Review
Computer Science, Artificial Intelligence
Sicheng Zhao, Xingxu Yao, Jufeng Yang, Guoli Jia, Guiguang Ding, Tat-Seng Chua, Bjorn W. Schuller, Kurt Keutzer
Summary: This survey comprehensively reviews the development of affective image content analysis (AICA) in the past two decades, focusing on the state-of-the-art methods and addressing three main challenges. It provides an overview of emotion representation models, available datasets, and compares representative approaches in emotion feature extraction, learning methods, and AICA-based applications. The survey also discusses future research directions and challenges in the field.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Biology
Md Rabiul Islam, Md Milon Islam, Md Mustafizur Rahman, Chayan Mondal, Suvojit Kumar Singha, Mohiuddin Ahmad, Abdul Awal, Md Saiful Islam, Mohammad Ali Moni
Summary: The study proposed a deep machine-learning model using Convolutional Neural Network to convert EEG data and recognize emotions on images, overcoming the challenge of emotion recognition from low amplitude variation in EEG signals.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Psychology, Multidisciplinary
Lin Lai
Summary: With the development of modern information technology, the flipped classroom teaching mode has become a hot topic in contemporary education and is being applied in various disciplines. However, this teaching mode still faces challenges such as low efficiency and lack of teacher-student interaction, leading to low student enthusiasm for learning. Thus, further testing and revision of the flipped classroom teaching mode is needed.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Engineering, Biomedical
M. A. H. Akhand, Mahfuza Akter Maria, Md Abdus Samad Kamal, Tetsuya Shimamura
Summary: The study proposes an enhanced connectivity feature map for emotion recognition by introducing partial mutual information and an additional channel, which improves the performance of emotion recognition by extracting more information from brain signals.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Article
Engineering, Multidisciplinary
K. A. Shahul Hameed, K. A. Shaheer Abubacker, A. Banumathi, G. Ulaganathan
Summary: This paper presents an automatic image analysis technique for p53 immunostained tissue sections of oral cancer, achieving high classification accuracy from features extracted from the blue component. The method involves segmenting tissue images, clustering cells, classifying cell nuclei as positive or negative, and determining tissue score according to the J-scoring protocol. The automatic technique based on the blue component showed strong agreement with manual scoring, demonstrating high potential for modern cancer diagnosis and therapy design.
Article
Engineering, Multidisciplinary
K. A. Shahul Hameed, K. A. Shaheer Abubacker, A. Banumathi, G. Ulaganatha
Summary: This paper presents an automatic image analysis technique for p53 immunostained tissue sections of oral cancer, which achieves high classification accuracy and consistency in cell nucleus classification and scoring.
Article
Computer Science, Artificial Intelligence
Weigang Wang, Juchao Ma, Chendong Xu, Yunwei Zhang, Ya Ding, Shujuan Yu, Yun Zhang, Yuanjian Liu
Summary: The article proposes a novel feature selection model for dimension reduction and an improved version of the lightweight convolutional neural network, newCNN, to enhance the system's classification performance. By combining newCNN with Support Vector Machines (SVM) to build a hybrid classification (HC) model, the problem of overfitting in the training process is solved, and it demonstrates excellent generalization ability and robustness.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Oznur Ozaltin, Ozgur Yeniay
Summary: The automatic classification of ECG signals is crucial for the diagnosis and treatment of heart disease, which has seen an increase in sudden deaths due to the coronavirus pandemic. In this study, a novel CNN architecture is proposed to detect ECG types and automatically extract features from images. The proposed CNN outperforms other known architectures in classifying ECG images. Short-time Fourier transform and cross-validation are applied in the study to improve the classification results, and the highest accuracy of 99.21% is achieved with the proposed CNN-SVM using CWT.
Article
Thermodynamics
Maryam Imani
Summary: A new nonlinear relationship extraction method is proposed in this work, using convolutional neural network and support vector regression for load forecasting, showing superior performance compared to several outstanding forecasters.
Article
Biology
Abdul Baseer Buriro, Bilal Ahmed, Gulsher Baloch, Junaid Ahmed, Reza Shoorangiz, Stephen J. Weddell, Richard D. Jones
Summary: This study investigated the effectiveness of WST-based feature extraction technique in discriminating between alcoholic and normal EEG records, achieving good classification results with SVM and LDA classifiers.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Agronomy
Yun Peng, Shenyi Zhao, Jizhan Liu
Summary: The paper proposes a fast and accurate identification method based on Canonical Correlation Analysis (CCA) that fuses deep features extracted from Convolutional Neural Networks (CNN) with Support Vector Machine (SVM), achieving better identification performance for different grape varieties in modern agriculture production.
Article
Computer Science, Artificial Intelligence
B. Vidya, P. Sasikumar
Summary: This study presents a gait classification decision support system based on multi-class support vector machine to assist clinicians in diagnosing Parkinson's disease and rating the severity level. By performing kinematic analysis and feature selection to extract gait features, the system demonstrates high accuracy in PD diagnosis according to experimental results.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Jian-Guo Wang, Hui-Min Shao, Yuan Yao, Jian-Long Liu, Hua-Ping Sun, Shi-Wei Ma
Summary: This paper introduces a new EEG-based emotion recognition model built with a convolutional neural network (CNN), which accurately classifies positive, neutral, and negative emotions and achieves improved accuracy. It also studies the factors that affect recognition results using full-channel and full-band data.
APPLIED SOFT COMPUTING
(2022)
Article
Chemistry, Analytical
Ngoc-Dau Mai, Boon-Giin Lee, Wan-Young Chung
Summary: The research developed an affective computing method based on machine learning for emotion recognition using a wearable EEG device. Experiment results showed highest accuracies of 85.81% and 78.52% in subject-dependent and subject-independent cases, with T8 identified as a critical channel for emotion classification through electrode selection.
Article
Computer Science, Information Systems
Huan Deng, Zhenguo Yang, Tianyong Hao, Qing Li, Wenyin Liu
Summary: This paper proposes a dense fusion transformer (DFT) framework for integrating textual, acoustic, and visual information for multimodal affective computing. DFT utilizes a modality-shared transformer (MT) module to extract modality-shared features and fuses sequential features of multiple modalities through dense fusion blocks, achieving affective predictions with a transformer.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)