TransTM:A device-free method based on time-streaming multiscale transformer for human activity recognition

RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.

Intelligent Deep Learning Enabled Human Activity Recognition for Improved Medical Services

Human Activity Recognition(HAR)has been made simple in recent years,thanks to recent advancements made in Artificial Intelligence(AI)techni-ques.These techniques are applied in several areas like security,surveillance,healthcare,human-robot interaction,and entertainment.Since wearable sensor-based HAR system includes in-built sensors,human activities can be categorized based on sensor values.Further,it can also be employed in other applications such as gait diagnosis,observation of children/adult’s cognitive nature,stroke-patient hospital direction,Epilepsy and Parkinson’s disease examination,etc.Recently-developed Artificial Intelligence(AI)techniques,especially Deep Learning(DL)models can be deployed to accomplish effective outcomes on HAR process.With this motivation,the current research paper focuses on designing Intelligent Hyperparameter Tuned Deep Learning-based HAR(IHPTDL-HAR)technique in healthcare environment.The proposed IHPTDL-HAR technique aims at recogniz-ing the human actions in healthcare environment and helps the patients in mana-ging their healthcare service.In addition,the presented model makes use of Hierarchical Clustering(HC)-based outlier detection technique to remove the out-liers.IHPTDL-HAR technique incorporates DL-based Deep Belief Network(DBN)model to recognize the activities of users.Moreover,Harris Hawks Opti-mization(HHO)algorithm is used for hyperparameter tuning of DBN model.Finally,a comprehensive experimental analysis was conducted upon benchmark dataset and the results were examined under different aspects.The experimental results demonstrate that the proposed IHPTDL-HAR technique is a superior per-former compared to other recent techniques under different measures.

Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

Human Activity Recognition(HAR)is an active research area due to its applications in pervasive computing,human-computer interaction,artificial intelligence,health care,and social sciences.Moreover,dynamic environments and anthropometric differences between individuals make it harder to recognize actions.This study focused on human activity in video sequences acquired with an RGB camera because of its vast range of real-world applications.It uses two-stream ConvNet to extract spatial and temporal information and proposes a fine-tuned deep neural network.Moreover,the transfer learning paradigm is adopted to extract varied and fixed frames while reusing object identification information.Six state-of-the-art pre-trained models are exploited to find the best model for spatial feature extraction.For temporal sequence,this study uses dense optical flow following the two-stream ConvNet and Bidirectional Long Short TermMemory(BiLSTM)to capture longtermdependencies.Two state-of-the-art datasets,UCF101 and HMDB51,are used for evaluation purposes.In addition,seven state-of-the-art optimizers are used to fine-tune the proposed network parameters.Furthermore,this study utilizes an ensemble mechanism to aggregate spatial-temporal features using a four-stream Convolutional Neural Network(CNN),where two streams use RGB data.In contrast,the other uses optical flow images.Finally,the proposed ensemble approach using max hard voting outperforms state-ofthe-art methods with 96.30%and 90.07%accuracies on the UCF101 and HMDB51 datasets.

Optimal Deep Convolutional Neural Network with Pose Estimation for Human Activity Recognition

Human Action Recognition(HAR)and pose estimation from videos have gained significant attention among research communities due to its applica-tion in several areas namely intelligent surveillance,human robot interaction,robot vision,etc.Though considerable improvements have been made in recent days,design of an effective and accurate action recognition model is yet a difficult process owing to the existence of different obstacles such as variations in camera angle,occlusion,background,movement speed,and so on.From the literature,it is observed that hard to deal with the temporal dimension in the action recognition process.Convolutional neural network(CNN)models could be used widely to solve this.With this motivation,this study designs a novel key point extraction with deep convolutional neural networks based pose estimation(KPE-DCNN)model for activity recognition.The KPE-DCNN technique initially converts the input video into a sequence of frames followed by a three stage process namely key point extraction,hyperparameter tuning,and pose estimation.In the keypoint extraction process an OpenPose model is designed to compute the accurate key-points in the human pose.Then,an optimal DCNN model is developed to classify the human activities label based on the extracted key points.For improving the training process of the DCNN technique,RMSProp optimizer is used to optimally adjust the hyperparameters such as learning rate,batch size,and epoch count.The experimental results tested using benchmark dataset like UCF sports dataset showed that KPE-DCNN technique is able to achieve good results compared with benchmark algorithms like CNN,DBN,SVM,STAL,T-CNN and so on.

Research on Human Activity Recognition Algorithm Based on LSTM-1DCNN

With the rapid advancement of wearable devices,Human Activities Recognition(HAR)based on these devices has emerged as a prominent research field.The objective of this study is to enhance the recognition performance of HAR by proposing an LSTM-1DCNN recognition algorithm that utilizes a single triaxial accelerometer.This algorithm comprises two branches:one branch consists of a Long and Short-Term Memory Network(LSTM),while the other parallel branch incorporates a one-dimensional Convolutional Neural Network(1DCNN).The parallel architecture of LSTM-1DCNN initially extracts spatial and temporal features from the accelerometer data separately,which are then concatenated and fed into a fully connected neural network for information fusion.In the LSTM-1DCNN architecture,the 1DCNN branch primarily focuses on extracting spatial features during convolution operations,whereas the LSTM branch mainly captures temporal features.Nine sets of accelerometer data from five publicly available HAR datasets are employed for training and evaluation purposes.The performance of the proposed LSTM-1DCNN model is compared with five other HAR algorithms including Decision Tree,Random Forest,Support Vector Machine,1DCNN,and LSTM on these five public datasets.Experimental results demonstrate that the F1-score achieved by the proposed LSTM-1DCNN ranges from 90.36%to 99.68%,with a mean value of 96.22%and standard deviation of 0.03 across all evaluated metrics on these five public datasets-outperforming other existing HAR algorithms significantly in terms of evaluation metrics used in this study.Finally the proposed LSTM-1DCNN is validated in real-world applications by collecting acceleration data of seven human activities for training and testing purposes.Subsequently,the trained HAR algorithm is deployed on Android phones to evaluate its performance.Experimental results demonstrate that the proposed LSTM-1DCNN algorithm achieves an impressive F1-score of 97.67%on our self-built dataset.In conclusion,the fusion of temporal and spatial information in the measured data contributes to the excellent HAR performance and robustness exhibited by the proposed 1DCNN-LSTM architecture.

Modified Wild Horse Optimization with Deep Learning Enabled Symmetric Human Activity Recognition Model

Traditional indoor human activity recognition(HAR)is a timeseries data classification problem and needs feature extraction.Presently,considerable attention has been given to the domain ofHARdue to the enormous amount of its real-time uses in real-time applications,namely surveillance by authorities,biometric user identification,and health monitoring of older people.The extensive usage of the Internet of Things(IoT)and wearable sensor devices has made the topic of HAR a vital subject in ubiquitous and mobile computing.The more commonly utilized inference and problemsolving technique in the HAR system have recently been deep learning(DL).The study develops aModifiedWild Horse Optimization withDLAided Symmetric Human Activity Recognition(MWHODL-SHAR)model.The major intention of the MWHODL-SHAR model lies in recognition of symmetric activities,namely jogging,walking,standing,sitting,etc.In the presented MWHODL-SHAR technique,the human activities data is pre-processed in various stages to make it compatible for further processing.A convolution neural network with an attention-based long short-term memory(CNNALSTM)model is applied for activity recognition.The MWHO algorithm is utilized as a hyperparameter tuning strategy to improve the detection rate of the CNN-ALSTM algorithm.The experimental validation of the MWHODL-SHAR technique is simulated using a benchmark dataset.An extensive comparison study revealed the betterment of theMWHODL-SHAR technique over other recent approaches.

Cascade Human Activity Recognition Based on Simple Computations Incorporating Appropriate Prior Knowledge

The purpose of Human Activities Recognition(HAR)is to recognize human activities with sensors like accelerometers and gyroscopes.The normal research strategy is to obtain better HAR results by finding more efficient eigenvalues and classification algorithms.In this paper,we experimentally validate the HAR process and its various algorithms independently.On the base of which,it is further proposed that,in addition to the necessary eigenvalues and intelligent algorithms,correct prior knowledge is even more critical.The prior knowledge mentioned here mainly refers to the physical understanding of the analyzed object,the sampling process,the sampling data,the HAR algorithm,etc.Thus,a solution is presented under the guidance of right prior knowledge,using Back-Propagation neural networks(BP networks)and simple Convolutional Neural Networks(CNN).The results show that HAR can be achieved with 90%–100%accuracy.Further analysis shows that intelligent algorithms for pattern recognition and classification problems,typically represented by HAR,require correct prior knowledge to work effectively.

DL-HAR: Deep Learning-Based Human Activity Recognition Framework for Edge Computing

Human activity recognition is commonly used in several Internet of Things applications to recognize different contexts and respond to them.Deep learning has gained momentum for identifying activities through sensors,smartphones or even surveillance cameras.However,it is often difficult to train deep learning models on constrained IoT devices.The focus of this paper is to propose an alternative model by constructing a Deep Learning-based Human Activity Recognition framework for edge computing,which we call DL-HAR.The goal of this framework is to exploit the capabilities of cloud computing to train a deep learning model and deploy it on less-powerful edge devices for recognition.The idea is to conduct the training of the model in the Cloud and distribute it to the edge nodes.We demonstrate how the DL-HAR can perform human activity recognition at the edge while improving efficiency and accuracy.In order to evaluate the proposed framework,we conducted a comprehensive set of experiments to validate the applicability of DL-HAR.Experimental results on the benchmark dataset show a significant increase in performance compared with the state-of-the-art models.

Human activity recognition based on HMM by improved PSO and event probability sequence

This paper proposes a hybrid approach for recognizing human activities from trajectories. First, an improved hidden Markov model （HMM） parameter learning algorithm, HMM-PSO, is proposed, which achieves a better balance between the global and local exploitation by the nonlinear update strategy and repulsion operation. Then, the event probability sequence （EPS） which consists of a series of events is computed to describe the unique characteristic of human activities. The anatysis on EPS indicates that it is robust to the changes in viewing direction and contributes to improving the recognition rate. Finally, the effectiveness of the proposed approach is evaluated by data experiments on current popular datasets.

Human Activity Recognition and Embedded Application Based on Convolutional Neural Network

With the improvement of people’s living standards,the demand for health monitoring and exercise detection is increasing.It is of great significance to study human activity recognition(HAR)methods that are different from traditional feature extraction methods.This article uses convolutional neural network(CNN)algorithms in deep learning to automatically extract features of activities related to human life.We used a stochastic gradient descent algorithm to optimize the parameters of the CNN.The trained network model is compressed on STM32CubeMX-AI.Finally,this article introduces the use of neural networks on embedded devices to recognize six human activities of daily life,such as sitting,standing,walking,jogging,upstairs,and downstairs.The acceleration sensor related to human activity information is used to obtain the relevant characteristics of the activity,thereby solving the HAR problem.By drawing the accuracy curve,loss function curve,and confusion matrix diagram of the training model,the recognition effect of the convolutional neural network can be seen more intuitively.After comparing the average accuracy of each set of experiments and the test set of the best model obtained from it,the best model is then selected.

HARTIV:Human Activity Recognition Using Temporal Information in Videos

Nowadays,the most challenging and important problem of computer vision is to detect human activities and recognize the same with temporal information from video data.The video datasets are generated using cameras available in various devices that can be in a static or dynamic position and are referred to as untrimmed videos.Smarter monitoring is a historical necessity in which commonly occurring,regular,and out-of-the-ordinary activities can be automatically identified using intelligence systems and computer vision technology.In a long video,human activity may be present anywhere in the video.There can be a single ormultiple human activities present in such videos.This paper presents a deep learning-based methodology to identify the locally present human activities in the video sequences captured by a single wide-view camera in a sports environment.The recognition process is split into four parts:firstly,the video is divided into different set of frames,then the human body part in a sequence of frames is identified,next process is to identify the human activity using a convolutional neural network and finally the time information of the observed postures for each activity is determined with the help of a deep learning algorithm.The proposed approach has been tested on two different sports datasets including ActivityNet and THUMOS.Three sports activities like swimming,cricket bowling and high jump have been considered in this paper and classified with the temporal information i.e.,the start and end time for every activity present in the video.The convolutional neural network and long short-term memory are used for feature extraction of temporal action recognition from video data of sports activity.The outcomes show that the proposed method for activity recognition in the sports domain outperforms the existing methods.

Deep learning and transfer learning for device-free human activity recognition:A survey

Device-free activity recognition plays a crucial role in smart building,security,and human–computer interaction,which shows its strength in its convenience and cost-efficiency.Traditional machine learning has made significant progress by heuristic hand-crafted features and statistical models,but it suffers from the limitation of manual feature design.Deep learning overcomes such issues by automatic high-level feature extraction,but its performance degrades due to the requirement of massive annotated data and cross-site issues.To deal with these problems,transfer learning helps to transfer knowledge from existing datasets while dealing with the negative effect of background dynamics.This paper surveys the recent progress of deep learning and transfer learning for device-free activity recognition.We begin with the motivation of deep learning and transfer learning,and then introduce the major sensor modalities.Then the deep and transfer learning techniques for device-free human activity recognition are introduced.Eventually,insights on existing works and grand challenges are summarized and presented to promote future research.

Coupling Analysis of Multiple Machine Learning Models for Human Activity Recognition

Artificial intelligence(AI)technology has become integral in the realm of medicine and healthcare,particularly in human activity recognition(HAR)applications such as fitness and rehabilitation tracking.This study introduces a robust coupling analysis framework that integrates four AI-enabled models,combining both machine learning(ML)and deep learning(DL)approaches to evaluate their effectiveness in HAR.The analytical dataset comprises 561 features sourced from the UCI-HAR database,forming the foundation for training the models.Additionally,the MHEALTH database is employed to replicate the modeling process for comparative purposes,while inclusion of the WISDM database,renowned for its challenging features,supports the framework’s resilience and adaptability.The ML-based models employ the methodologies including adaptive neuro-fuzzy inference system(ANFIS),support vector machine(SVM),and random forest(RF),for data training.In contrast,a DL-based model utilizes one-dimensional convolution neural network(1dCNN)to automate feature extraction.Furthermore,the recursive feature elimination(RFE)algorithm,which drives an ML-based estimator to eliminate low-participation features,helps identify the optimal features for enhancing model performance.The best accuracies of the ANFIS,SVM,RF,and 1dCNN models with meticulous featuring process achieve around 90%,96%,91%,and 93%,respectively.Comparative analysis using the MHEALTH dataset showcases the 1dCNN model’s remarkable perfect accuracy(100%),while the RF,SVM,and ANFIS models equipped with selected features achieve accuracies of 99.8%,99.7%,and 96.5%,respectively.Finally,when applied to the WISDM dataset,the DL-based and ML-based models attain accuracies of 91.4%and 87.3%,respectively,aligning with prior research findings.In conclusion,the proposed framework yields HAR models with commendable performance metrics,exhibiting its suitability for integration into the healthcare services system through AI-driven applications.

Smart Healthcare Activity Recognition Using Statistical Regression and Intelligent Learning

In this present time,Human Activity Recognition(HAR)has been of considerable aid in the case of health monitoring and recovery.The exploitation of machine learning with an intelligent agent in the area of health informatics gathered using HAR augments the decision-making quality and significance.Although many research works conducted on Smart Healthcare Monitoring,there remain a certain number of pitfalls such as time,overhead,and falsification involved during analysis.Therefore,this paper proposes a Statistical Partial Regression and Support Vector Intelligent Agent Learning(SPR-SVIAL)for Smart Healthcare Monitoring.At first,the Statistical Partial Regression Feature Extraction model is used for data preprocessing along with the dimensionality-reduced features extraction process.Here,the input dataset the continuous beat-to-beat heart data,triaxial accelerometer data,and psychological characteristics were acquired from IoT wearable devices.To attain highly accurate Smart Healthcare Monitoring with less time,Partial Least Square helps extract the dimensionality-reduced features.After that,with these resulting features,SVIAL is proposed for Smart Healthcare Monitoring with the help of Machine Learning and Intelligent Agents to minimize both analysis falsification and overhead.Experimental evaluation is carried out for factors such as time,overhead,and false positive rate accuracy concerning several instances.The quantitatively analyzed results indicate the better performance of our proposed SPR-SVIAL method when compared with two state-of-the-art methods.

Online conflict resolution strategies for human activity recognition in smart homes

DCR-OL is a Distributed Collaborative Reasoning multi-agent model with an Online Learning thataims to identify human activities in smart homes from distributed, heterogeneous and dynamicsensor data. In this model, distributed learning agents with diverse classifiers, detect sensorstream data, make local predictions, communicate and collaborate to identify current activities.Then, they learn from their collaborations to improve their own performance in activity recognition.Conflict resolution strategies are applied to generate one final predicted activity when thelocal predicted activity of an agent is different from received predicted activities of other agents.In this paper, two conflict resolution strategies using online learning, w-max-trust and w-maxfreq,are proposed. We experimentally test these strategies by performing an evaluation studyon the Aruba dataset. The obtained results indicate an enhancement in terms of accuracy and Fmeasuremetrics compared to the offline strategies max-trust and max-freq and also to the onlineexisting one max-wPerf .

Parameter-Tuned Deep Learning-Enabled Activity Recognition for Disabled People

Elderly or disabled people can be supported by a human activity recognition(HAR)system that monitors their activity intervenes and pat-terns in case of changes in their behaviors or critical events have occurred.An automated HAR could assist these persons to have a more indepen-dent life.Providing appropriate and accurate data regarding the activity is the most crucial computation task in the activity recognition system.With the fast development of neural networks,computing,and machine learning algorithms,HAR system based on wearable sensors has gained popularity in several areas,such as medical services,smart homes,improving human communication with computers,security systems,healthcare for the elderly,mechanization in industry,robot monitoring system,monitoring athlete train-ing,and rehabilitation systems.In this view,this study develops an improved pelican optimization with deep transfer learning enabled HAR(IPODTL-HAR)system for disabled persons.The major goal of the IPODTL-HAR method was recognizing the human activities for disabled person and improve the quality of living.The presented IPODTL-HAR model follows data pre-processing for improvising the quality of the data.Besides,EfficientNet model is applied to derive a useful set of feature vectors and the hyperparameters are adjusted by the use of Nadam optimizer.Finally,the IPO with deep belief network(DBN)model is utilized for the recognition and classification of human activities.The utilization of Nadam optimizer and IPO algorithm helps in effectually tuning the hyperparameters related to the EfficientNet and DBN models respectively.The experimental validation of the IPODTL-HAR method is tested using benchmark dataset.Extensive comparison study highlighted the betterment of the IPODTL-HAR model over recent state of art HAR approaches interms of different measures.

Deep Pyramidal Residual Network for Indoor-Outdoor Activity Recognition Based on Wearable Sensor

Recognition of human activity is one of the most exciting aspects of time-series classification,with substantial practical and theoretical impli-cations.Recent evidence indicates that activity recognition from wearable sensors is an effective technique for tracking elderly adults and children in indoor and outdoor environments.Consequently,researchers have demon-strated considerable passion for developing cutting-edge deep learning sys-tems capable of exploiting unprocessed sensor data from wearable devices and generating practical decision assistance in many contexts.This study provides a deep learning-based approach for recognizing indoor and outdoor movement utilizing an enhanced deep pyramidal residual model called Sen-PyramidNet and motion information from wearable sensors(accelerometer and gyroscope).The suggested technique develops a residual unit based on a deep pyramidal residual network and introduces the concept of a pyramidal residual unit to increase detection capability.The proposed deep learning-based model was assessed using the publicly available 19Nonsens dataset,which gathered motion signals from various indoor and outdoor activities,including practicing various body parts.The experimental findings demon-strate that the proposed approach can efficiently reuse characteristics and has achieved an identification accuracy of 96.37%for indoor and 97.25%for outdoor activity.Moreover,comparison experiments demonstrate that the SenPyramidNet surpasses other cutting-edge deep learning models in terms of accuracy and F1-score.Furthermore,this study explores the influence of several wearable sensors on indoor and outdoor action recognition ability.

Cross-scene passive human activity recognition using commodity WiFi

With the development of the Internet of Things(IoT)and the popularization of commercial WiFi,researchers have begun to use commercial WiFi for human activity recognition in the past decade.However,cross-scene activity recognition is still difficult due to the different distribution of samples in different scenes.To solve this problem,we try to build a cross-scene activity recognition system based on commercial WiFi.Firstly,we use commercial WiFi devices to collect channel state information(CSI)data and use the Bi-directional long short-term memory(BiLSTM)network to train the activity recognition model.Then,we use the transfer learning mechanism to transfer the model to fit another scene.Finally,we conduct experiments to evaluate the performance of our system,and the experimental results verify the accuracy and robustness of our proposed system.For the source scene,the accuracy of the model trained from scratch can achieve over 90%.After transfer learning,the accuracy of cross-scene activity recognition in the target scene can still reach 90%.

Adaptive transfer learning framework for dense prediction of human activity recognition

Human activity recognition(HAR)for dense prediction is proven to be of good performance,but it relies on labeling every point in time series with the high cost.In addition,the performance of HAR model will show significant degradation when tested on the sensor data with different distribution from the training data,where the training data and the test data are usually collected from different sensor locations or sensor users.Therefore,the adaptive transfer learning framework for dense prediction of HAR is introduced to implement cross-domain transfer,where the proposed multi-level unsupervised domain adaptation(MLUDA)approach combines the global domain adaptation and the specific task adaptation to adapt the source and target domain in multiple levels.The multi-connected global domain adaptation architecture is proposed for the first time,which can adapt the output layer of the encoder and the decoder in dense prediction model.After this,the specific task adaptation is proposed to ensure alignment of each class centroid in source domain and target domain by introducing the cosine distance loss and the moving average method.Experiments on three public HAR datasets demonstrate that the proposed MLUDA improves the prediction accuracy of target data by 20%compared to the source domain pre-trained model and it is more effective than the other three deep transfer learning methods with an improvement of 10%to 18%in accuracy.

MiTAR:a study on human activity recognition based on NLP with microscopic perspective

Nowadays,human activity recognition is becoming a more and more significant topic,and there is also a wide range of applications for it in real world scenarios.Sensor data is an important data source in engineering and application.At present,some studies have been carried out in the field of human activity recognition based on sensor data in a macroscopic perspective.However,many studies in this perspective face some limitations.One pivotal limitation is uncontrollable data segment length of different kinds of activities.Suitable feature and data form are also influencing factors.This paper carries out the study creatively on a microscopic perspective with an emphasis on the logic and relevance between data segments,attempting to apply the idea of natural language processing and the method of data symbolization to the study of human activity recognition and try to solve the problem above.In this paper,several activity-element definitions and three algorithms are proposed,including the algorithm of dictionary building,the algorithm of corpus building,and activity recognition algorithm improved from a natural language analysis method,TFIDF.Numerous experiments on different aspects of this model are taken.The experiments are carried out on six complex and representative single-level sensor datasets,namely UCI Sports and Daily dataset,Skoda dataset,WISDM Phoneacc dataset,WISDM Watchacc dataset,Healthy Older People dataset and HAPT dataset,which prove that this model can be applied to different datasets and achieve a satisfactory recognition result.