Article
Computer Science, Artificial Intelligence
Hong Peng, Cancheng Li, Jinlong Chao, Tao Wang, Chengjian Zhao, Xiaoning Huo, Bin Hu
Summary: This study proposes a novel sparse representation-based epileptic seizure classification method based on dictionary learning, which is evaluated on public EEG databases. The new method shows higher automation and recognition rates compared to traditional methods.
Article
Computer Science, Interdisciplinary Applications
Varanasi Satya Sreekanth, Karnam Raghunath, Deepak Mishra
Summary: Atmospheric Gravity Waves play a significant role in Middle Atmosphere Dynamics, and the breaking of Gravity Waves leads to turbulence. However, the accuracy and sparsity of Wind Velocity measuring instruments at the altitude of interest pose a problem for confirming the breaking of Atmospheric Gravity Waves. In this study, we propose a solution using Dictionary Learning and Deep Learning methods to detect Wave Breaking events from atmospheric temperature perturbations, and the effectiveness of this method is demonstrated through a case study using satellite data and validated with ground-based instruments.
COMPUTERS & GEOSCIENCES
(2023)
Article
Environmental Sciences
Tan Guo, Fulin Luo, Leyuan Fang, Bob Zhang
Summary: In this paper, a Meta-pixel-driven target detection model is proposed to address the challenges posed by the high-dimensionality, variability, and heterogeneity in hyperspectral images. By combining low-dimensional embeddable subspace projection and discriminative dictionary pair learning, the proposed model achieves promising performance in various benchmark datasets.
Article
Chemistry, Multidisciplinary
Marcin Kolodziej, Andrzej Majkowski, Andrzej Rysz
Summary: This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. It presents standard approaches for analyzing iEEG signals and discusses modern deep learning algorithms. The study shows that CNN and LSTM networks yield significantly better results, and the gradient-weighted class activation mapping algorithm can identify important iEEG signal fragments for seizure detection.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Wenjie Zhu, Bo Peng, Chunchun Chen, Hao Chen
Summary: This paper proposes a Deep Discriminative Dictionary Pair Learning (DPL-P-3) approach for image classification. By utilizing deep features derived from autoencoders and integrating discriminative dictionary learning and autoencoder loss function, DPL-P-3 can simultaneously learn the deep potential feature and the corresponding dictionary pair, leading to improved image classification performance.
APPLIED INTELLIGENCE
(2023)
Article
Engineering, Biomedical
Xuyang Zhao, Noboru Yoshida, Tetsuya Ueda, Hidenori Sugano, Toshihisa Tanaka
Summary: This study applies commonly used models such as LeNet, VGG, ResNet, and ViT to the EEG image classification task, and solves the problems of data imbalance and model interpretation through data augmentation and model explanation methods. The models achieve good performance in seizure detection and provide visual and quantitative information for clinical experts in diagnosis.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Chemistry, Multidisciplinary
Zakareya Lasefr, Khaled Elleithy, Ramasani Rakesh Reddy, Eman Abdelfattah, Miad Faezipour
Summary: This paper studied epileptic seizure detection methods based on EEG signals and proposed an enhanced technique with a mobile application for monitoring the classification of EEG signals. The proposed method achieved high accuracy and outperformed previous studies. It will have significant impacts in the medical field and Human-Computer Interaction fields.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Quanhong Wang, Weizhuang Kong, Jitao Zhong, Zhengyang Shan, Juan Wang, Xiaowei Li, Hong Peng, Bin Hu
Summary: In this paper, a novel classification algorithm called SVM-KSRC is proposed for automatic epilepsy detection based on electroencephalography (EEG). The algorithm combines support vector machine (SVM) and kernel sparse representation classification (KSRC) to classify EEG signals. Experimental results show that SVM-KSRC outperforms existing machine learning methods in epilepsy detection.
Review
Clinical Neurology
Manfred Hartmann, Johannes Koren, Christoph Baumgartner, Jonas Duun-Henriksen, Gerhard Gritsch, Tilmann Kluge, Hannes Perko, Franz Furbass
Summary: This study presents the design and validation of a deep neural network for two-channel seizure detection. The results show that automatic seizure detection based on two-channel EEG data is feasible.
Article
Computer Science, Information Systems
Jian Liu, Yipeng Du, Xiang Wang, Wuguang Yue, Jim Feng
Summary: In this paper, the possibility of using Automated Machine Learning (AutoML) for epilepsy EEG detection is explored. The neural architecture search (NAS) algorithm is applied to design a model for epilepsy EEG analysis, and feature interpretability methods are used to ensure the reliability of the searched model. Experimental results show that the NAS-based model outperforms the baseline model, improving classification accuracy, F1-score, and Cohen's kappa coefficient. Furthermore, the NAS-based model is capable of extracting EEG features related to seizures for classification.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Engineering, Electrical & Electronic
Yuxi Wang, Haishun Du, Yonghao Zhang, Yanyu Zhang
Summary: This study proposes an efficient and robust discriminant analysis-synthesis dictionary pair learning method for pattern classification. The method designs a coding coefficient discriminant term and imposes a low-rank constraint to enhance the discrimination capability of the structured analysis dictionary and weaken the influence of noises on the structured synthesis dictionary. Experimental results demonstrate that the method has higher classification accuracy and efficiency compared to state-of-the-art dictionary learning methods.
DIGITAL SIGNAL PROCESSING
(2021)
Article
Multidisciplinary Sciences
Artur Gramacki, Jaroslaw Gramacki
Summary: Electroencephalogram (EEG) is a main diagnostic test for epilepsy, but manual detection is time-consuming and challenging. This research fills the gap in the field of automated seizure detection by providing a complete framework using DL approaches and sharing the corresponding codes and results.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Information Systems
Haishun Du, Yonghao Zhang, Yuxi Wang, Linbing He
Summary: In this study, a double-constrained structured discriminant analysis-synthesis dictionary pair learning method is proposed to address the issues existing in existing discriminant ASDPL methods. By incorporating reconstruction and independence constraints, the proposed method enhances the representational and discriminative ability of learned dictionary pairs. Experimental results demonstrate the effectiveness of the method in pattern classification.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Biology
Hong Peng, Chang Lei, Shuzhen Zheng, Chengjian Zhao, Chunyun Wu, Jieqiong Sun, Bin Hu
Summary: This paper presents a novel method for seizure detection using Stein kernel-based sparse representation on EEG recordings. By utilizing the space of symmetric positive definite matrices, the method achieves efficient classification and good detection performance on multiple datasets. The fast computational speed also meets the basic requirements for real-time seizure detection.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Valentin Gabeff, Tomas Teijeiro, Marina Zapater, Leila Cammoun, Sylvain Rheims, Philippe Ryvlin, David Atienza
Summary: This study addressed the lack of interpretability of neural network models in medical decision support by developing a deep learning model from EEG signals for online detection of epileptic seizures and associating model behavior with expert medical knowledge. The focus was on aggregating classification results, identifying frequency patterns, and recognizing signal waveforms. Results showed that the kernel size in the first layer significantly impacts feature interpretability and model sensitivity.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2021)