Article
Neurosciences
Nikki Leeuwis, Sue Yoon, Maryam Alimardani
Summary: This study focused on comparing the functional connectivity of 54 novice MI-BCI users in different network scales during resting state, left vs. right-hand motor imagery task, and the transition between the two phases. The results showed that in the alpha band, functional connectivity in the right hemisphere was increased in High compared to Low aptitude MI-BCI users during motor imagery. These findings suggest that connectivity might be a valuable feature in MI-BCI classification and in solving the MI-BCI inefficiency problem.
FRONTIERS IN HUMAN NEUROSCIENCE
(2021)
Article
Neurosciences
Luke Tait, Jiaxiang Zhang
Summary: EEG microstate analysis is a method for studying brain states and transitions, but it is limited in its use at the sensor level. This study generalized the microstate methodology to source-reconstructed electrophysiological data and identified ten microstates with distinct spatial distributions. The study also found that source-level microstates were associated with different functional connectivity patterns.
Article
Engineering, Electrical & Electronic
Xiaodong Yang, Lei Guan, Yajun Li, Weigang Wang, Qing Zhang, Masood Ur Rehman, Qammer Hussain Abbasi
Summary: The study introduces a novel C-band microwave sensing method based on wireless channel information for quantitatively and qualitatively assessing finger tapping movements non-contact. By processing signal features and utilizing support vector machine, accurate results can be obtained for patients with different severity.
IEEE SENSORS JOURNAL
(2021)
Article
Neurosciences
Leonardo Versaci, Rodrigo Laje
Summary: The study demonstrates that focusing attention on the temporal aspects can improve accuracy and resynchronization efficiency in paced finger tapping.
EUROPEAN JOURNAL OF NEUROSCIENCE
(2021)
Article
Engineering, Biomedical
Jiayang Xu, Wenxia Qian, Liangliang Hu, Guangyuan Liao, Yin Tian
Summary: This study proposes a novel feature called asPLV based on multi-channel EEG emotional features, which shows superior classification performance and generalization in recognizing different emotions. The method also introduces a novel brain network metric to elucidate the collaboration and information exchange among emotion-related brain regions, and provides new insights for the development of an emotional brain-computer interface (BCI).
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Article
Multidisciplinary Sciences
Yuto Kurihara, Toru Takahashi, Rieko Osu
Summary: This study found that inter-brain synchronization significantly increased between multiple brain regions during fast tapping tasks, and synchronization between the central and left-temporal regions was positively correlated with the instability of coordination.
SCIENTIFIC REPORTS
(2022)
Article
Automation & Control Systems
Xiaolin Yuan, Guojian Ren, Yongguang Yu, Wenjiao Sun
Summary: This paper investigates the mean-square pinning control problem of fractional stochastic discrete-time complex networks. It establishes a new model with stochastic noise and develops pinning controllers and sufficient conditions for the complex networks. By utilizing Lyapunov energy function theory and matrix analysis theory, it proves that synchronization of the networks can be achieved in a mean-square sense via pinning control. Furthermore, these results are extended to solve the synchronization problem of general fractional discrete-time complex networks without noise.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2022)
Article
Mathematics, Applied
Kezhao Xiong, Man Zhou, Wei Liu, Chunhua Zeng, Zhengxin Yan
Summary: In this study, a heat conduction model on a complex network with non-uniformly distributed node masses was proposed. It was found that there exists a critical point at alpha=1, which determines the working mode of thermal rectification. The critical transition was identified as a general phenomenon that is independent of network size, average degree, or degree distribution. The physical mechanism of the critical transition was also identified through theoretical analyses based on phonon spectra.
Article
Psychology, Multidisciplinary
Segolene M. R. Guerin, Juliette Boitout, Yvonne N. Delevoye-Turrell
Summary: This study examined the role of attention in motor timing using time series analysis and a dual task paradigm. It found that different timing strategies were used for slow and fast movements, with contrasting attentional demands. The analysis also confirmed that temporal and spatial constraints impacted the attentional resources allocated to finger-tapping tasks.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Neurosciences
Zhiying Long, Xuanping Liu, Yantong Niu, Huajie Shang, Hui Lu, Junying Zhang, Li Yao
Summary: Dynamic functional connectivity (DFC) analysis is a method used to study the time-varying functional interactions between brain regions. In this study, an alternating HMM (aHMM) method was proposed, which showed better estimation of DFC with improved robustness to noise, parameter number, and sample size compared to the sliding window (SW) method and the standard hidden Markov model (HMM). Analysis of real fMRI data from patients with cerebral small vessel disease (CSVD) revealed that aHMM was able to detect significant differences in connectivity amplitude and fluctuations between patient groups, while HMM and SW failed to do so.
COGNITIVE NEURODYNAMICS
(2022)
Article
Neurosciences
Shuntaro Sasai, Takahiko Koike, Sho K. Sugawara, Yuki H. Hamano, Motofumi Sumiya, Shuntaro Okazaki, Haruka K. Takahashi, Gentaro Taga, Norihiro Sadato
Summary: The study used fast fMRI to investigate shifts in brain-wide neural coherence during different task states in the ultraslow frequency range. Through clustering analysis, four frequency bands were identified to show band-specific shifts of neural coherence. The study also found that regions with similar spectra formed functional modules of the brain network, with specific shifting patterns of coherence observed in different frequency bands.
Article
Automation & Control Systems
Ying Cui, Luyang Yu, Yurong Liu, Wenbing Zhang, Fawaz E. Alsaadi
Summary: This paper investigates the non-fragile state estimation problem for a class of continuous-time delayed complex networks. A dynamic event-triggering mechanism is applied to improve resource utilization efficiency and gain matrices of the estimator are computed based on certain matrix inequalities to ensure robustly exponential boundedness for estimation error dynamics. An illustrative simulation is presented to demonstrate the validity of the proposed non-fragile estimator.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2021)
Article
Mathematics, Applied
Ralph G. Andrzejak
Summary: Complex-valued quadratic maps exhibit various dynamic behaviors depending on the parameter c, including convergence, periodic cycles, aperiodic behavior, or divergence. Coupled networks of quadratic maps can display synchronization, desynchronization, and chimera states, with boundaries between bounded and divergent solutions being fractals. The set of bounded solutions is divided into countless subsets, each containing only one synchronization state, enclosed within fractal boundaries.
Article
Radiology, Nuclear Medicine & Medical Imaging
Priyanka Mittal, Anil K. Sao, Bharat Biswal
Summary: This study aims to explore and compare resting state functional brain networks based on instantaneous phase and instantaneous amplitude representations. The results demonstrate that both representations have their unique advantages in functional connectivity, and combining them improves the accuracy of the results.
MAGNETIC RESONANCE IMAGING
(2023)
Article
Neurosciences
Tatiana M. Medvedeva, Marina Sysoeva, Ilya Sysoev, Lyudmila V. Vinogradova
Summary: This study investigates the dynamic changes in functional connectivity during seizures and postictal periods, and finds that they have significant effects on interhemispheric coupling and resting-state connectivity. These findings suggest the presence of plastic network alterations that may contribute to seizure propagation and postictal behavioral impairments.
EXPERIMENTAL NEUROLOGY
(2023)
Article
Engineering, Biomedical
Juan Antonio Ramirez Torres, Ian Daly
Summary: Our study found that visual stimulus modulation based on Golay, almost perfect, and deBruijn sequences provided the best results, significantly outperforming commonly used m-sequences in all cases. Artificial neural network processing algorithms offer the best processing pipeline for this type of BCI, achieving a maximum classification accuracy of 94.7% on real EEG data while obtaining a maximum ITR of 127.2 bits min(-1) in a simulated 64-target system. The simulated framework used in this study demonstrated previously unattainable flexibility and convenience while remaining reasonably realistic, suggesting new considerations for further code-based BCI development.
JOURNAL OF NEURAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Jing Jin, Hua Fang, Ian Daly, Ruocheng Xiao, Yangyang Miao, Xingyu Wang, Andrzej Cichocki
Summary: A novel feature optimization and outlier detection method for the CSP algorithm is proposed, which utilizes MCD to detect and remove outliers, Fisher score to evaluate and select features, and an IMCD algorithm to prevent the emergence of new outliers. The proposed method shows significant improvement in classification accuracy and feature distribution compared to traditional CSP and other competing methods.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Clinical Neurology
Ian Daly
Summary: This study proposes a new method to reduce physiological artifacts in EEG recordings during joint EEG-fMRI sessions by combining independent component analysis and fMRI-based head movement estimation. The method significantly decreases the influence of physiological artifacts and outperforms other state-of-the-art methods in removing these artifacts.
CLINICAL NEUROPHYSIOLOGY
(2021)
Article
Engineering, Biomedical
Jing Jin, Hao Sun, Ian Daly, Shurui Li, Chang Liu, Xingyu Wang, Andrzej Cichocki
Summary: In this study, we propose a novel motor imagery classification model based on functional connectivity measurement between brain regions and graph theory. The model extracts motifs describing local network structures from functional connectivity graphs and uses a graph embedding model to build a classifier. Experimental results showed high classification accuracies, indicating the potential of our proposed method for motor imagery classification.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Engineering, Biomedical
Shurui Li, Jing Jin, Ian Daly, Chang Liu, Andrzej Cichocki
Summary: The study aims to improve the P300-based BCI system by proposing a novel hybrid feature selection method to address feature redundancy, with experimental results demonstrating superior performance. The main contribution of this method lies in enhancing the performance of the P300-based BCI speller.
JOURNAL OF NEURAL ENGINEERING
(2021)
Article
Biochemical Research Methods
Shurui Li, Jing Jin, Ian Daly, Xingyu Wang, Hak-Keung Lam, Andrzej Cichocki
Summary: The study proposed a novel multi-feature subset fuzzy fusion (MSFF) framework for recognizing P300 speller users' spelling intention, which achieved promising results in enhancing classification performance when evaluated on public datasets.
JOURNAL OF NEUROSCIENCE METHODS
(2021)
Article
Computer Science, Information Systems
Hua Fang, Jing Jin, Ian Daly, Xingyu Wang
Summary: This research proposes a fusion method combining Filter Banks and Riemannian Tangent Space (FBRTS) in multiple time windows for optimal feature extraction in multi-category motor imagery brain-computer interfaces (MI-BCIs). The experimental results demonstrate the effectiveness of the FBRTS method in addressing operational frequency band variance and noise interference, leading to improved classification accuracy.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Review
Engineering, Biomedical
Milan Rybar, Ian Daly
Summary: This paper reviews the current literature on semantic neural decoding, discussing neuroimaging methods, experimental designs, and machine learning pipelines used to aid the decoding process. The efficacy of semantic decoders is quantified through measuring information transfer rates. The paper also addresses challenges in this research area and presents potential solutions, as well as discussing future directions. Despite its increasing popularity, this is the first literature review focusing on semantic decoding across neuroimaging modalities and quantifying decoder efficacy.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Biochemical Research Methods
Chang Liu, Jing Jin, Ian Daly, Hao Sun, Yitao Huang, Xingyu Wang, Andrzej Cichocki
Summary: In this study, a novel framework called BHNN was proposed to improve the performance of MI-based BCIs using the bispectrum. The BHNN utilized convolutional neural networks, gated recurrent units, and squeeze-and-excitation modules to extract deep relations and sequential information from the bispectrum. The results demonstrated promising decoding performance in MI-EEG, outperforming other existing methods significantly.
JOURNAL OF NEUROSCIENCE METHODS
(2022)
Article
Neurosciences
Wei Liang, Jing Jin, Ian Daly, Hao Sun, Xingyu Wang, Andrzej Cichocki
Summary: Multi-channel EEG is used to capture features for motor imagery based BCI. Removing irrelevant channels can improve classification performance. This study introduces a new method based on graph convolutional neural network for channel selection, achieving significant improvements in performance on three MI datasets.
COGNITIVE NEURODYNAMICS
(2023)
Article
Multidisciplinary Sciences
Inas Al-Taie, Paola Di Giuseppantonio Di Franco, Michael Tymkiw, Duncan Williams, Ian Daly
Summary: Sound has a significant impact on the interest, emotional response, and engagement of virtual museum exhibit audiences. Customized soundscape design can improve audience engagement.
Article
Multidisciplinary Sciences
Ian Daly
Summary: Neural decoding models can be used to decode neural representations of visual, acoustic, or semantic information. In this study, the researchers explored the combination of functional magnetic resonance imaging (fMRI) and electroencephalogram (EEG) to develop an acoustic decoder. By using a joint EEG-fMRI paradigm and fMRI-informed EEG source localization, they were able to decode and reconstruct individual pieces of music from EEG data with a mean rank accuracy of 59.2%.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Biomedical
Runze Wu, Jing Jin, Ian Daly, Xingyu Wang, Andrzej Cichocki
Summary: This study proposes a new deep learning model for motor imagery-based brain-computer interface systems. The model utilizes a convolutional neural network with a multi-scale and channel-temporal attention module to automatically extract features and improve recognition ability.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Engineering, Biomedical
Chang Liu, Jing Jin, Ian Daly, Shurui Li, Hao Sun, Yitao Huang, Xingyu Wang, Andrzej Cichocki
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
Engineering, Biomedical
Yangyang Miao, Jing Jin, Ian Daly, Cili Zuo, Xingyu Wang, Andrzej Cichocki, Tzyy-Ping Jung
Summary: The CSP algorithm is widely used in MI-BCI systems, but its effectiveness depends on optimal frequency band and time window selection. This study proposes the CTFSP framework to extract sparse CSP features from multi-band filtered EEG data in multiple time windows, showing promising performance in improving MI-BCI systems.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)