检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Tianyi Zhou, Yijie Hu, Xiaotao Zhang, Kai Zhang, Anran Qiu, Xingye Xu, Jun School of Statistics and Data Science Nankai University Tianjin China College of Computer Science Nankai University Tianjin China School of Intelligence Science and Technology Nanjing University Suzhou China Tencent Data Platform Beijing China Zhejiang University Hangzhou China Systems Engineering Research Institute China State Shipbuilding Corporation Limited Beijing China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen China

Arbitrary-scale super-resolution (ASSR) aims to learn a single model for image super-resolution at arbitrary magnifying scales. Existing ASSR networks typically comprise an off-the-shelf scale-agnostic feature extractor and an arbitrary scale upsampler. These feature extractors often use fixed network architectures to address different ASSR inference tasks, each of which is characterized by an input image and an upsampling scale. However, this overlooks the difficulty variance of super-resolution on different inference scenarios, where simple images or small SR scales could be resolved with less computational effort than difficult images or large SR scales. To tackle this difficulty variability, in this paper, we propose a Task-Aware Dynamic Transformer (TADT) as an input-adaptive feature extractor for efficient image ASSR. Our TADT consists of a multi-scale feature extraction backbone built upon groups of Multi-Scale Transformer Blocks (MSTBs) and a Task-Aware Routing Controller (TARC). The TARC predicts the inference paths within feature extraction backbone, specifically selecting MSTBs based on the input images and SR scales. The prediction of inference path is guided by a new loss function to trade-off the SR accuracy and efficiency. Experiments demonstrate that, when working with three popular arbitrary-scale upsamplers, our TADT achieves state-of-the-art ASSR performance when compared with mainstream feature extractors, but with relatively fewer computational costs. The code will be publicly released. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time-series Electric Power Charge Load Prediction based on Graph Feature Fusion

Time-series Electric Power Charge Load Prediction based on G...

引用

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

作者： Yingjie Ren Lisha Wu Jing Xu Zhen Zhang Longgang He Zhenhua Wei Big Data Center of State Grid Corporation of China Beijing China Beijing China-Power Information Technology Co. LTD Beijing China School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

In this paper, we introduce CBAT, a novel method for temporal electric charge load prediction that integrates bidirectional LSTM and a graph attention mechanism. The bidirectional LSTM module captures global sequence information, while the graph attention module, leveraging time steps as graph nodes, models the intricate relationships between these steps by constructing an attenuation factor adjacency matrix. This approach effectively captures local temporal relationships. Experimental results demonstrate that the CBAT model outperforms existing mainstream models in electric charge load forecasting and other time series prediction tasks, showing superior performance in RMSE, MAPE, and R2 metrics. Additionally, ablation studies confirm the efficacy of the time-series-based graph attention module in electric charge load prediction.

关键词： Measurement Attention mechanisms Load forecasting Computational modeling Time series analysis Bidirectional long short term memory Predictive models Power systems Forecasting Load modeling

来源：评论

学校读者我要写书评

暂无评论

An Analytical Study of Internet Key Exchange (IKE) Protocol for Wireless Network Security

An Analytical Study of Internet Key Exchange (IKE) Protocol ...

引用

Communication & Computing (WCONF), World Conference on

作者： Vaishali Singh Pratik Pandey Santosh Chowhan S. Hemelatha Divya N Yogesh D. Deshpande Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Data Analytics and Mathematical Sciences Jain (Deemed to be University) Bangalore Karnataka Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore Department of Civil Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai-127 Department of Information Technology Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

This analytical examine investigates the safety of net Key change (IKE) Protocol for wireless networks. It specializes in how IKE works and the unique additives that it involves so one can provide relaxed key trade. The paper examines the IKE protocol primarily based at the maximum current requirements and gives a complete review of ways the protocol works, its key components, the safety mechanisms it is predicated on, its blessings, and its weaknesses. thru our examine, it's miles discovered that even though IKE is considered to be one of the most relaxed protocols for Wi-Fi networks, there are nevertheless certain regions within the protocol that have ability for improvement. The paper concludes with numerous tips on a way to maximize the security furnished by using IKE while minimizing its potential for weakness.

关键词： Protocols Additives Reviews Wireless networks Authentication Organizations Internet Security Protection Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning 29

Parsing Natural Language into Propositional and First-Order ...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Lu, Xuantao Liu, Jingping Gu, Zhouhong Tong, Hanwen Xie, Chenhao Huang, Junyang Xiao, Yanghua Wang, Wenguang Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China SenseDeal Intelligent Technology Co. Ltd. Beijing China School of Information Science and Engineering East China University of Science and Technology China Fudan-Aishu Cognitive Intelligence Joint Research Center China DataGrand Inc. Shanghai China

Semantic parsing converts natural language utterances into structured logical expressions. We consider two such formal representations: Propositional Logic (PL) and First-order Logic (FOL). The paucity of labeled data is a major challenge in this field. In previous works, dual reinforcement learning has been proposed as an approach to reduce dependence on labeled data. However, this method has the following limitations: 1) The reward needs to be set manually and is not applicable to all kinds of logical expressions. 2) The training process easily collapses when models are trained with only the reward from dual reinforcement learning. In this paper, we propose a scoring model to automatically learn a model-based reward, and an effective training strategy based on curriculum learning is further proposed to stabilize the training process. In addition to the technical contribution, a Chinese-PL/FOL dataset is constructed to compensate for the paucity of labeled data in this field. Experimental results show that the proposed method outperforms competitors on several datasets. Furthermore, by introducing PL/FOL generated by our model, the performance of existing Natural Language Inference (NLI) models is further enhanced. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Animal Behavior Monitoring Based on Sequence to Sequence Model

Animal Behavior Monitoring Based on Sequence to Sequence Mod...

引用

International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)

作者： Qing-Zhe Cui Xin Yuan Justine Partoon Alexandra L. Whittaker Li-Xiang Xu Lei Liu Peng Shi School of Computer Engineering and Science Shanghai University Shanghai China College of Artificial Intelligence and Big Data Hefei University Hefei China School of Electrical and Mechanical Engineering The University of Adelaide Adelaide Australia Zoos South Australia Adelaide Australia School of Animal and Veterinary Sciences The University of Adelaide Adelaide Australia Anhui Jiaoxin Technology Co. Ltd. Hefei China

ISBN: (数字)9798331528072

ISBN: (纸本)9798331528089

Object tracking is a core task in the field of computer vision, with wide-ranging applications in scenarios such as video surveillance and autonomous driving. This paper focuses on the application of the SeqTrack method, a sequence-to-sequence (Seq2Seq) model-based approach for object tracking, to animal behavior monitoring video datasets. The SeqTrack method leverages an encoder-decoder architecture to capture the temporal dependencies of objects, enabling accurate object localization and bounding box prediction. To validate the performance of SeqTrack in practical scenarios, we conducted comparative experiments on a self-made Adelaide Zoo dataset, comparing SeqTrack with three other mainstream object tracking algorithms: ToMP, OSTrack, and MixFormer. The experimental results show that SeqTrack outper-forms in terms of both precision and success rate, demonstrating its superior capability in handling challenges such as fast object movements, complex backgrounds, and partial occlusions. These findings indicate that SeqTrack is well-suited for high-precision tracking scenarios like animal behavior monitoring.

关键词： Location awareness Analytical models Accuracy Animal behavior Wavelet analysis Video surveillance Prediction algorithms Pattern recognition Object tracking Monitoring

来源：评论

学校读者我要写书评

暂无评论

EvoSampling: A Granular Ball-based Evolutionary Hybrid Sampling with Knowledge Transfer for Imbalanced Learning

arXiv

引用

arXiv 2024年

作者： Pei, Wenbin Dai, Ruohao Xue, Bing Zhang, Mengjie Zhang, Qiang Cheung, Yiu-Ming Xia, Shuyin The School of Computer Science and Technology Dalian University of Technology Dalian116024 China Ministry of Education Dalian116024 China The School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington6140 New Zealand The Department of Computer Science Hong Kong Baptist University Hong Kong The Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

Class imbalance would lead to biased classifiers that favor the majority class and disadvantage the minority class. Unfortunately, from a practical perspective, the minority class is of importance in many real-life applications. Hybrid sampling methods address this by oversampling the minority class to increase the number of its instances, followed by undersampling to remove low-quality instances. However, most existing sampling methods face difficulties in generating diverse high-quality instances and often fail to remove noise or low-quality instances on a larger scale effectively. This paper therefore proposes an evolutionary multi-granularity hybrid sampling method, called EvoSampling. During the oversampling process, genetic programming (GP) is used with multi-task learning to effectively and efficiently generate diverse high-quality instances. During the undersampling process, we develop a granular ball-based undersampling method that removes noise in a multi-granular fashion, thereby enhancing data quality. Experiments on 20 imbalanced datasets demonstrate that EvoSampling effectively enhances the performance of various classification algorithms by providing better datasets than existing sampling methods. Besides, ablation studies further indicate that allowing knowledge transfer accelerates the GP's evolutionary learning process. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Provably Secure Authenticated Key-Management Mechanism for e-Healthcare Environment

引用

IEEE Internet of Things Journal 2025年

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Ghaffar, Zahid Xie, Yong Wang, Guijuan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Douliu64002 Taiwan Qinghai Institute of Technology School of Computer and Information Science China Qinghai Provincial Laboratory for Intelligent Computing and Application China Key Laboratory of Computing Power Network and Information Security Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security China Shandong Fundamental Research Center for Computer Science Jinan250353 China

The Internet of Things (IoT) is rapidly permeating all aspects of human life, involving a network of devices that share sensitive data. A notable application is the e-healthcare systems, which employ connected sensors, medical servers, and wearable devices. However, the public nature of communication in e-healthcare systems poses challenges such as security, privacy, and authentication of participating entities. Recently, many authentication protocols have been introduced to address these challenges. However, most of these protocols remain vulnerable to various security attacks, including device or medical server impersonation, denial of service, physical or cloning, and de-synchronization attacks. Therefore, we introduce an authenticated key-management protocol utilizing hash functions and Cipher-Block Chaining-Advanced Encryption Standard encryption (CBC-AES) encryption. The proposed protocol also employs the Physical Unclonable Function (PUF), which makes it more robust and efficient in resisting physical or cloning attacks. Additionally, the proposed scheme resists various security threats, including impersonation, session key leakage, ephemeral secret leakage, and de-synchronization attacks. We analyze the scheme’s security and reliability through formal and informal analysis. The informal analysis demonstrates that the scheme encompasses crucial security features, while the formal analysis substantiates. Moreover, performance analysis of the proposed protocol with various competing results indicates that our protocol achieves an average reduction in communication and computation overheads by 36.03.% and 41.79%, respectively. © 2014 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Contrast-Free Myocardial Scar Segmentation in Cine MRI using Motion and Texture Fusion

Contrast-Free Myocardial Scar Segmentation in Cine MRI using...

引用

IEEE International Symposium on Biomedical Imaging

作者： Guang Yang Jingkun Chen Xicheng Sheng Shan Yang Xiahai Zhuang Betty Raman Lei Li Vicente Grau Department of Engineering Science University of Oxford Oxford UK School of Data Science Fudan University Shanghai China Department of Radiology Zhongshan Hospital Fudan University Shanghai China Radcliffe Department of Medicine University of Oxford Oxford UK School of Electronics & Computer Science University of Southampton Southampton UK Department of Biomedical Engineering National University of Singapore Singapore

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Late gadolinium enhancement MRI (LGE MRI) is the gold standard for the detection of myocardial scars post myocardial infarction (MI). LGE MRI requires the injection of a contrast agent, which carries potential side effects and increases scanning time and patient discomfort. To address these issues, we propose a novel framework that combines cardiac motion observed in cine MRI with image texture information to segment the myocardium and scar tissue in the left ventricle. Cardiac motion tracking can be formulated as a full cardiac image cycle registration problem, which can be solved via deep neural networks. Experimental results prove that the proposed method can achieve scar segmentation based on non-contrast cine images with comparable accuracy to LGE MRI. This demonstrates its potential as an alternative to contrast-enhanced techniques for scar detection.

关键词： Deep learning Image segmentation Image texture Contrast agents Tracking Magnetic resonance imaging Motion segmentation Artificial neural networks Myocardium Gadolinium

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Long-Term Sustainability of Healthcare data Optimization Through Deep Federated Learning

Enhancing the Long-Term Sustainability of Healthcare Data Op...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： Balraj Kumar Munni Evin Haewon Byeon M. Sivaprakash P. Maria Sheeba Sunil J School of Computer Application Lovely Professional University Phagwara Punjab India School of Engineering and Computing American International University Kuwait Department of AI-Big Data College of AI Convergence Inje University Gimhae Republic of Korea Department of Mechanical Engineering Stella Mary's College of Engineering Tamil Nadu India Department of Electronics and Communication Engineering St. Mother Theresa Engineering College Thoothukudi India Annai Vailankanni College of Engineering Kanyakumari Tamil Nadu India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

The medical industry regards the prevention and detection of skin diseases as a top priority. The number of people suffering from skin diseases is increasing faster than ever before due to increased levels of pollution and poor diet. Although it's not the major priority, having bad skin makes us less certain. Regularly inspecting your skin is an important step in identifying any degenerative or early changes in your skin that could lead to skin disease. Machine learning algorithms can be utilized to create robust models that can categorize a wide range of skin conditions. First, the skin and non-skin must be distinguished in order to identify skin conditions. In order to determine the unambiguous a group of skin conditions A selection of five distinct machine learning algorithms has been employed to compile a dataset of skin infections. These algorithms include Kernel Self- pattern, Random Forest, Naive Bayes, Logistic Regression, and CNN, among others. A comparable investigation based on training accuracy and skepticism matrix criterion has been carried out and illustrated with graphs. It has been determined that, of all the applicants, CNN offers the highest level of training accuracy for the appropriate assumption of skin disorders.

关键词： Training Machine learning algorithms Pollution Signal processing algorithms Signal processing Skin Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Crop Recommendation System

Machine Learning-Based Crop Recommendation System

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Ebenezer V Akash Nair Stewart Kirubakaran S Praising Linijah N L Jerlin Rajan Santhiya P Division of Data Sciences and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Karunya School of Management Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

The time-honored way that farmers have been used to apply to the identification of the best crops for better yield is not exhaustive. Under this technique, the management process of powerful and productive resources, cannot be done properly. The crop recommendation system comprising a machine learningbased model can be deployed to solve the problem. While using techniques such as Logistic Regression, Decision Trees, Random Forests, XGB boost, SVM and Stacking Classifier, the machine learning model attempts to predict the most suitable crops by taking and observing soil contents and environmental parameters. That study is devoted to helping farmers have comprehensive prescriptions and appropriate crop selections to optimize productivity and guarantee sustainability.

关键词： Support vector machines Computational modeling Stacking Crops Soil Ubiquitous computing Sustainable development Recommender systems Regression tree analysis Random forests

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：