检索结果-内蒙古大学图书馆

MOP-N: A Hybrid AI Model for Automated Deployment of Guns in Dynamic Wargaming Scenario

Defence science Journal 2025年第2期75卷 179-187页

作者： Taneja, S.B. Jaiswal, Sourabh Bisht, Sanjay Jindal, Vinita Bedi, Punam DRDO Institute for Systems Studies & Analyses Delhi110 054 India Keshav Mahavidyalaya University of Delhi Delhi110 034 India Department of Computer Science University of Delhi Delhi110 007 India

Wargames play a critical role in training of military officers/commanders for operations planning and execution. A typical training wargame may involve a large number of players as part of more than one competing forces. It is often desirable to reduce number of players to improve playability of wargames, which is in conflict with the requirements of operational realism. Successful automation of players and their decision making processes can result in reduction of number of players without loss in the operational realism. Also, depending upon the objective, a wargame can be played at various levels of abstraction viz. procedural, tactical, operational and strategic. Usually higher level (operational and strategic) wargames involve abstract (low resolution) entities. Developing models to simulate these abstract entities is most critical challenge for wargaming simulation designers. Alternatively, with incorporation of automation of lower level players’ decision making processes, detailed high resolution entities can be represented enabling modelling at abstraction closer to real physical entities, which is relatively simpler. The automation may be required at different stages of a wargame. It may be required during game initialisation or in relatively static situations where time constraint on decision making (and thus computation time) may not be severe. In contrast, decision making in dynamic situations may put severe time constraint on the automated decision making and computation time. Current work explores mechanism to automate the players’ decision making processes in time constrained scenarios. Specifically, problem of deployment of guns in the mountainous terrain has been considered. MOP-N a hybrid approach comprising of Monte-Carlo Simulation, Predator-Prey Particle Swarm Optimisation (PP-PSO) algorithm and Neural Network (NN) has been used for automated deployment of guns w.r.t. adversary deployments, terrain and road network in time constrained situations

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

An Innovative Hybrid Feature Extraction Method for the Diagnosis of Coconut Leaf Diseases

An Innovative Hybrid Feature Extraction Method for the Diagn...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： S. Nithya Priya L. Ramesh Department of computer science Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India Department of Computer Applications (UG) Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

In South India, cultivating coconuts is a major agricultural activity, but the trees are challenged by unfavorable weather conditions and environmental factors. These difficulties comprise pest infestations and a variety of leaf diseases. Because of the coconut trees' enormous foliage and shadowing, it might be challenging to identify and locate these problems. The study proposes a feature extraction strategy which integrates the feature vectors of deep learning (DL) and handcrafted features into a single, cohesive representation for detecting the coconut leaf diseases. The selected features were fed into the Machine learning (ML) classifier like Support Vector Machine (SVM), Random Forest (RF) and XGBoost. The experimental results show that the proposed technique outperforms with an accuracy of 97.4% showing the importance of feature extraction techniques in identifying the coconut leaf diseases.

关键词： Support vector machines Adaptation models Accuracy Computational modeling Feature extraction Vectors Random forests Diseases Classification tree analysis Shadow mapping

来源：评论

学校读者我要写书评

暂无评论

Enhancing Credit Card Fraud Detection With Sbpmc-Oa Based Feature Optimization

Enhancing Credit Card Fraud Detection With Sbpmc-Oa Based Fe...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： V. Suganthi J. Jebathangam Department of Computer Science Vels Institute of Science Technology & Advanced Studies(VISTAS) Chennai India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Credit Card Fraud Detection (CCFD) protects cardholders from money loss during transactions. However, the prevailing works could not adapt to new attack techniques, leading to fraudulent transactions. Hence, the Bias Wrapper C1 Gated Recurrent Unit (BWC1-GRU) is proposed. Initially, to train the CCFD model, the credit card transaction details are collected and pre-processed. Next, the data augmentation is done using the Synthetic Heuristic Minority Over-Sampling Technique (S-HeMOTE) technique. After augmentation, the features are extracted and using the Secretary Bird Principle of Maximum Continuous Optimization Algorithm (SBPMC-OA), optimal features are selected. Then, the CCFD is done using the BWC1-GRU method. Thus, the proposed framework detected Credit Card Fraud (CCF) with an accuracy of 97.721 %, which outperformed the existing works.

关键词： Adaptation models Accuracy Feature extraction Credit cards Data augmentation Birds Data models Fraud Mobile applications Optimization

来源：评论

学校读者我要写书评

暂无评论

An Effective Object Detection Model to Detect Floating Macroplastic Debris on the Waterways Using YOLO

An Effective Object Detection Model to Detect Floating Macro...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Ramya R J. Jebathangam Department of Computer Science Vels Institute of Science Technology &amp Advanced Studies(VISTAS) Chennai India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The escalating problem of plastic pollution in aquatic environments poses a significant threat to global ecosystems. Among the various forms of plastic debris, floating macroplastics are particularly persistent and visually conspicuous, demanding effective monitoring and quantification strategies. Traditional methods for surveying plastic pollution, such as manual collection and visual observation, are often laborintensive, geographically limited, and struggle to provide the comprehensive data required for effective mitigation strategies. However, existing detection methods primarily rely on manual surveys or simplistic computer vision approaches, which can be inaccurate and inefficient. To enhance the detection efficiency of macroplastics in waterways, a deep learning-based model was utilized, incorporating CSPDarknet, Bidirectional Feature Pyramid Network (BiFPN), and YOLOv7. This comprehensive approach addresses the global challenges introduced by macroplastic pollution and assesses its implications for environmental sustainability and public health. The experimental findings reveal that the proposed model showcases remarkable effectiveness and impressive efficiency, enabling the seamless automated identification of macroplastics on the waterways. The model delivers impressive detection accuracy (mAP) of 93.2 percent and effectively adapts to variations in object size and image quality. The model generates remarkable and more effective results when compared with the existing methods. Furthermore, its accuracy has improved by 2.3 to 2.9 percent.

关键词： YOLO Adaptation models Accuracy Pollution Computational modeling Transfer learning Water quality Real-time systems Monitoring Plastic waste

来源：评论

学校读者我要写书评

暂无评论

Finding the Sweet Spot: An Empirical Study on Dataset Size, Performance, and Efficiency in Relation Extraction

Finding the Sweet Spot: An Empirical Study on Dataset Size, ...

引用

International CSI computer Conference, CSICC

作者： Sohrab Pirhadi Babak Niroomand Ebrahim Ansari Department of Computer Science Institute for Advanced Studies in Basic Sciences (IASBS) Zanjan Iran

ISBN: (数字)9798331523114

ISBN: (纸本)9798331523121

Relation extraction (RE) is a critical task in natural language processing that identifies relationships between entities within text. While increasing the size of annotated datasets generally enhances model performance, the cost and effort associated with human annotation can be prohibitive. This study investigates the impact of dataset size on RE performance using the Semantic Evaluation 2010 Task 8 dataset. Four deep neural models-Attention-Based Convolutional Neural Network, Attention-Based Bidirectional Long Short-Term Memory Network, Relation Bidirectional Encoder Representations from Transformers, and Matching the Blanks-were evaluated across eight subsets of the dataset to simulate size reduction. Performance metrics such as accuracy, precision, recall, and F1-score were analyzed. The results indicate that although larger datasets improve model performance, the benefits diminish beyond a certain size, illustrating the law of diminishing returns. These findings emphasize the importance of balancing dataset size and quality for cost-effective training and suggest strategies such as data augmentation and transfer learning to optimize performance with limited data.

关键词： Training Measurement Annotations Computational modeling Transfer learning Semantics Performance gain Transformers Natural language processing Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of YOLO versions for Real-time Pothole Detection

引用

Procedia computer science 2025年 257卷 77-84页

作者： Leonhel V. Fortin Orven E. Llantos Department of Computer Applications College of Computer Studies MSU-Iligan Institute of Technology Tibanga Iligan City 9200 Philippines Department of Computer Science

The integration of lightweight computer vision models emerges as a promising solution for automating road inspection processes. The evolution of YOLO architectures, particularly their lightweight variants, enables significant improvements in both detection accuracy and computational efficiency. Recent iterations through YOLOv9-tiny, YOLOv10-nano, and YOLOv11-nano enhance real-time performance capabilities while maintaining acceptable accuracy through optimized network architectures. The implementation of these lightweight YOLO variants presents a compelling approach to automated pothole detection. Previous studies utilizing limited datasets of approximately 1,388 images established initial feasibility but left significant room for improvement in model robustness and generalization. This research addresses these limitations by employing an expanded dataset of 16,054 images, encompassing diverse environmental conditions and road surface characteristics. The comparative analysis establishes new benchmarks for pothole detection in resource-constrained environments, demonstrating the viability of nano/tiny models for practical applications.

关键词： Lightweight computer Vision YOLO Pothole Detection Real-time Object Detection Road Surface Inspection

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Potential of the Internet of Things: Navigating Choices Between Fog and Cloud Infrastructure in Agriculture 2nd

Harnessing the Potential of the Internet of Things: Navigati...

引用

2nd International Conference on Cyber Intelligence and Information Retrieval, CIIR 2023

作者： Singh, Malikhan Arora, Kavita Pathak, Sonal Quraishi, Suhail Javed Singh, Anupam Ather, Danish Computer Science and Engineering Modern Institute of Technology and Research Centre Rajasthan Alwar India School of Computer Applications Manav Rachna International Institute of Research and Studies Haryana Faridabad India Department of Computer Science and Engineering Graphic era Hill University Dehradun India Amity University in Tashkent Tashkent Uzbekistan

ISBN: (纸本)9789819776023

In recent years, the Internet of Things (IoT) has become a pivotal force in transforming various sectors, with agriculture being a prominent beneficiary. The integration of smart devices, sensors, and data-driven decision-making tools has led to the emergence of a more efficient and sustainable farming landscape. Central to this transformation is the decision of where and how to process and store the vast amounts of data generated by these devices. This paper delves into the practical implications of fog and cloud computing systems in the agricultural domain taking Delhi NCR and region as a sample area by considering factors like efficiency, scalability, and real-world challenges faced by farmers. The aim here is to provide a comprehensive guide to stakeholders in making an informed choice between fog and cloud infrastructure for their IoT-enabled agricultural endeavors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Multitask-Oriented Efficient Computational Offloading Orchestrator for IoT Applications in Mobile-Edge Computing

引用

IEEE Internet of Things Journal 2025年第10期12卷 14096-14108页

作者： Wang, Leilei Deng, Xiaoheng Zhang, Honggang Wan, Shaohua Min, Geyong Xi’an University of Technology School of Computer Science and Engineering Shanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China Central South University School of Computer Science and Engineering Changsha410075 China Central South University Shenzhen Research Institute Shenzhen518057 China University of Massachusetts at Boston Engineering Department BostonMA02125 United States University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518110 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

Mobile-edge computing (MEC) can accelerate computation-intensive applications and emerge as a promising technology for enabling Internet of Things (IoT). MEC improves the processing performance of tasks by assigning them to the edge nodes. However, with massive terminals contending for computation and communication resources simultaneously, how to develop a flexible computational offloading mechanism becomes the fundamental issue of MEC-enabled IoT systems. This article aims to develop an effective computational offloading decision scheme by jointly considering the computational resource and diverse user demands with two goals, i.e., minimizing both the latency and the energy consumption. Specifically, we develop a two-stage computational offloading mechanism, where the computational resources and offloading decisions can be allocated and coordinated with the variation of computation requirements. To achieve the two goals, this work introduces an edge node recommendation model within the cloud-edge–end architecture to reduce the offloading optimization search space. Furthermore, we propose a new computational offloading (CROCA) algorithm based on chemical reaction optimization (CRO) for optimizing offloading utility, which thoroughly considers the competition between mobile device requests and computational resources. Extensive evaluation results demonstrate that the proposed CROCA scheme can effectively improve the computational offloading performance. © 2014 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Enhancing Missing Data Imputation for Migrants Data: A Neutrosophic Set-Based Machine Learning Approach

引用

Neutrosophic Sets and Systems 2025年 81卷 479-502页

作者： Abdo, Doaa A. Salama, A.A. Abdelmegaly, Alaa A. Mahmoud, Hanan Khadari Mahdi Applied statistics and insurance department faculty of commerce Mansoura university Mansoura Egypt Dept. of Math and Computer Sci. Faculty of Science Port Said Univ. Egypt Higher Institute of Advanced Management Sciences and Computers Al-Buhayrah Egypt Depatrment of applied statistics at the Nile Higher Institute of commercial sciences and Computer Technology in Mansoura Egypt

This study tackles the problem of missing data in migrant datasets by introducing a new framework that combines machine learning techniques with neutrosophic sets. These sets, which can represent uncertainty and ambiguity, are well-suited for managing the complex nature of missing information in sensitive fields like migration research. We test the effectiveness of KNN, SVM, decision tree, random forest, and Ada Boost algorithms on a migrant dataset, comparing their results using different imputation methods (mean/mode, model-based imputer (simple tree), and random values). Our research showed that our proposed approach, which used neutrosophic sets, improved imputation accuracy and strengthened model reliability. Our results underscored the potential of neutrosophic set-based machine learning for addressing missing data issues across various fields. © 2025, University of New Mexico. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Cultivating Cluster Enactment in Wireless Sensor Networks Through Hybrid Metaheuristics Intended for Energy Optimization

引用

SN computer science 2025年第3期6卷 1-12页

作者： Kushwaha, Ajay Goswami, Anjali Sharada, K. Sharma, Manmohan Berar, Gagandeep Edara, Deepak Chowdary Department of Computer Science and Engineering Rungta College of Engineering and Technology R1 CG Bhilai India Department of Mathematics and Statistics College of Science and Theoretical Studies Saudi Electronic University Riyadh 13323 Saudi Arabia Department of Computer Science and Engineering GITAM (Deemed to be University) AP Visakhapatnam India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Department of Computer Science and Engineering Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Department of CSE Vignan’s Foundation for Science Technology and Research Vadlamudi AP Guntur India

Though traditional search methods shine when faced with local goals and a plethora of decision factors, they could struggle when faced with engineering design limitations. On the other hand, metaheuristic approaches promise to find global optima in real-world optimization problems, even in nonlinear and multimodal settings. In order to improve cluster head selection in Wireless Sensor Networks (WSNs), this research presents a new metaheuristic method that combines the principles of Cuckoo Search method (CSA) and Selection by Optimization (SBO). When choosing a Chief Cluster Head (CCH), the CSA algorithm takes hop count into account, whereas SBO finds the best cluster heads by considering communication range. By comparing the suggested approach to both stand-alone SBO and CSA methods, we can see how well it performs in terms of throughput, latency, energy usage, delivery ratio, and packet overhead. The combined SBO-CSA method improves cluster performance, simplifies cluster head selection in WSNs, and increases network efficiency overall, according to the results. To prove its efficacy in enhancing network performance, the suggested solution outperforms standalone SBO and CSA approaches across a range of performance parameters, such as throughput, latency, energy consumption, and packet overhead. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： CCH CH CSA Metaheuristic methods SBO

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：