检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jin Li Ruifan Yuan Yu Tian Jingsong Li School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China College of Biomedical Engineering & Instrumental Science Zhejiang University Hangzhou China Zhejiang Lab Research Center for Data Hub and Security Hangzhou China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Biomedical information extraction, including tasks like Named Entity Recognition (NER) and Relationship Extraction (RE), plays a critical role in analyzing unstructured biomedical data, facilitating more accurate downstream applications such as clinical decision support and personalized medicine. Although Large Language Models (LLMs) excel in various domains, they often struggle with issues like hallucinations and domain-specific inaccuracies, limiting their effectiveness in biomedical applications. To tackle these challenges, we propose a novel framework that incorporates an external dual-stage verifier to enhance biomedical information extraction. This verifier is prompted to first identify and complete missing entities and relations, and then filter out incorrect extractions, thereby enhancing both precision and recall in information extraction. Furthermore, we proposed an approach for constructing the instruction-tuning dataset using both positive and negative demonstrations, which improves the verifier’s correction capabilities through Parameter-Efficient Fine-Tuning (PEFT). Our extensive experiments on three public benchmark datasets cover both biomedical NER and RE tasks, comparing four LLMs ranging from 7 to 175 billion parameters to validate the effectiveness and scalability of our approach. The results demonstrate that by integrating an external verifier specifically finetuned for biomedical tasks, we achieve substantial improvements in precision, recall, and F1 scores for NER and RE tasks. Our method consistently outperforms In-Context Learning (ICL) approaches in F1 scores, achieving increases of up to 20% in some cases. Furthermore, ablation studies demonstrate the effectiveness of both stages in the verification process. The proposed framework provides valuable insights for accurate biomedical information extraction using LLMs, highlighting its potential applications in real-world clinical settings.

关键词： Accuracy Limiting Large language models Scalability Precision medicine Named entity recognition Information filters Distance measurement data mining Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Shortest Path Optimized Algorithm for Vehicle Adhoc Networks System 7

An Efficient Shortest Path Optimized Algorithm for Vehicle A...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Shalini, K. Reddy, K. Harinath Punati, Kondalarao Kavin, K.S. Veena, P. Pushpalatha, K. Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Shamshabad India Annamacharya Institute of Technology and Sciences Department of Electrical and Electronics Engineering Rajampet India Hyderabad Institute of Technology and Management Faculty of Electronics and Communication Engineering Hyderabad500090 India Government College of Engineering Department of Electrical and Electronics Engineering Tamilnadu Tirunelveli India N. S. S. Polytechnic College Department of Computer Engineering Pandalam Pathanamthitta India Coimbatore Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore641109 India

ISBN: (纸本)9798350372816

VANET (Vehicular ad-hoc network) is a network of advanced automobiles designed to solve the problem of mobility and, as a result, reduce the number of accidents. Because VANET is a type of MANET (mobile ad hoc network) surrounded by human-driven nodes, the social concept can be used to explain VANET routing decisions. This motivates academics to look into the possibilities of using Social Network Analysis (SNA) to create routing strategies. The most critical problem in any system is parcel drop. Social characteristics-based architectures encounter comparable challenges, resulting in inefficient message delivery. In this research, the dragonfly method is used to the shortest path methodology for fixed line VANET with the purpose of reducing package drop and increasing network reliability. This is made achievable by sculpted system of values centralization analysis, which improves the decision via dragonfly optimization methodology. The behavior of the using nodes capability then be determined by the importance computation. In this study, the sustainability of the optimized shortest path system is measured in terms of End to End delay, Energy Consumption, Packet Loss, and Throughput. The dragonfly algorithm's throughput evaluation is 650 kbps as compared to the traditional way. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

GraphBot: Botnet Detection via Dynamic Graph Representation Learning

GraphBot: Botnet Detection via Dynamic Graph Representation ...

引用

International Conference on Computer and Communications (ICCC)

作者： Siyu Cheng Jingxian Shuai Fengrui Xiao Dan Yang Yuanyi Ma Shuangwu Chen School of Information Science and Technology University of Science and Technology of China Hefei China Institute of Advanced Technology University of Science and Technology of China Hefei China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong China School of Information Science and Technology University of Science and Technology of China Institute of Artificial intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Botnets, networks of compromised devices controlled remotely by attackers, are particularly threatening due to their ability to conduct various cyber-attacks, such as Distributed Denial of Service (DDoS) attacks, data theft, and spamming. Existing botnet detection methods often rely on static or manually designed features, which are increasingly ineffective against modern botnets that utilize sophisticated encryption and evasion techniques. In this paper, we propose GraphBot, a novel botnet detection method that leverages dynamic graph representation learning to overcome these challenges. GraphBot introduces the concept of superflows, which are collections of network flows exhibiting similar behavior. It constructs a superflow correlation graph with timestamps to model temporal correlations and continuously updates node representations. This dynamic learning framework effectively captures the complex and evolving patterns in network traffic. We evaluate GraphBot on two public datasets, and the experimental results demonstrate that GraphBot outper-forms state-of-the-art botnet detection methods, achieving high precision and recall while maintaining a low false positive rate. These highlight GraphBot's robustness, reliability, and practical applicability in real-world network security scenarios.

关键词： Representation learning Correlation Botnet Heuristic algorithms Unsolicited e-mail Telecommunication traffic Network security Feature extraction Robustness Encryption

来源：评论

学校读者我要写书评

暂无评论

Improved task scheduling and load balancing in fog computing infrastructure using hybrid evolutionary method

引用

Cluster Computing 2025年第6期28卷 1-34页

作者： Zhao, Li Lin, Zhenhua Shao, Hongfei Zheng, Wei Zhang, Shihong Wang, Yongjie Li, Qinghua College of Mechanical and Vehicle Engineering Changchun University Changchun China Tianjin University of Science and Technology College of Artificial Intelligence Tianjin China Tianjin Huafang Tech Co. Ltd Tianjin China Jilin Puna Automation Equipment Co. Ltd Changchun China

Task scheduling and virtual machine (VM) placement are two of the main issues in fog computing infrastructure. These elements are closely related to the crucial issue of fog computing’s resource and energy usage. Achieving cost-effective execution and improving resource utilization requires careful consideration of task scheduling and VM deployment. Because the task scheduling problem is NP-hard, scientists are exploring metaheuristic algorithms that are inspired by nature. On the other hand, evolutionary algorithms can perform significantly better when their initialization solutions are well-designed. In this paper, a hybrid evolutionary task scheduling (HETS) approach for reliable fog computing task scheduling and VM placement is presented. By combining a new VM placement method with an enhanced particle swarm optimization (PSO) algorithm and using the ability of direct binary. The direct binary encoding technique in PSO represents particle positions as binary values (0 or 1) and velocity within [0, 1], suited for task scheduling problems. A probabilistic approach is used to update binary positions based on the continuous velocity. This method efficiently applies PSO to binary decision spaces, enhancing its applicability to complex optimization problems. Also, a new method was introduced to enhance VM placement, focusing on memory and processor utilization for balanced resource distribution. This approach allocates resources based on memory, processor consumption, and remaining capacity, categorizing physical machines into groups by available resources. This categorization helps select suitable VMs according to tasks and resource needs. The simulation results show that the HETS, compared to other evolutionary algorithms ACO, GASA, and GA, on average, reduces the energy consumption by 5, 9, and 14% and makespan 4, 6, and 11%, respectively. Additionally, the results show a better degree of load balancing and execution time compared to other approaches.

关键词： VM placement Fog computing IoT Task scheduling Load balancing

来源：评论

学校读者我要写书评

暂无评论

The Role of Edge Computing in Enhancing Cloud Performance and Reducing Latency 7

The Role of Edge Computing in Enhancing Cloud Performance an...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Sharma, Puneet Shyamala Devi, J. Manikandan, K. Ani Minisha, R. Harini, R. Karthik, S. Sr University School of Cs & Ai Telangana Warangal India Rajalakshmi Institute of Technology Chennai India Tamilnadu Vellore632014 India R.M. K. Engineering College Department of Artificial Intelligence and Data Science India Veltech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Computer Science and Engineering India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Mathematics Avadi Tamilnadu Chennai600062 India

ISBN: (纸本)9798350350067

The flexibility of implementing edge computing over cloud infrastructures has become essential for responding to the need for reducing latency and improving data processing in a distributed environment. This research aims to determine the use of edge computing in enhancing the effectiveness of cloud utilization through conducting machine learning investigations utilizing Random Forest in the determination of the optimum contribution of resources. The work also set up and applied real-world datasets from Kaggle to illustrate that edge computing can alleviate the latency issue mainly by offloading computationally intensive tasks to edge nodes away from the central cloud. The results show that edge computing with the help of Machine learning is the best solution for cutting-edge cloud environments as it is fast and does not aggravate the problems of excessive use of resources. Therefore, this research will be a great addition to the existing literature on the integration of cloud and edge computing and is hoped to offer useful information for future developments in the field of cloud computing. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Joint Load Prediction of Multiple Buildings Using Multi-Task Learning with Selected-Shared-Private Mechanism

SSRN

引用

SSRN 2023年

作者： Cao, Minghui Xiao, Jiang-Wen Fang, Hongliang Li, Yuan-Zheng Wang, Yan-Wu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China

Short-term load forecasting for residential buildings is of great significance to ensure the safe and economic operation of power grid. However, most of the existing prediction methods focus on the temporal characteristics of individual buildings and ignore the importance of spatial characteristics between different buildings. To tackle this problem and realize joint prediction for multiple buildings, a novel multi-task learning model with the selected-shared-private mechanism is proposed in this paper. Firstly, the temporal and spatial characteristics hidden in electricity consumption patterns are analyzed and represented by auto-correlation and cross-correlation, respectively. Then, a correlation-oriented combination strategy considering the auto-correlation and time dependency is proposed to build input set for the prediction model, and the temporal convolutional network is adopted to extract features. Furthermore, this paper designs a novel selected-shared-private mechanism based on the cross-correlation, which can selectively utilize information from related tasks while focusing on private features to improve prediction accuracy. The proposed model is compared with other methods on the public dataset, and the results demonstrate the superiority of this model in load prediction for multiple buildings. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

RMDA: A Regressive Multiple-Source Domain Adaption Approach for Early Prediction of Lithium-ion Battery Lifetime

RMDA: A Regressive Multiple-Source Domain Adaption Approach ...

引用

Chinese Control Conference (CCC)

作者： Songpei Xu Xiaoran Yang Guijun Ma Ye Yuan School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan P. R. China School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan P. R. China

Early prediction of battery lifetime is crucial for manufacturers to sort and group lithium-ion batteries (LIBs). This article introduces a regressive multiple-source domain adaption (RMDA) method for accurate early lifetime prediction with multiple LIB datasets. First, a common feature extractor is used to extract common features from different domains. Then, the domain-specific extractors followed by a maximum mean discrepancy loss are utilized to reduce the shift of source domains. Next, the domain-specific regressors are adopted to predict the lifetime of the source domains and the target domain. The effectiveness of the proposed RMDA method is validated on three LIB datasets with different chemistries and operating conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VRoPE: Rotary Position Embedding for Video Large Language Models

arXiv

引用

arXiv 2025年

作者： Liu, Zikang Guo, Longteng Tang, Yepeng Cai, Junxian Ma, Kai Chen, Xi Liu, Jing Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Computer Science and Technology Beijing Jiaotong University China Basic Algorithm Center Tencent China

Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations, such as RoPE-3D, attempt to encode spatial and temporal dimensions separately but suffer from two major limitations: positional bias in attention distribution and disruptions in video-text transitions. To overcome these issues, we propose Video Rotary Position Embedding (VRoPE), a novel positional encoding method tailored for Video-LLMs. Our approach restructures positional indices to preserve spatial coherence and ensure a smooth transition between video and text tokens. Additionally, we introduce a more balanced encoding strategy that mitigates attention biases, ensuring a more uniform distribution of spatial focus. Extensive experiments on Vicuna and Qwen2 across different model scales demonstrate that VRoPE consistently outperforms previous RoPE variants, achieving significant improvements in video understanding, temporal reasoning, and retrieval tasks. Code will be available at https://***/johncaged/VRoPE Copyright © 2025, The Authors. All rights reserved.

关键词： Rope

来源：评论

学校读者我要写书评

暂无评论

Navigating Grid Dynamics with V2G technology and Naive Bayes Optimization in IoT Systems 3

Navigating Grid Dynamics with V2G Technology and Naive Bayes...

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Arulprakash, M. Raman, Ramakrishnan Gokhale, Atul A. Saravanan, K. Ishwarya, M.V. Sujatha, S. Srm Institute of Science and Technology Department of Computing Technologies Chennai Tamil Nadu Kattankulathur India Maharashtra Pune India Symbiosis School of Culinary Arts Maharashtra Pune India R.M.D. Engineering College Department of Information Technology Tamil Nadu Chennai India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350381931

Vehicle-to-Grid (V2G) technology and Naive Bayes optimization, which might help IoT devices, navigate grid dynamics. Electric vehicles (EVs) with bidirectional charging capability may provide grid assistance using their energy storage capacity. These cars can take and return energy from the grid using V2G technology, stabilizing the system. This paper proposes a unique technique to intelligently control energy flow between the grid and EVs using V2G technology and Naive Bayes optimization algorithms. Using previous data on energy consumption, grid circumstances, and vehicle charging behavior, the Naive Bayes algorithm makes real-time predictions and decisions. In IoT-enabled smart grids, this connection improves energy management efficiency and reliability. The implementation methods and experimental findings of the suggested strategy are discussed in the study. The system grid stability, energy usage, and grid dynamics management are also assessed. The results show that V2G technology and Naive Bayes optimization in IoT systems can intelligently navigate grid dynamics, creating a more sustainable and resilient energy infrastructure. To smart grid expertise and shows how V2G-enabled IoT devices may optimize energy distribution and ensure grid stability in the face of dynamic energy needs. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Investigating the Benefits of Machine Learning Algorithms for Text Classification 3

Investigating the Benefits of Machine Learning Algorithms fo...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Gowrishankar, J. Vinithra Banu, T. Parikshit, N. Singh, Vandana Kalra, Hitesh Sahoo, Girija Shankar Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

This paper affords a research into using gadget studying algorithms for textual content category duties, with a focal point on understanding the importance of these algorithms and their ability to enhance the accuracy of textual content classification. it's miles located that, while conventional techniques, which include rule based models and hand-engineered features, can attain first-class outcomes, there are compelling motives to explore the capability of device getting to know algorithms to further improve the accuracy and performance of textual content class. The paper discusses the 3 maximum famous gadget gaining knowledge of algorithms for this project: the NaÏve Bayes classifier, help Vector Machines, and synthetic Neural Networks, and presents a top level view of the latest research findings that demonstrate the prevalence of these algorithms over traditional methods. The paper additionally presents an outline of the distinctive approaches for introducing era into text type, and discusses modern-day strategies for implementing and deploying those algorithms. Finally, the paper outlines ability areas for destiny research associated with information the results of system studying algorithms for this mission, and suggests viable instructions for exploration. © 2023 IEEE.

关键词： Classification (of information)

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：