Real-Time Monitoring and Assessment System with Facial Landmark Estimation for Emotional Recognition in Work

Abstract

The Model for Monitoring and Regulating Emotional States in the Work Environment based on Neural Networks and Emotion Recognition Algorithms presents an innovative approach to enhancing employee well-being and productivity by leveraging advanced technologies. This paper on the development of a system that utilizes neural networks and emotion recognition algorithms to monitor and interpret emotional cues exhibited by individuals in real-time within the work environment. With the uses of novel Directional Marker Controlled Facial Landmark (DMCFL) Emotion recognition algorithms are employed to analyze facial expressions, speech patterns, physiological data, and text-based communication to infer the emotional state of employees. Neural networks are then utilized to process this data and provide more sophisticated emotion classification and prediction. The emotional states are classified with the integrated Regression Logistics Classifier (RLC) model for classification. The analysis of the findings expressed that the real-time monitoring enables employers and supervisors to gain insights into the emotional well-being of employees, identifying patterns and potential issues. The system facilitates feedback and regulation mechanisms, allowing for personalized interventions and support tailored to individual emotional needs.

Systematic Literature Review: The Influence and Effectiveness of Deep Learning in Image Processing for Emotion Recognition

“…Table IV shows the frequent use of deep learning algorithms in emotional recognition in research. [19], [20], [21], [22], [5], [23], [24], [25], [26], [27], [28], [5], [4], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38] CNN + GoogleNet [39], [40], [41], [42] CNN + VGG 19 [43], [44], [27], [28], [5], [42] CNN + VGG There is also SHCNN which uses Leaky ReLU to avoid the "Dead ReLU problem" which can bring better convergence on the dataset [65]. CNN can also combine with CRBM and Transfer Learning.…”