检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial intelligence 2025年

作者： Hassan, Eman Bettayeb, Meriem Halawani, Yasmin Genssler, Paul R. Tesfai, Huruy Zweiri, Yahya Amrouch, Hussam Hadjileontiadis, Leontios J. Saleh, Hani Mohammad, Baker Khalifa University System on Chip Lab Department of Computer and Information Engineering Abu Dhabi127788 United Arab Emirates Abu Dhabi University Department of Computer Science and Information Technology College of Engineering Abu Dhabi United Arab Emirates University of Dubai College of Engineering and IT Dubai United Arab Emirates Munich Institute of Robotics and Machine Intelligence Technical University of Munich TUM School of Computation Information and Technology Chair of AI Processor Design Munich Germany Abu Dhabi United Arab Emirates Stuttgart Germany Khalifa University of Science and Technology Department of Biomedical Engineering Abu Dhabi United Arab Emirates Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki Greece

Artificial intelligence (AI) relies on pattern recognition and classification algorithms to achieve accurate and efficient decision-making. Convolutional neural networks (CNNs) are the state-of-the-art for processing 2D image data, but their high computational and data requirements limit their use in resource-constrained environments. Hyperdimensional computing (HDC) offers a lightweight alternative, excelling in 1D tasks, but struggles to achieve competitive accuracy for 2D image classification. Hybrid frameworks combining HDC with CNNs have been proposed to improve accuracy but inherit the computational demands of deep learning, making them unsuitable for edge and IoT devices. To address this, we propose TransHD, a framework integrating lightweight spatial transformer networks (STNs) with HDC to enhance image classification performance while maintaining efficiency. TransHD achieves up to 9% higher accuracy than base HDC models on MNIST and Fashion-MNIST using only 30% of the training data, and reduces computational complexity by 2.5x through optimized STN feature map usage. On resource-constrained platforms like the Raspberry Pi 4, TransHD accelerates inference times by 3.4x and improves energy efficiency by 3.2x, with an accuracy trade-off of approximately 3% compared to CNNs. This study demonstrates the potential of combining HDC with STNs to develop efficient AI solutions for IoT and edge computing, where low energy consumption and computational efficiency are critical. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Brain Rhythmic Activity and Hemodynamic Response During Wrist Extension Induced by Functional Electrical Stimulation

Brain Rhythmic Activity and Hemodynamic Response During Wris...

引用

Rehabilitation engineering and Assistive Technology (i-CREATe), International Convention on

作者： He Mao Yinghu Peng Yue Zheng Guanglin Li Hai Li Yongan Xu Peng Fang CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Engineering Laboratory of Neural Rehabilitation Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China Department of Rehabilitation Medicine Shenzhen Hospital Neurorehabilitation Laboratory Southern Medical University Shenzhen China Department of Emergency Medicine Second Affiliated Hospital & Institute of Emergency Medicine Zhejiang University School of Medicine Hangzhou China

ISBN: (数字)9798350355154

ISBN: (纸本)9798350355161

Functional electrical stimulation (FES) is an effective therapy for motor function restoration after stroke. To investigate brain activation during FES-induced wrist extension, electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) were simultaneously measured for 6 healthy subjects. We found an increase in oxygenated hemoglobin (HbO) concentration, which was accompanied by a decrease in deoxygenated hemoglobin (HbR) concentration in bilateral sensorimotor cortex (SMC) during movement. We also found event-related desynchronization (ERD) of alpha and beta EEG rhythms during movement and event-related synchronization (ERS) after the cessation of the movement. Neurovascular coupling (NC) was evaluated by the correlation coefficient (cc) between alpha ERD and HbO, and a higher cc value was found on the contralateral hemisphere. These findings demonstrate the potential application of EEG-fNIRS for quantifying NC during FES therapy.

关键词： Wrist Electric potential Electric variables measurement Motors Iron Electroencephalography Hemodynamics Neuromuscular stimulation Synchronization Functional near-infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

A moving target detection and localization strategy based on optical flow and pin-hole imaging methods using monocular vision

A moving target detection and localization strategy based on...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Wang, Shun Guo, Qingqiang Xu, Sheng Su, Dan School of Control Science and Engineering Shandong University Shandong Jinan250061 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China Shandong Institute of Advanced Technology Chinese Academy of Sciences Shandong Jinan250102 China Orbbec Inc. Shenzhen518057 China

ISBN: (纸本)9781665436786

This paper proposes a new strategy for moving target detection and localization based on monocular vision. Firstly, to detect a moving target with large displacement and high speed accurately, two consecutive video images captured by a monocular camera are preprocessed using the enhancement and denoising methods. Then, the optical flow representing motion information is calculated iteratively by the modified Lucas-Kanade optical flow method. Secondly, a new interest region extraction method is developed to overcome the negative impacts caused by the noises in the background. Specifically, this proposed method combines a two-level image segmentation strategy from coarse to fine, including median filtering, two-direction dynamic threshold segmentation, the Otsu method, and morphological processing. Thirdly, a low computational cost target localization algorithm is proposed based on pin-hole imaging theory. Besides, it only uses two-dimensional image and camera parameters to obtain the moving target's position in the three-dimensional space. Finally, experimental results show that the proposed strategy can effectively eliminate noise interferences and realize moving target detection, extraction, and localization. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A differential public PUF design for lightweight authentication 16

A differential public PUF design for lightweight authenticat...

引用

2021 International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit design, SMACD 2021 and 16th Conference on PhD Research in Microelectronics and Electronics, PRIME 2021

作者： Duan, Shengyu Sai, Gaole School of Computer Engineering and Science Shanghai University Shanghai200444 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China

ISBN: (纸本)9783800755899

Physical Unclonable Functions (PUFs) have emerged as a promising primitive to provide a hardware keyless security mechanism for integrated circuit applications. Public PUFs (PPUFs) address the crucial PUF vulnerability of requiring databases to store the secrete reference information. This paper investigates one of the PPUF families, differential PPUF (dPPUF), which exploits complexly interacted logic to create time gap between actual execution and simulation, and to prevent simulation attacks. Conventional dPPUFs have high costs. We observe the repressers have large impact on simulation time, but take a great proportion in current dPPUF structure. We thereby present a represser network with specially designed interconnection and shared logic, to maintain a high circuit complexity and to reduce the area cost. We show the proposed dPPUF has similar resilience over simulation attacks as the conventional design. Area cost can be reduced by up to 44%, and thus the proposed design can be used for lightweight authentication. © VDE VERLAG GMBH.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Experimental and Theoretical Study on the Evolution of Functional Groups in Cellulose Char During Oxidative Pyrolysis

SSRN

引用

SSRN 2022年

作者： Xiao, Fan Yang, Li He, Ben Tian, Hong Cheng, Shan Yin, Yanshan Leng, Erwei College of Mechanical and Vehicle Engineering Hunan University Changsha410082 China Innovation Institute of Industrial Design and Machine Intelligence Quanzhou-Hunan University Quanzhou362006 China School of Energy and Power Engineering Key Laboratory of Renewable Energy Electric Technology of Hunan Province Changsha University of Science & Technology Hunan Changsha410114 China

Oxidative pyrolysis of biomass is a promising substitute technology for conventional pyrolysis and is also crucial to the related degradation process of biomass materials such as aging, combustion, fire hazard, etc. The intertwining of heterogeneous oxidation and homogeneous oxidation of biomass and its derivative muffles the detailed mechanism of oxidative pyrolysis. To unravel the mechanism of heterogeneous oxidation in the cellulose condensed phase, the real-time evolution of functional groups in cellulose char during oxidative pyrolysis was probed by the in situ diffuse reflectance infrared Fourier transform technology, which is further analyzed by a homemade semi-quantitative analysis program based on the perturbation-correlation moving-window two-dimensional correlation spectroscopy and two-dimensional correlation spectroscopy. The experimental results show the obvious promotion effects of O 2 on the direct oxidation of hydroxyls to unconjugated C=O and the cleavage of C–O–C in the development stage between the temperatures of the initiation and the maximum rate of weight loss, resulting in the lowered thermostability and devolatilization of cellulose. At elevated temperatures, the hydroxyls and C=O were further oxidized by O 2 into carboxyls, and released at around 450 ºC in the last decline stage, performing the second peak of the DTG curve for oxidative stress pyrolysis. Through DFT calculation of the hydroxyl oxidation, a low-temperature oxidation mechanism competitive with the transglycosylation and other dehydration reactions was proposed. Its rate is determined by the initiating H abstraction, which highly depends on the spin density (population) for the transition state and pyrolysis temperature. © 2022, The Authors. All rights reserved.

关键词： Cellulose

来源：评论

学校读者我要写书评

暂无评论

Mechanism of Acid-Catalyzed Pyrolysis of Levoglucosan: Formation of Anhydro-Disaccharides

SSRN

引用

SSRN 2023年

作者： He, Ben Yu, Yun Gong, Xun Liu, Shuai Tian, Hong Leng, Erwei College of Mechanical and Vehicle Engineering Hunan University Changsha410082 China Innovation Institute of Industrial Design and Machine Intelligence Quanzhou-Hunan University Quanzhou362006 China State Key Laboratory of Coal Combustion School of Energy and Power Engineering Huazhong University of Science and Technology Wuhan430074 China Hunan province Key Laboratory of Efficient & Clean Thermal Power Generation Technologies State Grid Hunan Electric Power Corporation Research Institute Changsha410007 China School of Energy and Power Engineering Changsha University of Science & Technology Changsha410114 China

Highlights1. Pathways were proposed for levoglucosan polymerization with and without H2SO4.2. The thermodynamic and kinetic factors of each pathway were analyzed.3. The superior pathways for the generation of anhydro-disaccharides were proposed.4. H2SO4 can significantly reduce the energy barrier of the polymerization reaction. © 2023, The Authors. All rights reserved.

关键词： Polymerization

来源：评论

学校读者我要写书评

暂无评论

Robust Point Cloud Registration Based on Semantic Iterative Closest Point Algorithm

引用

Fundamental Research 2025年

作者： Shaoyi Du Tiancheng Shao Canhui Tang Wei Zeng Zhiqiang Tian National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an 710049 China School of Software Engineering Xi’an Jiaotong University Xi’an 710049 China School of Physics and Mechanical and Electrical Engineering Longyan University Longyan 364012 China

Point cloud registration is a fundamental problem in computer vision, which is extremely challenging for LiDAR point clouds with a lot of noise, outliers, and poor initial position. To deal with these difficulties, this paper proposes a semantic-based iterative closest point algorithm, which utilizes bidirectional distance and correntropy for robust point cloud registration. Firstly, we propose a semantic-guided correspondence establishment strategy that utilizes semantic information to narrow down the search range of correspondences and improve registration accuracy. Secondly, a bidirectional semantic search point matching strategy is introduced to the algorithm, which increases its error correction ability. Thirdly, the maximum correntropy criterion strategy is used to suppress the noise and outliers to further enhance the algorithm in robustness. Experimental results demonstrate the accuracy and robustness of our algorithm compared with other registration methods.

关键词： Iterative closest point Point cloud registration Semantic information Bidirectional distance Maximum correntropy criterion

来源：评论

学校读者我要写书评

暂无评论

Estimating motor symptom presence and severity in Parkinson’s disease from wrist accelerometer time series using ROCKET and InceptionTime

引用

Scientific Reports 2025年第1期15卷 1-15页

作者： Donié, Cedric Das, Neha Endo, Satoshi Hirche, Sandra TUM School of Computation Information and Technology Department of Computer Engineering Chair of Information-oriented Control Technical University of Munich Munich Germany Munich Data Science Institute (MDSI) Munich Germany Munich Institute of Robotics and Machine Intelligence (MIRMI) Munich Germany

Parkinson’s disease (PD) is a neurodegenerative condition characterized by frequently changing motor symptoms, necessitating continuous symptom monitoring for more targeted treatment. Classical time series classification and deep learning techniques have demonstrated limited efficacy in monitoring PD symptoms using wearable accelerometer data due to complex PD movement patterns and the small size of available datasets. We investigate InceptionTime and RandOm Convolutional KErnel Transform (ROCKET) as they are promising for PD symptom monitoring. InceptionTime’s high learning capacity is well-suited to modeling complex movement patterns, while ROCKET is suited to small datasets. With random search methodology, we identify the highest-scoring InceptionTime architecture and compare its performance to ROCKET with a ridge classifier and a multi-layer perceptron on wrist motion data from PD patients. Our findings indicate that all approaches can learn to estimate tremor severity and bradykinesia presence with moderate performance but encounter challenges in detecting dyskinesia. Among the presented approaches, ROCKET demonstrates higher scores in identifying dyskinesia, whereas InceptionTime exhibits slightly better performance in tremor and bradykinesia estimation. Notably, both methods outperform the multi-layer perceptron. In conclusion, InceptionTime can classify complex wrist motion time series and holds potential for continuous symptom monitoring in PD with further development. © The Author(s) 2025.

关键词： Accelerometer Deep learning IMU InceptionTime machine learning Parkinson’s disease ROCKET Time series classification

来源：评论

学校读者我要写书评

暂无评论

Mechanics of soft-body rolling motion without external torque

arXiv

引用

arXiv 2024年

作者： Liang, Xudong Ding, Yimiao Yuan, Zihao Jiang, Junqi Xie, Zongling Fei, Peng Sun, Yixuan Gu, Guoying Zhong, Zheng Chen, Feifei Si, Guangwei Gong, Zhefeng School of Science Harbin Institute of Technology Shenzhen518055 China Department of Neurology The Fourth Hospital and School of Brain Science and Brain Medicine Zhejiang University School of Medicine Hangzhou310058 China Liangzhu Laboratory MOE Frontier Science Center for Brain Science and Brain-Machine Integration State Key Laboratory of Brain-Machine Intelligence Zhejiang University 1369 West Wenyi Road Hangzhou311121 China NHC and CAMS Key Laboratory of Medical Neurobiology Zhejiang University Hangzhou310058 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Brain and Cognitive Science Institute of Biophysics Chinese Academy of Sciences 15 Datun Road Beijing100101 China University of Chinese Academy of Sciences 19A Yuquan Road Beijing100049 China Huazhong University of Science and Technology Optical and Electronic Information Wuhan430074 China Zhejiang Lab. Hangzhou311121 China

The Drosophila larva, a soft-body animal, can bend its body and roll efficiently to escape danger. However, contrary to common belief, this rolling motion is not driven by the imbalance of gravity and ground reaction forces. Through functional imaging and ablation experiments, we demonstrate that the sequential actuation of axial muscles within an appropriate range of angles is critical for generating rolling. We model the interplay between muscle contraction, hydrostatic skeleton deformation, and body-environment interactions, and systematically explain how sequential muscle actuation generates the rolling motion. Additionally, we constructed a pneumatic soft robot to mimic the larval rolling strategy, successfully validating our model. This mechanics model of soft-body rolling motion not only advances the study of related neural circuits, but also holds potential for applications in soft robotics. © 2024, CC BY.

关键词： Pneumatics

来源：评论

学校读者我要写书评

暂无评论

Synchronous Motion Generation of Multiple Continuum Robots Based on a Jacobian-Estimation Strategy

Synchronous Motion Generation of Multiple Continuum Robots B...

引用

IEEE International Conference on robotics and Biomimetics

作者： Ning Tan Ruikun Hu Yuyang Wu Xinyu Zhang Fenglei Ni Zhenglong Sun School of Computer Science and Engineering Sun Yat-sen University Guangzhou PR China State Key Laboratory of Robotics and Systems (HIT) Harbin PR China Engineering Research Center of Software/Hardware Co-Design Technology and Application Ministry of Education (East China Normal University) Shanghai PR China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9781665405362

In this paper, a novel model-free control scheme is proposed for synchronous motion control of multiple continuum robots. The control problem is formulated as two convex optimization routines in an adaptive and model-free closed-loop framework. The proposed approach is heading to address cooperative task execution for multiple continuum robots. The model-free feedback control guarantees the high portability for a wide range of continuum robots. Simulation studies are conducted on two kinds of tasks, which are cooperative task execution with two robots and simultaneously tracking control with three robots. Besides, the superiority of proposed approach is validated through comparisons with other methods. Simulation results prove the high accuracy and efficiency of this model-free feedback control scheme.

关键词： Jacobian matrices Adaptation models Tracking Simulation Conferences Convex functions Feedback 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：