similar and affinity attention maps by encoding channel attention in the input features. These maps are complementarily applied to the input feature map and graph topology, which can realize the refinement of joint features and construct an adaptive and non-shared channel-based adjacency matrix. This method of constructing the adjacency matrix improves the model's capacity to capture intricate non-natural connections between joints, prevents the accumulation of unnecessary information, and minimizes the number of computational parameters. In addition, integrating the Edgeconv module into a multi-branch aggregation improves the model's ability to aggregate different scale and temporal features. Ultimately, comprehensive experiments were carried out on NTU-RGB+D 60 and NTU-RGB+D 120, which are two substantial datasets. On the NTU RGB+D 60 dataset, the accuracy of human action recognition was 92% (X-Sub) and 96.3% (X-View). The model achieved an accuracy of 96.6% on the NW-UCLA dataset. The experimental results confirm that the ACE-GCN exhibits superior recognition accuracy and lower computing complexity compared to current methodologies. [ABSTRACT FROM AUTHOR]

With the evolution of smart devices like smartphones, smartwatches, and other wearable devices, motion sensors have been integrated into these devices to collect data and analyze human activities. Consequently, sensor-based Human Activity Recognition (HAR) has emerged as a significant research area in the fields of ubiquitous computing and wearable computing. This paper presents a novel approach that employs Latent Dirichlet Allocation (LDA) to extract meaningful representations from activity signals. The method involves transforming the activity signal, which is a sequence of samples, into a sequence of discrete symbols using vector quantization. Subsequently, LDA is utilized to embed the symbol sequence into a fixed-length representation vector. Finally, a classifier is employed to classify the obtained representation vector. The effectiveness of the proposed method is evaluated using the UNIMIB-SHAR dataset. Experimental results demonstrate its competitive performance in terms of accuracy and F1-score metrics when compared to existing methods. Moreover, our method boasts a more lightweight architecture and incurs lower computational costs compared to deep learning-based approaches. The findings of this study contribute to the advancement of HAR and hold practical implications for HAR systems. [ABSTRACT FROM AUTHOR]

Mobile and wearable devices have revolutionized the field of continuous user activity monitoring. However, analyzing the vast and intricate data captured by the sensors of these devices poses significant challenges. Deep neural networks have shown remarkable accuracy in Human Activity Recognition (HAR), but their application on mobile and wearable devices is constrained by limited computational resources. To address this limitation, we propose a novel method called Knowledge Distillation for Human Activity Recognition (KD-HAR) that leverages the knowledge distillation technique to compress deep neural network models for HAR using inertial sensor data. Our approach transfers the acquired knowledge from high-complexity teacher models (state-of-the-art models) to student models with reduced complexity. This compression strategy allows us to maintain performance while keeping computational costs low. To assess the compression capabilities of our approach, we evaluate it using two popular databases (UCI-HAR and WISDM) comprising inertial sensor data from smartphones. Our results demonstrate that our method achieves competitive accuracy, even at compression rates ranging from 18 to 42 times the number of parameters compared to the original teacher model. [ABSTRACT FROM AUTHOR]

Nowadays, video surveillance systems are gaining increasing attention in the computer vision fields due to user demands for security purposes. Observing human movement and predicting such movement perception are promising due to video surveillance systems. In this work, Hierarchical Auto-Associative Polynomial Convolutional Neural Networks (HA-PCNN) with Garran Rufa Fish Optimization (GRFO) is proposed for Human Activity Recognition (HAR) using a video surveillance system. Initially, video surveillance systems-based human activity images are obtained, which are collected by video camera by recording daily human activities. After that, the input images are fed to a pre-processing approach named as Switched Mode Fuzzy Median Filter (SMFM) method. In this, the noise presented in the input images is reduced by applying the SMFM model to normalize the dataset and improve the image quality. After that, the pre-processed images are given to the developed Fast Discrete Curvelet Transform with Wrapping (FDCT-WRP)-based feature extraction method to extract the relevant features. Moreover, the extracted features are given to the HA-PCNN model for HA classification. Generally, the HA-PCNN method does not express any adoption of optimization methods for scaling the ideal parameters and classification. Here, Garra Rufa Fish Optimization (GRFO) is proposed to enhance the parameters of HA-PCNN. Thus, the proposed HA-PCNN-GRFO methodology can classify human activities like standing, sitting, running, walking and sleeping. By then the performance of the proposed HA-PCNN-GRFO methodology is evaluated using Python Platform, and metrics like recall, accuracy, F-measure, precision, and specificity are analyzed. Thus, the proposed HA-PCNN-GRFO approach achieved 97.3% average accuracy rate, 96.5% average recall, 97.2% average precision, 95.9% average specificity, and 96.8% average F1-score for classifying human activities using UCI HAR dataset. Also, the proposed HA-PCNN-GRFO approach is outperformed in HAR than the conventional approaches. [ABSTRACT FROM AUTHOR]

Current approaches to activity-assisted living (AAL) are complex, expensive, and intrusive, which reduces their practicality and end user acceptance. However, emerging technologies such as artificial intelligence and wireless communications offer new opportunities to enhance AAL systems. These improvements could potentially lower healthcare costs and reduce hospitalisations by enabling more effective identification, monitoring, and localisation of hazardous activities, ensuring rapid response to emergencies. In response to these challenges, this paper introduces the TransparentRFIDTag Wall (TRT-Wall), a novel system taht utilises a passive ultra-high frequency (UHF) radio-frequency identification (RFID) tag array combined with deep learning for contactless human activity monitoring. The TRT-Wall is tested on five distinct activities: sitting, standing, walking (in both directions), and no-activity. Experimental results demonstrate that the TRT-Wall distinguishes these activities with an impressive average accuracy of 95.6 % under four distinct distances (2, 2.5, 3.5 and 4.5 m) by capturing the RSSI and phase information. This suggests that our proposed contactless AAL system possesses significant potential to enhance elderly patient-assisted living. [ABSTRACT FROM AUTHOR]

Wearable sensor-based human activity recognition (HAR) methods hold considerable promise for upper-level control in exoskeleton systems. However, such methods tend to overlook the critical role of data quality and still encounter challenges in cross-subject adaptation. To address this, we propose an active learning framework that integrates the relation network architecture with data sampling techniques. Initially, target data are used to fine tune two auxiliary classifiers of the pre-trained model, thereby establishing subject-specific classification boundaries. Subsequently, we assess the significance of the target data based on classifier discrepancy and partition the data into sample and template sets. Finally, the sampled data and a category clustering algorithm are employed to tune model parameters and optimize template data distribution, respectively. This approach facilitates the adaptation of the model to the target subject, enhancing both accuracy and generalizability. To evaluate the effectiveness of the proposed adaptation framework, we conducted evaluation experiments on a public dataset and a self-constructed electromyography (EMG) dataset. Experimental results demonstrate that our method outperforms the compared methods across all three statistical metrics. Furthermore, ablation experiments highlight the necessity of data screening. Our work underscores the practical feasibility of implementing user-independent HAR methods in exoskeleton control systems. [ABSTRACT FROM AUTHOR]

Background: Accurately measuring energy expenditure during physical activity outside of the laboratory is challenging, especially on a large scale. Thigh-worn accelerometers have gained popularity due to the possibility to accurately detect physical activity types. The use of machine learning techniques for activity classification and energy expenditure prediction may improve accuracy over current methods. Here, we developed a novel composite energy expenditure estimation model by combining an activity classification model with a stride specific energy expenditure model for walking, running, and cycling. Methods: We first trained a supervised deep learning activity classification model using pooled data from available adult accelerometer datasets. The composite energy expenditure model was then developed and validated using additional data based on a sample of 69 healthy adult participants (49% female; age = 25.2 ± 5.8 years) who completed a standardised activity protocol with indirect calorimetry as the reference measure. Results: The activity classification model showed an overall accuracy of 99.7% across all five activity types during validation. The composite model for estimating energy expenditure achieved a mean absolute percentage error of 10.9%. For running, walking, and cycling, the composite model achieved a mean absolute percentage error of 6.6%, 7.9% and 16.1%, respectively. Conclusions: The integration of thigh-worn accelerometers with machine learning models provides a highly accurate method for classifying physical activity types and estimating energy expenditure. Our novel composite model approach improves the accuracy of energy expenditure measurements and supports better monitoring and assessment methods in non-laboratory settings. [ABSTRACT FROM AUTHOR]

Recent generation Microsoft Kinect Camera captures a series of multimodal signals that provide RGB video, depth sequences, and skeleton information, thus it becomes an option to achieve enhanced human action recognition performance by fusing different data modalities. However, most existing fusion methods simply fuse different features, which ignores the underlying semantics between different models, leading to a lack of accuracy. In addition, there exists a large amount of background noise. In this work, we propose a Vision Transformer-based Bilinear Pooling and Attention Network (VT-BPAN) fusion mechanism for human action recognition. This work improves the recognition accuracy in the following ways: 1) An effective two-stream feature pooling and fusion mechanism is proposed. The RGB frames and skeleton are fused to enhance the spatio-temporal feature representation. 2) A spatial lightweight multiscale vision Transformer is proposed, which can reduce the cost of computing. The framework is evaluated based on three widely used video action datasets, and the proposed approach performs a more comparable performance with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) has gained much attention since sensor technology has become more advanced and cost-effective. HAR is a process of identifying the daily living activities of an individual with the help of an efficient learning algorithm and prospective user-generated datasets. This paper addresses the technical advancement and classification of HAR systems in detail. Design issues, future opportunities, recent state-of-the-art related works, and a generic framework for activity recognition are discussed in a comprehensive manner with analytical discussion. Different publicly available datasets with their features and incorporated sensors are also descr-processing techniques with various performance metrics like - Accuracy, F1-score, Precision, Recall, Computational times and evaluation schemes are discussed for the comprehensive understanding of the Activity Recognition Chain (ARC). Different learning algorithms are exploited and compared for learning-based performance comparison. For each specific module of this paper, a compendious number of references is also cited for easy referencing. The main aim of this study is to give the readers an easy hands-on implementation in the field of HAR with verifiable evidence of different design issues. [ABSTRACT FROM AUTHOR]

In recent years, human activity recognition (HAR) has been widely used in medical rehabilitation, smart home and other fields. Currently, the recognition performance highly depends on feature extraction and effective algorithm. On the one hand, traditional manual feature extraction and classification algorithms hinder the improvement of HAR. On the other hand, the latest deep learning technology can automatically process data and extract features, but it faces the problems of poor feature quality and information loss. In order to solve this problem, this paper proposes a new recognition method using only wearable sensor data. In the feature extraction stage, the axis information of each sensor is extracted separately into one-dimensional data, and information of all axes is integrated into a two-dimensional graph. Then, two deep convolutional neural network models are designed to train the features based on one-dimensional data and two-dimensional graph respectively. Finally, weighted voting method is used to get the classification results. Experiments have shown that the average recognition accuracy of the method in this paper is about 3% higher than that of other HAR deep neural network methods, which shown the advantage of the method in this paper in obtaining better recognition result with limited data. [ABSTRACT FROM AUTHOR]

Smartphone-based Human Activity Recognition (HAR) identifies human movements using inertial signals gathered from multiple smartphone sensors. Generally, these signals are stacked as one (data-level fusion) and fed into deep learning algorithms for feature extractions. This research studies feature-level fusion, individually processing inertial signals from each sensor, and proposes a lightweight deep temporal learning model, Feature-Level Fusion Multi-Sensor Aggregation Temporal Network (FLF-MSATN), that performs feature extraction on inertial signals from each sensor separately. The raw signals, segmented into equally sized time windows, are passed into individual Dilated-Pooled Convolutional Heads (DPC Heads) for temporal feature analysis. Each DPC Head has a spatiotemporal block containing dilated causal convolutions and average pooling, to extract underlying patterns. The DPC Heads' outputs are concatenated and passed into a Global Average Pooling layer to generate a condensed confidence map before activity classification. FLF-MSATN is assessed using a subject-independent protocol on a publicly available HAR dataset, UCI HAR, and a selfcollected HAR dataset, achieving 96.67% and 82.70% accuracies, respectively. A Data-Level Fusion MSATN is built to compare and verify the model performance attained by the proposed FLF-MSATN. The empirical results show that implementing FLF-MSATN enhances the accuracy by ~3.4% for UCI HAR and ~9.68% for self-collected datasets. [ABSTRACT FROM AUTHOR]

This study investigates the feasibility of using a basic 24 GHz one-dimensional (1D) radar for Human Activity Recognition (HAR), focusing on differentiating between walking and standing movements. We evaluate the radar's performance using various machine learning models, including K-means, GMM, SVM, and LSTM. Using the silhouette score and the Davies-Bouldin index, we evaluate the intra- and interclass results of K-means and GMM, while SVM and LSTM are used to analyze their performance. The results indicate that the LSTM model achieves high accuracy in both vertical and horizontal dimensions, with precision, recall, and F1-scores all above 98% for both standing and walking movements. However, the SVM model faces challenges in horizontal movement detection, consistent with the unsupervised learning results where the inter-class and intra-class distances for the horizontal dimension are not significant, making differentiation difficult. These findings delineate the boundaries and capabilities of a lower-specification radar for HAR, providing insights into its practical applications and limitations. [ABSTRACT FROM AUTHOR]

This study investigates the effectiveness of an education intervention that targets low‐income farmers regarding the consequences of agricultural burning. Agricultural burning is a major contributor to carbon emissions, second only to those from the energy sector. Using three treatment arms and a control group, I provided rural farmers in Nigeria with information on the social (health impacts, wildfire spread, biodiversity loss) and economic (income implications) consequences of agricultural burning. The third group received information that combined aspects from the first and second treatments, offering a comprehensive view of the effects of agricultural burning. The analysis suggests that exposure to this information prompts farmers to view agricultural burning as unacceptable, reducing their likelihood of engaging in this practice during the upcoming planting season. In addition, exposed farmers demonstrate a higher willingness to pay nominal fees for government services, such as weed disposal. This outcome demonstrates their support for sustainable farming practices, rather than resorting to burning. The influence of economic information is particularly noteworthy; farmers exposed to it demonstrate a higher willingness to pay such fees. Furthermore, the interventions led to a shift in farmers' perceptions regarding the primary drivers of climate change, with increased recognition of human activity as the dominant factor. The study highlights how the gender of the farmer and their religious beliefs influence attitudes towards environmental protection. Specifically, male and less religious farmers tend to be more responsive to the interventions. These findings provide valuable insights into the effectiveness of "low‐cost" educational interventions in promoting sustainable agricultural practices among low‐income communities. [ABSTRACT FROM AUTHOR]

Research on smartphone-based human activity recognition (HAR) is prevalent in the field of healthcare, especially for elderly activity monitoring. Researchers usually propose to use of accelerometers, gyroscopes or magnetometers that are equipped in smartphones as an individual sensing modality for human activity recognition. However, any of these alone is limited in capturing comprehensive movement information for accurate human activity analysis. Thus, we propose a smartphone-based HAR approach by leveraging the inertial signals captured by these three sensors to classify human activities. These heterogeneous sensors deliver information on various aspects of nature, motion and orientation, offering a richer set of features for more accurate representations of the activities. Hence, a deep learning approach that amalgamates long short-term memory (LSTM) in temporal convolutional network (TCN) is proposed. We use independent temporal convolutional networks, coined as temporal convolutional streams, to independently analyse the temporal data of each sensing modality. We name this architecture multi-stream TC-LSTM. The performance of multi-stream TC-LSTM is assessed on the self-collected elderly activity database. Empirical results exhibit that multi-stream TC-LSTM outperforms the existing machine learning and deep learning models, with an F1 score of 98.3%. [ABSTRACT FROM AUTHOR]

Human action recognition from skeleton motion sequences is widely applied in various fields such as virtual reality, human-computer interaction and kinematic rehabilitation. With the wide use of graph neural networks for extracting spatial features from skeleton anatomy connectivity, spatial-temporal extension of single graph models on human skeleton may improve the network performance. In this paper, we propose a priori separation graph convolution (PS-GCN) network composition with a priori mixed GCN by introducing a hypergraph representation of the skeleton spatial features, and a dynamic adaptive GCN to describe the respective graph model for each sample at each layer of the network of spatial features. For temporal feature analysis, a global attention unit is added to describe the long-term relationship. Moreover, a feature fusion structure is applied for short-term temporal features in the input of the network. The proposed model is evaluated on the NTU-RGB+D, NTU-RGB+D 120 and NW-UCLA datasets via a comprehensive ablative study. The results show that our model is comparable in accuracy to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]