检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： Xiaolong Liang Juanjuan Li Rui Qin Wenwen Ding Fei-Yue Wang Faculty of Innovation Engineering Macau University of Science and Technology Macao China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems and State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences and Collaborative Laboratory for Intelligent Science and Systems Beijing China

Intelligent Transportation Systems (ITS) are heavily dependent on private user data. However, most ITS fails to harness the potential of this invaluable data due to the absence of effective data governance mechanisms promoting users' contributions. Moreover, data contributors face security risks such as privacy preservation, data leakage, etc., as well as high costs in data sharing, while benefits are disproportionately reaped by system operators and interaction. This systemic imbalance could indirectly incentivize a surge in inactions and even malicious actions. In response to these challenges, we propose the design of a True Autonomous Organization (TAO) for ITS, namely ITS TAO. Utilizing the newly designed decision models with decentralized organization structures and the three-power structure, ITS TAO aims to realize the fair distribution of rights and benefits for ITS data contributors. Furthermore, we design a real-time evaluation system based on parallel intelligence capable of identifying potential hazards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perceptive self-supervised learning network for noisy image watermark removal

arXiv

引用

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Li, Bo Zhang, Yanning Zhang, Shichao Zhang, David School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China School of Electronics and Information Northwestern Polytechnical University Xi’an710129 China School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology Xi’an710129 China Guangxi Key Lab of Multisource Information Mining & Security College of Computer Science & Engineering Guangxi Normal University Guilin541004 China Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by cameras suffer from noise. To overcome these drawbacks, we propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) in this paper. PSLNet depends on a parallel network to remove noise and watermarks. The upper network uses task decomposition ideas to remove noise and watermarks in sequence. The lower network utilizes the degradation model idea to simultaneously remove noise and watermarks. Specifically, mentioned paired watermark images are obtained in a self-supervised way, and paired noisy images (i.e., noisy and reference images) are obtained in a supervised way. To enhance the clarity of obtained images, interacting two sub-networks and fusing obtained clean images are used to improve the effects of image watermark removal in terms of structural information and pixel enhancement. Taking into texture information account, a mixed loss uses obtained images and features to achieve a robust model of noisy image watermark removal. Comprehensive experiments show that our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal. Codes can be obtained at https://***/hellloxiaotian/PSLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Validation and Verification of Remaining Useful Life Prediction for Lithium-Ion Batteries based on AM-CNN Approach

Validation and Verification of Remaining Useful Life Predict...

引用

Self Sustainable artificial intelligence Systems (ICSSAS), International Conference on

作者： Prasanna Kumara S G Asheesh Kumar Shaik Fakruddin Babavali Chetan Shankar Patil M J Murali T Ch Anil Kumar Department of Physics Government Science College (Autonomous) Hassan Karnataka India Department of Mechanical Engineering Mahatma Gandhi Institute of Technology Hyderabad India Department of Physics V.R.Siddhartha Engineering College Vijayawada Andhra Pradesh India Artificial Intelligence and Data Science Angadi Institute of Technology and Management Belagavi India Department of Electrical and Electronics Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Mechanical Engineering VFSTR Deemed to be University Vadlamudi Guntur Andhra Pradesh India

An empirical model decomposition algorithm, Elman neural networks, and long-term memory are employed to predict the remaining battery life. The method for deconstructing empirical models is given the data on battery capacity vs cycle number that has been acquired. After that, recurrent long short-term memory and Elman neural networks are used to make predictions for the high-frequency and low-frequency sub-layers, respectively. data gathered at an unprecedented scale during battery testing has aided in model parameterization and performance evaluation. The first three steps of the proposed process are processing the data, choosing the features to use, and training the model. The proposed approach uses a Denoising Transformer (De-Transformer) network to clean up the raw data. The extended Kalman Particle Filter (EKPF) is a crucial sample density function that the proposed system employ in feature selection. AM-CNN is then used to train the models after the features have been chosen. The proposed method is superior to AM and CNN, two common substitutes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing sugarcane leaf disease classification using vision transformers over CNNs

Discover Artificial Intelligence

引用

Discover artificial intelligence 2025年第1期5卷 1-18页

作者： Miryala, Saritha Rasane, Krupa Department of Artificial Intelligence and Data Science S.G. Balekundri Institute of Technology Belagavi India Department of Electronics and Communication Engineering Jain College of Engineering Belagavi India

Sugarcane is a globally significant crop facing threats from leaf diseases that impact its productivity. Traditional detection methods are often inefficient and time-consuming. This study explores the use of Vision Transformers (ViT) for classifying sugarcane leaf diseases and compares their performance with traditional CNNs. A dataset of 19,926 images across six classes was used to fine-tune both ViT and CNN models. The optimized ViT model achieved a test accuracy of 96.53%, outperforming the CNN models (ResNet50 and VGG16) with accuracies of 91.92% and 92.30%, respectively. These findings demonstrate the superior performance of ViTs over CNNs in early disease detection for sustainable crop management. Future work will focus on expanding the dataset and optimizing model parameters for further improvements in disease classification accuracy. © The Author(s) 2025.

关键词： Sugar cane

来源：评论

学校读者我要写书评

暂无评论

From DAO to TAO: Finding The Essence of Decentralization

From DAO to TAO: Finding The Essence of Decentralization

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Juanjuan Li Xiaolong Liang Rui Qin Fei-Yue Wang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Innovation Engineering Macau University of Science and Technology Macau China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Decentralized Autonomous Organizations (DAOs) have been gaining popularity in recent years due to their promise of realizing the decentralized Web 3.0. However, most DAOs rely heavily on token-centric value systems as well as allocate decision-making authority and yield-sharing rights according to the held tokens, which often lead to monopolization of power and rights. To address this issue, this paper contributes to propose a truly democratic organization model, named True Autonomous Organizations and Operations (TAOs), that does not count upon tokens and is guided by principles of contribution-based and on-demand allocation. We first discuss the design of TAOs, including their infrastructures, power structures, and value systems, and then provide a technical roadmap for implementing TAOs in the DeSci context. This research can provide a valuable guidance for the construction and application of TAOs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DT-GRU Approach for Developing Remotely Monitored Central Nervous System Using Wearable Sensors

DT-GRU Approach for Developing Remotely Monitored Central Ne...

引用

Self Sustainable artificial intelligence Systems (ICSSAS), International Conference on

作者： Sreejith L Das Aaftab Alam B. Anjanee Kumar K. K. Sunalini Vidhya P Sakthivel M ECE Department Sri Venkateswara College of Engineering and Technology Chittoor Andhra Pradesh India Department of CSE Integral University Lucknow India Department of ECE Dadi Institute of Engineering and Technology Anakapalle Visakhapatnam India Department of English Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Andhra Pradesh India Department of Artificial Intelligence and Data Science M. Kumarasamy College of Engineering Karur India Department of CSE-AIML Malla Reddy College Of Engineering Hyderabad Telangana India

The capacity to evaluate numerous bio- behavioral factors concurrently is a potential strength of RMT for patients with neurological diseases. Although the benefits of RMT have been demonstrated in a large body of research, there is still some debate over its usefulness among medical experts. Providing doctors with visual summaries of data in the patient record is one way that RMT could enhance the system of care for patients with illnesses of the central nervous system. It's important to think about the constraints on the benefits these technologies can provide and the difficulties of using them effectively. The proposed strategy makes use of pre-processing, feature selection, and model training. data is preprocessed in LMS. Feature selection employs PCA. The DT -GRU algorithm is used to train the model. Two additional models, GRU and DT, are contrasted with the suggested method. The proposed method is quite effective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cortical reorganization pattern of stroke patients under upper limb multi-joint linkage task 12

Cortical reorganization pattern of stroke patients under upp...

引用

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

作者： Chu, Qitong Huo, Congcong Zhang, Tengyu Zhang, Xuemin Xu, Gongcheng Cheng, Shengcui Li, Huiyuan Xie, Ping Guo, Xin School of Artificial Intelligence and Data Science Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology The Ministry of Education Hebei University of Technology Tianjin300130 China National Research Center for Rehabilitation Technical Aids Beijing Key Laboratory of Rehabilitation Technical Aids for Old-Age Disability Key Laboratory of Neuro-functional Information and Rehabilitation Engineering The Ministry of Civil Affairs Beijing100176 China Beijing Advanced Innovation Centre for Biomedical Engineering School of Biological Science and Medical Engineering Beihang University Beijing100191 China School of Electrical Engineering Yanshan University Key Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Hebei Qinhuangdao066004 China Qinhuangdao Research Institute of National Research Center for Rehabilitation Technical Aids Qinhuangdao066004 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Motor dysfunction in stroke patients is caused by the brain damage, which greatly affects the life quality of the survivors. It is essential to explore the cortical reorganization pattern of stroke patients for revealing the mechanism of neural remodeling and guiding rehabilitation training. A total of 9 stroke patients and 12 age matched healthy subjects were recruited. Changes of oxyhemoglobin concentration (ΔHbO2) of bilateral prefrontal and motor cortex were measured in resting state and upper limb multi-j oint linkage motor state using functional near-infrared spectroscopy (fNIRS) neuroimaging technique. Cortical activation and functional connectivity were analyzed to describe the brain functional status associated with specific motor task. Results showed that compared with healthy subjects, significantly greater cortical activation was observed in stroke patients in responding to the multi-joint motor of the affected limb. Besides, inter-hemisphere connectivity of bilateral homotopic MC and PFC were significantly lower than healthy controls, however, the connectivity between PFC and MC were significantly higher than healthy controls. The results indicate the brain functional reorganization of stroke patients and offer new insights into the neural basis for cortical plasticity for stroke rehabilitation. To perform complex motor tasks, more brain resources was expended and more brain regions were involved in stroke patients. © 2022 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Imbalanced Least Squares Regression with Adaptive Weight Learning

SSRN

引用

SSRN 2022年

作者： Li, Yanting Jin, Junwei Ma, Jiangtao Zhu, Fubao Jin, Baohua Liang, Jing Chen, C.L. Philip College of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou450001 China School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou450001 China School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China School of Computer Science and Engineering South China University of Technology China

Least squares regression (LSR) has demonstrated promising performance in various classification tasks owing to the effectiveness and efficiency. However, there are some deficiencies that seriously plague its application in imbalanced data scenarios. The first is the success of LSR heavily relies on the balanced class distribution, more fundamentally, a severely imbalanced class distribution may damage the effectiveness of the algorithm seriously. Secondly, the utilized binary label matrix in conventional LSR model may be too strict to learn a discriminative transform matrix for imbalanced learning. To address the above issues, in this paper an adaptive weight learning mechanism and a novel label relaxation constraint are proposed and incorporated into the framework of LSR to tackle the imbalanced classification problem. Specifically, the weight of each sample can be adaptively obtained according to the original distribution information of the imbalanced data, in which the importance of the minority class samples can be better reflected with greater weights. Then a new label relaxation matrix is constructed to widen the margins between different classes. Further, we provide an iterative algorithm to solve the resulting optimization problem. Extensive experimental results on diverse imbalanced datasets show that the proposed method outperforms the majority of imbalanced learning approaches. © 2022, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Chain-Based Outlier Detection for Complex data Scenarios

Chain-Based Outlier Detection for Complex Data Scenarios

引用

IEEE International Conference on Big data

作者： Huiwen Dong Qing-Guo Wang Wei Ding Institute of Artificial Intelligence and Future Networks Beijing Normal University Beijing China Guangdong Key Lab of AI and MM Data Processing Guangdong Provincial Key Laboratory IRADS IAS DST BNU-HKBU United International College Institute for Advanced Study Zhuhai China Faculty of Electrical Engineering and Automation Changshu Institute of Technology Changshu China

Outlier detection is a challenging problem due to the complexity of real-life data. Specifically, an effective outlier detection method should be able to handle (1) different types of outliers: local outliers, global outliers, and cluster outliers; (2) a lack of prior knowledge of outlier number or percentage; (3) neighboring clusters with different densities; and (4) real-time detection. Unfortunately, few algorithms can tackle all these challenges simultaneously. In this paper, we propose a chain-based theory to address these issues, where a minority of data points will be considered outliers if their distances from normal data points change abruptly. We present the parallel chaining method based on this theory. Experiments demonstrate that the proposed method exhibits comparable performance to other state-of-the-art methods in the synthetic datasets and outperform other methods in the real-life datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

XAI-PSSGAN: Perception-Enhanced Spectrum Shift Generative Adversarial Network with Explainable AI System for NIR-II Fluorescence Molecular Imaging 22

XAI-PSSGAN: Perception-Enhanced Spectrum Shift Generative Ad...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Fu, Lidan Lu, Binchun Li, Lingbing Shi, Xiaojing Tian, Jie Hu, Zhenhua Cas Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Precision Instrument Tsinghua University Beijing China Interventional Radiology Department Chinese Pla General Hospital Beijing China Beijing Advanced Innovation Center for Big Data-based Precision Medicine School of Engineering Medicine Beihang University Beijing China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and Technology Xidian University Xi'an China National Key Laboratory of Kidney Diseases Beijing China

ISBN: (纸本)9798331520526

Fluorescence imaging in the second near-infrared window (NIR-II) facilitates the real-time optical contrast for in vivo biomedical imaging. However, the detection noise is an inevitable byproduct of the real-time imaging process. Additionally, fluorescent probes currently approved for clinical use remain limited within the wavelength of NIR-IIa (1000-1300 nm). NIR-IIb (1500-1700 nm) imaging has the potential to deliver higher resolution than NIR-IIa, but relies on toxic fluorescent probes not approved for human use. To support clinical high-precision imaging, we propose a NIR-II fluorescence enhanced imaging method based on perception-enhanced spectrum shift generative adversarial network with explainable AI systems (xAI-PSSGAN). The proposed method tackles the problem of limited unpaired data training, and generates NIR-IIb resembling images with enhanced resolution and reduced noise. Experimental results demonstrate that proposed method effectively improves the imaging quality and surpasses competing alternatives, which is of great significance to promote the high-quality NIR-II imaging in clinical practice. © 2025 IEEE.

关键词： Molecular imaging

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：