4/20/2023 0 Comments Bitmessage 1488Video analysis can be viewed as a form of time series data modeling, which is similar to the HAR application discussed in this paper. This could be useful for increasing the complexity of activity recognition. Second, deep learning (DL) techniques are able to identify features related to the dynamics of producing the human motion, ranging from lower-layer simple activity encoding to upper-layer more complex activity dynamics. First and foremost, performance can be improved through the current proposed system. Our research focuses on the performance impact of key architectural hyperparameters, with the goal of identifying ways to improve those impacts.ĭeep learning techniques appear to have the potential to meet the needs of activity recognition through videos. Because recurrent neural networks (RNNs) related to time series domains have recently been successful, we present an all-encompassing, general deep framework to recognize activity based on convolutional network and long short-term memory (LSTM) recurrent units. HAR, on the other hand, relies on capturing the temporal dynamics of human abnormal activities, which involves sequence of more complex activities. Deep neural networks may be able to automate extraction of features from raw video inputs, according to current research findings. IntroductionĮngineered features obtained through heuristic processes have traditionally been used to solve HAR tasks. Finally, the observations have proved that the proposed LSTM model is best suitable in recognizing and classifying the human activities well even for real-time videos. But the proposed LSTM model has outperformed the basic model while achieving 100% classification accuracy. The basic LSTM model has achieved a training accuracy of just 18% and testing accuracy of 21% with higher training and classification loss values. Later, a comparative analysis is performed to understand the efficiencies of the models during the classification of five human activities like abuse, arrest, arson, assault, and fighting images classification. To understand the complexity of activities recognition and classification, two LSTM models, basic model and the proposed model, were used. The new network is capable of avoiding gradient vanishing in both temporal and spatial dimensions with a view to increase the rate of recognition. The present study proposed a deep network architecture based on one of the techniques of deep learning named as residual bidirectional long-term memory (LSTM). ![]() Recurrent neural networks (RNNs) in deep learning (DL) provide higher opportunity in recognizing the abnormal behavior of humans to avoid any kind of security issues. The researchers began working on the new ideas by combining the two emerging areas to solve HAR problems using deep learning. Human activity recognition (HAR), on the other hand, has become a popular research topic due to its wide range of applications. Deep learning techniques have recently demonstrated their ability to be applied in any field, including image processing, natural language processing, speech recognition, and many other real-world problem-solving applications.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |