检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： Yimeng Dong Guangyao Liu Yankai Yin Mengxuan Wu Feng Duan Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University School of Software Tiangong University Department of Communication Sciences and Disorders University of Texas at Rio Grande Valley Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Tianjin China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Despite the success of pixel-based black-box models in most semantic segmentation algorithms for autonomous driving technology, identifying the causes of recognition errors remains challenging. To address this issue, we propose a hierarchical graph convolutional semantic segmentation method based on superpixels. This approach employs a superpixel segmentation algorithm to convert the original image into graph-structured data with rich semantic information, which is then updated with a graph neural network that utilizes spatial relationships. Graph pooling aggregates results, while graph unpooling restores richer node information, leading to final semantic segmentation. The proposed method captures extensive node information and enhances the interpretability of semantic segmentation by demonstrating the process from pixels to superpixels, aggregated results, and ultimately semantic segmentation. Experimental results demonstrate that compared to GraphSAGE and TAGCN, our method improves the mean Intersection over Union by over 10% on the VOC2012 and Cityscapes datasets. This research provides a more interpretable and efficient approach to semantic segmentation in autonomous driving applications.

关键词： Convolution Semantic segmentation Biomimetics Aggregates Semantics Closed box Graph neural networks Image restoration Autonomous vehicles Robots

来源：评论

学校读者我要写书评

暂无评论

A discussion of statistical criteria for assessing awareness with SMR BCI after brain injury

A discussion of statistical criteria for assessing awareness...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Amaunam, Idorenyin Schneider, Christoph Da Silva, Marina Lopes Jöhr, Jane Diserens, Karin Perdikis, Serafeim Brain-Computer Interface and Neural Engineering Laboratory School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom Gordon Center for Medical Imaging Massachusetts General Hospital Harvard Medical School Department of Radiology BostonMA United States Acute Neurorehabilitation Unit Division of Neurology Centre Hospitalier Universitaire Vaudois Department of Clinical Neurosciences Lausanne Switzerland

ISBN: (纸本)9798350337020

This work discusses the implications of selecting particular statistical metrics and thresholds as criteria to diagnose awareness through brain-computer interface (BCI) technology in patients with Disorders of Consciousness (DOC). We report a first analysis of a novel dataset collected to investigate whether a motor attempt electroencephalography (EEG) paradigm coupled with Functional Electrical Stimulation (FES) can detect command following and, therefore, signs of conscious awareness in DOC. We assessed 22 DOC patients admitted to the acute rehabilitation unit after a brain lesion over one or more sessions. We extracted EEG sensorimotor rhythms and performed a standard open-loop BCI pipeline evaluation, classifying motor attempt against resting-state trials. We validate this approach by correlating classification accuracy with the established clinical scale Coma Recovery Scale Revised. We employ a machine learning (ML)-inspired diagnostic criterion based on confidence intervals over chance-level classification accuracy and show that it yields more conservative and, arguably, reliable inference of Cognitive Motor Dissociation (CMD) by means of command-following, neuroimaging-based tools, compared to diagnoses based on clinical assessments or criteria examining the statistical significance of brain features across different mental states. © 2023 IEEE.

关键词： awareness brain-computer interface chance-level disorders of consciousness motor attempt

来源：评论

学校读者我要写书评

暂无评论

Decoding Respiratory Signals from LFP in Olfactory Bulb based on ConvLSTM Framework 7

Decoding Respiratory Signals from LFP in Olfactory Bulb base...

引用

7th International Conference on Biological Information and Biomedical Engineering, BIBE 2024

作者： Xu, Haoze Yu, Bowen Yu, Chaonan Xu, Kedi Qiushi Academy for Advanced Studies Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal Key Laboratory for Biomedical Engineering of Ministry of Education School of Biomedical Engineering and Instrument Science Zhejiang University China Nanhu Brain-computer interface institute Hangzhou311100 China State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China

ISBN: (纸本)9783800762910

Respiratory signals are crucial for decoding olfactory neural circuits and understanding respiration-entrained local field potential (LFP) rhythms. Acquiring high-precision respiratory signals often requires additional equipment, increasing the experimental burden, particularly in free-moving paradigms. However, within the current neuroscience paradigm, we have not yet found a non-invasive method for obtaining the respiratory signals of laboratory animals. To minimize surgical trauma to experimental animals, this paper introduces a ConvLSTM-based decoding method, which uses the LFP from the olfactory bulb (OB) region of animals to accurately decode respiratory signals. After validating the effectiveness of the ConvLSTM method through comparative experiments, we further investigated the factors influencing the model's decoding performance. The Gamma frequency band exhibited the best decoding results, with a mean absolute error (MAE) of 0.16±0.09, which may be related to the causal direction from respiratory signals to Gamma rhythms. Additionally, the ConvLSTM model demonstrated strong trend prediction capabilities in multi-sequence point predictions and forward predictions, despite a slight decline in single-point prediction accuracy. Extensive validation on publicly available datasets indicates that the ConvLSTM-based respiratory decoding approach is highly applicable, offering a non-invasive alternative for respiratory signal acquisition in animal studies. © VDE VERLAG GMBH.

关键词： Noninvasive medical procedures

来源：评论

学校读者我要写书评

暂无评论

Decomposition frequency optimization in wavelet-based template matching algorithms to manage P300 latency jitter

Decomposition frequency optimization in wavelet-based templa...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Ilaria Quattrociocchi Valentina Caracci Angela Riccio Valentina Galiotta Mariagrazia D’Ippolito Febo Cincotti Jlenia Toppi Laura Astolfi Department of Computer Control and Management Engineering Sapienza University of Rome Italy Neuroelectrical Imaging and Brain Computer Interface Laboratory Fondazione Santa Lucia IRCCS Rome Italy

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Event-Related Potentials (ERPs) are modifications of the brain activity in response to external sensory stimulation. P300 is a positive ERP component that occurs 300 ms after the presentation of a rare stimulus and indicates conscious perception of an unexpected change in sensory stimulation. Since the amplitude of ERPs is comparable to that of background electroencephalography, the most widespread approach to render ERPs correctly detectable is time-domain averaging. ERPs are physiologically affected by variations in latency, referred to as latency jitter. The most promising techniques to address latency jitter are cross-correlation template matching algorithms, which estimate single-trial latencies and resynchronize them according to a template that best describes the ERP component. Adaptive Wavelet Filtering (AWF) is an algorithm applied in the wavelet domain to provide the optimal compromise of time-frequency resolution in detecting ERPs. The choice of an appropriate decomposition frequency is crucial in the application of AWF, as it is essential for identifying the correct template and estimating single-trial latencies. In this study, we investigated the influence of frequency on the performance of AWF to optimize it. The algorithm was tested on simulated data with varying latency shifts and signal-to-noise ratios as well as for data recorded from 11 healthy subjects during an auditory oddball paradigm. Results on both simulated and real EEG data showed how frequency decomposition of 3 Hz is the most appropriate for P300 waveform detection.

关键词： Time-frequency analysis Wavelet domain Jitter Electroencephalography Physiology Frequency estimation Time-domain analysis Signal resolution Optimization Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Active Learning for High-Quality Sawtooth Wave Dataset Generation in Sleep Analysis

Active Learning for High-Quality Sawtooth Wave Dataset Gener...

引用

Frontiers Technology of Information and computer (ICFTIC), IEEE International Conference on

作者： Jinghuang Chen Xiaoyu Bao Yuntao Ye Qiyun Huang School of Automation Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Research Center for Brain-Computer Interface Guangzhou China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Sawtooth Waves (STW) that occur during Rapid Eye Movement (REM) sleep are closely associated with memory consolidation and the regulation of brain functions. However, due to challenges in data acquisition and the high cost of manual annotation, there is currently an absence of a publicly massive STW annotated dataset. This study focuses on constructing a high-quality STW dataset, comprising 4912 samples from 200 participants, and developing classification algorithms for STW detection. We utilized three prevalent algorithms-Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Convolutional neural Network (CNN)-to assess the dataset's quality. The dataset achieved a maximum classification accuracy of 95.62% with the CNN, confirming the gold standard of STW dataset. Finally, we studied age and gender difference in physiological characteristics of STW, including average frequency of STW, peak-to-peak amplitude(PTP), root mean square(RMS) and spectrum power. This study created a public STW dataset and a STW detection model, laying the groundwork for analyzing the mechanisms of STW events.

关键词： Support vector machines Accuracy Annotations Active learning Vectors Regulation Classification algorithms Convolutional neural networks Rapid eye movement sleep Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Creating Virtual Fear to Control the Locomotion Behavior of Pigeon Robots Using Micro-Stimulation

Creating Virtual Fear to Control the Locomotion Behavior of ...

引用

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Long Yang Zuohao Ma Mengmeng Li Lifang Yang Zhigang Shang School of Electrical Engineering Zhengzhou University Zhengzhou China Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology Zhengzhou China

Unlike the flight control of UAVs, the motion control of the pigeon robot needs to consider biological perceptions and decisions. Since it was impossible to perceive the state of the pigeon in the wild environment in real-time, this paper proposed whether instinctive fear emotions can be used to intervene in the movement intention of the pigeon to achieve control of its flight direction by autonomous avoidance. In this paper, we demonstrated that the neural activity of the substantia grisea et fibrosa periventricularis (SGP) nucleus in the pigeon was related to their fearful emotions through tonic immobility (TI) experiments and looming visual stimulation experiments. To verify that the SGP nucleus can modify the motor intention of the pigeon, we conducted electrical stimulation experiments on the SGP nucleus. We found that all pigeons’ SGP nuclei showed avoidance behavior on the same side of the stimulated brain area after stimulation. Thus, using the avoidance behavior produced by micro-stimulation of the SGP nucleus, we achieved control of the flight direction of the free-flying pigeon robot outdoors. This kind of locomotion control utilizing fear emotion can exert the biological intelligence to make the most adaptive behavior and provide technical reference for the outdoor long-distance control of bird robots.

关键词： Visualization neural activity Electrical stimulation Birds Biology Real-time systems Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Development of yellow-light TiO2 integrated photonics

引用

Optics Letters 2025年第11期50卷 3489-3492页

作者： Chen, Zequn Tang, Yiheng Wei, Maoliang Li, Xiaojing Sun, Boshu Wu, Yingchun Zou, Sishuo Huang, Ji Si, Ke Gong, Wei Lin, Hongtao Li, Lan Institute of Advanced Technology Westlake Institute for Advanced Study Hangzhou310024 China Zhejiang Key Laboratory of 3D Micro Nano Fabrication and Characterization School of Engineering Westlake University Hangzhou310030 China The State Key Lab of Brain-Machine Intelligence College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China MOE Frontier Science Center for Brain Science & Brain-Machine Integration Zhejiang University Hangzhou310027 China Nanhu Brain-Computer Interface Institute Hangzhou311100 China College of Optical Science and Engineering Zhejiang University Hangzhou310027 China Westlake Institute for Optoelectronics Fuyang Zhejiang Hangzhou311421 China

Visible-light photonic integrated circuits (PICs) are rapidly emerging as a crucial technology to overcome the scaling challenges in quantum information processing and biosensing. Titanium dioxide (TiO2), with its high transparency in the visible range, is regarded as a promising material for facilitating the development of high-performance visible-light integrated systems. In this paper, we introduce a series of passive TiO2 integrated devices, which include waveguides, multimode interferometers (MMIs), and thermo-optic switches (TOSs), monolithically integrated for the first time to our knowledge at a working wavelength of 589 nm. A propagation loss of 5.46 ± 0.17 dB/cm demonstrates a significant improvement over previous reports on yellow-light TiO2 waveguides. This study marks the first fabrication of a TOS operating at 589 nm, featuring a TiO2 core and polymer cladding. Notably, it achieves a power consumption (Pπ) of 8.24 mW, which represents a threefold reduction compared to silicon nitride-based TOSs operating in the visible spectrum. These results offer new insight into the design and fabrication of visible waveguide-integrated devices, paving the way for future emerging applications, such as quantum information, sensors, and biomedical science. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Gossip-Based Economic Dispatch Algorithm of Grid-Connected Microgrids Over Unbalanced Directed Networks

Gossip-Based Economic Dispatch Algorithm of Grid-Connected M...

引用

Asian Control Conference

作者： Yanmeng Zhang Yalin Zhang Zhongxin Liu College of Artificial Intelligence Nankai University Tianjin China Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Tianjin China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

A gossip-based distributed economic dispatch (ED) algorithm of grid-connected microgrids is introduced in this paper to optimize distributed generation costs despite random communication link failures. The algorithm solves the ED problem under asynchronous and synchronous directed communication within the framework of a multi-agent system. It employs a leader-following consensus approach to achieve distributed ED, ensuring supply-demand balance and adherence to generator constraints. The convergence analysis proves the algorithm's ability to reach mean square consensus and almost sure consensus if the expectation of the switching topologies is strongly connected, which is a milder condition than uniformly jointly strongly connected or balanced switching topologies. The specific proof holds for any initial value, indicating the proposed algorithm has no requirement in initialization. Simulations validate the algorithm's robustness against communication disruptions and its effectiveness in plug-and-play and maintaining economic operations.

关键词： Network topology Microgrids Switches Propagation losses Robustness Generators Topology

来源：评论

学校读者我要写书评

暂无评论

An Improvement of the Trajectory Segmented DDPC:Utilizing LQ Decomposition

An Improvement of the Trajectory Segmented DDPC:Utilizing LQ...

引用

第43届中国控制会议

作者： Jingqian Yan Malika Sader Yucheng Li Zhongxin Liu College of Artificial Intelligence Nankai University Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Department of Automation Tsinghua University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Behavioral systems theory has inspired the emergence of the data-driven predictive control methods(DDPC).These DDPC methods are influenced by non-causal terms,which are primarily responsible for the poor performance of systems in noisy *** the existing trajectory segmentation DDPC methods enforce causality,they increase the dimension of decision variables,resulting in computational *** address this problem,an improvement of trajectory segmentation DDPC utilizing LQ decomposition is proposed in this ***,the equivalence between the proposed DDPC and the existing DDPC is demonstrated in a noise-free *** proposed method decreases computational complexity and improves noise robustness by reducing decision variable dimensions and matching initial conditions *** in noisy conditions,the proposed DDPC method effectively solves problems without needing extra ***,the efficacy of the proposed method is shown through a numerical case study by varying parameters like noise level.

关键词： Data-driven predictive control trajectory segmentation LQ decomposition

来源：评论

学校读者我要写书评

暂无评论

A Teleoperated Manipulator Control System Based on Surface Electromyography Using Deep Learning 12

A Teleoperated Manipulator Control System Based on Surface E...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Lai, Zhiping Zhang, Xueze Wang, Junkongshuai Mu, Wei Wang, Aiping Niu, Lan Zhang, Lihua Wang, Hongbo Kang, Xiaoyang Bin, Jianxiong Shanghai Engineering Research Center of Ai and Robotics Moe Frontiers Center for Brain Science Institute of Ai and Robotics Academy for Engineering and Technology Fudan University Laboratory for Neural Interface and Brain Computer Interface State Key Laboratory of Medical Neurobiology Engineering Research Center of Ai and Robotics Ministry of Education Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Yiwu Research Institute of Fudan University Zhejiang Yiwu City322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Gesture recognition based on surface electromyography (sEMG) is a popular topic in teleoperation field, which has the characteristics of convenience, maneuverability, flexibility and adaptability. With the continuous development of deep learning technology, the variety and accuracy of gesture recognition are constantly improving. In our previous research, a new neural network based on graph convolutional network and temporal convolutional network (STCN-GR) was proposed and achieved good results in gesture recognition task. In this paper, we develop a teleoperated manipulator control system based on STCN-GR combined with majority voting. The experimental results show that the performance of proposed system can achieve relatively excellent performance in recognition accuracy and computation speed. In this paper, we choose a mechanism hand as a peripheral to test the performance of the STCN-GR based control system, and the results show that this system can be applied in teleoperation in feature work to provide convenience for human life. © 2022 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：