检索结果-内蒙古大学图书馆

CCA-Net: Zero-shot SSVEP classification via an integration of canonical correlation analysis and deep neural network

学校读者我要写书评

暂无评论

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Deng, Yang Ji, Zhiwei Wang, Yijun Zhou, S. Kevin Harbin Institute of Technology School of Life Science and Technology Heilongjiang Harbin 150001 China University of Science and Technology of China Division of Life Sciences and Medicine School of Biomedical Engineering Anhui Hefei 230026 China University of Science and Technology of China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research Jiangsu Suzhou 215123 China Nanjing Agricultural University College of Artificial Intelligence Jiangsu Nanjing 210095 China Chinese Academy of Sciences State Key Laboratory on Integrated Optoelectronics Institute of Semiconductors Beijing 100083 China University of Science and Technology of China Key Laboratory of Precision and Intelligent Chemistry Anhui Hefei 230026 China Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Beijing 100190 China

Accurate decoding of electroencephalographic (EEG) signals is a crucial foundation for brain-computer interface (BCI) applications. Among various decoding approaches, those that do not require calibration are particularly significant for advancing BCI technologies into everyday life, as they alleviate user fatigue by eliminating the need for user-specific training. In this study, we integrate a deep neural network with canonical correlation analysis (CCA) to form the CCA-Net approach for decoding steady-state visually evoked potential (SSVEP) based BCI without user-specific calibration, i.e., at the zero-shot scenario. The CCA-Net aims to reduce the cross-subject domain gap for better transfer learning and make full use of the testing signal itself. Specifically, it adapts the cross-subject dual-domain fusion network (CSDuDoFN) by transferring the global multi-reference least-squares transformation coefficient from source subjects to both source and target data to reduce the cross-subject domain gap. In addition, CCA-Net enhances the transfer template-based canonical correlation analysis (tt-CCA) by introducing a subject-specific template to replace the sine-cosine reference template and adding an extra CCA coefficient to make full use of the testing signal itself, resulting in the Modified tt-CCA. Finally, the features extracted by CSDuDoFN and Modified tt-CCA are integrated to produce the final decoding result. Our approach leverages the strengths of both data-driven and model-driven methods and achieves state-of-the-art performance on three publicly available datasets, thus holding the potential to facilitate everyday BCI applications based on SSVEP. The reproducibility code is available at: https://***/Sungden/Zero-shot-SSVEP-classification. © 1963-2012 IEEE.

关键词： Brain-computer interface (BCI) canonical correlation analysis (CCA) deep neural network (DNN) steady-state visual evoked potential (SSVEP) zero-shot learning

Taming Stable Diffusion for MRI Cross-Modality Translation

学校读者我要写书评

暂无评论

Taming Stable Diffusion for MRI Cross-Modality Translation

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yingtai Li Shuo Yang Xiaoyan Wu Shan He S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine USTC Hefei P.R. China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research USTC P.R. China iFLYTEK Research iFLYTEK Co. Ltd Hefei P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing P.R. China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In this study, we explore using Stable Diffusion (SD) for unsupervised medical image-to-image translation. SD has shown remarkable performances in generating high-quality images and can be easily applied to generate custom contents by injecting standard plug-ins like LoRA, offering a promising solution to tackle the complexity caused by variations in imaging modalities, acquisition parameters, and body parts in medical imaging. However, We empirically find that existing pipelines designed for natural images fail to translate directly to medical images due to weak structural control and inappropriate color preservation. To address these issues, we propose a novel two-branch image translation pipeline. This pipeline decouples the generation of target image along the time axis and employs ControlNet to ensure precise structural preservation. Additionally, we customize SD to generate images of extreme brightness, a common feature in medical imaging. Our results on the BraTS dataset demonstrate that SD with task-specific plug-ins can generate high-quality medical images comparable to those generated by task-specific models. Since the development of these standard plug-ins can be easily done by clinicians without much knowledge of the underlying algorithm, such a mode holds the potential to significantly extend the use of medical image computing algorithms in the clinical environment.

关键词： Translation Image color analysis Computational modeling Biological system modeling Magnetic resonance imaging Pipelines Brightness Complexity theory Standards Biomedical imaging

MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Fenghe Nian, Bingkun Li, Yingtai Jiang, Zihang Yang, Jie Liu, Wei Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China Suzhou Institute for Advanced Research USTC Suzhou China Department of Automation Shanghai Jiao Tong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University China State Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China Anhui Hefei230026 China

Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-supervised learning methods have not yet fully unleashed Mamba’s potential for handling long-range dependencies because they overlook the inherent causal properties of state space sequences in masked modeling. To address this challenge, we propose a general-purpose pre-training framework called MambaMIM, a masked image modeling method based on a novel TOKen-Interpolation strategy (TOKI) for the selective structure state space sequence, which learns causal relationships of state space within the masked sequence. Further, MambaMIM introduces a bottom-up 3D hybrid masking strategy to maintain a masking consistency across different architectures and can be used on any single or hybrid Mamba architecture to enhance its multi-scale and long-range representation capability. We pre-train MambaMIM on a large-scale dataset of 6.8K CT scans and evaluate its performance across eight public medical segmentation benchmarks. Extensive downstream experiments reveal the feasibility and advancement of using Mamba for medical image pre-training. In particular, when we apply the MambaMIM to a customized architecture that hybridizes MedNeXt and Vision Mamba, we consistently obtain the state-of-the-art segmentation performance. The code is available at: https://***/FengheTan9/MambaMIM. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

DATA-EFFICIENT VISUOMOTOR POLICY TRAINING USING REINFORCEMENT LEARNING AND GENERATIVE MODELS

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ghadirzadeh, Ali Kyrki, Ville Kragic, Danica Poklukar, Petra Björkman, Mårten Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden Intelligent Robotics Research Group Aalto University Espoo Finland

We present a data-efficient framework for solving deep visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) with the latent variable generative models. Our framework trains deep visuomotor policies by introducing an action latent variable such that the feed-forward policy search can be divided into two parts: (1) training a sub-policy that outputs a distribution over the action latent variable given a state of the system, and (2) training a generative model that outputs a sequence of motor actions given a latent action representation. Our approach enables safe exploration and alleviates the data-inefficiency problem as it exploits prior knowledge about valid sequences of motor actions. Moreover, by evaluating the quality of the generative models we are able to predict the performance of the RL policy training prior to the actual training on the physical robot. We achieve this by defining two novel measures, disentanglement and local linearity, for assessing the quality of generative models’ latent spaces, and complementing them with the existing measures for evaluation of generative models. We demonstrate the efficiency of our approach on a picking task using several different generative models and determine which of their properties have the most influence on the final policy training. Copyright © 2020, The Authors. All rights reserved.

关键词： Decision making

Control of Smart Buildings and Utility-Scale Batteries Enabling 24/7 Carbon-Free Energy*

学校读者我要写书评

暂无评论

Control of Smart Buildings and Utility-Scale Batteries Enabl...

European Control Conference (ECC)

作者： Faran A. Qureshi Jeff S. Shamma Robotics Intelligent Systems and Control (RISC) Laboratory Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia University of Illinois at Urbana-Champaign USA

Wind power is a clean and sustainable source of electricity, but its intermittent nature creates challenges for its grid integration. Utility-scale batteries are a popular and effective solution to make wind power dispatchable, however, batteries are expensive and increase the overall cost of operation. In this paper, we propose utilizing the flexibility in the consumption of smart buildings to reduce the size of the utility-scale batteries needed for the dispatchability of wind energy. A method based on stochastic optimization is proposed to compute the dispatch plan required to participate in the day-ahead energy market. A stochastic model predictive controller is proposed for the control of the buildings and batteries to track the dispatch plan in real-time. Simulations are carried out with realistic building models and real weather, wind power production, and forecast data. Results demonstrate that utilizing the flexibility of building thermodynamics can significantly reduce the size (and usage) of the required battery for making the wind power production dispatchable.

关键词： Smart buildings Computational modeling Stochastic processes Production Wind power generation Predictive models Data models

Gait Analysis of Multi-Step Climbing Active Wheeled Snake Robot 4

学校读者我要写书评

暂无评论

Gait Analysis of Multi-Step Climbing Active Wheeled Snake Ro...

4th International Conference on robotics and Automation Engineering, ICRAE 2019

作者： Sahu, Divyanshu Kodi, Ramachandra Singh, Sartaj Institute of Technology Nirma University Department of Mechanical Engineering Ahmedabad India Intelligent Systems and Robotics Division Bangalore India

ISBN: (纸本)9781728147406

Snake robots have been a popular choice for search and rescue operations in disaster-prone areas, cramped spaces, uneven terrain and in hazardous environments unfit for humans due to their flexibility, modular design and highly articulated body structure. One of the salient features required by these robots is the ability to climb multiple steps at a time. Inspired by biological snakes which can seamlessly change their shape according to the contour of stairs for climbing multiple steps, this paper proposes a 'Step Morphing Gait' which would enable the proposed snake robot design to ascend multiple steps at a time. Gait analysis in this paper shows the step by step procedure of how the gait is implemented. Also, a looping technique in this gait is developed which makes the problem of climbing multiple steps for hyper redundant systems intuitively easier to understand and implement in realtime simulated environment. Co-simulation results validate the proposed gait. © 2019 IEEE.

关键词： Gait analysis

Localization state induced superconductivity, pseudogap and strange metal

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hung, Kuan-Ming Shieh, Tung-Ho Wu, Kun-Yuan Department of Electronics Engineering National Kaohsiung University of Science and Technology Kaohsiung807 Taiwan Department of Intelligent Robotics Engineering Kun-Shan University Tainan710 Taiwan Division of Intellectual Property & Design Support United Microelectronics Corporation Tainan710 Taiwan

The emergence of superconductivity in unconventional superconductors usually accompanies the normal-state phases of pseudogap, strange metal and Fermi liquid. It indicates these phases are strongly related to the superconducting state and should be dominated by yet unclear mechanism of superconductivity. Here, we propose a microscopic theory that, according to the coupling between localized and extended states, the pairing electrons which leap on and off a localized state result in superconducting instability. Two distinguishable pairing gaps are observed in these states, one dominates the superconducting temperature and another the temperature of a coherent pair confined at localized area. The pairing correlation between these states results in four phases. Their characteristics are manifested in universal Planckian-like resistivity and unusual carrier distribution, as observed in recent experiments. © 2021, CC BY-SA.

关键词： Fermi liquids

Detect-and-segment: A deep learning approach to automate wound image segmentation

学校读者我要写书评

暂无评论

Informatics in Medicine Unlocked 2022年 29卷

作者： Scebba, Gaetano Zhang, Jia Catanzaro, Sabrina Mihai, Carina Distler, Oliver Berli, Martin Karlen, Walter Mobile Health Systems Lab Institute of Robotics and Intelligent Systems Department of Health Sciences and Technology ETH Zurich Switzerland Unit for Clinical and Applied Research Balgrist University Hospital Zurich Switzerland Department of Rheumatology University Hospital Zurich University of Zurich Switzerland Division of Technical Orthopedics Department of Orthopedic Surgery Balgrist University Hospital Zurich Switzerland

Chronic wounds significantly impact quality of life. They can rapidly deteriorate and require close monitoring of healing progress. Image-based wound analysis is a way of objectively assessing the wound status by quantifying important features that are related to healing. However, high heterogeneity of the wound types and imaging conditions challenge the robust segmentation of wound images. We present Detect-and-Segment (DS), a deep learning approach to produce wound segmentation maps with high generalization capabilities. In our approach, dedicated deep neural networks detected the wound position, isolated the wound from the perturbing background, and computed a wound segmentation map. We tested this approach on a diabetic foot ulcers data set and compared it to a segmentation method based on the full image. To evaluate its generalizability on out-of-distribution data, we measured the performance of the DS approach on 4 additional independent data sets, with larger variety of wound types from different body locations. The Matthews’ correlation coefficient (MCC) improved from 0.29 (full image) to 0.85 (DS) on the diabetic foot ulcer data set. When the DS was tested on the independent data sets, the mean MCC increased from 0.17 to 0.85. Furthermore, the DS enabled the training of segmentation models with up to 90% less training data without impacting the segmentation performance. The proposed DS approach is a step towards automating wound analysis and reducing efforts to manage chronic wounds. © 2022 The Authors

关键词： Chronic wounds Generalizability Machine learning Semantic segmentation Smartphone

Novel Smart N95 Filtering Facepiece Respirator with Real-time Adaptive Fit Functionality and Wireless Humidity Monitoring for Enhanced Wearable Comfort

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kwon, Kangkyu Lee, Yoon Jae Jung, Yeongju Soltis, Ira Choi, Chanyeong Na, Yewon Romero, Lissette Kim, Myung Chul Rodeheaver, Nathan Kim, Hodam Lloyd, Michael S. Zhuang, Ziqing King, William Xu, Susan Ko, Seung-Hwan Lee, Jinwoo Yeo, Woon-Hong School of Electrical and Computer Engineering College of Engineering Georgia Institute of Technology AtlantaGA30332 United States Center for Human-Centric Interfaces and Nanoengineering Institute for Electronics and Nanotechnology Georgia Institute of Technology AtlantaGA30332 United States Applied Nano and Thermal Science Lab Department of Mechanical Engineering Seoul National University 1 Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30332 United States School of Industrial Design Georgia Institute of Technology AtlantaGA30332 United States Division of Cardiology Emory University School of Medicine AtlantaGA30322 United States National Institute for Occupational Safety and Health National Personal Protective Technology Laboratory PittsburghPA15236 United States Seoul National University Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of Department of Mechanical Robotics and Energy Engineering Dongguk University 30 Pildongro 1-gil Jung-gu Seoul04620 Korea Republic of Wallace H. Coulter Department of Biomedical Engineering Parker H. Petit Institute for Bioengineering and Biosciences Neural Engineering Center Institute for Materials Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA30332 United States

The widespread emergence of the COVID-19 pandemic has transformed our lifestyle, and facial respirators have become an essential part of daily life. Nevertheless, the current respirators possess several limitations such as poor respirator fit because they are incapable of covering diverse human facial sizes and shapes, potentially diminishing the effect of wearing respirators. In addition, the current facial respirators do not inform the user of the air quality within the smart facepiece respirator in case of continuous long-term use. Here, we demonstrate the novel smart N-95 filtering facepiece respirator that incorporates the humidity sensor and pressure sensory feedback-enabled self-fit adjusting functionality for the effective performance of the facial respirator to prevent the transmission of airborne pathogens. The laser-induced graphene (LIG) constitutes the humidity sensor, and the pressure sensor array based on the dielectric elastomeric sponge monitors the respirator contact on the user’s face, providing the sensory information for a closed-loop feedback mechanism. As a result of the self-fit adjusting mode along with elastomeric lining, the fit factor is increased by 3.20 and 5 times at average and maximum respectively. We expect that the experimental proof-of-concept of this work will offer viable solutions to the current commercial respirators to address the *** Codes 92C55 Copyright © 2023, The Authors. All rights reserved.

关键词： Graphene