检索结果-内蒙古大学图书馆

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Hemapriya, H.P.B.D. Hewaranaweera, D.S. Sajith, N.T.M. Aslam Saja, A.M. Aashiq, M.N.M. South Eastern University of Sri Lanka Dept. of Electrical and Telecommunication Engineering Oluvil Sri Lanka South Eastern University of Sri Lanka Dept. of Computer Science and Engineering Oluvil Sri Lanka

ISBN: (纸本)9798331530983

This paper presents a research study on the development of smart solutions for waste collection and monitoring adapted for Sri Lankan cities. The proposed system includes a user reward mechanism, real-time monitoring of bins, identification of filled bins, and optimized route suggestions for collecting them. A unified mobile application has been developed to serve both the general public and authorities. Users are rewarded based on the weight of the recyclable waste they dispose of, and they can track their points and locate bins through the mobile application. Authorities can monitor the filling level of each bin in real time with help of the application. When a bin reaches its maximum capacity, a notification is displayed in the app and provides an optimized route for collecting the filled bins. Additionally, this system is designed to be seamlessly integrated with existing recyclable waste collection bins, making it affordable. It allows authorities to gather waste generation data from each area, enabling informed decision-making while encouraging community members to actively engage with the system. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Maximizing Performance in Wireless Mobile Ad-Hoc Networks Through Unconventional Routing Strategies

引用

SN computer science 2025年第2期6卷 1-13页

作者： Singh, Satyanand Sreelakshmy, R. Bhagyalakshmi, L. Shekhar, Himanshu Thanuja, Annamaraju Suman, Sanjay Kumar School of Electrical & Electronics Engineering Fiji National University Suva Fiji Dept. of ECE Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Tamil Nadu Chennai India Rajalakshmi Engineering College Tamil Nadu Chennai India Dept. of ECE Hindustan Institute of Technology and Science Tamil Nadu Chennai India Dept. of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Dept. of ECE and Dean R & D St. Martin’s Engineering College Telangana Secunderabad India

A Mobile Ad-Hoc Network (MANET) comprises wireless mobile nodes without a fixed infrastructure or central control. Nodes communicate within range, with distant nodes acting as intermediaries. Frequent connection failures occur due to node mobility. This work aims to enhance a novel MANET routing algorithm and assess its impact on selected multipath protocols. Prioritizing paths with higher residual energy optimizes battery usage, minimizing route lifetimes and communication delays. Energy and link quality considerations led to the development of an Energy and Link aware Ad hoc On-Demand Multipath Distance Vector (AOMDV) protocol, outperforming traditional AOMDV in energy efficiency. Additionally, a Reliable Link AOMDV protocol predicts connection failures based on received signal strength, pre-emptively switching paths to maintain data transfer reliability, ultimately improving packet transfer efficiency and productivity. These enhancements in route discovery contribute to overall routing quality improvement. Compared to AOMDV, EQL-simulation AOMDV’s results show that it uses 87% less energy when selecting a reliable link. The novel finding is that enhanced AOMDV protocols prioritizing energy and link quality improve energy efficiency and reliability in MANETs, reducing communication delays and maintaining stable data transfer through pre-emptive path switching. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： AOMDV EQL-AOMDV MANET REL-AOMDV

来源：评论

学校读者我要写书评

暂无评论

Advancing Drug Discovery through a Deep Learning-Based Protein-Ligand Interaction Prediction Tool 3

Advancing Drug Discovery through a Deep Learning-Based Prote...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Hunge, Sudhir S. Yadao, Aman Rajendra Shewate, Varsha Tekdas Lalsare, Prakash Namdeorao Prasannan, Shiji Ramulu, Kothuri Parashu Chintamani College of Science Pg Dept. of Chemistry Maharashtra Pombhurna India Shriram Arts And Science Junior College Dept. Of Chemistry Maharashtra Ramtek India Chintamani College of Science Dept. of Chemistry Maharashtra Pombhurna India Shri Prabhu Ramchandra Junior College Dept. of Chemistry Nanda Tah Korpana Maharashtra India Faculty of Management Studies Parul Institute of Management and Research Parul University Gujarat Vadodara India Indur Institute Of Engineering And Technology Dept. of Computer Science and Engineering India

ISBN: (纸本)9798331515911

In recent years, deep learning has emerged as a promising approach to advance drug discovery by accurately predicting interactions between proteins and small molecules, or ligands. The identification of these interactions is essential in developing drugs, as it informs us about a molecule's potential therapeutic efficacy. Traditional methods, like molecular docking, often struggle with accuracy and computational efficiency, limiting their application in high-throughput settings. In this paper, we propose a novel deep learning-based tool designed to predict protein-ligand interactions with enhanced precision and scalability. Our model leverages convolutional and graph neural networks to capture the complex, three-dimensional nature of these interactions. Using a large, curated dataset, we train and test the model to optimize binding affinity prediction, employing metrics such as mean squared error and accuracy to validate performance. The results show that our approach outperforms conventional techniques and recent machine learning models, demonstrating a significant improvement in predictive reliability. This tool has potential applications in screening vast compound libraries in early-stage drug discovery, reducing time and costs associated with experimental trials. By providing more accurate insights into protein-ligand affinities, our method represents a step forward in computational drug design, with implications for developing targeted therapies across various disease areas. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

The Medical Segmentation Decathlon without a Doctorate

The Medical Segmentation Decathlon without a Doctorate

引用

Medical Imaging 2025: Clinical and Biomedical Imaging

作者： Samir, Jessica Ramadass, Karthik Saunders, Adam M. Krishnan, Aravind R. Remedios, Lucas W. McMaster, Elyssa M. Landman, Bennett A. Dept. of Psychological Science and Neuroscience Belmont University NashvilleTN United States Dept. of Computer Science NashvilleTN United States Dept. of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States Vanderbilt University Institute of Imaging Science Vanderbilt University Medical Center NashvilleTN United States

ISBN: (纸本)9781510685987

Segmentation of anatomical structures leverages medical imaging technology for accurate diagnosis and treatment planning. Recent advances in active learning offer the opportunity for the interactive creation of artificial intelligence (AI) segmentation algorithms. Although active learning has been extensively investigated retrospectively, prospective studies have not been widely reported. This study aimed to determine whether a novice in medical imaging could independently label anatomical structures using Radiopaedia, 20% of clinician-generated labels for education of the novice, and AI guidance. Given the pancreas and spleen challenges from the Medical Segmentation Decathlon (MSD), a novice employed the MONAI Label extension on 3D Slicer with active learning (AL) techniques to perform segmentation. This study also explored the use of MONAI (Medical Open Network for AI) Label, a user-friendly framework for label submission and model training. Our segmentation results yielded Dice scores comparable to the range of those from the 2018 segmentation challenges of the MSD. We achieved Dice scores of 0.209 for the pancreas task using 70 images and 0.831 for the spleen using 34 images. The pancreas results do not fall within MSD’s reported ranges for the L1 region which is 0.48-0.80. However, the spleen results fall within the MSD’s reported range of 0.83-0.97. The interactive AI framework by MONAI Label effectively segments as we reached reasonable performance in less than a month with one person without clinical expertise. © 2025 SPIE.

关键词： Medical education

来源：评论

学校读者我要写书评

暂无评论

Unpaired Shadow Removal: Enhancing Attention to Shadow Areas via Dropkey

Unpaired Shadow Removal: Enhancing Attention to Shadow Areas...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Yang, Jaewon Shin, Ukcheol Cho, Donghyeon Chungnam National University Dept. of Electronics Engineering Daejeon Korea Republic of Robotics Institute Carnegie Mellon University Pittsburgh United States Hanyang University Dept. of Computer Science Seoul Korea Republic of

ISBN: (纸本)9798331510756

Shadows appear in image areas where an object obstructs the light path. These areas, having lower values than non-shadow areas, degrade image quality and lead to issues in object recognition and segmentation. Supervised shadow removal depends on datasets with shadow and shadow-free image pairs, sparking increased interest in unpaired techniques. However, unpaired shadow removal faces challenges in accurately focusing on shadow areas without direct supervisory signals from ground truth. Consequently, shadows are not effectively removed, and non-shadow areas may suffer from unintended distortions. In this paper, we introduce a transformer-based network designed to identify shadow areas accurately, leveraging global context through spatial and channel attention mechanisms. Additionally, in the training phase, the transformer network is trained to precisely concentrate on shadow areas using a domain classifier and a dropkey mechanism, which randomly drops features of the keys to enhance focus. Our method is tested across several benchmark datasets for shadow removal, such as ISTD, ISTD+, SRD and WSRD, demonstrating better performance compared to current unpaired approaches. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Breaking Tester Stereotypes: who is testing and why it matters 24

Breaking Tester Stereotypes: who is testing and why it matte...

引用

Proceedings of the 37th International BCS Human-computer Interaction Conference

作者： Isabel Evans Chris Porter Mark Micallef Dept. of Computer Information Systems Faculty of ICT University of Malta Msida Malta Dept. of Computer Science

Testing is essential for successful delivery of software solutions and is not always performed by specialist testers. In earlier studies, we noted a wide diversity in the backgrounds of the testers participating in these studies, prompting our research question: Who is Testing? We conducted a qualitative study of over 70 industry testers, covering testers from multiple countries and domains, with information about their backgrounds, hobbies, roles and characteristics. We show testers are from a wide range of backgrounds, with differing needs, characteristics, and problem-solving preferences. Their roles in software projects are multi-faceted, requiring a high cognitive skill level. We discuss how to break stereotyping and best support diversity in testers’ backgrounds and *** consider whether software testers are different from other software practitioners, and how understanding tester personas helps support of testers and testing.

关键词： Software Testing

来源：评论

学校读者我要写书评

暂无评论

Characterization and Statistical Analysis of Beer Produced by Bacterial Strains Isolated from Traditional Fermented Foods of Northeast India 14

Characterization and Statistical Analysis of Beer Produced b...

引用

14th IEEE International Conference on Communication systems and Network Technologies, CSNT 2025

作者： Borthakur, Debashree Chowdhury, Ranbir Sharma, Bipin Kumar Dept. of Microbiology Tripura University Tripura India Dept. of Bio Sciences Assam Don Bosco University Assam India Dept. of Computer Science and Engineering Assam Don Bosco University Assam India

ISBN: (纸本)9798331531935

Beer fermentation is a multifaceted biochemical process influenced by microbial activity, with yeasts and lactic acid bacteria (LAB) playing pivotal roles in determining its sensory attributes. This study aims to isolate and characterize LAB strains from traditional fermented foods of Northeast India and evaluate their potential in enhancing the sensory properties of beer. A total of 41 LAB strains were isolated and subjected to biochemical characterization, including proteolytic, lipolytic, and carbohydrate fermentation assays. Non-pathogenic strains (B/4, Chuwan/YEPD/1, HTK/5, Khorisa/NA/3, NAP/2, NGA/5, NGA/6, Soibum/NA/3, TL/2, TL/4, TL/5 and TL/6) exhibiting favorable metabolic activities were selected for beer fermentation using a rice-based substrate. Sensory evaluation was conducted by a trained panel to assess attributes such as aroma, flavor, mouthfeel, and overall acceptability. Statistical analyses, including the Friedman and Nemenyi tests, revealed significant variations in the sensory profiles of beer samples produced by different LAB strains. Notably, the strains (B/4, Chuwan/YEPD/1, HTK/5, Khorisa/NA/3, NAP/2, NGA/5, NGA/6 and TL/2) imparted distinctive aroma and flavor, indicating its potential application in specialty beer production. These findings underscore the role of LAB in modulating beer characteristics and offer valuable insights for the development of innovative, naturally fermented beverages. These findings highlight the potential application of LAB strains in specialty beer production, emphasizing their role in enhancing sensory appeal. While the study confirms LAB’s viability in small-scale brewing, further research involving large-scale trials and advanced metabolomic analyses is recommended to assess their full industrial potential. This study provides valuable insights into the use of indigenous LAB strains for developing innovative, naturally fermented beverages. © 2025 IEEE.

关键词： Beer

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Coupling Characteristics of Wheel Polygon and Rail Corrugation in High-Speed Railways 3

Investigation of the Coupling Characteristics of Wheel Polyg...

引用

3rd International Conference on Rail Transportation, ICRT 2024

作者： Gao, Wanlin Yin, Yue Bu, Han Wang, Shiqi Cui, Xiaolu Dept. of Computer Science and Technology Chongqing Jiaotong Univ. Chongqing China Dept. of Rail Transit Chongqing Vocational College of Transportation Research State Univ. Chongqing China Dept. of Mechanical and Electrical Engineering and Vehicle Engineering Chongqing Jiaotong Univ. Chongqing China

ISBN: (数字)9780784485941

ISBN: (纸本)9780784485941

Wheel polygon and rail corrugation are common types of periodic wear in the wheel-rail system. This research investigates their interaction in high-speed railways using friction coupling vibration theory. A finite element model of the wheel-rail system is developed to study friction coupling vibrations in straight sections of long slopes. The study identifies the causes of 22nd-order wheel polygonization and rail corrugation with a 130 mm wavelength and creates wear models for both. The effects of their interaction on friction coupling vibrations are analyzed, with an emphasis on frequency-dependent coupling characteristics. Results indicate that saturated wheel-rail creep forces in long slopes easily trigger friction coupling vibrations, which are worsened by both wheel polygon and rail corrugation, with wheel polygon having a more pronounced impact. These findings offer insights for improving wheel-rail system design and maintenance in high-speed railways. Future research should aim to develop advanced techniques to mitigate the negative effects of wheel polygon and rail corrugation on system performance and safety. © ASCE.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Deep Learning Models for Structural Defect Segmentation in Bridges

Comparative Analysis of Deep Learning Models for Structural ...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： O'Neal, Kiara Hu, Da Kennesaw State University Dept. of Computer Science MariettaGA United States Kennesaw State University Dept. of Civil and Environmental Engineering MariettaGA United States

ISBN: (纸本)9798331504847

Automated structural defect detection is essential for ensuring the safety and maintenance of civil infrastructure, particularly in bridges where defects such as cracks, spalling, and corrosion can compromise structural integrity. This paper presents a comparative study of three semantic segmentation models - U-Net, Feature Pyramid Network (FPN), and DeepLabv3+ - for detecting and classifying structural defects in bridge imagery. Each model was evaluated using two encoder architectures, EfficientNet B3 and MobileOne S4, to assess the impact of different feature extraction strategies on segmentation accuracy. The experiments were conducted using the DACL benchmark dataset, which includes a wide range of defect classes. FPN paired with EfficientNet B3 demonstrated the highest mean accuracy across most defect categories, outperforming the other combinations, particularly in detecting common defects such as cracks and graffiti. However, certain defect types, such as hollow areas and cavities, presented challenges for all models. These results highlight the effectiveness of deep learning models in automated defect detection, while also identifying areas where further refinement is needed to improve performance in more complex defect scenarios. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Event Identification and Chronology Model of Ramayana

Event Identification and Chronology Model of Ramayana

引用

International Conference on Electronics, Materials engineering and Nano-Technology (IEMENTech)

作者： Apurba Paul Rishabh Mishra Nayan Padia Dipankar Das Dept. of Computer Science & Engineering IEM Kolkata UEM Kolkata Kolkata India Dept. of Computer Science & Engineering IEM Kolkata Kolkata India Dept. of Computer Science & Engineering Jadavpur University Kolkata India

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

The paper introduces an event chronology model for Hindu mythological texts, with a focus on the Ramayana's Bala-kanda. It captures and structures sentence-level events based on their chronological order to better understand narrative progression and character interactions. A manually crafted dataset of 1217 events, involving 214 characters across 75 chapters, is used to generate a knowledge graph. The graph organizes events by sequence, linking characters, actions, and chapters within the storyline. The event chronology is mapped by establishing relationships between events, ensuring they are connected in the proper sequence to reflect the narrative flow. This approach enables a deeper understanding of how each event contributes to the overarching story, providing insights into both the individual actions of characters and their significance within the broader mythological narrative. Transformer-based models (BERT, DistilBERT, and RoBERTa) were utilized for predicting subsequent events, with RoBERTa showing the highest accuracy in preserving the correct event chronology. This structure is key to analyzing the sequential development of the Ramayana's storyline.

关键词： Accuracy Annotations Refining Knowledge graphs Manuals Predictive models Transformers Guidelines

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：