检索结果-内蒙古大学图书馆

Evaluation of Manifold Dual Contouring Algorithms Based on k-d tree and Octree Data Structures

Informatica (Slovenia) 2024年第3期48卷 399-418页

作者： Ramaijane, Thabang Hlomani, Hlomani Zlotnikova, Irina Maupong, Thabiso Department of Computing and Informatics School of Pure and Applied Sciences Botswana International University of Science and Technology Botswana Botswana

This study evaluated the performance and efficiency of manifold dual contouring algorithms using k-d trees and octrees, therefore, addressing a critical gap in comparative analysis of these data structures. Despite the popularity of k-d trees and octrees in isosurface extraction, their performance has not been empirically compared. This research specifically focuses on visualization quality, performance metrics, and efficiency across various simplification error thresholds. A comprehensive comparative analysis was conducted to identify the conditions under which each data structure is most suitable. Both algorithms employed the manifold vertex clustering scheme for dual contouring of isosurfaces. The methodology involved evaluating visual output, build time, extraction time, and efficiency based on triangle counts during the simplification process. Computational experiments demonstrated that the octree-based algorithm is superior for rendering large models, producing an average of 20% more visual detail due to a higher triangle count. In contrast, the k-d tree-based algorithm showed a 40% reduction in build time and a 35% reduction in extraction time, making it more efficient for processing large implicit models by reducing geometric complexity. These findings provide metrics to assist researchers and practitioners in selecting the most suitable adaptive data structure for achieving optimal simplification results in manifold dual contouring algorithm implementations. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Deep learning-powered mobile app for early brahmi script decipherment in sri lanka

Deep learning-powered mobile app for early brahmi script dec...

引用

2024 International Research Conference on Smart computing and Systems Engineering, SCSE 2024

作者： Gunasekara, Sakith Lafir, Muhammed Haleef Dulaj, Chavindu Haputhanthri, Lakidu Alwis, Dileeka Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798350375688

This ongoing research delves into ancient Brahmi writings carved on stone surfaces, particularly focusing on early Brahmi characters which serves as critical artifacts to illuminate the island's historical ties with India, religious and cultural practices of the era. The study aims to develop a mobile application utilizing deep learning techniques to recognize and translate ancient early Brahmi characters, ensuring enhanced efficiency and accuracy in the decipherment process. A comprehensive literature review highlighted the absence of a mobile application, challenges of contextual translation, and difficulties in accurate predicting translation for damaged inscriptions and translation to foreign languages were identified as notable research gaps. Drawing upon interdisciplinary expertise and stakeholder analysis, the research tackles these complex challenges of script recognition, linguistic translation, accurate prediction by employing a data-driven approach, cutting-edge algorithms, and user-centric design principles. After the creation of a refined, precise digitized dataset of early Brahmi characters with found variations, the research aims to utilize semantic segmentation techniques to recognize characters using TensorFlow and Keras. OpenCV for image preprocessing, Flutter framework for development of mobile application. Expected outcomes include improved recognition accuracy, linguistically faithful translations, and user-friendly interfaces, contributing to advancements in digital humanities, cultural preservation, and computational linguistics. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LawKey-Law Constitution Chatbot 8

LawKey-Law Constitution Chatbot

引用

8th SLAAI - International Conference on Artificial Intelligence, SLAAI-ICAI 2024

作者： Fernando, W Shamini Handapangoda, Mandinu Samindi, Nividula Gamage, Maneth Alwis, Dileeka Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331509170

In response to a pervasive lack of legal awareness among Sri Lanka, this research introduces a law constitution chatbot utilizing Natural Language Processing (NLP). The chatbot is designed to offer precise legal guidance by extracting pertinent laws from the Sri Lankan constitution based on user input. Building on existing studies at the intersection of NLP and the legal domain, this chatbot addresses the lack of relevant legal context for Sri Lanka. Reinforcement learning is integrated to refine the chatbot's behavior through user feedback, ensuring optimal selection of the most relevant laws. An exploration of applications in countries like Canada and India, where NLP and machine learning have successfully addressed legal information gaps, focuses on various legal domains in Sri Lanka with the aim of empowering the public. The research methodology involves leveraging the Sri Lankan constitution as the dataset, extracting keywords from legal documents, and employing various NLP models, and limitations of the application. A comprehensive literature review reveals the potential energy of NLP techniques in legal chatbots. The global analysis of legal chatbots significantly contributes to the theoretical foundation of this project. In summary, this project seeks to advance legal chatbot technology in Sri Lanka, utilizing NLP and reinforcement learning techniques to empower citizens with legal knowledge and enhance overall legal awareness, thereby addressing the critical issue of legal unawareness and fostering a more informed society. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Knee Osteoarthritis Detection Using Machine Learning on Pre-Processed X-ray Images and Treatment Recommendation 8

Knee Osteoarthritis Detection Using Machine Learning on Pre-...

引用

8th SLAAI - International Conference on Artificial Intelligence, SLAAI-ICAI 2024

作者： Rameez, Nuha Dewmi Dissanayake, G.G.D. Chanula Senindu, G.A.C. Liyanage, P.M.H. Embuldeniya, Vishmi Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331509170

Osteoarthritis (OA) is a degenerative joint disease marked by the gradual breakdown of cartilage and changes in the underlying bone. The condition is most prevalent in older adults and is often exacerbated by joint injuries and mechanical stress. Knee osteoarthritis (KOA) is one of the common disability adjusted life years. There is no cure for the disease, but a combination of lifestyle changes, medications, physical therapies, and sometimes knee transplants can help manage the condition. Despite being time-consuming and highly prone to user variation, manual segmentation, diagnosis, annotation of knee joints, and personalized treatment recommendations remain common procedures for diagnosing osteoarthritis in clinical practice. This research addresses these limitations and reduces diagnostic errors and time and enhance the efficiency and accuracy of knee osteoarthritis diagnosis. The proposed KOA detection model utilizes a deep learning-based approach with Convolutional Neural Networks (CNNs) to identified knee joints in x-rays, Binary classification to determine the presence of disease, a pre trained network(VGG16) and custom CNN used to classify the Kellgren-Lawrence (KL) grades, and random forest model recommending and validating treatment options based on severity. The proposed model has shown promising results by obtaining 98% overall accuracy. © 2024 IEEE.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation 5

Parameter Efficient Diverse Paraphrase Generation Using Sequ...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Jayawardena, Lasal Yapa, Prasan School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (纸本)9798350394764

Over the past year, the field of Natural Language Generation (NLG) has experienced an exponential surge, largely due to the introduction of Large Language Models (LLMs). These models have exhibited the most effective performance in a range of domains within the Natural Language Processing and Generation domains. However, their application in domain-specific tasks, such as paraphrasing, presents significant challenges. The extensive number of parameters makes them difficult to operate on commercial hardware, and they require substantial time for inference, leading to high costs in a production setting. In this study, we tackle these obstacles by employing LLMs to develop three distinct models for the paraphrasing field, applying a method referred to as sequence-level knowledge distillation. These distilled models are capable of maintaining the quality of paraphrases generated by the LLM. They demonstrate faster inference times and the ability to generate diverse paraphrases of comparable quality. A notable characteristic of these models is their ability to exhibit syntactic diversity while also preserving lexical diversity, features previously uncommon due to existing data quality issues in datasets and not typically observed in neural-based approaches. Human evaluation of our models shows that there is only a 4% drop in performance compared to the LLM teacher model used in the distillation process, despite being 1000 times smaller. This research provides a significant contribution to the NLG field, offering a more efficient and cost-effective solution for paraphrasing tasks. © 2024 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fan Base Engagement through Explainable Self-Learning Sentiment Analysis 10

Enhancing Fan Base Engagement through Explainable Self-Learn...

引用

10th International Multidisciplinary Engineering Research Conference on Moratuwa Engineering Research, MERCon 2024

作者： Lye, Mikael Wijesinghe, Nethmi Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331529048

Individuals and brands with large fan bases face difficulty in understanding fan sentiment and its potential impact on fan engagement and performance. This is particularly pertinent within fast-paced sports such as Formula 1, where fan opinions can significantly influence driver and team morale. To address the above-mentioned problem, this study proposes the use of deep learning-based sentiment analysis techniques to enhance fan base engagement. The system would act as a tool to automate the process of marketing and public relations teams by analysing textual data provided by the fan base and providing meaningful insight/reports of the fan base's emotion of the posted content. This is achieved by a novel multi-class sentiment analysis system that utilizes a fine-tuned Distil-BERT model for classification, self-supervised techniques for self-improvement, and an explainable AI (XAI) approach for interpretability. The proposed system demonstrated strong performance during testing and evaluation, achieving an overall accuracy of 82% and an F1-score of 80%. Overall, the systems components and structure focuses on utilizing the least amount of resources while also maintaining a high prediction accuracy and speed. This ultimately results in a budget friendly and robust tool that can be integrated into bigger analytics systems. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Advancements in Natural Language Processing for Automatic Text Summarization 4

Advancements in Natural Language Processing for Automatic Te...

引用

4th International Conference on Computer Systems, ICCS 2024

作者： Jayatilleke, Nevidu Weerasinghe, Ruvan Senanayake, Nipuna School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (纸本)9798350366341

The substantial growth of textual content in diverse domains and platforms has led to a considerable need for Automatic Text Summarization (ATS) techniques that aid in the process of text analysis. The effectiveness of text summarization models has been significantly enhanced in a variety of technical domains because of advancements in Natural Language Processing (NLP) and Deep Learning (DL). Despite this, the process of summarizing textual information continues to be significantly constrained by the intricate writing styles of a variety of texts, which involve a range of technical complexities. Text summarization techniques can be broadly categorized into two main types: abstractive summarization and extractive summarization. Extractive summarization involves directly extracting sentences, phrases, or segments of text from the content without making any changes. On the other hand, abstractive summarization is achieved by reconstructing the sentences, phrases, or segments from the original text using linguistic analysis. Through this study, a linguistically diverse categorizations of text summarization approaches have been addressed in a constructive manner. In this paper, the authors explored existing hybrid techniques that have employed both extractive and abstractive methodologies. In addition, the pros and cons of various approaches discussed in the literature are also investigated. Furthermore, the authors conducted a comparative analysis on different techniques and matrices to evaluate the generated summaries using language generation models. This survey endeavors to provide a comprehensive overview of ATS by presenting the progression of language processing regarding this task through a breakdown of diverse systems and architectures accompanied by technical and mathematical explanations of their operations. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Parameter-efficient fine-tuning of pre-trained code models for just-in-time defect prediction

引用

Neural computing and Applications 2024年第27期36卷 16911-16940页

作者： Abu Talib, Manar Bou Nassif, Ali Azzeh, Mohammad Alesh, Yaser Afadar, Yaman Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics Sharjah United Arab Emirates King Hussein School for Computing Sciences Princess Sumaya University for Technology Amman Jordan

Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebases to ensure each change is defect-free, and it is not enough to test changed files alone. Just-in-time software defect prediction (JIT-SDP) systems have been proposed to solve this by predicting the likelihood that a code change is defective. Numerous techniques have been studied to build such JIT software defect prediction models, but the power of pre-trained code transformer language models in this task has been underexplored. These models have achieved human-level performance in code understanding and software engineering tasks. Inspired by that, we modeled the problem of change defect prediction as a text classification task utilizing these pre-trained models. We have investigated this idea on a recently published dataset, ApacheJIT, consisting of 44k commits. We concatenated the changed lines in each commit as one string and augmented it with the commit message and static code metrics. Parameter-efficient fine-tuning was performed for 4 chosen pre-trained models, JavaBERT, CodeBERT, CodeT5, and CodeReviewer, with either partially frozen layers or low-rank adaptation (LoRA). Additionally, experiments with the Local, Sparse, and Global (LSG) attention variants were conducted to handle long commits efficiently, which reduces memory consumption. As far as the authors are aware, this is the first investigation into the abilities of pre-trained code models to detect defective changes in the ApacheJIT dataset. Our results show that proper fine-tuning improves the defect prediction performance of the chosen models in the F1 scores. CodeBERT and CodeReviewer achieved a 10% and 12% increase in the F1 score over the best baseline models, JITGNN and JITLine, when commit messages and code metrics are included. Our approach sheds more light on the abilities of l

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Lightweight 1-D Convolutional Neural Network Model for Predicting Snoring Duration 2

Lightweight 1-D Convolutional Neural Network Model for Predi...

引用

2nd IEEE International Conference on Sensors, Electronics and Computer Engineering, ICSECE 2024

作者： Abhishek, Yohan School of Computing Informatics Institute of Technology Colombo006 Sri Lanka

ISBN: (纸本)9798350373646

This paper introduces an approach to snoring duration prediction utilizing a custom 1-D Convolutional Neural Network (CNN) implemented into TensorFlow Lite. Snoring is a prevalent symptom of sleep disorders which presents challenges in diagnosis and management due to its disruptive effects on sleep quality and potential indication of underlying health issues like obstructive sleep apnea (OSA). Despite the significance of accurate snoring prediction and monitoring, existing research lacks specific exploration of lightweight and accurate CNN models tailored for this purpose. Leveraging the advantages of 1-D CNNs, such as efficient processing of 1D signals without extensive preprocessing, this paper addresses the research gap by proposing a custom TensorFlow Lite-based model for snoring prediction. Through a comprehensive literature review, the efficiency of CNNs in predictive modeling across various domains is highlighted, underscoring the need for specialized models in healthcare applications like snoring prediction. The proposed approach not only supports the gap in existing research but also opens possibilities for lightweight, real-time snoring monitoring, potentially integrated into mobile or wearable devices for continuous assessment of sleep-related disorders. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

GreenGuard: Mobile Application for Real-Time Tea Leaves Disease Detection and Treatment Guidance 6

GreenGuard: Mobile Application for Real-Time Tea Leaves Dise...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Obadaarachchi, Esandu Saputhanthri, Damika Vithanarachchi, Pramuditha Zuhry, Yoosuf Rathnayake, Rasanjalee School of Computing Informatics Institute of Technology Colombo 04 Sri Lanka

ISBN: (纸本)9798331517878

Accurate tea leaves disease detection is essential in agriculture to maintain healthy crops, food security, and economic stability. Tea leaves disease identification is challenging due to traditional detection methods, frequently constrained by the knowledge gap between small-scale and general-level farmers. To alleviate this issue, the proposed study presents an Artificial Intelligence (AI)-enhanced tea plant disease detection system that can accurately identify ailments and suggest relevant treatments. The proposed Convolutional Neural Network (CNN) architecture ensures high accuracy while efficiently working in real time for disease detection and treatment suggesting. The custom CNN model surpasses the ResNet50V2 model's accuracy while achieving 94% accuracy in disease detection. Further, the study initiative promises to make a major contribution to the advancement of agricultural technology in the tea plantation sector and the support of farming-dependent people worldwide by fusing AI with traditional methods while ensuring sustainable development and food security. © 2024 IEEE.

关键词： Convolutional neural networks

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：