Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Xin Wu et al.
Summary: This paper proposes a simple and effective UIU-Net framework for small object detection in infrared images, which consists of a large U-Net backbone and an embedded small U-Net for multi-level and multi-scale representation learning. Experimental results demonstrate the superior performance of UIU-Net on infrared single-frame image datasets and video sequence datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Biology
Huiying Li et al.
Summary: A novel dual-attention-based adversarial network for motor imagery classification (MI-DABAN) is proposed, which leverages multiple subjects' knowledge to improve a single subject's classification performance. The method employs a clever adversarial learning method and two unshared attention blocks, resulting in effective and superior classification performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Dongxue Zhang et al.
Summary: Due to its convenience and safety, EEG data is widely used in MI-BCIs. Recent research has begun applying Transformer to EEG signal decoding, but the challenge lies in effectively using data from other subjects to improve single-subject classification performance. To address this, we propose a novel architecture called MI-CAT, which utilizes Transformer's self-attention and cross-attention mechanisms to resolve the distribution differences between domains. Our method achieves competitive performance on real EEG datasets, demonstrating its effectiveness in decoding EEG signals and advancing the development of Transformer for BCIs.
Article
Agricultural Engineering
Rui Li et al.
Summary: In this paper, a novel multi-branch convolutional neural network (Mb-CNN) with density map is proposed for aphid counting. The approach generates an aphid density map to estimate the number of aphids, and achieves better performance compared to state-of-the-art methods.
BIOSYSTEMS ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Ji-Seon Bang et al.
Summary: CNNs have been applied to EEG-based BCIs, but the high-dimensional feature space and subject-specific signal patterns require appropriate methods to enhance decoding accuracy. This study proposes a spatiospectral feature representation method to preserve multivariate information, achieving better classification results than state-of-the-art techniques. The decomposition model obtained relevance scores for electrode channels and frequency domains, confirming the validity of the approach.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Automation & Control Systems
Peiyin Chen et al.
Summary: A novel multiattention adaptation network integrating multiple attention mechanism and transfer learning is proposed for classifying EEG signals in Brain-Computer Interface (BCI) applications. By introducing a multiattention convolutional neural network for processing EEG signals, the classification accuracy is significantly increased. The experiments demonstrate the effectiveness and robustness of the proposed method, showing improved performance in BCI systems by enhancing transfer ability of deep features from local brain regions.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Peixiang Zhong et al.
Summary: In this article, a regularized graph neural network (RGNN) is proposed for EEG-based emotion recognition. The RGNN captures both local and global relations among different EEG channels by considering the biological topology among different brain regions. The proposed adjacency matrix and two regularizers contribute to the improved performance of the RGNN model.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)
Article
Engineering, Biomedical
Yi Chen et al.
Summary: This paper introduces a novel multi-subdomain adaptation method (MSDAN) to improve the classification accuracy of the traditional approaches in EEG-based cross-subject motor imagery (MI) classification tasks.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Yue Gao et al.
Summary: In this paper, the authors propose an EEG-based emotion recognition method using graph networks that can model multi-channel features of EEG signals. The method incorporates spatio-temporal attention mechanism and a self-adaptive brain network adjacency matrix to capture sequential and spatial information. It also introduces a multi-view approach to effectively integrate diverse features. Experimental results demonstrate the superior performance of the proposed method.
IEEE SIGNAL PROCESSING LETTERS
(2022)
Article
Computer Science, Information Systems
Abbas Salami et al.
Summary: In recent years, neural networks and deep architectures have gained attention in brain-computer interfaces for EEG signal analysis. End-to-end models are favored over traditional approaches, as they eliminate the need for prior information and feature extraction. However, the lack of interpretability and the sensitivity of deep neural networks pose challenges for their adoption in the neuroscience community. This study proposes a new deep learning architecture called EEG-ITNet, which extracts rich information from multi-channel EEG signals with less complexity than existing models. Evaluation results show improved classification accuracy compared to competitors, and the validity of network interpretation is supported from a neuroscientific perspective.
Article
Engineering, Biomedical
Chang Liu et al.
Summary: This study proposes a hybrid neural network called SHNN for motor imagery-based brain-computer interfaces. The SHNN utilizes SincNet as band-pass filters to filter EEG data, and incorporates compression and excitation mechanisms, convolutional neural networks, and a gated recurrent unit module for deep feature representation and classification. The results show that the SHNN outperforms other state-of-the-art methods on the BCI competition IV datasets.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Geochemistry & Geophysics
Anwen Wu et al.
Summary: Synthetic Aperture Radar (SAR) and Inverse Synthetic Aperture Radar (ISAR) imaging technologies play a crucial role in acquiring high-resolution radar images, which serve as important basis for automatic target recognition (ATR). This work extends the Complex Approximated Message Passing (CAMP) method to an iterative thresholding method in ISAR imaging, incorporating compressed sensing (CS) and regularization for improved target enhancement and noise reduction. Experimental results demonstrate the advantage of regularization in SAR image processing.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Review
Neurosciences
Zhongke Gao et al.
Summary: The article introduces the research and analysis of EEG signals, explores the application of brain network and deep learning in EEG signal analysis, and proposes a framework combining recurrence plots and convolutional neural networks to achieve fatigue driving recognition.
COGNITIVE NEURODYNAMICS
(2021)
Article
Biochemical Research Methods
Mouad Riyad et al.
Summary: The study developed a deeper ConvNet model with improved performance and optimal complexity by introducing new convolutional layers and an Inception-inspired block to extract richer features for better classification performance. The experimental results were comparable to other state-of-the-art techniques, demonstrating that motor imagery decoding is achievable without handcrafted features.
JOURNAL OF NEUROSCIENCE METHODS
(2021)
Article
Computer Science, Artificial Intelligence
He Zhao et al.
Summary: The proposed method improves classification performance on a single subject by considering information from multiple subjects, reducing calibration time for BCI and promoting its development.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Geochemistry & Geophysics
Danfeng Hong et al.
Summary: This study introduces a general multimodal deep learning (MDL) framework for the classification and identification challenges in geoscience and remote sensing. By investigating a special case of multi-modality learning (MML), the study presents five fusion strategies and demonstrates how to train deep networks and build network architectures effectively. Experimental results on two different multimodal RS data sets confirm the efficiency and advantages of the proposed MDL framework.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Danfeng Hong et al.
Summary: This article thoroughly investigates the applications of Convolutional Neural Networks (CNNs) and Graph Convolutional Networks (GCNs) in hyperspectral image classification. By developing a new minibatch GCN (miniGCN) to train and infer large-scale GCNs, as well as exploring fusion strategies for different types of HS features, the study achieves good classification performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Ali Al-Saegh et al.
Summary: This study introduces a novel augmentation method for enlarging EEG datasets by cutting and concatenating different periods in EEG trials. Experimental results demonstrate the method's potential in handling classification of small-scale datasets, and show improvement over existing research in terms of classification results.
Article
Engineering, Biomedical
Yang Li et al.
Summary: This study introduces a novel MI-EEG decoding framework, which enhances the extraction efficiency of EEG signals through a time-spectral feature fusion network, leading to better decoding performance.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Engineering, Biomedical
Xiaolin Hong et al.
Summary: The proposed method utilizes an adversarial learning strategy and introduces a dynamic joint domain adaptation network to learn domain-invariant feature representation, significantly improving EEG classification performance.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Engineering, Biomedical
He He et al.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2020)
Article
Engineering, Biomedical
Ahmed M. Azab et al.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2019)
Article
Neurosciences
Qiyun Huang et al.
FRONTIERS IN NEUROSCIENCE
(2019)
Article
Computer Science, Information Systems
Gaowei Xu et al.
Article
Engineering, Biomedical
Vernon J. Lawhern et al.
JOURNAL OF NEURAL ENGINEERING
(2018)
Article
Computer Science, Artificial Intelligence
Qingqing Zheng et al.
PATTERN RECOGNITION
(2018)
Article
Computer Science, Information Systems
Jun Yang et al.
Article
Neurosciences
Robin Tibor Schirrmeister et al.
HUMAN BRAIN MAPPING
(2017)
Article
Engineering, Biomedical
Wojciech Samek et al.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2013)
Article
Engineering, Biomedical
Fabien Lotte et al.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2011)
Article
Engineering, Electrical & Electronic
Hyohyeong Kang et al.
IEEE SIGNAL PROCESSING LETTERS
(2009)
Article
Engineering, Biomedical
Moritz Grosse-Wentrup et al.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2008)
Article
Neurosciences
G. Pfurtscheller et al.
Article
Engineering, Biomedical
G Schalk et al.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2004)
Review
Clinical Neurology
JR Wolpaw et al.
CLINICAL NEUROPHYSIOLOGY
(2002)
