检索结果-内蒙古大学图书馆

Energy-Aware Congestion Control Technique Based on Hybrid Weight-Based Optimization Algorithm in Wireless Mobile Communication Networks

引用

Journal of The Institution of Engineers (India): Series B 2025年第1期106卷 189-206页

作者： Jeen Shene, S. Sam Emmanuel, W.R. Vimal Kumar Stephen, K. Department of Computer Science & Research Centre Nesamony Memorial Christian College Marthandam Affiliated to Manonmaniam Sundaranar University Tamil Nadu Tirunelveli India Department of Information Technology University of Technology and Applied Sciences Ibra Ibra400 Oman

Energy-aware congestion-free data routing is one of the critical challenges in successful data transmission for mobile sensor communication environments. Conventional techniques suffer from limitations such as high packet drop, ineffective Cluster Head (CH) selection, and unnecessary data retransmission, leading to high energy usage in mobile networks. To overcome these challenges, we propose Weight-based Prominent Wolf Preference Grey wolf optimization (2WP-GWO) with congestion control route selection through Separation Enhanced Elephant Herd Optimization algorithm (SEEHO). In this model, we enhance the efficiency of the standard GWO algorithm by prioritizing the location of the fittest wolves at each generation. Furthermore, we fix the priority level based on adopting weight measures to highly rank the fittest wolf (efficient CH), thereby lowering the influence of other mobile nodes over specific time intervals (generations). Additionally, congestion control is integrated into the SEEHO algorithm to find congestion-free paths for data transmission. This approach significantly improves network lifetime, reduces data traffic, and optimizes congestion-free optimal path selection. The proposed method is validated with other techniques using different performance measures, indicating promising results compared to other state-of-the-art approaches. © The Institution of Engineers (India) 2024.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Image to Audio Conversion to Aid Visually Impaired People by CNN 4

Image to Audio Conversion to Aid Visually Impaired People by...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Sivaganesan, D. Venkateshwaran, M. Dhinesh, S.P. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Sri Krishna Arts and Science College Department of Computer Science Coimbatore India

ISBN: (纸本)9798350300093

This study suggests an innovative method for helping people who are blind or visually handicapped by turning visuals into sounds. In the proposed system, audio descriptions are produced in real-time together with significant features that are extracted from photos using deep learning algorithms. The proposed work is developed to be user-friendly, which includes a simple interface that aids blind individuals to easily capture and process images using a mobile device. A user research was undertaken to assess the efficiency of the suggested method, and the results were encouraging in terms of precision and usability. This initiative offers a promising technique to give people who are blind or visually impaired an alternate means of perceiving and interacting with their environment, therefore improving their quality of life. The suggested picture to audio converter system aims to overcome the drawbacks of current assistive devices that rely on braille or textual descriptions. Blind people can more easily interpret visual information that is necessary for daily life, such as recognising items, interpreting signs, or navigate unfamiliar situations, through offering audio descriptions of images. The system makes use of recent deep learning developments that have significantly improved picture identification as natural language processing. As a result, the suggested technique has the ability to offer audio descriptions that are more precise and comprehensive than current methods. This technology has the potential to be implemented into a variety of products, from cellphones to intelligent glasses, and could significantly improve the lives of people who are blind or visually impaired. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Learning Empowered Real Time Object Detection for Unmanned Aerial Vehicles based Surveillance Applications

引用

Journal of Mobile Multimedia 2023年第2期19卷 451-476页

作者： Ranjith, C. Prasanna Hardas, Bhalchandra M. Khaja Mohideen, M. Syed Nijil Raj, N. Robert, Nismon Rio Mohan, Prakash Faculty in Information Technology Department University of Technology and Applied Sciences Shinas Oman Electronics Engineirng Dept Shri Ramdeobaba College of Enginering and Management Nagpur India Department of Information Technology University of Technology and Applied Science Salalah Oman Department of Computer Science and Engineering Younus College of Engineering and Technology Kollam India Department of Computer Science Christ University Bangalore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

Surveillance is a major stream of research in the field of Unmanned Aerial Vehicles (UAV), which focuses on the observation of a person, group of people, buildings, infrastructure, etc. With the integration of real time images and video processing approaches such as machine learning, deep learning, and computer vision, the UAV possesses several advantages such as enhanced safety, cheap, rapid response, and effective coverage facility. In this aspect, this study designs robust deep learning based real time object detection (RDL-RTOD) technique for UAV surveillance applications. The proposed RDL-RTOD technique encompasses a two-stage process namely object detection and objects classification. For detecting objects, YOLO-v2 with ResNet-152 technique is used and generates a bounding box for every object. In addition, the classification of detected objects takes place using optimal kernel extreme learning machine (OKELM). In addition, fruit fly optimization (FFO) algorithm is applied for tuning the weight parameter of the KELM model and thereby boosts the classification performance. A series of simulations were carried out on the benchmark dataset and the results are examined under various aspects. The experimental results highlighted the supremacy of the RDL-RTOD technique over the recent approaches in terms of several performance measures. © 2022 River Publishers.

关键词： computer vision deep learning image processing object detection Surveillance unmanned aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

Renewable Energy Efficiency of Unmanned Aerial Vehicles Operating with Wireless Sensor Networks and Mobile Ad Hoc Networks 2

Renewable Energy Efficiency of Unmanned Aerial Vehicles Oper...

引用

2nd International Conference on Smart Technologies for Power and Renewable Energy, SPECon 2024

作者： Ahmad, Wakeel Ahmed, Sarfaraz Ahmad, Adeel Siddiqui, Shams Tabrez Khamruddin, Mohammad Khan, Haneef Jazan University College of Applied Industrial Tech Deptartment of Electrical Engineering Technology Jazan Saudi Arabia Jazan University College of Computer Science and Information Technology Dept. of Cnet Jazan Saudi Arabia Aligarh Muslim University Faculty of Science Department of Computer Science U.P Aligarh India Jazan University College of Computer Science and Information Technology Department of Computer Science Jazan Saudi Arabia

ISBN: (纸本)9798350383041

The amalgamation of Unmanned Aerial Vehicles (UAVs) into Wireless Sensor Networks (WSNs) and Mobile Ad Hoc Networks (MANETs) provides significant prospects to improve network capabilities. This study examines the energy renewable efficiency and performance of UAVs operating in WSNs and MANETs. The assessment considers a variety of elements that influence energy consumption, including the possibility of integrating renewable energy, energy management measures, and the impact on overall network performance. This seeks to provide insights into optimizing energy usage and improving the operating efficiency of UAVs in these dynamic network situations through extensive analysis and evaluation. A special emphasis is placed on the management of mobility, the optimization of energy usage, and the effectiveness of routing protocols. The paper explores existing protocols such as LEACH, AODV and OLSR highlighting their benefits and challenges for UAV's. A comparative analysis evaluates adapted protocols based on metrics such as energy efficiency, latency, and reliability. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Availability assessment of repairable linear consecutive k-out-of-n: F systems incorporating uncertainty and multiple failure modes

引用

Life Cycle Reliability and Safety Engineering 2025年 1-10页

作者： Khati, Amisha Singh, S.B. Department of Mathematics Statistics and Computer Science G. B. Pant University of Agriculture and Technology Pantnagar India Department of Applied Science and Humanities RIT Roorkee India

This study evaluates the interval-valued availability of a linear consecutive k-out-of-n: F system while considering uncertainty, where the probability that the system will perform as intended is not known with precision. The proposed system is susceptible to µ number of different failure modes and undergoes periodic inspections. Each failure mode has a randomly assigned failure time, and upon failure due to the mth failure mode, an immediate corrective repair is carried out, taking an arbitrary length of time ψm (m = 1, 2,…, µ). By integrating these factors, this research establishes theorems describing point and steady-state availability bounds. Subsequently, it conducts a sensitivity assessment to evaluate how variations in the inspection period affect the system’s availability. The findings are demonstrated with an instance of an oil pipeline system. This study offers valuable insights into the reliability and availability modelling of complex systems under uncertainty, with applications across diverse engineering domains. © The Author(s), under exclusive licence to Society for Reliability and Safety (SRESA) 2025.

关键词： Interval valued point availability Interval valued steady state availability Linear consecutive k-out-of n: F system Multiple failure modes Sensitivity analysis Uncertainty

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

Intelligent Personality Assessment and Verification from Handwriting using Machine Learning

引用

International Journal of Information technology (Singapore) 2024年第7期16卷 4541-4546页

作者： Mishra, Pradeep Kumar Mishra, Gouri Sankar Abidi, Ali Imam Kumar, Rajiv Sahoo, Ashok Kumar Maini, Tarun Department of Computer Science and Application SSET Sharda University Department of Computer Science and Engineering SSET Sharda University NVIDIA AI Learning & amp Research Center Department of Applied Computational Science and Engineering G L Bajaj Institute of Technology and Management Greater Noida Graphic Era Hill University School of Computer Science and Engineering Galgotias University

It is possible to tell a lot about a person just by looking at their handwriting. The way someone writes might tell you a lot about who, they are as a person. There has been a lot of study on the possibility of deducing aspects of a person’s character from their handwriting. In this piece, we’ll look at the different personality qualities and how they might be utilized to make an evaluation. The report includes a dataset showing a correlation between several traits of personality. The Big Five Personality Traits are mapped using handwritten personality data. It was suggested that a comparison table should be used to spot distinctive character quirks. The article includes a review of previous studies and an assessment of the current status of the topic. Handwriting embodies have both creativity and expressiveness. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Agreeableness Conscientiousness Extraversion Neuroticism Openness

来源：评论

学校读者我要写书评

暂无评论

Navigating Opinion Space: A Study of Explicit and Implicit Opinion Generation in Language Models 1

Navigating Opinion Space: A Study of Explicit and Implicit O...

引用

1st Language Understanding in the Human-Machine Era Workshop, LUHME 2024

作者： Liebeskind, Chaya Lewandowska-Tomaszczyk, Barbara Department of Computer Science Jerusalem College of Technology Israel Department of Language and Communication University of Applied Sciences Konin Poland

The paper focuses on testing the use of conversational Large Language Models (LLMs), in particular chatGPT and Google models, instructed to assume the role of linguistics experts to produce opinionated texts, which are defined as subjective statements about animates, things, events or properties, in contrast to knowledge/evidence-based objective factual statements. The taxonomy differentiates between Explicit (Direct or Indirect), and Implicit opinionated texts, further distinguishing between positive and negative, ambiguous, or balanced opinions. Examples of opinionated texts and instances of explicit opinion-marking discourse markers (words and phrases) we identified, as well as instances of opinion-marking mental verbs, evaluative and emotion phraseology, and expressive lexis, were provided in a series of prompts. The model demonstrated accurate identification of Direct and Indirect Explicit opinionated utterances, successfully classifying them according to language-specific properties, while less effective performance was observed for prompts requesting illustrations for Implicitly opinionated texts. To tackle this obstacle, the Chain-of-Thoughts methodology was used. Requested to convert the erroneously recognized opinion instances into factual knowledge sentences, LLMs effectively transformed texts containing explicit markers of opinion. However, the ability to transform Explicit Indirect, and Implicit opinionated texts into factual statements is lacking. This finding is interesting as, while the LLM is supposed to give a linguistic statement with factual information, it might be unaware of implicit opinionated content. Our experiment with the LLMs presents novel prospects for the field of linguistics. © 2024 LUHME. All Rights Reserved.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Modified CNN-Watershed for Corneal Endothelium Segmentation: Image-to-Image Versus Sliding-Window Comparison 23rd

Modified CNN-Watershed for Corneal Endothelium Segmentation:...

引用

Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023

作者： Kucharski, Adrian Fabijańska, Anna Lodz University of Technology Institute of Applied Computer Science 18 Stefanowskiego Str. Lodz90-537 Poland

ISBN: (纸本)9783031384295

This paper considers the problem of corneal endothelium image segmentation using a method that combines a CNN model with a watershed transform. Specifically, first CNN predicts cell bodies, edges, and centers. Next, cell centers are used as markers that guide the watershed transform performed concerning the cell edge probability maps inferred by the CNN to outline cell edges. Different variants of the method are considered. Specifically, a downscaled U-Net is compared with the Attention U-Net in the image-to-image and sliding window setup. Results show that using a marker-driven watershed transform to post-process cell edge probability maps allows for replacing the sliding window setup with an image-to-image setup, reducing prediction time while maintaining similar or better segmentation accuracy. Also, when used as a backbone, Attention U-Net outperforms classical U-Net in determining cell morphometric parameters with high accuracy. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Incorporating Artificial Intelligence Powered Immersive Realities to Improve Learning using Virtual Reality (VR) and Augmented Reality (AR) technology 3

Incorporating Artificial Intelligence Powered Immersive Real...

引用

3rd International Conference on applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Balushi, Jasim Sharki Ghulam Al Jabri, Malak Ibrahim Ahmed Al Palarimath, Suresh Maran, Pyingkodi Thenmozhi, K. Balakumar, C. Univesity of Technology and Applied Sciences College of Computing and Information Sciences Information Technology Department Salalah Oman Kongu Engineering College Department of Computer Applications Erode India Department of Computer Science Bengaluru India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India

ISBN: (纸本)9798350375190

This study analyzes the transformative potential of combining artificial intelligence (AI) with immersive technologies, specifically virtual reality (VR) and augmented reality (AR), to elevate educational outcomes significantly. The synergy of AI and immersive technologies presents a unique opportunity to enhance students' motivation, memory retention, and comprehension of complex subjects, creating a distinct and impactful learning experience. The research comprehensively explores the current understanding of the effectiveness of VR and AR in educational settings, placing special emphasis on their applications in diverse fields such as science, technology, Engineering, And Mathematics (STEM), medicine, language acquisition, and the development of interpersonal skills. Beyond highlighting the immense potential, the study acknowledges and addresses the obstacles that include the costs associated with equipment, training, and content creation. It underscores the importance of collaborative efforts among technology suppliers, educators, and content producers to overcome these challenges effectively. By recognizing and navigating these hurdles, the study aims to provide practical insights for educational institutions and policymakers, advocating for the integration of AI-powered immersive technology to enhance the overall learning experience for students. The findings underscore the transformative impact of such technologies, emphasizing their role in shaping the future of education and preparing students for the dynamic challenges of the modern world. © 2024 IEEE.

关键词： Augmented reality

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

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

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：