Exploiting Facial Action Unit in Video for Recognizing Depression using Metaheuristic and Neural Networks

Akbar, Habibullah; Dewi, Sintia; Rozali, Yuli Asmi; Lunanta, Lita Patricia; Anwar, Nizirwan; Anwar, Djasminar

doi:10.1109/iccsai53272.2021.9609747

Cited by 9 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, Wang et al [28] proposed a method utilizing facial landmarks, implementing an LSTM network and global max pooling to identify which instances signal symptoms of depression. Studies by Akbar et al [29] and Rathi et al [30] aimed to optimize depression detection by selecting relevant features from visual behavior. The first work employed Particle Swarm Optimization (PSO) and feedforward neural networks, while the second utilized Fisher Discriminant Ratio (FDR), an incremental formulation of Linear Discriminant Analysis (LDA), to optimally combine these characteristics.…”

Section: A Unimodal Modelsmentioning

confidence: 99%

Multimodal Fusion for Depression Detection Assisted by Stacking Deep Neural Networks

Almeida,

Aires,

Soares

et al. 2024

Preprint

View full text Add to dashboard Cite

Depression is a severe psychosocial pathology that causes mood changes, characterized by a strong feeling of hopelessness and deep sadness. In advanced stages, it can predispose patients to suicidal thoughts, highlighting the importance of finding methods that provide more accurate diagnoses. Traditional diagnosis relies on semi-structured interviews and complementary questionnaires. Combining these methods with careful data analysis that incorporates audiovisual and textual characteristics can obtain valuable clues about the presence of depression in individuals. Therefore, this study proposes a multimodal Ensemble Stacking Deep Neural Network model based on the analysis of facial expression characteristics, audio signals, and textual transcriptions to automatically detect depression. A comprehensive model was evaluated on the multimodal Distress Analysis Interview Corpus-Wizard of Oz dataset. We incorporated substantial volumes of data into the analysis and achieved a degree of separability greater than 0.9. Our results demonstrate both the effectiveness of the method and its superiority to other reference approaches.

show abstract

Section: A Unimodal Modelsmentioning

confidence: 99%

Multimodal Fusion for Depression Detection Assisted by Stacking Deep Neural Networks

Almeida,

Aires,

Soares

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The DAIC-WOZ data set was used as input in the proposed algorithms that only concentrate on facial features. By employing particle swarm optimization (PSO) [20] to choose the best predictors of AUs, one proposed strategy focuses on minimizing AUs in a feed-forward neural network (FFNN). The most accurate predictors are AU04, AU06, AU09, AU10, AU15, AU25, AU26, AU04, AU12, AU23, AU28, and AU45.…”

Section: Related Workmentioning

confidence: 99%

Explainable Depression Detection Based on Facial Expression Using LSTM on Attentional Intermediate Feature Fusion with Label Smoothing

Mahayossanunt,

Nupairoj,

Hemrungrojn

et al. 2023

Sensors

View full text Add to dashboard Cite

Machine learning is used for a fast pre-diagnosis approach to prevent the effects of Major Depressive Disorder (MDD). The objective of this research is to detect depression using a set of important facial features extracted from interview video, e.g., radians, gaze at angles, action unit intensity, etc. The model is based on LSTM with an attention mechanism. It aims to combine those features using the intermediate fusion approach. The label smoothing was presented to further improve the model’s performance. Unlike other black-box models, the integrated gradient was presented as the model explanation to show important features of each patient. The experiment was conducted on 474 video samples collected at Chulalongkorn University. The data set was divided into 134 depressed and 340 non-depressed categories. The results showed that our model is the winner, with a 88.89% F1-score, 87.03% recall, 91.67% accuracy, and 91.40% precision. Moreover, the model can capture important features of depression, including head turning, no specific gaze, slow eye movement, no smiles, frowning, grumbling, and scowling, which express a lack of concentration, social disinterest, and negative feelings that are consistent with the assumptions in the depressive theories.

show abstract

“…Habibullah et al (16) reflects a study on facial behavior evaluation to identify depression from facial action units derived from pictures. Authors used a metaheuristic method to identify a smaller set of facial action unit characteristics.…”

Section: Literature Surveymentioning

confidence: 99%

Optimizing Emotion Recognition of Non-Intrusive E-Walking Dataset

Jain,

Maan

2023

Data and Metadata

View full text Add to dashboard Cite

Emotion recognition being a complex task because of its valuable usages in critical fields like Robotics, human-computer interaction and mental health has recently gathered huge attention. The selection and optimization of suitable feature sets that can accurately capture the underlying emotional states is one of the critical challenges in Emotion Recognition. Metaheuristic optimization techniques have shown promise in addressing this challenge by efficiently exploring the large and complex feature space. This research paper proposes a novel framework for emotion recognition that uses metaheuristic optimization. The key idea behind metaheuristic optimization is to explore the search space in an intelligent way, by generating candidate solutions and iteratively improving them until an optimal or near-optimal solution is found. The accuracy & robustness of emotion identification systems can be enhanced by optimizing the metaheuristic optimization. The major contribution of this research is to develop a Chiropteran Mahi Metaheuristic optimization which emphasizes the weights updating in the classifier for improving the accuracy of the proposed system.

show abstract

Exploiting Facial Action Unit in Video for Recognizing Depression using Metaheuristic and Neural Networks

Cited by 9 publications

References 14 publications

Multimodal Fusion for Depression Detection Assisted by Stacking Deep Neural Networks

Multimodal Fusion for Depression Detection Assisted by Stacking Deep Neural Networks

Explainable Depression Detection Based on Facial Expression Using LSTM on Attentional Intermediate Feature Fusion with Label Smoothing

Optimizing Emotion Recognition of Non-Intrusive E-Walking Dataset

Contact Info

Product

Resources

About