检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Li, Haopeng Drummond, Tom Gong, Mingming Bennamoun, Mohammed Ke, Qiuhong The School of Computing and Information Systems University of Melbourne Australia The School of Mathematics and Statistics University of Melbourne Australia The school of Physics Maths and Computing The University of Western Australia Australia The Department of Data Science & AI Monash University The School of Computing and Information Systems University of Melbourne Australia

Significant progress has been made in the field of video question answering (VideoQA) thanks to deep learning and large-scale pretraining. Despite the presence of sophisticated model structures and powerful video-text foundation models, most existing methods focus solely on maximizing the correlation between answers and video-question pairs during training. We argue that these models often establish shortcuts, resulting in spurious correlations between questions and answers, especially when the alignment between video and text data is suboptimal. To address these spurious correlations, we propose a novel training framework in which the model is compelled to acknowledge its ignorance when presented with an intervened question, rather than making guesses solely based on superficial question-answer correlations. We introduce methodologies for intervening in questions, utilizing techniques such as displacement and perturbation, and design frameworks for the model to admit its lack of knowledge in both multi-choice VideoQA and open-ended settings. In practice, we integrate a state-of-the-art model into our framework to validate its effectiveness. The results clearly demonstrate that our framework can significantly enhance the performance of VideoQA models with minimal structural modifications. Copyright © 2025, 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

Lead-cnn: lightweight enhanced dimension reduction convolutional neural network for brain tumor classification

引用

International Journal of Machine Learning and Cybernetics 2025年 1-20页

作者： Khan, Saif Ur Rehman Asif, Sohaib Bilal, Omair Rehman, Hafeez Ur School of Computer Science and Engineering Central South University 932 Lushan S Rd Yuelu District Hunan Changsha China School of Computing and Data Sciences Oryx Universal College with Liverpool John Moores University Doha Qatar Department of Computer Science National University of Computer and Emerging Sciences Islamabad Pakistan Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence Taizhou Campus of Zhejiang Cancer Hospital Taizhou Cancer Hospital Taizhou317502 China Chinese Academy of Sciences Taizhou317502 China Chinese Academy of Sciences Hangzhou310022 China

In many nations, brain tumors are among the most serious medical conditions affecting both adults and children. Timely and accurate diagnosis is crucial, as the life of a patient may be shortened if brain tumors are not identified promptly. When brain tumors are diagnosed accurately and promptly, patients can receive the appropriate treatment. One of the challenging aspects of dealing with brain tumors is their diversity, making it difficult to categorize them accurately due to their varying characteristics. Deep learning (DL) models have emerged as a valuable tool in classifying brain tumors into distinct groups. However, these models face challenges related to accuracy and computational cost, necessitating advancements in brain image classification. Our primary aim is to develop a lightweight convolutional neural network (CNN) architecture that offers high efficiency, we incorporate a modified dimension reduction block with CNN to detect brain cancers with minimal computational resources while maintaining a high level of accuracy. In this research, we introduce a novel lightweight network called LEAD-CNN, designed specifically for the accurate and reliable identification of brain cancers from magnetic resonance images (MRI). Our approach begins by evaluating the effectiveness of several pre-trained DL models, including ResNet-101, VGG-19, MobileNet-V1, and DenseNet-201, which have been recommended for the classification of medical images. Subsequently, we propose a dimension reduction base CNN architecture with a lightweight design aimed at achieving a low false-negative rate in tumor image classification for patients. To assess the performance of the proposed model, we utilize a benchmark brain MRI dataset (Kaggle) comprising 7023 images, encompassing three different types of brain tumors long with normal brain images. Our experimental results are demonstrating an overall classification accuracy of 98.70%, with an average recall, F1-score, and precision of 98.60%

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

HerbSimNet: Deep Learning -Based Classification of Indian Medicinal Plants with High Inter-Class Similarities

引用

Procedia Computer science 2025年 258卷 765-774页

作者： N. Shobha Rani Bhavya K R Pushpa B.R. Ragavendra M. Devadas Department of Artificial Intelligence and Data Science GITAM School of Technology Bengaluru GITAM (Deemed to be) University India Department of Computer Science and Engineering GITAM School of Technology Bengaluru GITAM (Deemed to be) University India Department of Computer Science School of Computing Mysuru Amrita Vishwa Vidyapeetham India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

Medicinal plant species recognition is important across diverse sectors such as Ayurveda, agriculture, environment conservation and botanical research. Specific groups of plants in Indian medicinal plant ecosystem exhibit significant inter-class similarities due to varying abundance and ecological factors. To address the challenges involved in the process of classifying these species in this work a deep learning model Herb-SimNet is proposed. The Herb-SimNet analyzes similarity of plant species over other plant species using vision based deep learning and machine learning techniques. The proposed model works based on the combination of wavelet features and convolutional features extracted using three sequential convolution layers to extract the prominent features that distinguish variations among the inter class similarity plant species. To perform experiments, a dataset is created by capturing medicinal plant leaf images using box model in plain background and uniform lighting. A smart phone captured twelve Indian medicinal plant species comprising of about 1400+ samples that belongs different plant species but similar morphological structure is collected. Baseline experiments are carried out between Herb-SimNet and other state-of-the-art deep learning models for classification based on the proposed dataset. The outcomes demonstrate that Herb_SimNet provides clear interpretation one plant variety with others and achieves superior accuracy in prediction than that of state-of-the-art approaches. Furthermore, the model demonstrates better generalization towards the other inter-class similarity groups considered for testing. In conclusion, the proposed dataset and Herb-SimNet plays a a crucial role in advancement of research concerning Indian medicinal plant species classification resulting into enhancement of AI-based technology for biodiversity conservation and ethnobotanical studies.

关键词： Classification inter-class similarities confusing plant species medicinal plants wavelet image features

来源：评论

学校读者我要写书评

暂无评论

ACGraph: Accelerating Streaming Graph Processing via Dependence Hierarchy 23

ACGraph: Accelerating Streaming Graph Processing via Depende...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Zihan Jiang Fubing Mao Yapu Guo Xu Liu Haikun Liu Xiaofei Liao Hai Jin Wei Zhang 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 Electronic and Computer Engineering HKUST Hong Kong

ISBN: (纸本)9798350323481

Streaming graph processing needs to timely evaluate continuous queries. Prior systems suffer from massive redundant computations due to the irregular order of processing vertices influenced by updates. To address this issue, we propose ACGraph, a novel streaming graph processing approach for monotonic graph algorithms. It maintains dependence trees during runtime, and makes affected vertices processed in a top-to-bottom order in the hierarchy of the dependence trees, thus normalizing the state propagation order and coalescing of multiple propagation to the same vertices. Experimental results show that ACGraph reduces the number of updates by 50% on average, and achieves the speedup of 1.75~7.43× over state-of-the-art systems.

关键词： graph processing

来源：评论

学校读者我要写书评

暂无评论

Color Space Search Algorithm (CSSA): A Novel Optimization Approach

Color Space Search Algorithm (CSSA): A Novel Optimization Ap...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hossam M. J. Mustafa Nedal Nwasra Ahmad Khasawneh Department of Data Science and Artificial Intelligence Faculty of Information Technology University of Petra Amman Jordan Computer Science Department Faculty of Information Technology University of Petra Amman Jordan School of Computing Skyline University College Sharjah UAE

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This paper presents a novel CSSA (Color Space Search Algorithm), introducing a metaheuristic optimization algorithm that addresses critical limitations in existing optimization methods. While current algorithms demonstrate suboptimal performance in multimodal landscapes, revealing premature convergence rates, CSSA introduces a novel approach by leveraging color theory principles in the optimization domain. The proposed algorithm combines complementary color transformations for global exploration with triadic color relationships for local exploitation, which aims to improve the exploration-exploitation balance compared to conventional methods. The algorithm's performance is evaluated across three categories of benchmark functions: unimodal functions, multimodal functions, and fixed-dimensional multimodal functions. Comprehensive experiments compared CSSA against classical (PSO, GA) and modern (MPA, EO, ALO, SSA, DA) optimization algorithms, with performance metrics including best fitness, mean fitness, solution consistency, and convergence rate analysis. Statistical analyses through the Friedman test (ranking 4.22) confirm the algorithm's robust performance, particularly in handling complex optimization landscapes. These results place CSSA as a promising optimization algorithm for complex optimization problems.

关键词： Ranking (statistics) Statistical analysis Metaheuristics Optimization methods Color Evolutionary computation Benchmark testing Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年

作者： Yang, Chuanxiang Zhou, Yuanfeng Wei, Guangshun Ma, Long Hou, Junhui Liu, Yuan Wang, Wenping The School of Software Shandong University Jinan250100 China The Department of Computer Science City University of Hong Kong Hong Kong The College of Computing and Data Science Nanyang Technological University Singapore The Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States

As commonly used implicit geometry representations, the signed distance function (SDF) is limited to modeling watertight shapes, while the unsigned distance function (UDF) is capable of representing various surfaces. However, its inherent theoretical shortcoming, i.e., the non-differentiability at the zero-level set, would result in sub-optimal reconstruction quality. In this paper, we propose the scaled-squared distance function (S2DF), a novel implicit surface representation for modeling arbitrary surface types. S2DF does not distinguish between inside and outside regions while effectively addressing the non-differentiability issue of UDF at the zero-level set. We demonstrate that S2DF satisfies a second-order partial differential equation of Monge-Ampere-type, allowing us to develop a learning pipeline that leverages a novel Monge-Ampere regularization to directly learn S2DF from raw unoriented point clouds without supervision from ground-truth S2DF values. Extensive experiments across multiple datasets show that our method significantly outperforms state-of-the-art supervised approaches that require ground-truth surface information as supervision for training. The code will be publicly available at https://***/chuanxiang-yang/S2DF. © 2025 IEEE. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Energy Efficient Communication for Large-Scale Industrial Internet of Things 2nd

Real-Time Energy Efficient Communication for Large-Scale Ind...

引用

2nd International Conference on Sustainability: Developments and Innovations, ICSDI 2024

作者： Khan, Musfira Khan, Muazzam A. Farman, Haleem Malik, Asad W. Ramzan, Muhammad Sher Islamabad Pakistan Department of Computer Science Quaid-I-Azam University Islamabad Pakistan ICESCO Chair for Big Data Analytics and Edge Computing Quaid-I-Azam University Islamabad Pakistan Smart Systems Engineering Lab College of Engineering Prince Sultan University Riyadh Saudi Arabia King Abdulaziz University Jeddah Saudi Arabia

ISBN: (纸本)9789819783441

Industrial Internet of Things (IIoTs) comprises large-scale sensors deployed to monitor and control the system. Deploying IoT devices presents challenges due to frequent disconnections and sudden power drainage in intermediate devices responsible for routing data. Consequently, the deployed network becomes sporadic, hindering connectivity with the industrial controller system, especially critical during emergencies. Furthermore, IoT node failures lead to a short network lifetime, which is intolerable in real-time industrial applications. This paper introduces a multi-hop clustering framework designed for reliable communication in industrial environments. The framework dynamically forms clusters, employing cluster heads and backup nodes to stabilize communication in the absence of a cluster head. Each cluster selects a backup node during the initial cluster head selection and later through data piggybacking. The proposed framework provides efficient communication across the IIoT network with the help of a backup and multi-hop clustering mechanism. The proposed framework is compared with two existing protocols i.e. cluster-based coordination routing (CRC) and energy-efficient quality of service routing (EEQSRP) protocols. The results show a considerable decrease in sensor energy consumption and packet delay. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Malicious Web Request Detection based on Transformer and Contrastive Learning

引用

IEEE Transactions on Network and Service Management 2025年

作者： He, Shiming Zhang, Ying Liang, Diqing Sharma, Pradip Kumar Changsha University of Science and Technology School of Computer Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha410114 China University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom

The World Wide Web (Web) is a crucial part of the Internet. Web attacks are becoming more and more serious and complex. Malicious Web request detection aims to rapidly and accurately identify abnormal attacks on the network. Deep learning is being applied to malicious Web request detection, resulting in high detection performance. However, most deep learning-based methods are supervised and ignore special characters, which are hard to detect unknown malicious Web requests. The labels of Web request are fewer and Web request data is insufficient. Therefore, we propose an unsupervised malicious Web request detection based on transformer and contrastive learning (UTCDetector). UTCDetector exploits preprocessing and 2-gram word segmentationto preserve special characters, extracts semantic feature by Transformer, and leverages hypersphere loss function and contrastive learning to handle insufficient Web data without abnormal label. Since the public Web request datasets (CSIC 2010, CSIC TORPEDA 2012, and ECML/PKDD 2007) were created before 2012, we collected Web requests from a university Web application server in 2023 to build a private dataset named School 2023. This dataset contains more modern and complex attacks. The experimental results on the four datasets demonstrate that our method achieves a higher F1-score than other existing methods and ablation variants. © 2004-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Systems for Autonomous IoT Network Management Using Distributed Reinforcement Learning 3

Multi-Agent Systems for Autonomous IoT Network Management Us...

引用

3rd International Conference on Intelligent Systems, Advanced computing, and Communication, ISACC 2025

作者： Neelamegam, G. Venkatesan, Rajaram Ramya, S.R. Ramya, R.S. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak VSB College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Builders Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Tirupur India Dr NGP Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Tamil Nadu Coimbatore India SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Networking and Communications Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798331523893

The ever-growing complexity of IoT networks ignited by their wide scale adoption in applications such as smart cities, the industrial automation, and health care, compelled to develop sophisticated yet resource efficient and scalable network management solution. Centralized systems are traditional in architecture, which leads to higher latency and bottlenecks, while decentralized systems can distribute workloads however the lack of adaptability to real time, along with the difficulty of extracting maximum resource usage, are limitations. In recent years, reinforcement learning (RL) based approaches have taken shape as a promising alternative to facilitate the automated learning and optimisation of task management. However, there are two challenges for existing RL based methods: slow convergence, inefficient priority assignment of tasks, and poor coordination amongst agents in the case of dynamic, large scale IoT environment. To solve these challenges, in this research we propose a distributed reinforcement learning based multi agent framework for managing IoT network. The framework also integrates a task prioritization mechanism to dynamically choose an optimal task allocation solution. Further validation was performed in a simulated IoT environment where real world inspired datasets were used. The proposed framework demonstrated 30% more task throughput than centralized, 25% less latency than decentralized, and 40% more energy efficiency than current RL based systems. The system was further validated using advanced visualizations such as anomaly detection maps and resource allocation efficiency graphs, demonstrating its capacity to manage dynamic load of tasks and resource allocation. The proposed framework addresses the critical limitations of current methods, through scalable, adaptive, and energy efficient framework for managing IoT network, and accordingly helps advancing the intelligent and autonomous IoT systems. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

CONTRASTIVE REPRESENTATION LEARNING HELPS CROSS-INSTITUTIONAL KNOWLEDGE TRANSFER: A STUDY IN PEDIATRIC VENTILATION MANAGEMENT

arXiv

引用

arXiv 2025年

作者： Liu, Yuxuan Han, Jinpei Ramnarayan, Padmanabhan Faisal, A. Aldo UKRI Centre for Doctoral Training in AI for Healthcare Department of Computing Imperial College London United Kingdom Department of Computing Imperial College London United Kingdom Department of Surgery Cancer Imperial College London United Kingdom Chair in Digital Health & Data Science University of Bayreuth Germany

Clinical machine learning deployment across institutions faces significant challenges when patient populations and clinical practices differ substantially. We present a systematic framework for crossinstitutional knowledge transfer in clinical time series, demonstrated through pediatric ventilation management between a general pediatric intensive care unit (PICU) and a cardiac-focused unit. Using contrastive predictive coding (CPC) for representation learning, we investigate how different data regimes and fine-tuning strategies affect knowledge transfer across institutional boundaries. Our results show that while direct model transfer performs poorly, CPC with appropriate fine-tuning enables effective knowledge sharing between institutions, with benefits particularly evident in limited data scenarios. Analysis of transfer patterns reveals an important asymmetry: temporal progression patterns transfer more readily than point-of-care decisions, suggesting practical pathways for crossinstitutional deployment. Through a systematic evaluation of fine-tuning approaches and transfer patterns, our work provides insights for developing more generalizable clinical decision support systems while enabling smaller specialized units to leverage knowledge from larger centers. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

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：