检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Luo, Xiaoling Xu, Qihao Wu, Huisi Liu, Chengliang Lai, Zhihui Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR diagnosis because of the wide coverage of the field of view. Therefore, different from the previous single-view DR grading methods, we design a dynamic selection-driven multi-view DR grading method to fit clinical scenarios better. Since lesion information plays a key role in DR diagnosis, previous methods usually boost the model performance by enhancing the lesion feature. However, during the actual diagnosis, ophthalmologists not only focus on the crucial parts, but also exclude irrelevant features to ensure the accuracy of judgment. To this end, we introduce the idea of dynamic selection and design a series of selection mechanisms from fine granularity to coarse granularity. In this work, we first introduce an Ophthalmic Image Reader (OIR) agent to provide the model with pixel-level prompts of suspected lesion areas. Moreover, we design a Multi-View Token Selection Module (MVTSM) that prunes redundant feature tokens and dynamically selects key information. In the final decision stage, we dynamically fuse multi-view features through the novel Multi-View Mixture of Experts Module (MVMoEM), to enhance key views and reduce the impact of conflicting views. Extensive experiments on a large multi-view fundus image dataset with 34,452 images prove that our method performs favorably against state-of-the-art models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN LSTM Approach for Sentiment Analysis of Bengali Language Comment on Facebook

Hybrid CNN LSTM Approach for Sentiment Analysis of Bengali L...

引用

Integrated Circuits and Communication systems (ICICACS), IEEE International Conference on

作者： SM Nuruzzaman Nobel S M Masfequier Rahman Swapno Ramachandra A C Hasibul Hossain Shajeeb Md Babul Islam Rezaul Haque Dept of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru Dept. of Computer Modeling Electronic and System Engineering UNICAL Rende Italy Dept of CSE East West University Dhaka Bangladesh

This study addresses the challenge of sentiment analysis in Bengali Facebook comments, where users express their opinions on various topics. Existing sentiment analysis techniques have difficulty achieving high accuracy in this situation, which has inspired the creation of a fresh methodology. To improve sentiment analysis of Bengali Facebook comments, we suggest a model that combines a hybrid convolutional neural network (CNN) and a long short-term memory network (LSTM). Our research adds to the expanding area of sentiment analysis, especially for languages with few resources, such as Bengali. The success of the Hybrid CNN LSTM model opens the door for more precise and context-aware sentiment analysis on social media platforms, allowing for a better understanding of user sentiments and boosting user experiences. Our study focused on dividing comments into five groups according to their emotional content: troll, not bully, sexual, religious, and threat. We carefully generated the handmade dataset and ensured the quality and relevance of a dataset of 50,000 Bengali comments before using it to train and test our algorithm. The Hybrid CNN LSTM model outperforms conventional approaches and achieves an outstanding accuracy rate of 92.09%, demonstrating amazing efficiency in sentiment recognition. This dramatic increase in precision indicates that machine learning techniques are successful in sentiment analysis of Bengali Facebook comments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decision-Making for Satellite Anti-Interception Missions Leveraging Multi-Agent Reinforcement Learning

Decision-Making for Satellite Anti-Interception Missions Lev...

引用

Data-driven Optimization of Complex systems (DOCS), International Conference on

作者： Zixuan Chen Jianqi Wang Dan Wang Sheng Yu Jing Huo Yang Gao Department of Computer Science Nanjing University Nanjing China Institute of Spacecraft System Engineering (ISSE) China Academy of Space Technology (CAST) Beijing China

Many-to-many spacecraft autonomous evasion missions necessitate highly coordinated decision-making among several spacecraft to successfully avoid interceptions. Conventional control methods often struggle to manage the inherent complexity and uncertainty of these missions. In response to this challenge, we employ multi-agent reinforcement learning (MARL) algorithms that draw upon machine learning and game theory concepts. Our work is devoted to implementing MARL to facilitate autonomous and intelligent evasion maneuvers by spacecraft, considering the dynamic nature of the space environment and the multiple agent interactions. We utilize the Satellite Tool Kit (STK) as a simulation environment and assess cutting-edge MARL algorithms, with the goal of showcasing the potential of MARL in complex spacecraft evasion missions. Our research endeavors to enhance the autonomy, adaptability, and mission success rate of spacecraft systems under unpredictable circumstances, thereby facilitating more intelligent and adaptive space exploration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implicit Supervision-Assisted Graph Collaborative Filtering for Third-Party Library Recommendation

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1459-1471页

作者： Lianrong Chen Mingdong Tang Naidan Mei Fenfang Xie Guo Zhong Qiang He School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China Unicom (Guangdong) Industry Internet Company Guangzhou China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computing Technologies Swinburne University of Technology Melbourne VIC Australia

Third-party libraries (TPLs) play a crucial role in software development. Utilizing TPL recommender systems can aid software developers in promptly finding useful TPLs. A number of TPL recommendation approaches have been proposed and among them graph neural network (GNN)-based recommendation is attracting the most attention. However, GNN-based approaches generate node representations through multiple convolutional aggregations, which is prone to introducing noise, resulting in the over-smoothing issue. In addition, due to the high sparsity of labelled data, node representations may be biased in real-world scenarios. To address these issues, this paper presents a TPL recommendation method named Implicit Supervision-assisted Graph Collaborative Filtering (ISGCF). Specifically, it takes the App-TPL interaction relationships as input and employs a popularity-debiased method to generate denoised App and TPL graphs. This reduces the noise introduced during graph convolution and alleviates the over-smoothing issue. It also employs a novel implicitly-supervised loss function to exploit the labelled data to learn enhanced node representations. Extensive experiments on a large-scale real-world dataset demonstrate that ISGCF achieves a significant performance advantage over other state-of-the-art TPL recommendation methods in Recall, NDCG and MAP. The experiments also validate the superiority of ISGCF in mitigating the over-smoothing problem.

关键词： Vectors Noise Training Collaborative filtering Recommender systems Libraries Predictive models Graph neural networks Electronic mail Convolution

来源：评论

学校读者我要写书评

暂无评论

Compression-based Privacy Preservation for Distributed Nash Equilibrium Seeking in Aggregative Games

arXiv

引用

arXiv 2024年

作者： Huo, Wei Chen, Xiaomeng Ding, Kemi Dey, Subhrakanti Shi, Ling The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong The School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China The Department of Electrical Engineering Uppsala University Uppsala75103 Sweden

This paper explores distributed aggregative games in multi-agent systems. Current methods for finding distributed Nash equilibrium require players to send original messages to their neighbors, leading to communication burden and privacy issues. To jointly address these issues, we propose an algorithm that uses stochastic compression to save communication resources and conceal information through random errors induced by compression. Our theoretical analysis shows that the algorithm guarantees convergence accuracy, even with aggressive compression errors used to protect privacy. We prove that the algorithm achieves differential privacy through a stochastic quantization scheme. Simulation results for energy consumption games support the effectiveness of our approach. © 2024, CC BY.

关键词： Random errors

来源：评论

学校读者我要写书评

暂无评论

Real-Time Scheduling for Periodic Tasks on Uniform Multiprocessors

引用

Journal of Computing science and engineering 2020年第3期14卷 121-130页

作者： Lee, Sang-Gil Lee, Cheol-Hoon System Software Lab. Department of Computer Science and Engineering Chungnam National University Daejeon Korea Republic of

The problem of scheduling a set of periodic tasks on a uniform multiprocessor system is considered in the present study. Each processor in a uniform multiprocessor system is characterized by its speed or computation capacity, i.e., execution of a job on a processor with speed s for t time units completes s × t units of execution. In the commonly-known partitioned scheduling, each task is assigned to a processor and all of its jobs are required to be executed on that processor. However, partitioning of periodic tasks requires solving the bin-packing problem, which is known to be intractable (NPhard in the strong sense). This paper presents a global scheduling algorithm that transforms a given periodic task system into another using a "task-splitting" (as opposed to the "set-splitting") technique. Each transformed periodic task system is guaranteed to be scheduled successfully on any uniform multiprocessor using a partitioned scheduling algorithm. The earliest deadline first (EDF) algorithm is chosen for scheduling tasks on each processor. It is proven that the proposed algorithm results in the theoretical-maximum utilization bound on any uniform multiprocessor platform if the platform is "reasonably powerful". Therefore, the proposed algorithm is optimal in the sense of maximizing achievable utilization. Since the task-splitting technique will incur context switches during runtime, we have also considered the ways of reducing the number of context switches, and suggest a method which can significantly reduce the number of context switches in the schedules generated by the proposed algorithm. © 2020 xx

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Intelligence for Innovative Technopreneurial Business Models

Leveraging Artificial Intelligence for Innovative Technopren...

引用

Creative Communication and Innovative Technology (ICCIT), IEEE

作者： Sudaryono Inayatul Izzati Diana Yusuf Sabda Maulana Aptanta Pratiangga Dwi Apriliasari Department of Informatics Engineering University of Raharja Tangerang Indonesia Department of Informatics Engineering Bina Bangsa University Serang Indonesia Department of Digital Business Bosindo Tangerang Indonesia Department of Computer Science REY Tangerang Indonesia Department of Information System Pandawan Sejahtera Indonesia Tangerang Indonesia

ISBN: (数字)9798350367492

ISBN: (纸本)9798350367508

This study examines the rapid growth of startups integrating artificial intelligence (AI) into their business models, aiming to analyze and compare these startups with traditional IT organizations to understand their differences. Analyzing 162 global startups, this research identifies four unique archetypal business models, introducing novel methodologies in AI integration and data utilization that contrast with conventional IT paradigms. The focus is on technologies providing data analytics solutions, AI products and services, and the expansion of AI use. Key components of AI startup business models are highlighted: (1) advantages of AI in new value propositions, (2) data use to create value, and (3) the impact of AI on business decision-making. This research enhances the understanding of AI startup business models and suggests future research directions in entrepreneurship. The developed taxonomy highlights four distinct AI business models: the Deep Tech Researcher, Data Analytics Provider, AI Product/Service Provider, and AI Development Facilitator, each offering unique value propositions and leveraging AI technologies in different ways to address specific market needs. The research framework fosters entrepreneurial efforts with taxonomies and models as useful instruments.

关键词： Analytical models Data analysis Biological system modeling Taxonomy Entrepreneurship Data models Stakeholders Artificial intelligence Sustainable development Business

来源：评论

学校读者我要写书评

暂无评论

Advancing agriculture with machine learning:a new frontier in weed management

引用

农业科学与工程前沿（英文） 2025年第2期12卷 288-307页

作者： Mohammad MEHDIZADEH Duraid K.A.AL-TAEY Anahita OMIDI Aljanabi Hadi Yasir ABBOOD Shavan ASKAR Soxibjon TOPILDIYEV Harikumar PALLATHADKA Renas Rajab ASAAD Department of Agronomy and Plant Breeding Faculty of Agriculture and Natural ResourcesUniversity of Mohaghegh Ardabili***ArdabilIran Ilam Science and Technology Park ***IlamIran Department of Horticulture College of AgricultureUniversity of Al-Qasim Green00964 BabylonIraq Department of GIS and Remote Sensing Faculty of GeographyUniversity of Tehran***TehranIran Medical Laboratories Techniques Department Al-Mustaqbal University College51001 HillahIraq Erbil polytechnic university Technical engineering collegeinformation system engineering department44001 ErbilIraq Department of Fundamental Economics Tashkent State University of Economics100066TashkentUzbekistan Manipur International University Manipur 795140ImphalIndia Department of Computer Science Nawroz UniversityPO BOX 77DuhokIraq

Weed management is a crucial aspect of modern agriculture as invasive plants can negatively impact crop yields and ***-established methods of weed control,such as manual labor and synthetic herbicides,have been widely used but come with their own set of *** methods are often time-consuming,labor-intensive,and pose environmental *** have been the primary method of weed control due to their efficiency and ***,over-reliance on herbicides has led to environmental contamination,weed resistance,and potential health *** address these issues,researchers and industry experts are now exploring the integration of machine learning into chemical weed management *** technology advances,there is a growing interest in exploring innovative and sustainable weed management *** review examines the potential of machine learning in chemical weed *** learning offers innovative and sustainable approaches by analyzing large data sets,recognizing patterns,and making accurate *** learning models can classify weed species and optimize herbicide ***-time monitoring enables timely intervention,preventing invasive species spread,Integrating machine learning into chemical weed management holds promise for enhancing agricultural practices,reducing herbicide usage and minimizing environmental *** and refinement of these algorithms are needed for practical application.

关键词： Weed management herbicides machine learning agricultural practices environmen-tal impact

来源：评论

学校读者我要写书评

暂无评论

Driver Fatigue Detection Using OpenCV and Dlib Library

Driver Fatigue Detection Using OpenCV and Dlib Library

引用

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Shen, Kuang Ramli, Rusyaizila Chuah, Joong Huang Chai, Grace Mei Ting School of Electronics and Computer Science University of Southampton Southampton United Kingdom University of Southampton Malaysia Carbon Neutrality Research Group Johor Iskandar Puteri79100 Malaysia University of Malaya Faculty of Engineering Department of Electrical Engineering Kuala Lumpur50603 Malaysia University of Southampton Malaysia Smart Manufacturing System Reasearch Group Johor Iskandar Puteri79100 Malaysia

ISBN: (纸本)9798350341072

Driver fatigue and distraction are major contributors to fatal road accidents worldwide. To enhance vehicle safety, this article proposes a fatigue detection system using EAR and MAR algorithms to identify signs of fatigue, such as eye closure and yawning. When prolonged eye closure or yawning is detected, the system issues an alert to the driver. It leverages OpenCV and Dlib libraries for implementation. Additionally, the system detects driver distraction by monitoring head swivels, counting left and right movements. It's worth noting that Dlib may yield facial landmark deviations for non-frontal faces. To mitigate this, the study selected 69 videos from the YawDD database, focusing on near-frontal face views, achieving a 91.3% accuracy rate. © 2023 IEEE.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

Advancing Survey on Multi-Tenant Cloud Environments: Challenges and Solutions

Advancing Survey on Multi-Tenant Cloud Environments: Challen...

引用

Intelligent systems for Cybersecurity (ISCS), International Conference on

作者： Bhawani Shanker Amina Tufail Chandradeep Bhatt Keshav Kaushik Ahthasham Sajid Inam Ullah Khan Department of Information Security Riphah Institute of System Engineering Islamabad Pakistan Department of CSE Graphic Era Hill University Uttarakhand India Graphic Era Deemed to be University Dehradun Uttarakhand India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Computer Science SZABIST Islamabad Pakistan

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

This research examines cloud forensic challenges and solutions using quantitative methodologies. Major challenges in cloud forensics, including data dispersion, loss of control, multi-tenancy, and integrity/authenticity, were identified. The effectiveness of cloud forensic tools was evaluated, with Tool 2 identified as the most effective. Factors A and B were found to influence tool adoption. Emerging trends in cloud forensics, such as advancements in cloud technologies and new security threats, were explored. The study provides valuable insights for practitioners and researchers, informing decision-making in addressing challenges, selecting tools, and considering future directions in cloud forensics.

关键词： Surveys Forensics Decision making Organizations Market research Intelligent systems computer security

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：