Article
Computer Science, Artificial Intelligence
Biao Sun, Zexu Wu, Yong Hu, Ting Li
Summary: This paper proposes a deep learning-based method to improve the accuracy of brain computer interfaces (BCIs) by transferring the data distribution from golden subjects to BCI-illiterate users. By aligning the dimensionality-reduced BCI-illiterate data with the data of golden subjects using a generator and a CNN classifier, this method outperforms traditional classification methods in terms of accuracy and robustness. The results demonstrate the effectiveness of this approach in identifying EEG signals and its robustness to inter-subject variations.
Article
Engineering, Biomedical
Arunabha M. Roy
Summary: This study proposes an efficient multi-scale convolutional neural network (MS-CNN) for EEG-based motor imagery classification. The model extracts distinguishable features from EEG signals and improves the classification accuracy. The results show that the model outperforms other baseline models and has significance in real-time human-robot interaction.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Engineering, Biomedical
Zhuyao Fan, Xugang Xi, Yunyuan Gao, Ting Wang, Feng Fang, Michael Houston, Yingchun Zhang, Lihua Li, Zhong Lu
Summary: This study proposes a novel algorithm by inserting two modules into CNN to solve the problem that traditional 1D-CNNs are unable to acquire both frequency domain and channel association information. The proposed algorithm achieved an improvement of 6.6% on the motion imagery 4-classes recognition mission and 11.3% on the 2-classes classification task compared to traditional decoding algorithms.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Patrick Oliveira de Paula, Thiago Bulhoes da Silva Costa, Romis Ribeiro de Faissol Attux, Denis Gustavo Fantinato
Summary: Research on brain-computer interface (BCI) systems based on electroencephalography (EEG) signals is rapidly advancing, with a focus on achieving robust performance. Recently, deep learning methods, specifically convolutional neural networks (CNNs), have been applied to BCI systems to enhance performance. This study encodes EEG data as images and uses 2D-kernel-based CNNs for classification, yielding favorable results.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Xiaolin Liu, Ying Sun, Dezhi Zheng, Rui Na
Summary: This paper proposes a novel method based on Hilbert-Huang transformation for subject-specific time-frequency-space pattern optimization in MI-EEG classification. By utilizing joint time-frequency pattern optimization module and spatial pattern optimization module, the method achieves optimized features that improve classification accuracy and demonstrate remarkable computational efficiency.
Article
Engineering, Electrical & Electronic
Changbo Hou, Yuqian Li, Xiang Chen, Jing Zhang
Summary: Signal automatic modulation classification plays an important role in military and civilian fields, but still faces many challenges in complex wireless communication environments. To address these challenges, an algorithm based on feature fusion of convolutional neural network is proposed in this paper, which effectively improves the modulation classification performance.
PHYSICAL COMMUNICATION
(2021)
Article
Chemistry, Analytical
Ye Jin, Mei Wang, Liyan Luo, Dinghao Zhao, Zhanqi Liu
Summary: This paper proposes a TFFS-CRNN model based on TF attention mechanism and FS attention mechanism, which improves feature representation in polyphonic sound event detection. By using two attention modules, it can focus on important features, and experiments show better performance in the DCASE challenge.
Article
Computer Science, Information Systems
Chao Peng, Hong Jiang, Liangdong Qu
Summary: This paper proposes a deep convolutional neural network-based approach for passive RFID tag localization, utilizing joint fingerprint features. Experimental results demonstrate that the method can accurately and stably locate multiple tags in complex indoor environments, outperforming existing schemes.
Article
Biology
Jing Luo, Yaojie Wang, Shuxiang Xia, Na Lu, Xiaoyong Ren, Zhenghao Shi, Xinhong Hei
Summary: Objective: This study proposes a shallow mirror transformer for subject-independent motor imagery EEG classification, which utilizes a multihead self-attention layer to detect and utilize discriminative segments from the entire input EEG trial. The mirror EEG signal and network structure are also constructed to improve classification precision through ensemble learning. Main results: Experiments on different datasets demonstrate the promising effectiveness of the proposed shallow mirror transformer, achieving high accuracies and demonstrating the effectiveness of multihead self-attention in capturing global EEG signal information in motor imagery classification. Significance: This study provides an effective model for subject-independent motor imagery-based BCIs, with the shallowest transformer model available for small sample problems.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biology
Noor Kamal Al-Qazzaz, Zaid Abdi Alkareem Alyasseri, Karrar Hameed Abdulkareem, Nabeel Salih Ali, Mohammed Nasser Al-Mhiqani, Christoph Guger
Summary: This study introduces a new BCI feature fusion method and develops an automatic MI framework for detecting changes pre- and post-rehabilitation. The AICA-WT-TEF framework shows significant performance in MI rehabilitation for post-stroke patients, outperforming other classifiers.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Engineering, Electrical & Electronic
Xiaonan Cui, Tianlei Wang, Xiaoping Lai, Tiejia Jiang, Feng Gao, Jiuwen Cao
Summary: This article proposes a cross-subject transfer learning framework to improve the classification performance of epileptic seizure detection. By transferring useful information from multiple subjects with labeled EEGs to new subjects with unlabeled EEG samples, this method achieves high detection accuracy on new subjects.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Yan Li, Qingguo Wei, Yuebin Chen, Xichen Zhou
Summary: This paper introduces a novel transfer learning approach that combines data alignment and source subject selection for motor imagery based BCIs. Experimental results demonstrate that the hybrid-space data alignment methods outperform two single-space alignment methods significantly, and the source subject selection method substantially enhances the similarity between source subjects and the target subject.
Article
Computer Science, Artificial Intelligence
Mingtao Lei, Xi Zhang, Lingyang Chu, Zhefeng Wang, Philip S. Yu, Binxing Fang
Summary: This article explores the problem of finding route hotspots in large labeled networks, proposes a scalable algorithm FastRH, and designs an RH-Index index structure for storing hotspot and pattern information. Experimental results demonstrate the effectiveness and scalability of these methods on real-world datasets.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)
Article
Instruments & Instrumentation
Fei Wang, Jingyu Ping, Zongfeng Xu, Jinying Bi
Summary: The MJDA and MJRA algorithms address the challenge of collecting labeled data for MI-BCI by transferring knowledge from other subjects. Both methods aim to help subjects with limited labeled data through multi-source joint domain adaption and multi-source joint Riemannian adaption.
REVIEW OF SCIENTIFIC INSTRUMENTS
(2021)
Article
Computer Science, Information Systems
Sung-Jin Kim, Dae-Hyeok Lee, Seong-Whan Lee
Summary: This paper discusses the potential problems of the ShallowConvNet method in EEG-based BCI technology and proposes a novel model called M-ShallowConvNet to solve these problems. Experimental results demonstrate the improved performance of the proposed model.
Article
Engineering, Electrical & Electronic
Jiang Zhu, Daxiong Ji, Zhiwei Xu, Bailu Si
IET SIGNAL PROCESSING
(2018)
Article
Robotics
Wenchuan Qiao, Zheng Fang, Bailu Si
INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Taiping Zeng, Fengzhen Tang, Daxiong Ji, Bailu Si
Article
Neurosciences
Taiping Zeng, Bailu Si
Summary: This paper presents a compact cognitive mapping approach inspired by neurobiological experiments, optimizing the process of describing segments of the explored environment through neighborhood fields to reduce map size and maintain overall environmental layout. Loop closure edges are clustered based on time intervals for batch global optimization to satisfy combined constraints of the whole cluster.
COGNITIVE NEURODYNAMICS
(2021)
Article
Computer Science, Artificial Intelligence
Fengzhen Tang, Mengling Fan, Peter Tino
Summary: The article proposes a new classification method for data points living in curved Riemannian manifolds within the framework of LVQ, which significantly outperforms Euclidean GLVQ in empirical investigations.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Review
Neurosciences
Taiping Zeng, Bailu Si, Jianfeng Feng
Summary: This study introduces a new theory for constructing cognitive maps, describing a range of cell types including boundary vector cells, border cells, and geometry cells that encode the geometric layout of space.
PROGRESS IN NEUROBIOLOGY
(2022)
Article
Automation & Control Systems
Dongye Zhao, Zheng Zhang, Hong Lu, Sen Cheng, Bailu Si, Xisheng Feng
Summary: This study proposes a neural network model called SeMINet, which learns cognitive map representations by integrating sensory and motor information. The model consists of a deep neural network, a recurrent network, and a decoding network, and is able to accurately predict the agent's location and correct path integration errors.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Neurosciences
Jialiang Guo, Xiangsheng Luo, Yuanjun Kong, Bingkun Li, Bailu Si, Li Sun, Yan Song
Summary: This study investigated brain oscillations in children with attention-deficit/hyperactivity disorder (ADHD) during a visual search task. The results revealed impaired target-induced posterior alpha lateralization and midfrontal theta synchronization, indicating deficiencies in executive control and attention networks. These findings provide novel evidence for the understanding of brain oscillations in children with ADHD during stimulus-driven selective attention.
BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING
(2023)
Article
Mathematics
Changbo Zhu, Ke Zhou, Fengzhen Tang, Yandong Tang, Xiaoli Li, Bailu Si
Summary: This study develops a hierarchical Bayesian model for inference and decision making in multi-dimensional volatile environments. Simulation results demonstrate that the model is able to infer and update the agent's internal belief about sensory inputs, and the agent can generate near-optimal behavior based on the internal belief.
Article
Automation & Control Systems
Fengzhen Tang, Peter Tino, Haibin Yu
Summary: This article introduces a method for dealing with data on the manifold of symmetric positive-definite matrices, considering the nonlinear geometry of the manifold through the log-Euclidean distance. GLVQ-LEM and GLVQ-LEML methods are proposed, and experiments are conducted to validate their performance.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Engineering, Civil
Shangshu Yu, Xiaotian Sun, Wen Li, Chenglu Wen, Yunuo Yang, Bailu Si, Guosheng Hu, Cheng Wang
Summary: Absolute pose regression has great potential in LiDAR localization, but current methods suffer from scene ambiguities. This paper proposes a novel framework called NIDALoc, which is inspired by neurobiological localization mechanisms and incorporates a memory module and a pose constrained framework to improve localization accuracy and robustness.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Multidisciplinary Sciences
Taiping Zeng, Bailu Si
Proceedings Paper
Engineering, Electrical & Electronic
Wenchuan Qiao, Zheng Fang, Bailu Si
2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO)
(2018)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.