Attention Aware Deep Learning Approaches for an Efficient Stress Classification Model

In today’s world, stress is a major factor for various diseases in modern societies which affects the day-to-day activities of human beings. The measurement contributing governments and that impacts quality daily lives. strategy monitoring systems requires an accurate classification technique identified via reactions body to regulate itself changes within environment through mental emotional responses. Therefore, this research proposed novel deep learning approach system. paper, we presented Enhanced Long Short-Term Memory(E-LSTM) based on feature attention mechanism focuses determining categorizing polarity using sequential modeling word-feature seizing. integrates pre-feature E-LSTM identify complicated relationship extract keywords layer classification. This has been evaluated selected dataset accessed from sixth Korea National Health Nutrition Examination Survey conducted 2013 2015 (KNHANES VI) analyze health-related data. Statistical performance developed was analyzed nine features detection, compared effectiveness with other different approaches. experimental results shown obtained accuracy, precision, recall F1-score 75.54%, 74.26%, 72.99% 74.58%, respectively. mechanism-based demonstrated superior detection when methods including naïve Bayesian, SVM, belief network, standard LSTM. study efficiency accurately classifying particularly where it expected be effective prediction.