In order to improve human-computer interaction (HCI), computers need to recognize and respond properly to their user’s emotional state. This paper introduces emotional pattern recognition method of Least Squares Support Vector Machine (LS_SVM). The experiment introduces wavelet transform to analyze the Surface Electromyography (EMG) signal, and extracts maximum and minimum of the wavelet coefficients in every level. Then we construct the coefficients as eigenvectors and input them into improved Least Squares Support Vector Machines. The result of experiment shows that recognition rate of four emotional signals (joy, anger, sadness and pleasure) are all more than 80%. The results of experiment also show that the wavelet coefficients as the eigenvector can be effective characterization of EMG. The experimental results demonstrate that compared with classical L_M BP neural network and RBF neural network, LS_SVM has a better recognition rate for emotional pattern recognition.<a href="/index.php/jcp/author/saveSubmit/3#_ftn1"> </a>
With the development of information technology, the informationization of the medical industry is also constantly developing rapidly, and medical data is growing exponentially. In the context of ''Big Data +'', people began to study the application of data visualization to medical data. Data visualization can make full use of the human sensory vision system to guide users through data analysis and present information hidden behind the data in an intuitive and easy-to-use manner. This paper first introduces the workflow of DBN, a deep learning algorithm, and summarizes the computational characteristics of the algorithm. The classification function is translated into an assembler using an instruction set-based assembly language, and the program is evaluated for performance. Secondly, based on the Hadoop ecosystem, this paper analyzes the BDMISS system for big data medical information resource sharing. Based on the system's requirements and functional positioning, from the medical information collection and sharing, data mining and knowledge management level, the big data medical service system is constructed. Based on the semantic network and ontology theory, big data mining technology and the design of ''medical cloud'', the resource sharing mechanism is analyzed. Based on the Spring MVC framework, using Echarts, HCharts and other data visualization technology, according to the design of specific modules, the visualization and display of medical data is realized, which has certain promotion effect on the research and development of medical big data visualization analysis.
With the development of medical multimedia analysis methods based on DBN, DBN models have gained the ability to surpass medical experts in the evaluation of multimedia in some clinical examinations. Firstly, based on the existing architecture of the Internet of Things, combined with the actual characteristics of the hospital, the medical multimedia data is accessed from the IoT support platform. Secondly, the medical multimedia data modeling and classification method based on DBN is studied and analyzed. Three network structure models, a deep belief network, a stacking automatic encoder and a convolutional neural network, were introduced and analyzed. The medical multimedia data classification modeling method based on DBN was proposed to further improve the accuracy of medical multimedia data classification. The experimental results show that compared with the traditional feature extraction based neural network classification method, the classification performance is better. Thirdly, the medical state assessment model is constructed based on the multivariate Gaussian distribution theory. To study how to use the multivariate Gaussian distribution theory to design an evaluation model that can evaluate the health status of users efficiently and accurately. Finally, using the MATLAB software platform, through the experiment and simulation of 40 groups of 8×8064-dimensional physiological big data of 32 volunteers, First, determine the optimal parameters of a set of health assessment models; then use the model to learn the characteristics of physiological parameters; finally, the state assessment model to obtain the health assessment results. The experimental results show that the feature learning model based on convolutional neural network theory can effectively extract the deep features of medical multimedia big data. The health state assessment model based on multivariate Gaussian distribution theory can effectively evaluate the health status of human body. INDEX TERMS DBN, medical multimedia, neural network, feature extraction, multivariate Gaussian distribution.
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.