Human Activity Identification Research Articles

Human Action Recognition: A Taxonomy-Based Survey, Updates, and Opportunities.

Human action recognition systems use data collected from a wide range of sensors to accurately identify and interpret human actions. One of the most challenging issues for computer vision is the automatic and precise identification of human activities. A significant increase in feature learning-based representations for action recognition has emerged in recent years, due to the widespread use of deep learning-based features. This study presents an in-depth analysis of human activity recognition that investigates recent developments in computer vision. Augmented reality, human-computer interaction, cybersecurity, home monitoring, and surveillance cameras are all examples of computer vision applications that often go in conjunction with human action detection. We give a taxonomy-based, rigorous study of human activity recognition techniques, discussing the best ways to acquire human action features, derived using RGB and depth data, as well as the latest research on deep learning and hand-crafted techniques. We also explain a generic architecture to recognize human actions in the real world and its current prominent research topic. At long last, we are able to offer some study analysis concepts and proposals for academics. In-depth researchers of human action recognition will find this review an effective tool.

Human Activity Identification and Suspicious Behaviour Detection System

Recognizing human action has been one of the biggest challenges in computer vision for the past two decades. Recently, it has become feasible to extract precise and cost-effective skeleton information. Our proposed system utilizes a cut-based framework to identify human actions using skeleton data. By using a single stationary camera as input, this system can recognize various continuous human activities in real-time, including raising or waving one or more hands, sitting down, and bending over. The recognition process is based on machine learning. Firstly, a dataset with the human body's coordinates is created. Then, a training model is developed using Logistic Regression and an outcome to be achieved. Finally, the model is utilized to identify human activities such as sitting, running, and waking up, as well as recognizing suspicious behaviour.

A new method for human activity identification using convolutional neural networks

Body fitness monitoring applications are using mobile sensors to identify human activities. Human activity identification is a challenging task because of the wide availability of human activities. This paper proposes a novel technique that extracts the discriminative dimensions for human activity identification. Particularly, a novel technique with convolutional neural networks (CNN) is used for catching dependency. A deep convolutional neural network (DCNN) consists of two different types of layers, convolutional and pooling are used. The depth of each filter increases from left to right in the network. Three activities like walking, running, remaining still are collected from smart mobile sensors. The axis like x, y, and z information was transferred with column vector magnitude information and utilised for studying or training CNN. Experimental results show that CNN-based method achieves 93.67% accuracy than the baseline random forest approach's 89.20%.

Fire Hawk Optimizer with Deep Learning Enabled Human Activity Recognition

Human-Computer Interaction (HCI) is a sub-area within computer science focused on the study of the communication between people (users) and computers and the evaluation, implementation, and design of user interfaces for computer systems. HCI has accomplished effective incorporation of the human factors and software engineering of computing systems through the methods and concepts of cognitive science. Usability is an aspect of HCI dedicated to guaranteeing that human–computer communication is, amongst other things, efficient, effective, and sustaining for the user. Simultaneously, Human activity recognition (HAR) aim is to identify actions from a sequence of observations on the activities of subjects and the environmental conditions. The vision-based HAR study is the basis of several applications involving health care, HCI, and video surveillance. This article develops a Fire Hawk Optimizer with Deep Learning Enabled Activity Recognition (FHODL-AR) on HCI driven usability. In the presented FHODL-AR technique, the input images are investigated for the identification of different human activities. For feature extraction, a modified SqueezeNet model is introduced by the inclusion of few bypass connections to the SqueezeNet among Fire modules. Besides, the FHO algorithm is utilized as a hyperparameter optimization algorithm, which in turn boosts the classification performance. To detect and categorize different kinds of activities, probabilistic neural network (PNN) classifier is applied. The experimental validation of the FHODL-AR technique is tested using benchmark datasets, and the outcomes reported the improvements of the FHODL-AR technique over other recent approaches.

A new method for human activity identification using convolutional neural networks

A new method for human activity identification using convolutional neural networks

Exploring police methods and challenges of identifying human trafficking activities in the City of Tshwane Metropolitan Municipality, South Africa

This article explored police methods and challenges in the identification of human trafficking activities by the South African Police Service (SAPS). A qualitative research method was employed in this study that used semi-structured interviews to collect data. Participants were sourced from three key stakeholder groups: (1) the SAPS (Headquarters), (2) Sunnyside Community Service Centre, and (3) Directorate for Priority Crime Investigation (DPCI) officials with expertise related to human trafficking. This sample comprised 15 participants and a purposive sampling procedure was adopted. The study found that there are various methods of identifying human trafficking identified by the SAPS in the City of Tshwane Metropolitan Municipality (CTMM). Furthermore, the findings highlighted that human trafficking has a national dimension despite that trafficking could occur within the same province or policing area. However, it remains a concern that policing methods to reduce the scourge are not effectively implemented hence an increased rate of human trafficking not only in the CTMM policing area but in many parts of South Africa. It was also found that in the process of identifying human trafficking activities, the SAPS is often faced with various challenges that may be linked to ineffective implementation of methods of identifying human trafficking activities

Wearable Sensors for Evaluation Over Smart Home Using Sequential Minimization Optimization-based Random Forest

In our everyday life records, human activity identification utilizing MotionNode sensors is becoming more and more prominent. A difficult issue in ubiquitous computing and HCI is providing reliable data on human actions and behaviors. In this study, we put forward a practical methodology for incorporating statistical data into Sequential Minimization Optimization-based random forests. In order to extract useful features, we first prepared a 1-Dimensional Hadamard transform wavelet and a 1-Dimensional Local Binary Pattern-dependent extraction technique. Over two benchmark datasets, the University of Southern California-Human Activities Dataset, and the IM-Sporting Behaviors datasets, we employed sequential minimum optimization together with Random Forest to classify activities. Experimental findings demonstrate that our suggested model may successfully be utilized to identify strong human actions for matters related to efficiency and accuracy, and may challenge with existing cutting-edge approaches.

Transportation Mode Detection Using Temporal Convolutional Networks Based on Sensors Integrated into Smartphones.

In recent years, with the development of science and technology, people have more and more choices for daily travel. However, assisting with various mobile intelligent services by transportation mode detection has become more urgent for the refinement of human activity identification. Although much work has been done on transportation mode detection, accurate and reliable transportation mode detection remains challenging. In this paper, we propose a novel transportation mode detection algorithm, namely T2Trans, based on a temporal convolutional network (i.e., TCN), which employs multiple lightweight sensors integrated into a phone. The feature representation learning of multiple preprocessed sensor data using temporal convolutional networks can improve transportation mode detection accuracy and enhance learning efficiency. Extensive experimental results demonstrated that our algorithm attains a macro F1-score of 86.42% on the real-world SHL dataset and 88.37% on the HTC dataset, with an average accuracy of 86.37% on the SHL dataset and 89.13% on the HTC dataset. Our model can better identify eight transportation modes, including stationary, walking, running, cycling, car, bus, subway, and train, with better transportation mode detection accuracy, and outperform other benchmark algorithms.

Multi action recognition using machine learning

One of the most exciting and useful computer vision research topics is automated human activity identification. The majority of existing research, as well as most traditional approaches and classic neural networks, disregard the In video sequences, the appearance and patterns of motion are important. Individuals are unableIn video sequences, the appearance and patterns of motion are important.. This paper outlines a system for detecting, recognising, and summarising diverse human actions.The multiple action detection method takes the silhouettes of human bodies and then uses motion detection and tracking to create a unique sequence for each one.Based on the Each of the recovered sequences is then separated into shots based on the similarity between each pair of frames.show the sequence's homogenous activity. The activity is identified by looking at thedata oriented gradient (HOG) histogram of the frames in each shot's Temporal Difference Map (TDMap). comparing generated HOG to previous HOGs in the early stages of training. Making use of the TDMap image and a proposed CNN model, we can additionally recognise the action. Action summarising is carried out for each person found.

EfficientFi: Toward Large-Scale Lightweight WiFi Sensing via CSI Compression

WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access. Recently, besides network services, WiFi sensing is appealing in smart homes since it is device-free, cost-effective and privacy-preserving. Though numerous WiFi sensing methods have been developed, most of them only consider single smart home scenario. Without the connection of powerful cloud server and massive users, large-scale WiFi sensing is still difficult. In this paper, we firstly analyze and summarize these obstacles, and propose an efficient large-scale WiFi sensing framework, namely EfficientFi. The EfficientFi works with edge computing at WiFi APs and cloud computing at center servers. It consists of a novel deep neural network that can compress fine-grained WiFi Channel State Information (CSI) at edge, restore CSI at cloud, and perform sensing tasks simultaneously. A quantized auto-encoder and a joint classifier are designed to achieve these goals in an end-to-end fashion. To the best of our knowledge, the EfficientFi is the first IoT-cloud-enabled WiFi sensing framework that significantly reduces communication overhead while realizing sensing tasks accurately. We utilized human activity recognition and identification via WiFi sensing as two case studies, and conduct extensive experiments to evaluate the EfficientFi. The results show that it compresses CSI data from 1.368Mb/s to 0.768Kb/s with extremely low error of data reconstruction and achieves over 98% accuracy for human activity recognition.

Daily life human activities recognition using a novel AR‐DenseNet

SUMMARYWith the introduction of mobile‐wearable gadgets, the embedding of health‐tracking capabilities has advanced dramatically. The Covid‐19 years have accelerated research toward wearable sensor‐based health monitoring. One of the most important applications in health monitoring is human activity identification. Daily behaviors like walking, sitting and jogging, as well as crucial activities such as falling forward and backward, provide a barrier in HAR (human action recognition) since they are semantically comparable. Previously developed deep learning algorithms have addressed some of these issues. However, these algorithms are hindered by a lack of training data. To cope with nonuniform samples in the human activities data, which can lead to overfitting results, this work introduces the synthetic minority oversampling approach. This article proposes a unique configuration of stacked convolutional neural network (CNN)‐AR‐DenseNet. With Bayesian optimization, the parameters of AR‐DenseNet are optimally optimized. When compared to state‐of‐the‐art stacked CNN network methods, the classification accuracy improved by up to 3.22%, with a substantial improvement of 5.8% over the standard CNN algorithm.

Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images.

The identification of human activities from videos is important for many applications. For such a task, three-dimensional (3D) depth images or image sequences (videos) can be used, which represent the positioning information of the objects in a 3D scene obtained from depth sensors. This paper presents a framework to create foreground–background masks from depth images for human body segmentation. The framework can be used to speed up the manual depth image annotation process with no semantics known beforehand and can apply segmentation using a performant algorithm while the user only adjusts the parameters, or corrects the automatic segmentation results, or gives it hints by drawing a boundary of the desired object. The approach has been tested using two different datasets with a human in a real-world closed environment. The solution has provided promising results in terms of reducing the manual segmentation time from the perspective of the processing time as well as the human input time.

Pruning Growing Self-Organizing Map Network for Human Physical Activity Identification.

Human physical activity identification based on wearable sensors is of great significance to human health analysis. A large number of machine learning models have been applied to human physical activity identification and achieved remarkable results. However, most human physical activity identification models can only be trained based on labeled data, and it is difficult to obtain enough labeled data, which leads to weak generalization ability of the model. A Pruning Growing SOM model is proposed in this paper to address the limitations of small-scale labeled dataset, which is unsupervised in the training stage, and then only a small amount of labeled data is used for labeling neurons to reduce dependency on labeled data. In training stage, the inactive neurons in network can be deleted by pruning mechanism, which makes the model more consistent with the data distribution and improves the identification accuracy even on unbalanced dataset, especially for the action categories with poor identification effect. In addition, the pruning mechanism can also speed up the inference of the model by controlling its scale.

RF-Sensing: A New Way to Observe Surroundings

Radio frequency sensing (RF-sensing) is an emerging field assisting vision technology for object detection, tracking, and various such use cases. RF-Sensing technology uses radio signals and their reflections in order to capture the surrounding details and then applies artificial intelligence algorithms to sense the objects. RF-sensing has advantage over the existing vision technology when it comes to low light conditions, privacy concerns, and far-range scenarios. In this paper, we propose different RF-sensing methods for person identification (PI), human activity identification (HAI), and surrounding-location identification (SLI). Here, we make use of data generated from millimeter-Wave sensors and pre-process it using signal processing techniques before feeding it to deep learning (DL) based classifiers. For PI and SLI, we propose a DL network consisting of convolutional neural network (CNN) and long short term memory (LSTM) blocks. Here, first the input is passed through the CNN layers and then followed by the LSTM. For HAI, we propose a hierarchical classifier consisting of two stages. First, similar activities are clubbed together and the coarse level classifier is trained to distinguish among the non-similar activities. This is followed by fine level classifiers, which are trained to distinguish between the those activities which are deemed to be similar while training the coarse level classifier. While testing, we employ the coarse level classifier unconditionally. The fine level classifier is employed only when the coarse level classifier’s output class corresponds to that of similar activity. We use the output of the hierarchical classifier to determine the activity. Further, we show that the proposed algorithms for the PI and SLI are able to predict accurately among 5 persons and among 5 different surrounding-locations respectively and the proposed hierarchical classifier for HAI, which is used to classify among 11 different activities, shows an improvement of ≈ 4% compared to other DL based architectures in the literature.

RNN-based deep learning for physical activity recognition using smartwatch sensors: A case study of simple and complex activity recognition.

Currently, identification of complex human activities is experiencing exponential growth through the use of deep learning algorithms. Conventional strategies for recognizing human activity generally rely on handcrafted characteristics from heuristic processes in time and frequency domains. The advancement of deep learning algorithms has addressed most of these issues by automatically extracting features from multimodal sensors to correctly classify human physical activity. This study proposed an attention-based bidirectional gated recurrent unit as Att-BiGRU to enhance recurrent neural networks. This deep learning model allowed flexible forwarding and reverse sequences to extract temporal-dependent characteristics for efficient complex activity recognition. The retrieved temporal characteristics were then used to exemplify essential information through an attention mechanism. A human activity recognition (HAR) methodology combined with our proposed model was evaluated using the publicly available datasets containing physical activity data collected by accelerometers and gyroscopes incorporated in a wristwatch. Simulation experiments showed that attention mechanisms significantly enhanced performance in recognizing complex human activity.

Multi-Scenario Model of Plastic Waste Accumulation Potential in Indonesia Using Integrated Remote Sensing, Statistic and Socio-Demographic Data

As a significant contributor of plastic waste to the marine environment, Indonesia is striving to construct a national strategy for reducing plastic debris. Hence, the primary aim of this study is to create a model for plastic waste quantity originating from the mainland, accumulated in estuaries. This was achieved by compiling baseline data of marine plastic disposal from the mainland via comprehensive contextualisation of data generated by remote sensing technology and spatial analysis. The parameters used in this study cover plastic waste generation, land cover, population distribution, and human activity identification. These parameters were then used to generate the plastic waste disposal index; that is, the distribution of waste from the mainland, flowing through the river, and ultimately accumulating in the estuary. The plastic waste distribution is calculated based on the weighting method and overlap analysis between land and coastal areas. The results indicate that 0.6% of Indonesia, including metropolitan cities, account for the highest generation of plastic waste. Indicating of plastic releases to the ocean applied by of developing three different scenarios with the highest estimation 11.94 tonnes on a daily basis in an urban area, intended as the baseline study for setting priority zone for plastic waste management.

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

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

Feature fusion using deep learning for smartphone based human activity recognition.

Identification of human physical activities is an active research area since long due to its application in personalized health and fitness monitoring. The performance accuracy of human activity recognition (HAR) models mainly depend on the features which are extracted from domain knowledge. The features are the input of the classification algorithm to efficiently identify human physical activities. Manually extracted features (handcrafted) need expert domain knowledge. Thus these features have significant importance to identify different human activities. Recently deep learning methods are utilized to extract the features automatically from raw sensory data for HAR models. However, state-of-the-art HAR literature established that the importance of handcrafted features can’t be ignored as it is extracted from expert domain knowledge. Thus, in this paper we use the fusion of both the handcrafted features and automatically extracted features using deep learning (DL) for HAR model to enhance the performance of HAR. Extensive experimental results demonstrate that our proposed feature fusion based HAR model gives higher accuracy compared with state-of-the-art HAR literature for both the self collected and public dataset.

Video Analytics Framework for Human Action Recognition

Human action recognition (HAR) is an essential but challenging task for observing human movements. This problem encompasses the observations of variations in human movement and activity identification by machine learning algorithms. This article addresses the challenges in activity recognition by implementing and experimenting an intelligent segmentation, features reduction and selection framework. A novel approach has been introduced for the fusion of segmented frames and multi-level features of interests are extracted. An entropy-skewness based features reduction technique has been implemented and the reduced features are converted into a codebook by serial based fusion. A custom made genetic algorithm is implemented on the constructed features codebook in order to select the strong and well-known features. The features are exploited by a multi-class SVM for action identification. Comprehensive experimental results are undertaken on four action datasets, namely, Weizmann, KTH, Muhavi, and WVU multi-view. We achieved the recognition rate of 96.80%, 100%, 100%, and 100% respectively. Analysis reveals that the proposed action recognition approach is efficient and well accurate as compare to existing approaches.

Smartphone Motion Sensor-Based Complex Human Activity Identification Using Deep Stacked Autoencoder Algorithm for Enhanced Smart Healthcare System.

Human motion analysis using a smartphone-embedded accelerometer sensor provided important context for the identification of static, dynamic, and complex sequence of activities. Research in smartphone-based motion analysis are implemented for tasks, such as health status monitoring, fall detection and prevention, energy expenditure estimation, and emotion detection. However, current methods, in this regard, assume that the device is tightly attached to a pre-determined position and orientation, which might cause performance degradation in accelerometer data due to changing orientation. Therefore, it is challenging to accurately and automatically identify activity details as a result of the complexity and orientation inconsistencies of the smartphone. Furthermore, the current activity identification methods utilize conventional machine learning algorithms that are application dependent. Moreover, it is difficult to model the hierarchical and temporal dynamic nature of the current, complex, activity identification process. This paper aims to propose a deep stacked autoencoder algorithm, and orientation invariant features, for complex human activity identification. The proposed approach is made up of various stages. First, we computed the magnitude norm vector and rotation feature (pitch and roll angles) to augment the three-axis dimensions (3-D) of the accelerometer sensor. Second, we propose a deep stacked autoencoder based deep learning algorithm to automatically extract compact feature representation from the motion sensor data. The results show that the proposed integration of the deep learning algorithm, and orientation invariant features, can accurately recognize complex activity details using only smartphone accelerometer data. The proposed deep stacked autoencoder method achieved 97.13% identification accuracy compared to the conventional machine learning methods and the deep belief network algorithm. The results suggest the impact of the proposed method to improve a smartphone-based complex human activity identification framework.