Reliability of Emotion Analysis from Human Facial Expressions Using Multi-task Cascaded Convolutional Neural Networks.

The suicide mortality rate per 100 000 population (SMRP) consistently decreased before the COVID-19 pandemic outbreak in Japan and then unexpectedly increased during the pandemic. However, the underlying mechanisms remain poorly understood. To identify trends in and factors associated with suicidal mortality and motives among students in Japan from 2007 to 2022. In this cross-sectional study, data on SMRPs among Japanese middle-school, high-school, and university students were obtained from the government suicide database Suicide Statistics of the National Police Agency. Age-dependent and temporal fluctuations in annual SMRPs, disaggregated by suicidal motive (7 categories and 52 subcategories), sex, and school, were analyzed using linear mixed-effect and joinpoint regression models, respectively. Total suicide numbers from 2007 to 2022 were as follows: 760 male middle-school students, 635 female middle-school students, 2376 male high-school students, 1566 female high-school students, 5179 male university students, and 1880 female university students. The mean (SD) student populations from 2007 to 2022 were as follows: 1 752 737 (81 334) male middle-school students, 1 675 572 (78 824) female middle-school students, 1 648 274 (67 520) male high-school students, 1 614 828 (60 032) female high-school students, 1 652 689 (32 724) male university students, and 1 229 142 (57 484) female university students. Among male students, the leading motives were school-related factors (underachievement and worrying about the future), followed by family-related and health-related motives. Among female students, school-related and family-related motives decreased, but health-related motives showed an age-dependent increase. The SMRPs of middle-school male students and female students were almost equal (mean [SD], 2.7 [1.0] vs 2.4 [1.4]), but the age-dependent increase in SMRPs among male students was pronounced (mean [SD], high-school vs university male students, 9.1 [2.4] vs 19.6 [3.0]; high-school vs university female students, 6.1 [2.4] vs 9.6 [1.8]). However, the incidence of suicide among high-school students associated with health-related motives was greater in female students. The majority of suicides associated with major impactable suicidal motives (school-related, health-related, and family-related motives) began increasing before the pandemic. Changes in SMRP associated with interpersonal relationships, such as conflict with classmates or parents, were not significant, but the rates increased greatly during the pandemic. School-related, health-related, and family-related problems were major motives, whereas the impacts of health-related and family-related motives increased and decreased with age, respectively. Notably, most SMRPs associated with major impactable motives (underachievement, conflict with a parent or classmate, and mental illnesses) had already begun increasing in the late 2010s, indicating that recent increasing SMRPs among school-aged individuals were associated with pandemic-related factors and other factors affecting this generation before the pandemic. It may be inappropriate to uniformly apply research findings based on school-aged individuals to school-based suicide prevention programs for students in middle school, high school, and university.

The study of emotions in human-computer interaction is a growing research area. Focusing on automatic emotion recognition, work is being performed in order to achieve good results particularly in speech and facial gesture recognition. In this paper we present a study performed to analyze different machine learning techniques validity in automatic speech emotion recognition area. Using a bilingual affective database, different speech parameters have been calculated for each audio recording. Then, several machine learning techniques have been applied to evaluate their usefulness in speech emotion recognition, including techniques based on evolutive algorithms (EDA) to select speech feature subsets that optimize automatic emotion recognition success rate. Achieved experimental results show a representative increase in the success rate.KeywordsAffective computingMachine Learningspeech features extractionemotion recognition in speech

Emotion refers to an inner feeling or affect that a person experiences toward people, objects, or events, influencing their behavior and speech, Human emotions flow like a clear stream through the fabric of words in the poetry of Laila Serahat Roshani, such as delicate love, deep sorrow, fragile hope, and the suffering that silently permeates the verse. In this study, a descriptive-analytical method has been employed, combining library research with the analysis of existing data to examine the subject matter. The aim of the present study was to analyze and examine the human emotions in the works of Laila Serahat. The findings of this study also indicate that the poetry of Laila Serahat serves as a clear mirror of her thoughts and emotions, employing a lucid and unadorned language that conveys meaning to the reader without ambiguity and conveys them while highlighting her literary identity The human emotions in her poetry are not merely expressions of feeling, but serve as a means to uncover a deeper truth about existence. A truth woven into words, resonating deeply within the reader’s soul.

Humans have traditionally found it simple to identify emotions from facial expressions, but it is far more difficult for a computer system to do the same. The social signal processing subfield of emotion recognition from facial expression is used in a wide range of contexts, particularly for human-computer interaction. Automatic emotion recognition has been the subject of numerous studies, most of which use a machine learning methodology. The recognition of simple emotions like anger, happiness, contempt, fear, sadness, and surprise, however, continues to be a difficult topic in computer vision. Deep learning has recently drawn increased attention as a solution to a variety of practical issues, including emotion recognition. In this study, we improved the convolutional neural network technique to identify 7 fundamental emotions and evaluated several preprocessing techniques to demonstrate how they affected the CNN performance. This research focuses on improving facial features and expressions based on emotional recognition. By identifying or recognising facial expressions that elicit human responses, it is possible for computers to make more accurate predictions about a person's mental state and to provide more tailored responses. As a result, we examine how a deep learning technique that employs a convolutional neural network might improve the detection of emotions based on facial features (CNN). Multiple facial expressions are included in our dataset, which consists of about 32,298 photos for testing and training. The preprocessing system aids in removing noise from the input image, and the pretraining phase aids in revealing face detection after noise removal, including feature extraction. As a result, the existing paper generates the classification of multiple facial reactions like the seven emotions of the facial acting coding system (FACS) without using the optimization technique, but our proposed paper reveals the same seven emotions of the facial acting coding system.

Human emotion recognition is critical to people managing their stress and emotions. Although many innovative techniques have been proposed to recognize human emotions, it is still challenging to understand the emotions due to individual differences in the diversity of emotions. This article focuses on analyzing the emotions computationally. In detail, a wavelet transform technique is utilized to extract significant features and find patterns in an emotion dataset. With the extracted features, both classification and visual analysis are performed. For the classification, Logistic Regression, C4.5, and Support Vector Machine are used. Visualization approaches are also utilized to represent similarities and differences among the emotion patterns. From the analysis, the authors found that the proposed method shows an improvement in identifying the differences among the emotions.

The paper concerns technology of automatic emotion recognition applied in e-learning environment. During a study of e-learning process the authors applied facial expressions observation via multiple video cameras. Preliminary analysis of the facial expressions using automatic emotion recognition tools revealed several unexpected results, including unavailability of recognition due to face coverage and significant inconsistency between the results obtained from two cameras. The paper presents the experiment on e-learning process and summarizes the observations that constitute limitations of emotion recognition from facial expressions applied in e-learning context. The paper might be of interest to researchers and practitioners who consider automatic emotion recognition as an option in monitoring e-learning processes.

Recognition of facial expression has many applications including human-computer interaction, human emotion analysis, personality development, cognitive science, health-care, virtual reality, image retrieval, etc. In this paper we propose a new method for recognition of facial expression using local region specific mean optical flow and local binary pattern feature descriptor with support vector machine classification. In general, facial expression recognition techniques divide the face into regular grid (holistic representation) and the facial features are extracted. However, in this paper we divide the face into domain specific local regions. At first a robust optical flow is utilized to get mean optical flow in different directions for each local region which considers both local statistic motion information and its spatial location. The features are used only from the key frames; which are detected based on maximal mean optical flow magnitude within a sequence w.r.t. neutral frame. Now, the region specific local binary pattern is extracted from key frame and concatenated with mean optical flow features. The performance of the proposed facial expression recognition system has been validated on CK+ facial expression dataset.

Background: Eating disorders are disturbances that result in severe and long-lasting abnormal eating patterns and consequences to a variety of physical and psychological components of health. Purpose: To determine the prevalence of risks for eating disorders among Emirati female undergraduate university students at higher colleges in the United Arab Emirates. Methods: Utilizing a cross-sectional design, a total of 501 university students were recruited conveniently to participate in this study (the response rate was 90%). A questionnaire consisting of demographical and eating pattern sections and the Eating Attitudes Test-26 (EAT-26) (Arabic version) were used and shared online with the university students using Google Forms. This study was conducted in the spring semester of 2020/2021. Descriptive and inferential statistics were utilized. Results: The prevalence of female university students with risks of eating disorders was 13.97%. The most frequent (13.6%) statement chosen by university students was “I am terrified of being overweight.” Almost 50% of the university students were not satisfied with their weight and 48.1% were dissatisfied with their physical appearance. Only 8.18% of the female university students have a family history of eating disorders and 8.98% were confirmed cases of eating disorders. Yet, the study revealed no statistically significant correlations between age (r= 0.036, P= 0.416), body mass index (r= 0.015, P= 0.734) or meals/day (r= -0.076, P= 0.087) and EAT-26 scores. Conclusions: The risks of eating disorders in the current study were lower compared to those obtained by previous studies. Regardless of that, the awareness regarding eating disorders is required by multiple education programs utilizing reading materials, online education sessions, games, mass media and social communication methods. Implications for Nursing: Extended community-based educational programs are suggested to enhance female university students’ knowledge about EDs, their consequences on health and methods to promote healthy eating habits and positive attitudes toward body image. Keywords: Eating disorders, Higher colleges, University students, United Arab Emirates, Female adolescents, Anorexia nervosa, EAT-26.

The human face reflects a person's character and emotions, both in health and disease. Charles Bell, published in 1806 Essays on the Anatomy of Expression in Painting in which he stressed the importance of understanding anatomy when studying art. He concluded that emotions were revealed in facial expression and that these expressions were only to be found in humans, not in lower animals. Charles Darwin in 1872 published The Expression of the Emotions in Man and Animals, where he acknowledged Bell’s contribution to facial expression especially the role of the nervous system, but questioned Bell’s conclusion, that animals were incapable of showing emotions through facial expression. Darwin reasoned that human facial expressions reflected emotions, some from our primeval state, some from habit but most were universal and controlled by an involuntary nervous system, described by Bell, and now known as the parasympathetic system. This paper explores Bell’s contribution to the understanding of facial expression. We conclude that his understanding of neuroanatomy along with his artistic ability enhanced our comprehension of human facial expressions, although his theological interpretation of the reason for facial expressions and emotions needs to be seen more in the context of nineteenth century Natural Theology.

Emotions play a major role in human decision making, perception, interaction & cognition. Visually human facial expressions can give us a lot of information, which plays an important role in the area of human-machine interaction. The main challenging task is recognizing the facial reaction of a person by the system. Face Recognition are carried out in three different stages: 1. face detection, 2.feature extraction, 3.expression classification. The main objective of this research methodology is to carry out emotion analysis by implementing and evaluating various research issues to obtain a high classification rate. Various researchers have implemented various algorithms for identifying various human emotions. This paper presents a review of the current work carried out in the field of human facial expression and EEG techniques. Pre-determination of disease identification can be done using this technique.

Human emotions analysis has been the focus of many studies, especially in the field of Affective Computing, and is important for many applications, e.g. human-computer intelligent interaction, stress analysis, interactive games, animations, etc. Solutions for automatic emotion analysis have also benefited from the development of deep learning approaches and the availability of vast amount of visual facial data on the internet. This paper proposes a novel method for human emotion recognition from a single RGB image. We construct a largescale dataset of facial videos (FaceVid), rich in facial dynamics, identities, expressions, appearance and 3D pose variations. We use this dataset to train a deep Convolutional Neural Network for estimating expression parameters of a 3D Morphable Model and combine it with an effective back-end emotion classifier. Our proposed framework runs at 50 frames per second and is capable of robustly estimating parameters of 3D expression variation and accurately recognizing facial expressions from in the-wild images. We present extensive experimental evaluation that shows that the proposed method outperforms the compared techniques in estimating the 3D expression parameters and achieves state-of-the-art performance in recognising the basic emotions from facial images, as well as recognising stress from facial videos.

Automatic emotion recognition is a critical part of human-machine interactions. Reflection of emotions and to develop its understanding is crucial to provide dealings across human beings and machine frameworks. This work determines an automatic system that distinguishes different emotions connoted on the face. The framework is deliberated to apply the hybridization of feature extraction and optimization using PCA and PSO, respectively, to accomplish a high precision rate. PCA is used to get high-quality feature vectors for each category of emotion. Swarm intelligence, optimization is applied to get an optimized feature vector which is essential for classifying the features in the testing phase. For exploratory work, the authors have considered the Japanese Female Facial Expression (JAFFE) dataset. A maximum classification rate of 94.97% is achieved with the proposed technique. The proposed framework execution is assessed in terms of the false rejection rate, false acceptance rate, and accuracy.

Objective: Breast cancer (BC) is the leading and most prevalent form of cancer among women in Bangladesh and worldwide. The objectives of this study were to assess the existing knowledge on breast cancer and the practices of breast self-examination among female Bangladeshi university students. Method: A cross-sectional study was carried out among the 276 female university students. Data were collected by face-to-face interview by using a pre-tested questionnaire.Results: The study results indicate that most of the participants were well informed about breast cancer. Predominantly mentioned signs of breast cancer was a lump in the breast followed by pain in the breast or nipple. The correct responses of breast cancer risk factors were exposure to radiation (58.20%), positive family history (47.6%), obesity (46.9%), lack of physical exercise (43.6%) and smoking (43.2%). The students were well informed about breast self-examination for early diagnosis, but they were not properly informed about frequency. Only 17% reported that they practiced breast self-examination. Respondent’s age, religion, marital status, having a problem in Breast and practices of breast self-examinations were significantly associated (p<0.05) with the knowledge scores in different aspects of breast cancer.Conclusion: The findings of this study indicate that the female students had inadequate knowledge on different aspects of BC and low compliance to recommended BSE practices. Initiating BC educational programs among university students is highly recommended for the early detection and treatment of this increasingly alarming disease.

Differences in stress levels between junior high school students and college students during online learning

We aimed to investigate the association between sleep disturbance and menstrual problems in female Chinese university students. A convenience sample of 1006 female university students participated in this study. Sleep duration, sleep quality, and insomnia symptoms were assessed by the Pittsburgh Sleep Quality Index and the Insomnia Severity Index. A structured questionnaire was used to assess participants' demographics and menstrual characteristics. The prevalence rates of irregular menstrual cycle, heavy menstrual bleeding, menstrual flow length ≥ 7days, period pain, and premenstrual syndrome were significantly higher in participants with sleep disturbance than those without sleep disturbance (all p < 0.05). After adjusting for potential confounding variables, poor sleep quality and insomnia symptoms were significantly associated with menstrual flow length ≥ 7days (OR = 1.81, 95% CI = 1.23-2.68, OR = 1.67, 95% CI = 1.13-2.45), period pain (OR = 1.55, 95% CI = 1.02-2.35, OR = 1.56, 95% CI = 1.02-2.37), and premenstrual syndrome (OR = 1.71, 95% CI = 1.30-2.24, OR = 1.93, 95% CI = 1.46-2.56). In addition, poor sleep quality was significantly associated with heavy menstrual bleeding (OR = 1.75, 95% CI = 1.12-2.72), and insomnia symptoms were significantly associated with irregular menstrual cycle (OR = 1.36, 95% CI = 1.02-1.80). However, short sleep duration (≤ 6h) was only associated with premenstrual syndrome. Our results suggested that sleep disturbance is associated with menstrual problems among female university students. More attention should be paid to improving the sleep quality and insomnia symptoms in individuals with menstrual problems.