检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Shi, Zhenwei Li, Weixing Pan, Xipeng Zhang, Zhen Wu, Guangyao Ye, Guanchao Wee, Leonard Dekker, Andre Han, Chu Shi, Lei Liu, Zaiyi Liu, Zhenbing School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Department of Radiology Huazhong University of Science and Technology Tongji Medical College Union Hospital Hubei Wuhan430021 China Clinical Data Science Faculty of Health Medicine Life Sciences Maastricht University Maastricht6229 ET Netherlands GROW School of Oncology and Reproduction Maastricht University Medical Centre+ Maastricht6229 ET Netherlands Guangdong Provincial People's Hospital China

Background and Objective: Accurate lung tumor segmentation is crucial for early clinical diagnosis and subsequent treatment planning for patients. Conducting centralized training to enhance model performance is impractical in real-world scenarios. Although federated learning offers a promising solution to this issue, effectively and efficiently utilizing unlabeled data remains a challenge. Methods: In this work, we propose a novel federated semi-supervised learning framework (FSSL) for complex and realistic scenario, which can efficiently leverage the limited labeled data and abundant unlabeled data from multiple clinical sites. Specifically, we initially conduct federated self-supervised pre-training at completely unlabeled sites using masked image modeling strategy. Subsequently, in the fine-tuning stage, we propose a pseudo supervision refinement strategy to leverage the unlabeled data from partially labeled sites, which not only reduces pseudo label noise but also helps stabilize the training process. Moreover, we propose a dynamic model aggregation strategy to assist the server in dynamically combining all local models during communication round. Results: We conducted extensive comparative and ablation experiments to validate the effectiveness of our proposed method. When only a limited amount of labeled data is available in the partially labeled sites, even without loading the pre-trained model, our approach consistently achieves the highest average Dice scores of 0.7383, 0.4768, and 0.6629 on the internal test sets, external unseen test sets, and pre-training test sets, respectively. Upon loading the pre-trained model, the scores on the three test sets further improve to 0.8205, 0.6185, and 0.7334, respectively. Conclusion: Our proposed method is capable of collaboratively training a global model with robust segmentation performance and generalizability by efficiently utilizing unlabeled data from different sites, even when only a limited amount of labeled da

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sliding Mode Control for an Unmanned Mini Vehicle

Adaptive Sliding Mode Control for an Unmanned Mini Vehicle

引用

International Conference on Mechanical, Control and computer engineering (ICMCCE)

作者： Jia-Peng Wang Xiang-Lian Meng Shi-Long Zhang Ying-Kun Zhu Institute of Data Science and Artificial Intelligence Harbin HuaDe University Harbin China School of Computer Information & Engineering Changzhou Institute of Technology Changzhou China

In this paper, an adaptive sliding mode controller with PID tuning method is presented for an unmanned mini vehicle. Moreover, in order to achieve system robustness against parameter variations and external disturbances, suitable PID control gain parameters can be systematically on-line computed based on the proposed adaptive law. The boundary layer condition is adopted to reduce the high frequency chattering in the switching part of the sliding mode controller. The asymptotic stability property can be guaranteed according to the Lyapunov stability theorem. Numerical simulation results illustrate that satisfactory trajectory tracking performance is achieved effectively and the input chattering is attenuated dramatically.

关键词： Training PI control Trajectory tracking Switches Turning Robustness Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Navigating the artificial intelligence Revolution in NeuroOncology: A Multidisciplinary Viewpoint

SSRN

引用

SSRN 2024年

作者： Saxena, Sanjay Panda, Soumyaranjan Tiwari, Ekta Singh, Rajesh Fouda, Mostafa M. Kalra, Mannudeep K. Kotecha, Ketan Saba, Luca Suri, Jasjit S. Department of Computer Science & Engineering International Institute of Information Technology Odisha Bhubaneswar India Department of Computer Science & Information Technology Mahatma Gandhi Central University Bihar India Department of Computer & Engineering Visvesvaraya National Institute of Technology Maharashtra Nagpur India Department of Research and Innovation Uttaranchal Institute of Technology Uttaranchal University Dehradun248007 India Department of Electrical and Computer Engineering Idaho State University PocatelloID83209 United States Department of Radiology Massachusetts General Hospital BostonMA United States Symbiosis centre for Applied Artificial Intelligence Symbiosis Institute of Technology Symbiosis International University Pune India Cagliari Italy Department of ECE Idaho State University PocatelloID83209 United States Department of CE Graphics Era Deemed to be University Dehradun248002 India University Center for Research & Development Chandigarh University Mohali India Pune India Stroke Diagnostic and Monitoring Division AtheroPoint RosevilleCA95661 United States Harvard Medical School United States University Hospital of Cagliari Italy

This comprehensive review presents the role of artificial intelligence (AI), machine learning (ML), and deep learning (DL) in neuro-oncology, focussing their groundbreaking impact on the field. It gives a historical overview of AI's evolution in area of neuro-oncology, representing its progress from basic data management to high-level predictive analytics that now significantly makes personalized treatment ***, This study examines various ML based methods that emphasize brain tumor classification, genetic profiling, and individualized care plans proposals, which basically reflects the shift towards precision medicine. This paper also highlights, developments in DL particularly in the development of neuro-imaging analysis, which has significantly guided surgical planning and radiation therapy for improved patient outcomes. Through various case studies, the paper presents recent breakthroughs where AI interventions have noticeably enhanced the treatment of neuro-oncological conditions. Moreover, It also addresses the ethical considerations encompassing the use of automated decision-making tools, emphasizing the need for ethical governance in AI deployment. By integrating multidisciplinary perspectives, the study underscores the collaborative effort between clinicians, data scientists, and ethicists, which is very crucial for the ethical and effective implementation of AI in current clinical practice. The main aim of discussion is to equip neurooncologists/sergeons and doctors with understandings into sustainable AI adoption which ensures that AI's path in neuro-oncology aligns with both clinical needs for personalized medicine and ethical *** paper concludes by outlining considered methods and frameworks for the future integration of AI in neuro-oncology, predicting trends, and preparing to meet the challenges ahead. © 2024, The Authors. All rights reserved.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

An artificial Neural Network Model to Forecast Grain Crops in North-Kazakstan Agricultural Experimental Station

An Artificial Neural Network Model to Forecast Grain Crops i...

引用

Communications, Information, Electronic and Energy Systems (CIEES), International Conference on

作者： Aigul Mimenbayeva Maylen Omirtay Rozamgul Niyazova Gulmira Bekmagambetova Raya Suleimenova Ainur Tursumbayeva Dept. of Computational and Data Sciences Astana IT University Astana Kazakstan Specialty Smart Technologies Astana IT University Astana Kazakstan Dept. of Artificial Intelligence Technologies L. Gumilyov Eurasian National University Astana Kazakhstan Dept. of Computer Science S. Seifullin Kazakh Agrotechnical Research University Astana Kazakstan School of Engineering and Information Technology Eurasian Technological University Almaty Kazakstan Dept. of Information Systems S. Seifullin Kazakh Agrotechnical Research University Astana Kazakstan

The paper analyzes and predicts the yield of grain crops of LLP “North-Kazakhstan Agricultural Experimental Station” for the last 30 years. The class of artificial neural networks-multilayer perceptron (MLP) was used as a research tool. The process of training of a model of a neural network consisting of 30 networks was performed on the basis of 70% training and 30% control samples. Based on the analysis of residuals histogram and scatter plot of the target and output function, the best neural network models MLP-1-7-1 (p=0.92), MLP-1-8-1 (p=0.97), MLP-1-5-1 (p=0.82) were selected. Next, using the best MLP 1-8-1 network, the model was tested the given data. Using time series projection, a graph was illustrated and a table of predicted grain yield values for the coming years was tabulated. The absolute error showed the high accuracy of the obtained best MLP 1-8-1 network for forecasting the amount of grain crop yield. The obtained model of artificial network can be applied in research and monitoring of agricultural production development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securing the road ahead: Machine learning-driven DDoS attack detection in VANET cloud environments

Cyber Security and Applications

引用

Cyber Security and Applications 2024年 2卷

作者： Setia, Himanshu Chhabra, Amit Singh, Sunil K. Kumar, Sudhakar Sharma, Sarita Arya, Varsha Gupta, Brij B. Wu, Jinsong Department of CSE Chandigarh College of Engineering and Technology Sector 26 Chandigarh India Department of CSE Chandigarh College of Engineering and Technology Chandigarh India Department of ECE Chandigarh College of Engineering and Technology Chandigarh India Department of Business Administration Asia University Taiwan Department of Computer Science and Information Engineering Asia University Taichung 413 Taiwan School of Artificial Intelligence Guilin University of Electronic Technology 510004 China Department of Electrical Engineering University of Chile 8370451 Chile Department of Electrical and Computer Engineering Lebanese American University Beirut 1102 Lebanon Symbiosis Centre for Information Technology (SCIT) Symbiosis International University Pune India School of Computing Skyline University College P.O. Box 1797 Sharjah United Arab Emirates Center for Interdisciplinary Research University of Petroleum and Energy Studies (UPES) Dehradun India

Vehicular ad-hoc network (VANET) technology has gained prominence, especially in the context of the emerging field of VANET Cloud as an integral part of connected and autonomous vehicles. The automotive industry's move towards automation and the integration of vehicles into the digital ecosystem has revolutionized wireless network communications. Nevertheless, security remains a paramount concern in these advanced technological landscapes. Safeguarding system integrity and data privacy is of utmost importance before the widespread adoption of VANET Cloud solutions. This study addresses the critical challenge of security within the context of VANET Cloud. Specifically, the focus is on anticipating and mitigating Distributed Denial of Service (DDoS) attacks, which can potentially disrupt the functioning of connected vehicles and associated cloud-based services. To tackle this issue, an innovative architectural framework is proposed to capture and analyze network flows within the VANET Cloud environment. Additionally, it leverages machine learning techniques for classification and predictive analytics with an accuracy of 99.59%. The architecture presented in this research offers the potential to significantly enhance security measures in VANET Cloud deployments. Its adaptability ensures practical applicability to real-world systems, enabling timely responses to security threats and breaches. © 2024

关键词： Cloud DDoS Fuzzification Machine learning NS2 Simulation VANET

来源：评论

学校读者我要写书评

暂无评论

Learning through AI-clones: Enhancing self-perception and presentation performance

Computers in Human Behavior: Artificial Humans

引用

computers in Human Behavior: artificial Humans 2025年 3卷

作者： Qingxiao Zheng Zhuoer Chen Yun Huang Institute for Artificial Intelligence and Data Science (IAD) Department of Computer Science and Engineering University at Buffalo SUNY NY USA HeyGen 12130 Millennium Dr. Ste 300 Los Angeles CA 90094 USA School of Information Sciences University of Illinois at Urbana Champaign 614 E Daniel St Champaign IL 61820 USA

This study examines the impact of AI-generated digital clones with self-images (AI-clones) on enhancing perceptions and skills in online presentations. A mixed-design experiment with 44 international students compared self-recording videos (self-recording group) to AI-clone videos (AI-clone group) for online English presentation practice. AI-clone videos were generated using voice cloning, face swapping, lip-syncing, and body-language simulation, refining the repetition, filler words, and pronunciation of participants' original presentations. The results, viewed through the lens of social comparison theory, showed that AI clones functioned as positive “role models” for encouraging positive social comparisons. Regarding self-perceptions, speech qualities, and self-kindness, the self-recording group showed an increase in pronunciation satisfaction. However, the AI-clone group exhibited greater self-kindness, a wider scope of self-observation, and a meaningful transition from a corrective to an enhancive approach in self-critique. Moreover, machine-rated scores revealed immediate performance gains only within the AI-clone group. Considering individual differences, aligning interventions with participants’ regulatory focus significantly enhanced their learning experience. These findings highlight the theoretical, practical, and ethical implications of AI clones in supporting emotional and cognitive skill development.

关键词： Social comparison theory Regulatory-focus AI avatar Deepfake Voice clone Experiment Self-kindness

来源：评论

学校读者我要写书评

暂无评论

Boosting Time-series Domain Adaptation via A Time-Frequency Consensus Framework

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2025年

作者： Yang, Wenmian Ragab, Mohamed Wu, Min Pan, Sinno Jialin Lin, Guosheng Jia, Weijia Chen, Zhenghua Institute of Technology Innovation Institute United Arab Emirates A∗STAR Singapore Department of Computer Science and Engineering Hong Kong Hong Kong Nanyang Technological University School of Computer Science and Engineering Singapore Beijing Normal University Institute of Artificial Intelligence and Future Networks Zhuhai519087 China BNUHKBU United International College Guangdong Key Lab of AI and Multi-Modal Data Processing Zhuhai519087 China

Unsupervised Domain Adaptation (UDA) has proven to be effective in addressing the domain shift problem in computer vision. However, compared with visual applications, UDA for time series brings forth additional challenges. Potential domain shifts may have varying impacts on both time and frequency features, rendering conventional UDA methods less effective in this context. To address these challenges, we propose a Time-Frequency Consensus Domain Adaption (TFCDA) framework to enhance UDA methods for time-series data. TFCDA designs a frequency encoder, a trainable Time-Frequency Mapping (TFM), and a consensus loss, building upon conventional UDA methods to boost their performance. The TFM is trained on source domain data to learn the inherent time-frequency feature mapping, while the novel consensus loss ensures consistent feature transfer during UDA in the target domain, effectively reducing domain shifts in both time and frequency, and thus boosting overall performance. Experimental evaluations on four publicly available time-series datasets demonstrate TFCDA's effectiveness in enhancing existing UDA methods for time-series data, highlighting its potential for real-world applications. © 2025 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Active legibility in multiagent reinforcement learning

引用

artificial intelligence 2025年 346卷

作者： Liu, Yanyu Pan, Yinghui Zeng, Yifeng Ma, Biyang Doshi, Prashant School of Automation Central South University No. 605 South Lushan Road Hunan Changsha410083 China School of Artificial Intelligence & National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen China Department of Computer and Information Sciences Northumbria University Newcastle United Kingdom School of Computer Science Minnan Normal University Fujian Zhangzhou China Department of Computer Science University of Georgia AthensGA United States

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others' behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework drives agents to conduct legible actions so as to help others optimize their behaviors. In addition, we design a series of problem domains that emulate a common legibility-needed scenario and effectively characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and requires less training time compared to several multiagent reinforcement learning algorithms. © 2025 The Author(s)

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Semi-WTC: A Practical Semi-supervised Framework for Attack Categorization through Weight-Task Consistency

arXiv

引用

arXiv 2022年

作者： Li, Zihan Chen, Wentao Wei, Zhiqing Luo, Xingqi Su, Bing The School of Informatics Xiamen University Xiamen361005 China The School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing100876 China The School of Computer Science & Technology Beijing Institute of Technology Beijing100081 China The Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China

Supervised learning has been widely used for attack categorization, requiring high-quality data and labels. However, the data is often imbalanced and it is difficult to obtain sufficient annotations. Moreover, supervised models are subject to real-world deployment issues, such as defending against unseen artificial attacks. To tackle the challenges, we propose a semi-supervised fine-grained attack categorization framework consisting of an encoder and a two-branch structure and this framework can be generalized to different supervised models. The multilayer perceptron with residual connection is used as the encoder to extract features and reduce the complexity. The Recurrent Prototype Module (RPM) is proposed to train the encoder effectively in a semi-supervised manner. To alleviate the data imbalance problem, we introduce the Weight-Task Consistency (WTC) into the iterative process of RPM by assigning larger weights to classes with fewer samples in the loss function. In addition, to cope with new attacks in real-world deployment, we propose an Active Adaption Resampling (AAR) method, which can better discover the distribution of unseen sample data and adapt the parameters of encoder. Experimental results show that our model outperforms the state-of-the-art semi-supervised attack detection methods with a 3% improvement in classification accuracy and a 90% reduction in training time. Copyright © 2022, The Authors. All rights reserved.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

You impress me: Dialogue generation via mutual persona perception

arXiv

引用

arXiv 2020年

作者： Liu, Qian Chen, Yihong Chen, Bei Lou, Jian-Guang Chen, Zixuan Zhou, Bin Zhang, Dongmei School of Computer Science and Engineering Beihang University China UCL Centre for Artificial Intelligence University College London United Kingdom School of Computer Science Fudan University China Microsoft Research Beijing China

Despite the continuing efforts to improve the engagingness and consistency of chit-chat dialogue systems, the majority of current work simply focus on mimicking human-like responses, leaving understudied the aspects of modeling understanding between interlocutors. The research in cognitive science, instead, suggests that understanding is an essential signal for a high-quality chit-chat conversation. Motivated by this, we propose P2 BOT, a transmitter-receiver based framework with the aim of explicitly modeling understanding. Specifically, P2 BOT incorporates mutual persona perception to enhance the quality of personalized dialogue generation. Experiments on a large public dataset, PERSONA-CHAT, demonstrate the effectiveness of our approach, with a considerable boost over the state-of-the-art baselines across both automatic metrics and human evaluations. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech processing

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：