检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent Systems for Collaborative intelligence, ICMSCI 2025

作者： Shoba, B. Raghunathan, T. Peter, S.Sam Karthick, K. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak Psn College of Engineering and Technology Department of Electronics and Communication Engineering Tirunelveli India Dr.NG.p.Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Sri Krishna College of Technology Department of Computer Science and Engineering Coimbatore India Sona College of Technology Department of Information Technology Salem India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

Pedestrian detection is a crucial aspect of autonomous vehicle (A V) safety, as it enables accurate identification and tracking of individuals in an A V environment. Effective pedestrian detection supports essential A V functions like braking, steering, and speed control to prevent accidents in urban settings. Traditional computer vision methods, such as Support Vector Machines and Random Forests, rely on pre-designed features like the Histogram of Oriented Gradients. While the existing techniques offer some performance, it face significant challenges in dynamic environments, especially under varying lighting conditions, occlusions, and diverse pedestrian poses. Traditional models also require extensive manual feature engineering and tuning, which limits scalability and adaptability. Recent advances in deep learning, particularly with Convolutional Neural Networks (CNNs), have allowed for automatic feature learning, yielding practical improvements over classical methods. However, CNNs can struggle in low light and when facing adversarial attacks, as they mainly capture spatial features. To address these limitations, this research proposes a new methodology combining CNNs for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to capture temporal dependencies. This hybrid approach enhances detection capabilities by learning both static and dynamic patterns. Our proposed CNN-BiLSTM model achieves a 92 % detection accuracy and an F1 score of 88.5% across diverse conditions, outperforming existing models by up to 15%. By integrating temporal features, the model reduces missed detections and false positives by up to 20%, providing a more reliable and adaptable solution for pedestrian detection in autonomous vehicles. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Quantum Algorithm for Evaluating the Hamming Distance

引用

Computers, Materials & Continua 2022年第4期71卷 1065-1078页

作者： Mohammed Zidan Manal G.Eldin Mahmoud Y.Shams Mohamed Tolan Ayman Abd-Elhamed Mahmoud Abdel-Aty Department of Artificial Intelligence Hurghada Faculty of Computers and Artificial IntelligenceSouth Valley UniversityEgypt Faculty of Engineering King Salman International UniversitySouth SinaiEgypt Department of Mathematics and Computer Science Faculty of ScienceBeni-Suef UniversityBeni-SuefEgypt Department of Machine Learning and Information Retrieval Faculty of Artificial IntelligenceKafrelsheikh UniversityEgypt Mechanical Department Faculty of Technology and EducationSuez UniversitySuezEgypt Faculty of Technological Industries King Salman International UniversitySouth SinaiEgypt Faculty of Engineering at Mataria Helwan UniversityCairoEgypt Department of Mathematics Faculty of SciencesSohag University82524 SohagEgypt

We present a novel quantum algorithm to evaluate the hamming distance between two unknown oracles via measuring the degree of entanglement between two ancillary *** particular,we use the power of the entanglement degree based quantum computing model that preserves at most the locality of interactions within the quantum model *** model uses one of two techniques to retrieve the solution of a quantum computing problem at *** the first technique,the solution of the problem is obtained based on whether there is an entanglement between the two ancillary qubits or *** the second,the solution of the quantum computing problem is obtained as a function in the concurrence value,and the number of states that can be generated from the Boolean *** proposed algorithm receives two oracles,each oracle represents an unknown Boolean function,then it measures the hamming distance between these two *** hamming distance is evaluated based on the second *** is shown that the proposed algorithm provides exponential speedup compared with the classical counterpart for Boolean functions that have large numbers of Boolean *** proposed algorithm is explained via a case ***,employing recently developed experimental techniques,the proposed algorithm has been verified using IBM’s quantum computer simulator.

关键词： Quantum computing quantum algorithm quantum circuit

来源：评论

学校读者我要写书评

暂无评论

Leveraging LLM in Genetic Programming Hyper-heuristics for Dynamic Microservice Deployment 37th

Leveraging LLM in Genetic Programming Hyper-heuristics for...

引用

37th Australasian Joint Conference on artificial intelligence, AJCAI 2024

作者： Fang, Zhengxin Ma, Hui Chen, Gang Hartmann, Sven Wang, Chen Centre for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Department of Informatics Clausthal University of Technology Clausthal-Zellerfeld Germany National Institute of Water and Atmospheric Research Wellington New Zealand

ISBN: (纸本)9789819603473

Microservice deployment in cloud computing is a challenging combinatorial optimization problem due to the complex dependencies among microservices and the intricate trade-offs among different QoS requirements, e.g., minimizing Energy Consumption (EC) vs. minimizing Communication Overhead (CO). Recently, some hyper-heuristics methods, particularly Genetic Programming Hyper-Heuristics (GPHH), have been proposed to automatically generate heuristics for solving dynamic microservice deployment problems. Meanwhile, Large Language Models (LLMs) are becoming popular for solving various domain-specific problems thanks to their strong ability to learn problem-related knowledge. However, hybridizing GPHH with LLM by combining their abilities in solving complex optimization problems remains unexplored. In this paper, we propose an LLM-enhanced Genetic Programming Hyper-Heuristic (LLM-GPHH) algorithm to evolve heuristics for the dynamic deployment of applications composed of microservices, to jointly optimize EC and CO. Our experiments on real-world datasets demonstrate the effectiveness of the newly proposed LLM-GPHH. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized Ensemble Model Towards Secured Industrial IoT Devices

arXiv

引用

arXiv 2024年

作者： Injadat, MohammadNoor Data Science and Artificial Intelligence Department Faculty of Information Technology Zarqa University Zarqa Jordan

The continued growth in the deployment of Internet-of-Things (IoT) devices has been fueled by the increased connectivity demand, particularly in industrial environments. However, this has led to an increase in the number of network related attacks due to the increased number of potential attack surfaces. Industrial IoT (IIoT) devices are prone to various network related attacks that can have severe consequences on the manufacturing process as well as on the safety of the workers in the manufacturing plant. One promising solution that has emerged in recent years for attack detection is Machine learning (ML). More specifically, ensemble learning models have shown great promise in improving the performance of the underlying ML models. Accordingly, this paper proposes a framework based on the combined use of Bayesian Optimization-Gaussian Process (BO-GP) with an ensemble tree-based learning model to improve the performance of intrusion and attack detection in IIoT environments. The proposed framework's performance is evaluated using the Windows 10 dataset collected by the Cyber Range and IoT labs at University of New South Wales. Experimental results illustrate the improvement in detection accuracy, precision, and F-score when compared to standard tree and ensemble tree models. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Image Fusion Using Wavelet Transformation and XGboost Algorithm

引用

Computers, Materials & Continua 2024年第4期79卷 801-817页

作者： Shahid Naseem Tariq Mahmood Amjad Rehman Khan Umer Farooq Samra Nawazish Faten S.Alamri Tanzila Saba Department of Information Sciences Division of S&TUniversity of EducationLahore54770Pakistan Artificial Intelligence and Data Analytics(AIDA)Lab CCIS Prince Sultan UniversityRiyadh11586Saudi Arabia Faculty of Information Sciences University of EducationVehari CampusVehari61100Pakistan Department of Computer Science University of Engineering and TechnologyTaxila47050Pakistan Department of Mathematical Sciences College of SciencePrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Recently,there have been several uses for digital image *** fusion has become a prominent application in the domain of imaging *** create one final image that provesmore informative and helpful compared to the original input images,image fusion merges two or more initial images of the same *** fusion aims to produce,enhance,and transform significant elements of the source images into combined images for the sake of human visual *** fusion is commonly employed for feature extraction in smart robots,clinical imaging,audiovisual camera integration,manufacturing process monitoring,electronic circuit design,advanced device diagnostics,and intelligent assembly line robots,with image quality varying depending on *** research paper presents various methods for merging images in spatial and frequency domains,including a blend of stable and curvelet transformations,everageMax-Min,weighted principal component analysis(PCA),HIS(Hue,Intensity,Saturation),wavelet transform,discrete cosine transform(DCT),dual-tree Complex Wavelet Transform(CWT),and multiple wavelet *** fusion methods integrate data from several source images of an identical target,thereby enhancing information in an extremely efficient *** precisely,in imaging techniques,the depth of field constraint precludes images from focusing on every object,leading to the exclusion of certain *** tackle thess challanges,a very efficient multi-focus wavelet decomposition and recompositionmethod is *** use of these wavelet decomposition and recomposition techniques enables this method to make use of existing optimized wavelet code and filter *** simulated outcomes provide evidence that the suggested approach initially extracts particular characteristics from images in order to accurately reflect the level of clarity portrayed in the original *** study enhances the performance of the eXtreme Gradient Boosting(XGBoos

关键词： Image fusion max-min average CWT XGBoost DCT inclusive innovations spatial and frequency domain

来源：评论

学校读者我要写书评

暂无评论

Malayalam Fake News Detection Using Optimized Convolutional Neural Network (OPCNN)

Malayalam Fake News Detection Using Optimized Convolutional ...

引用

International Conference on Advanced Computer Control, ICACC

作者： Aiswarya Mohan Nafla Iqbal Manaal Mashpher Department of Artificial Intelligence and Data Science Rajagiri School of Engineering and Technology Kakkanad India

ISBN: (数字)9798350379136

ISBN: (纸本)9798350379143

These days, a range of issues are being caused by fake news, including satirical pieces, fake news, and intentional government propaganda. Because of the blathering social media discourse, the idea of "fake news" has recently evolved. Wide-ranging consequences of fake news dissemination include the development of distorted opinions and the tampering of election outcomes to benefit specific politicians. Spammers also use captivating news headlines to entice readers to click on their advertisements. These days, it can be quite difficult to tell if the news we hear is accurate. There aren’t many methods for assessing authenticity, and the ones that are accessible are all difficult and beyond the capabilities of the average person. A fact-checking platform that gives us that chance is desperately needed. Deep Learning (DL) approaches are suited for more accurately and efficiently detecting false news because of their recent accomplishments in difficult natural language processing tasks. The suggested approach is a multi-layered, optimal CNN model for detecting fake news. The OPCNN and Word embedding are optimized for feature extraction using the hyperopt optimization method in order to produce highly accurate results. In this study, we generated word embeddings using the FastText technique. The purpose of the model is to identify news stories published in Malayalam that are either false or misleading. The model is trained on 80% of a newly compiled Malayalam dataset consisting of news articles from various online sources having 11,686 news items with 5843 false and real news entries apiece and then evaluated on the remaining 20%. The evaluation’s findings show that the suggested model works better than current methods and has a high degree of accuracy when it comes to identifying false information in Malayalam.

关键词： Visualization Accuracy Social networking (online) Voting Predictive models data models Robustness Convolutional neural networks Fake news Videos

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of alkali-treated natural fibres for improved interfacial adhesion in composite materials

引用

Interactions 2024年第1期245卷 1-13页

作者： Bhagat, Madhuri S. Jadhav, Varsha D. Kulkarni, Sumant Khanderao Satishkumar, P. Saminathan, Rajasekaran Department of Civil Engineering Yeshawantrao Chavan College of Engineering Maharashtra Wanadongari Nagpur India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Information Technology Maharashtra Pune India School of Civil Engineering REVA University Rukmini Knowledge Park Karnataka Kattigenahalli Bengaluru India Department of Mechanical Engineering Rathinam Technical Campus Tamilnadu Coimbatore India Department of Mechanical Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia

Natural fibers such as bamboo, kenaf, flax, ramie and hemp were chemically treated to improve their adherence with hydrophobic matrices. One common chemical process for altering the surface of these natural fibers is alkali treatment (AT). The experiment involves soaking bamboo fibers (BF) in solutions of 1, 10, and 30 wt % sodium hydroxide (NaOH) for one day, half an hour, and twenty minutes at room temperature. These alkali-treated and untreated bamboo fibers was compared with their physical and mechanical qualities. Using scanning electron microscopy (SEM) and the circular fiber assumption, the CSA of bamboo fibers both before and after AT were compared. Improving the AT procedures for BF at room temperature using varying NaOH concentrations is the focus of this effort. Additionally, the tensile characteristics of both untreated and variously treated AT Bamboo fibres are examined using a two-parameter Weibull distribution. Instead of just showing the average tensile strength, probabilistic tensile strength has shown to be a more effective method. This study proves without a reasonable doubt that adding 1 wt % NaOH to bamboo fiber makes natural fiber reinforced composites mechanically better. According to the SEM, the CSA of bamboo fibers decreases by about 13.62–20.24% and about 18.42–22.63%, respectively, after alkali treatment. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

Efficient Canine Vision: Accurate Dog Breed Classification with EfficientNet 2

Efficient Canine Vision: Accurate Dog Breed Classification w...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Godwin James, T. Prabahar Poonguzhali, C. Selvakumaran, S. Malathi, G. Kaliappan, S. Venu, Nookala Department of Computer Science and Engineering Sri Sairam Institute of Technology India Department of Electronics and Communication Engineering S.A. Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai India Department of Electrical and Electronics Engineering Kumaraguru College of Technology Saravanampatti Coimbatore India Madhya Pradesh Gwalior India

ISBN: (纸本)9798350384277

Understanding and classifying dog breeds is a fascinating yet challenging task due to the vast diversity within the canine species. In this project, we present a novel approach to dog breed classification utilizing the state-of-the-art Efficient Net architecture. Leveraging a comprehensive dataset comprising 133 distinct breeds, our method aims to accurately identify and categorize each breed with high precision. Efficient Net's innovative scaling method allows us to strike a balance between model complexity and computational efficiency, enabling robust classification performance even with limited computational resources. Through meticulous preprocessing techniques and data augmentation strategies, we enhance the model's ability to generalize across diverse breed characteristics, minimizing the risk of overfitting. Our experimental results demonstrate the efficacy of the proposed approach, achieving impressive classification accuracy on the challenging dog breed dataset. We conduct extensive evaluations and comparisons with existing methodologies, showcasing the superiority of Efficient Net in handling complex classification tasks with large-scale image datasets. Furthermore, we provide insights into the interpretability of the model's predictions, shedding light on the learned representations and key features contributing to breed classification. This project not only advances the state-of-the-art in dog breed classification but also contributes to our understanding of deep learning techniques applied to animal recognition tasks. In sum up, our work highlights the potential of leveraging advanced neural network architectures like Efficient Net for comprehensive and accurate dog breed classification, paving the way for applications in veterinary medicine, pet care, and animal welfare. © 2024 IEEE.

关键词： Veterinary medicine

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Algorithm for the Travelling Sales Man problem 3

An Evolutionary Algorithm for the Travelling Sales Man probl...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Waseem, Shaik Mohammad Jeshwanth, N.L. Lingesh, A. Jayanth, Matta Bhargavi, C.H. Dhanwanth, Batini Dept. of Computer Science and Engineering Chennai India Dept. of Artificial Intelligence and Data Science Chennai India Sai Spurthi Institute of Technology Dept. of Computer Science and Engineering Gangaram Sathuaplly India Jönköping University Dept. of Ai Engineering Jönköping Sweden

ISBN: (纸本)9798331509675

This study explores the use of Genetic Algorithms (GA) to solve the NP-hard combinatorial optimization problem known as the Travelling Salesman Problem (TSP). The suggested GA, called GA-P, performs better than conventional techniques because it uses a new randomized crossover threshold. According to experimental assessments, GA-P outperforms a normal Genetic Algorithm with fixed crossover (GA-N, 628.6) and approaches the best Branch and Bound solutions (B&B, 560.6) with an average cost of 617.4 for 16-node graphs. With average execution times of 0.1347 seconds for 16 nodes, GA-P also demonstrates constant computational efficiency, outperforming B&B's exponentially growing temporal complexity (169.37 seconds for 16 nodes). In order to balance solution quality and computational cost, hyperparameter tweaking revealed the ideal values of population percentage (pp = 1.1), crossover proportion (cp = 0.8), mutation threshold (mt = 0.3), and exploration probability (ep = 0.2). The results show that GA-P is a scalable and efficient substitute for TSP, with room for improvement via parallelization and exploratory techniques. © 2025 IEEE.

关键词： Traveling salesman problem

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：