8,623 Hits in 4.7 sec

Survey on Human Activity Recognition based on Acceleration Data

Salwa O. Slim, Ayman Atia, Marwa M.A., Mostafa-Sami M.Mostafa
2019 International Journal of Advanced Computer Science and Applications  
Finally, the paper concludes different challenges and issues online versus offline also using deep learning versus traditional machine learning for human activity recognition based on accelerometer sensors  ...  The state of the art in human activity recognition based on accelerometer is surveyed.  ...  CONCLUSION This paper surveys the state-of-the-art in human activity recognition based on measured acceleration components.  ... 
doi:10.14569/ijacsa.2019.0100311 fatcat:v475yhq52bd53k7usw3ifvjsne

Human Gait Recognition Using Deep Learning and Improved Ant Colony Optimization

Awais Khan, Muhammad Attique Khan, Muhammad Younus Javed, Majed Alhaisoni, Usman Tariq, Seifedine Kadry, Jung-In Choi, Yunyoung Nam
2022 Computers Materials & Continua  
Deep learning is a new machine learning technique that is gaining popularity. Many techniques for HGR based on deep learning are presented in the literature.  ...  Human gait recognition (HGR) has received a lot of attention in the last decade as an alternative biometric technique.  ...  In this approach, features are initially selected using ACO and then refined using an activation function based on the mean, standard deviation, and variance. • Used the IACO on both modified deep learning  ... 
doi:10.32604/cmc.2022.018270 fatcat:26mgssm57bexbjwts2gghu7kze

Multi-Layered Deep Learning Features Fusion for Human Action Recognition

Sadia Kiran, Muhammad Attique Khan, Muhammad Younus Javed, Majed Alhaisoni, Usman Tariq, Yunyoung Nam, Robertas Damaševičius, Muhammad Sharif
2021 Computers Materials & Continua  
Human Action Recognition (HAR) is an active research topic in machine learning for the last few decades.  ...  In this article, we proposed a new method for the use of deep learning for HAR.  ...  Figure 1 : 1 Figure 1: Proposed deep learning-based architecture for human action recognition 4068CMC, 2021, vol.69, no.3 Figure 3 : 3 Figure 3: Testing computational time for UCF sports dataset  ... 
doi:10.32604/cmc.2021.017800 fatcat:l3h4l2yaevfsfki4mp457d6e4i

Human action recognition using transfer learning with deep representations

Allah Bux Sargano, Xiaofeng Wang, Plamen Angelov, Zulfiqar Habib
2017 2017 International Joint Conference on Neural Networks (IJCNN)  
Researchers are motivated to shift from traditional feature-based approach to deep learning.  ...  Recently, due to the popularity and successful implementation of deep learning-based methods for image analysis, object recognition, and speech recognition.  ...  There are two major approaches for activity recognition; these include the traditional handcrafted feature-based representation, and learning-based representation.  ... 
doi:10.1109/ijcnn.2017.7965890 dblp:conf/ijcnn/SarganoWAH17 fatcat:pxqdjr3lbfctlezzgc7zbf73lu

Suspicious Activity Recognition Using Proposed Deep L4-Branched-ActionNet with Entropy Coded Ant Colony System Optimization

Tanzila Saba, Amjad Rehman, Rabia Latif, Suliman Mohamed Fati, Mudassar Raza, Muhammad Sharif
2021 IEEE Access  
Allah Bux Sargano et al [28] propose an innovative approach for human activity identification using the pre-trained structure of deep CNN for mining of features and depiction pursued by a fused SVM KNN  ...  categorizer for activity recognition.  ... 
doi:10.1109/access.2021.3091081 fatcat:msin6prqo5acxg6257xs75imgm

Performance evaluation of machine learning based voting classifier system for human activity recognition

Sonika Jindal, I. K. Gujral Punjab Technical University, Jalandhar, India, Monika Sachdeva, Alok K. S. Kushwaha, I. K. Gujral Punjab Technical University, Jalandhar, India, Guru Ghasidas Vishwavidyalaya , Bilaspur, India
2022 Maǧallaẗ Al-Kuwayt li-l-ʿulūm  
The present work has proposed the voting classifier system for human activity recognition.  ...  In the last few decades, Human Activity Recognition (HAR) has been a centre of attraction in many research domains, and it is referred to as the potential of interpreting human body gestures through sensors  ...  Performance evaluation of machine learning based voting classifier system for human activity recognition Sonika Jindal, Monika Sachdeva, Alok K.  ... 
doi:10.48129/kjs.splml.19189 fatcat:ap2noafcxnezbc6mpxxah3bu4a

Human Activity Recognition via Hybrid Deep Learning Based Model

Imran Ullah Khan, Sitara Afzal, Jong Weon Lee
2022 Sensors  
Many Artificial intelligence-based models are developed for activity recognition; however, these algorithms fail to extract spatial and temporal features due to which they show poor performance on real-world  ...  An extensive ablation study is performed over different traditional machine learning and deep learning models to obtain the optimum solution for HAR.  ...  Furthermore, we will explore advanced deep learningbased techniques such as reinforcement learning, lifelong learning, incremental and active learning for activity recognition.  ... 
doi:10.3390/s22010323 pmid:35009865 pmcid:PMC8749555 fatcat:3zrdns3pcfecvpxgmdsngdsgmm

Smartphone and Smartwatch for Human Activity Recognition

Mashhour M Bani Amer
2021 Annals of Advanced Biomedical Sciences  
Human activity recognition (HAR) systems are developed as aspect of a model to allow continual assessment of human behaviors in IoT environments in the areas of ambient assisted living, sports injury detection  ...  Five daily physical human activities are evaluated using five classifiers from WEKA, in addition to Artificial Neural Network (ANN), K- Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms  ...  Acknowledgment The authors would like to thank Electrical and Biomedical Engineering Departments, JUST, Irbid, Jordan for their support.  ... 
doi:10.23880/aabsc-16000159 fatcat:pqfkjxmoord6tbpybqfncrdohe

Human Action Recognition: A Paradigm of Best Deep Learning Features Selection and Serial Based Extended Fusion

Seemab Khan, Muhammad Attique Khan, Majed Alhaisoni, Usman Tariq, Hwan-Seung Yong, Ammar Armghan, Fayadh Alenezi
2021 Sensors  
Recently, the development of deep learning (DL)-based systems has shown significant success for HAR even for multi-view camera systems. In this research work, a DL-based design is proposed for HAR.  ...  Later, the extracted deep features are fused using the Serial based Extended (SbE) approach. Later on, the best features are selected using Kurtosis-controlled Weighted KNN.  ...  [39] presented a smartphone inertial sensors-based framework for human activity recognition.  ... 
doi:10.3390/s21237941 pmid:34883944 fatcat:dj3k5hqwjjai5aspkbrfpuz2cy

Activity Recognition System for Smart Campus

Manasi S. Khade
2020 International Journal for Research in Applied Science and Engineering Technology  
We recognize the frame difference and feature selection for human activities that permits recognition.  ...  The objective of this paper is to research and inspect machine and deep learning techniques by using videos for recognition of students indoor and outdoor activities.  ...  [13] has proposed a technique of systematic learning feature for the problem of human activity recognition.  ... 
doi:10.22214/ijraset.2020.31222 fatcat:7hbwirjg6bdlzjyw5ynunwy2cu

A Hybrid Duo-Deep Learning and Best Features Based Framework for燗ction燫ecognition

Muhammad Naeem Akbar, Farhan Riaz, Ahmed Bilal Awan, Muhammad Attique Khan, Usman Tariq, Saad Rehman
2022 Computers Materials & Continua  
We proposed a framework for accurate human action recognition (HAR) based on deep learning and an improved features optimization algorithm in this paper.  ...  Human Action Recognition (HAR) is a current research topic in the field of computer vision that is based on an important application known as video surveillance.  ...  Acknowledgement: We are thankful to National Institute of Science and Technology for overall support. Funding Statement: The authors received no specific funding for this study.  ... 
doi:10.32604/cmc.2022.028696 fatcat:hvye3vn4xbaw3ha6gncsh3is34

Comparison of the Predictive Models of Human Activity Recognition (HAR) in Smartphones

Muhmammad Ehsan
2021 UMT Artificial Intelligence Review  
KEYWORDS— decision tree, Human Activity Recognition (HAR), K-Nearest Neighbour (KNN), logistic regression, random forest, Support Vector Machine (SVM)  ...  Different machine learning algorithms were applied to this dataset for classification and their accuracy rates were compared. KNN and SVM were found to be the most accurate of all.  ...  In this paper, convolutional layers are combined with long short-term memory (LSTM), along with the deep learning neural network for human activities recognition (HAR).  ... 
doi:10.32350/air.0102.03 fatcat:g4oqkv5fmzd77jhlyu4conzczq

Human Activity Recognition using Multi-Head CNN followed by LSTM [article]

Waqar Ahmad, Misbah Kazmi, Hazrat Ali
2020 arXiv   pre-print
This study presents a novel method to recognize human physical activities using CNN followed by LSTM.  ...  The configuration of all three CNNs is kept the same so that the same number of features are obtained for every input to CNN.  ...  More specifically, we compared our results with both traditional machine learning methods such as SVM as well as more recent deep learning methods used for human activity recognition.  ... 
arXiv:2003.06327v1 fatcat:trdzdtspwvhwteoxeyzzftwy3y

Complex Human Action Recognition in Live Videos Using Hybrid FR-DL Method [article]

Fatemeh Serpush, Mahdi Rezaei
2020 arXiv   pre-print
We name our model as Feature Reduction & Deep Learning based action recognition method, or FR-DL in short.  ...  The combination of a CNN and the LSTM recursive network is considered for feature selection and maintaining the previous information, and finally, a Softmax-KNN classifier is used for labelling human activities  ...  In [24] , a pretrained deep CNN is used to extract features, followed by the combination of SVM and KNN classifiers for action recognition.  ... 
arXiv:2007.02811v1 fatcat:jyerl2lry5cbpnmd3kq54s4sg4

Complex Human Action Recognition Using a Hierarchical Feature Reduction and Deep Learning-Based Method

Fatemeh Serpush, Mahdi Rezaei
2021 SN Computer Science  
We name our model as "Hierarchical Feature Reduction & Deep Learning"-based action recognition method, or HFR-DL in short.  ...  The combination of a CNN and the LSTM recursive network is considered for feature selection and maintaining the previous information; and finally, a Softmax-KNN classifier is used for labelling the human  ...  In [38] , a pre-trained deep CNN is used to extract features, followed by the combination of SVM and KNN classifiers for action recognition.  ... 
doi:10.1007/s42979-021-00484-0 pmid:33615240 pmcid:PMC7881322 fatcat:htvuxaeqljcxjfl37m6y4ltrw4
« Previous Showing results 1 — 15 out of 8,623 results