Robotics & Machine Learning Daily News2024,Issue(Mar.13) :97-97.

National Institute of Technology Hamirpur Researcher Adds New Data to Research in Machine Learning (Optimized Ensemble Machine Learning Approach for Emotion Det ection from Thermal Images)

Robotics & Machine Learning Daily News2024,Issue(Mar.13) :97-97.

National Institute of Technology Hamirpur Researcher Adds New Data to Research in Machine Learning (Optimized Ensemble Machine Learning Approach for Emotion Det ection from Thermal Images)

扫码查看

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on artificial intelligen ce have been presented. According to news reporting out of Hamirpur, India, by N ewsRx editors, research stated, “Emotions indicate the feelings of the individua l which are linked with personal experiences, moods, and affective states.” The news editors obtained a quote from the research from National Institute of T echnology Hamirpur: “Detection of emotion can be helpful in many fields like mai ntaining a patient’s psychological well-being, surveillance, driver monitoring, etc. In this paper, an effective machine learning approach has been put forth fo r emotion detection where an ensemble of three out of five best-performing class ifiers has been formed to enhance the classification accuracy. Two deep learning models (AlexNet and ResNet) have been optimally combined with [Formula: see text]-nearest neighbor (KNN). The optimal weight s for ensemble weighted averaging of classifiers have been computed with aid of particle swarm optimization (PSO) and genetic algorithm (GA) optimization. The d eveloped framework has been tested on two publicly available datasets. An overal l accuracy of above 95% has been achieved on the testing set for b oth datasets.”

Key words

National Institute of Technology Hamirpu r/Hamirpur/India/Asia/Cyborgs/Emerging Technologies/Machine Learning

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文