Recent advances in artificial intelligence and machine learning (ML) led to effective methods and tools for analyzing the human behavior. Human Activity Recognition (HAR) is one of the fields that has seen an explosive research interest among the ML community due to its wide range of applications. HAR is one of the most helpful technology tools to support the elderly’s daily life and to help people suffering from cognitive disorders, Parkinson’s disease, dementia, etc. It is also very useful in areas such as transportation, robotics and sports. Deep learning (DL) is a branch of ML based on complex Artificial Neural Networks (ANNs) that has demonstrated a high level of accuracy and performance in HAR. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are two types of DL models widely used in the recent years to address the HAR problem. The purpose of this paper is to investigate the effectiveness of their integration in recognizing daily activities, e.g., walking. We analyze four hybrid models that integrate CNNs with four powerful RNNs, i.e., LSTMs, BiLSTMs, GRUs and BiGRUs. The outcomes of our experiments on the PAMAP2 dataset indicate that our proposed hybrid models achieve an outstanding level of performance with respect to several indicative measures, e.g., F-score, accuracy, sensitivity, and specificity.
In many real‐world applications, mathematical models are highly complex, and numerical simulations in high‐dimensional systems are challenging. Model order reduction is a useful method to obtain a reasonable approximation by significantly reducing the computational cost of such problems. Deep learning technology is a recent improvement in artificial neural networks that can find more hidden information from the data. Deep learning has the advantage of processing data in its raw form and trains the nonlinear system with different levels of representation and predicts the data. In this article, a reduced order model framework based on a combination of deep learning [long short‐term memory (LSTM)] and proper orthogonal decomposition/dynamic mode decomposition (POD/DMD) modes is presented. Due to the robustness and stability of the LSTM recurrent neural network in predicting chaotic dynamical systems, we consider LSTM architecture to develop our data‐driven reduced order modeling (ROM). We investigate the proposed method performance by solving two well‐known canonical cases: a steady shear flow exhibiting the Kelvin‐Helmholtz instability, and two‐dimensional and unsteady mass diffusion equation. The focus of this article is to use LSTM deep recursive neural network to learn the time dynamics and POD/DMD to generate the order reduction model. The results show that the proposed method is very accurate in predicting time dynamics and input reconstruction.
MHealth systems establish a new way to transfer the health service to remote places. These systems offer significant benefits for continuous health monitoring. Motion activity recognition is one of the challenging mHealth use cases that incorporates continuous data collection and analysis of measurements. The main goal of this research is to analyze physical activity data. We employ measurements from the WISDM lab dataset 1 . These data are collected from participants performing motion activities. This data is then used by deep learning algorithms to predict special activities. In particular, CNN and CNN-LSTM algorithms are used to compare their accuracy, which resulted in approximately 95% and 97% respectively. Thus, the CNN-LSTM has higher accuracy in this analysis.
The Partial differential equations are one of the main tools in modeling many phenomena in real life. Since the formation and solving of the governing equations requires high processing time and computational costs. This study seeks to provide a method based on deep learning algorithms that can solve the equations independently of direct and numerical solution methods only by applying the boundary conditions of the problem on the neural network. This work explores the application of this paradigm on two-dimensional steady-state heat transfer equation. Due to the challenges of preparation large data with large dimensions, a novel method has been proposed to reduce the necessity of gathering data in large dimensions and size. In this method, first the steady-state heat transfer pattern encrypted in a kernel using thermal data in small size and dimensions. It is then used to train the steady-state predictor network without observing any steady-state heat transfer data simply by imposing restrictions on its outputs. This model was compared with a supervised model that trained by the large size of labeled data in the original dimensions. The result signifies that the proposed model has more accuracy, learning capability, and higher speed during the training stage.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.