Search

In today's world which is digitizing increasingly, facial expressions serve as one of the vital indicators of variety of human emotions. With the advancement of technologies like Artificial Intelligence (AI) systems, even machines can process and understand these facial expressions with wide number of applications across various domains. However, the challenge still lies in accounting the human diversity, which leads to distinct characteristics for each individual. And an attempt of creating a single model to fit all such individuals becomes nearly impractical. To tackle this challenge, an organized approach based on inter country facial distinctions could be a feasible solution. This approach works better within the specific country, but the universality is also required which is again a very big challenge. For this as a solution a collaborative methodology is being proposed. The aim of this paper is to prove that it is possible to create a universal model for detecting facial expressions with higher precision and accuracy by combining various datasets from different nationalities to obtain a single dataset with uniform distribution. This paper does so by using datasets of two countries i.e., JAFFE and CK datasets and generating a convolutional neural network-based model by optimizing the trade-offs between model complexity, training time, and required computational resources. [ABSTRACT FROM AUTHOR]

Human facial expressions are one of the important techniques of non-verbal communication. Facial expressions are the most tender signs for larger communication and are complemented by other gestures like eye contact, hand movement, etc. This is the direct method of communication of human emotions and intent. In this paper, the authors present the Facial Emotion Recognition (FER) framework and a brief survey of various FER techniques. It also presents the various phases of the FER system i.e., face detection, pre-processing, feature extraction, and classification. Various FER databases like JAFFE, YALE, MUG, etc. are also summarized in terms of the number of emotions, number of images, and resolution. The importance of the domain in other related subject areas like medicine, neuroscience, psychology, decision science, gaming, mental research, etc., is also introduced. The authors explored the application areas of FER techniques. The authors also present the various challenges faced in the real-time implementation of FER models. Finally, the paper is concluded by discussing future research directions. [ABSTRACT FROM AUTHOR]

Emotional intelligence is a comparatively new term that is gaining traction in the modern era. In the 1990s, Peter Salovey and John Mayor were the ones responsible for coining the term "emotional intelligence." The ability to identify and control one's own emotions as well as those of others in order to arrive at reasonable conclusions is referred to as emotional intelligence (EQ). The ability to monitor one's own feelings and emotions as well as those of others, to differentiate between those feelings and emotions, and to utilize this information to guide one's thinking and behavior is referred to as emotional intelligence (EQ). Perceiving, absorbing, comprehending, and controlling one's feelings have been identified as the four main talents that comprise the concept of emotional intelligence. People who are able to control their own moods and emotions as well as understand the sentiments of others perform better academically, socially, and professionally. The success of a student and the likelihood that the student will go on to lead a fruitful life are directly reliant on the educator. Educators lay the groundwork for students' social, emotional, and intellectual potentials, as well as their success in teaching and learning and overall well-being. As a consequence of this, evaluating the emotional intelligence of instructors is of the utmost importance. The purpose of this study is to determine whether current educators have EI skills and whether they use them is identified with the help of literature studies in the paper. Understanding emotional intelligence is important, and this study will lay the groundwork for further studies in the area. [ABSTRACT FROM AUTHOR]

In recent times, the interaction between human beings and computers has become an increasing field of research due to its wide application of computational systems. Determination of the current state of human psychological problems, one of the most relevant techniques is emotion recognition. The dynamic behavior of human is crucial for its interpretation. So, Facial emotion recognition (FER) is an important research area for detection the of different facial emotions. In this paper, we proposed an Unconstrained Minimum Average Correlation Energy (UMACE) filter as a classifier for facial emotion recognition. We are applying this proposed method in the CK+ database and it can give a better recognition rate. [ABSTRACT FROM AUTHOR]

Requirement engineering is an essential process in software development. The modern method, like Agile, requires a focus on solving user problems integrated with development domains. Productivity of the Agile organization linearly between effort and resource. A good implementation strategy in Team Software Process (TSP) which has adequate resources, will guide TSP through its move to Agile practices. However, the resource limitation is very challenging for Personal Software Process (PSP) or Solo Software Process (SSP). Moreover, developers need to focus solve the problem on what the user needs. To increase the software's value, the user's needs are based on how the user solves the problems. Based on user experience, to solve that problem, hence, developers need to be aware of user behavior in daily activities. Moreover, a lack of understanding and regulate positive and negative emotions in user behavior reduces user productivity. This paper is preliminary research focusing on how solo development can capture emotion through user behavior integrated with elicitation in user requirements. Based on the previous research, we designed a framework to capture user emotions on their behavior while eliciting the requirements. [ABSTRACT FROM AUTHOR]

Stress and emotion assessment play a pivotal role in healthcare, aiding in the early detection and prevention of various diseases. In this research paper, we propose a novel healthcare model that harnesses the power of artificial neural networks (ANN) and discrete wavelet transform (DWT) to assess stress and emotion through speech signal recognition. The proposed model extracts essential features from speech signals using DWT and employs ANN for the classification of stress and emotional states. Both ANN and DWT are established signal processing techniques that find applications in diverse domains. We present a comprehensive analysis of our healthcare model, which effectively analyzes speech signals to identify the stress and emotional states of individuals. The model's performance is rigorously evaluated using a publicly available dataset comprising speech signals recorded from subjects experiencing varying stress and emotional states. Experimental results demonstrate that the proposed model achieves high accuracy and surpasses existing state-of-the-art techniques. By employing recurrent neural networks (RNN), we visualize speech's phonetic characteristics, such as Mel-frequency cepstral coefficients (MFCCs), transforming them into sequences of phonemes or words. RNNs, designed to handle sequential data, form the basis of our speech recognition using neural networks, contributing to the model's effectiveness and accuracy. [ABSTRACT FROM AUTHOR]

The heart sound is a common modality for analyzing heart activities. It is also an essential bio-signal to be used and studied to understand the human affective state, such as emotion or feeling. However, the effort in analyzing heart sound to recognize human emotions remain scarce. Therefore, we aim to investigate the potential use of Phonocardiography (PCG) signals combined with Mel-Frequency Cepstral Coefficients (MFCC) features extraction and Multilayer perceptron (MLP) classifier to recognize four specific individual emotions (calm, fear, happy and sad). Contrasting to existing approaches, in this paper, we proposed a method to effectively characterize heart sound signal (PCG) for the emotion recognition system by selecting a suitable window size and overlapping parameters of the Short-Time Fourier Transform (STFT). Those parameters are significant for the feature extraction phase. The experimental results indicate that phonocardiography (PCG) signals are a potential and effective modality for individual emotion recognition. The overall accuracy, average precision, and average recall for four emotions recognitions are 88.8%, 89.3%, and 89.25%, respectively. [ABSTRACT FROM AUTHOR]