检索结果-内蒙古大学图书馆

6th International Conference on Advancements in computing, ICAC 2024

作者： Kumari, Chamodya Bandara, Pinsara Weerasinghe, Lahiru Madhuthisara, Rithma Tissera, Wishalya Vidhanaarachchi, Samitha Peruma Godapitiya, Virajini Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798331517878

The Sri Lankan fisheries industry faces significant challenges, including communication gaps and safety risks. This research introduces a novel solution by developing a LoRa-based ad hoc network integrated with blockchain technology to address these issues. The proposed system enables real-time data communication between fishing boats and land stations, offering features such as emergency alerts, and barrier avoidance. Blockchain integration provides secure communication and verification of registered vessels. The primary goals of this research are to enhance communication efficiency, and improve safety through early warning systems. By implementing this system, we aim to promote the sustainability and economic growth of Sri Lanka's fisheries industry. © 2024 IEEE.

关键词： Fisheries

来源：评论

学校读者我要写书评

暂无评论

Todly: Multimodal Approach for Toddler Safety and Well-Being Using Advanced Machine Learning 6

Todly: Multimodal Approach for Toddler Safety and Well-Being...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Dewmini, Ashani Shashindi, Maleesha Uththara, Kaveen Sathushka, Gehan Manathunga, Kalpani Karunathilaka, Supipi Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798331517878

This study presents 'Todly,' an intelligent toddler monitoring system designed as a mobile application to ensure the safety and well-being of toddlers through cutting-edge technology. 'Todly' integrates advanced machine learning algorithms and neural networks to enhance child safety and provide caregiver support. This approach features face emotion and gesture detection, danger object detection, crying pattern analysis, and a chatbot assistant for new mothers. These components work together seamlessly to offer caregivers real-time insights into a child's emotional state, identify potential hazards, understand the reasons behind a toddler's crying, and provide timely support and guidance. The architecture is designed to be scalable and adaptable, making it suitable for various environments, such as homes, daycare centers, and pediatric healthcare facilities. Its user-friendly interface ensures accessibility for users with different levels of technical expertise, while the robust support infrastructure facilitates smooth operation and maintenance. The integrated solution demonstrated strong performance across its various components, achieving an accuracy of 89.9% in object detection, 85% in emotion detection, and 90.8% in cry analysis, encompassing all cry types. The chatbot's mT5 model also achieved BLEU scores of 38.7 for Sinhala-to-English translation and 31.2 for English-to-Sinhala translation. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Success Factors of Requirement Engineering that Influence Software Development Efficiency 6

Success Factors of Requirement Engineering that Influence So...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Yapa, Thilini Nawinna, Dasuni Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798331517878

Due to the rapid advancement of technology, the software industry has become one of the major industries all over the world. Many organizations invest large amounts of money to develop software products. Requirement engineering is one of the major phases in the software development process. It is a challenging and time-consuming task which should carefully be done because requirement engineering plays a vital role in shaping a project's success and efficiency. Software development teams face significant challenges in making functional software products that meet client's requirements due to lack of clear requirements. This study explores the critical success factors of requirement engineering that influence software development efficiency. A study was conducted to gather data from business analysts within a leading telecommunication organization and its subsidiaries across three countries. The data was thoroughly analyzed through a structured analysis using Smarts PLS. The success factors considered in this study are business analyst's skills, quality of the requirement, customer involvement and team capability. The results highlighted that software development efficiency is strongly influenced by requirements engineering factors, including the skills of the Business Analyst, customer involvement, and team capability, each with a significance value of less than 0.05. By addressing requirement engineering challenges and implementing standardized procedures derived fromcritical success factors, organizations can streamline their requirement engineering processes, and this study provides valuable insights to enhance requirement engineering best practices fostering software development efficiency. © 2024 IEEE.

关键词： Enterprise software

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diabetic Retinopathy Management Through Personalized Recommendations with Reinforcement Learning 13

Enhancing Diabetic Retinopathy Management Through Personaliz...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Herath, H.M.A.I.B. Sandakalum, H.G.D. Samoon, T.F. Thushan, P.V. Kasthurirathna, Dharshana Krishara, Jenny Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798350380583

Diabetic retinopathy (DR) is one of the main causes of vision impairment among diabetes patients, which leads to the requirement of effective management strategies to stop its progression. In traditional management methods, this process is often less personalized, which results in poor dietary and exercise practices among patients. This paper presents a mobile application, 'Retina-Care,' created to give out personalized dietary and exercise recommendations using Q-Iearning - a method of reinforcement learning. This proposed system dynamically learns and adapts to individual user behaviors, which leads to users engaging with the system more and adhering to the recommendations given. The paper addresses the cold start problem which can be seen in reinforcement learning systems, through a combination of epsilon-greedy methods, initialized Q-tables, and integration of an expert system. The results received through simulations and user testing indicate that the proposed strategy was successful in giving recommendations that were suitable to the unique medical conditions and preferences of the diabetic retinopathy patients. The said findings show that reinforcement learning can be used to enhance the effectiveness of diabetic retinopathy management systems, offering a promising solution for broader health care applications. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Typing Dynamics Emotion Recognition: A Multi-Class XGBoost Approach for Accurate Sentiment Detection 6

Enhancing Typing Dynamics Emotion Recognition: A Multi-Class...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Bandara, Sudesh Dasath, Tharindu Nanayakkara, Senula Rathnayake, Samadhi Thilakarthna, Thusithanjana Faculty of Computing Sri Lanka Institute of Information and Technology Malabe Sri Lanka

ISBN: (纸本)9798331517878

This research paper aims to enhance the accuracy and efficiency of emotion recognition through keystroke dynamics by utilizing a multi-class XGBoost model. The study addresses the limitations observed in previous models, such as Support Vector Machines and Logistic Regression, which struggled with the complex, high-dimensional nature of keystroke data. The primary objective was to develop a robust model capable of capturing the subtle variations in typing behavior associated with different emotional states. To achieve this, a comprehensive approach was adopted, involving the collection of detailed keystroke datasets, advanced feature engineering, and systematic hyperparameter tuning. The XGBoost model was chosen for its superior ability to manage complex interactions within large datasets. Through rigorous evaluation, the XGBoost model outperformed traditional models in accuracy, precision, and recall, demonstrating significant improvements in emotion classification tasks. The findings of this study reveal that XGBoost, when combined with meticulous feature engineering and hyperparameter optimization, offers a substantial advancement in the field of emotion recognition via keystroke dynamics. The research not only confirms the effectiveness of XGBoost in this domain but also provides new insights into optimizing machine learning models for emotion detection. These results have broad implications for the development of more emotionally aware computing systems, potentially improving user interaction across various applications. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Optimized Identification with Severity Factors of Gastric Cancer for Internet of Medical Things

引用

Computers, Materials & Continua 2023年第4期75卷 785-798页

作者： Kamalrulnizam Bin Abu Bakar Fatima Tul Zuhra Babangida Isyaku Fuad A.Ghaleb Faculty of Computing Universiti Teknologi MalaysiaJohor Bahru81310Malaysia Faculty of Science and Technology Shaheed Benazir Bhutto University Sanghar CampusPakistan Faculty of Computing and Information Technology Sule Lamido UniversityKafin HausaP.M.B.048Nigeria

The Internet of Medical Things (IoMT) emerges with the visionof the Wireless Body Sensor Network (WBSN) to improve the health monitoringsystems and has an enormous impact on the healthcare system forrecognizing the levels of risk/severity factors (premature diagnosis, treatment,and supervision of chronic disease i.e., cancer) via wearable/electronic healthsensor i.e., wireless endoscopic capsule. However, AI-assisted endoscopy playsa very significant role in the detection of gastric cancer. Convolutional NeuralNetwork (CNN) has been widely used to diagnose gastric cancer based onvarious feature extraction models, consequently, limiting the identificationand categorization performance in terms of cancerous stages and gradesassociated with each type of gastric cancer. This paper proposed an optimizedAI-based approach to diagnose and assess the risk factor of gastric cancerbased on its type, stage, and grade in the endoscopic images for smarthealthcare applications. The proposed method is categorized into five phasessuch as image pre-processing, Four-Dimensional (4D) image conversion,image segmentation, K-Nearest Neighbour (K-NN) classification, and multigradingand staging of image intensities. Moreover, the performance of theproposed method has experimented on two different datasets consisting ofcolor and black and white endoscopic images. The simulation results verifiedthat the proposed approach is capable of perceiving gastric cancer with 88.09%sensitivity, 95.77% specificity, and 96.55% overall accuracy respectively.

关键词： Artificial intelligence internet of things internet of medical things wireless body sensor network wireless endoscopic capsule gastric cancer

来源：评论

学校读者我要写书评

暂无评论

A Novel Mobile Application for Personalized Hair Care Using Advanced Machine Learning Techniques 6

A Novel Mobile Application for Personalized Hair Care Using ...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Kiriella, Anjali Rathnayake, Samadhi Thilakarthna, Thusithanjana Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798331517878

Recent advancements in computer vision and machine learning have enabled personalized hair care, advancing beyond traditional methods by catering to individual hair types and health. This paper presents Glowllp, a mobile application that provides personalized hair care recommendations through three primary modules: image quality assessment, hair type detection, and health prediction. The image quality assessment module employs edge detection and SVM classifiers to filter blurry images, achieving over 95% accuracy. For hair type classification, a hybrid model of Mask R-CNN and Vision Transformers (ViTs) identifies hair types with 92% accuracy. The health assessment module predicts hair loss and other conditions using Random Forest and XGBoost models with an F1 score of 0.91, while K-means clustering further tailor's recommendations. By integrating these modules, Glow Up delivers a comprehensive, user-friendly solution that enhances hair care personalization. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Optimizing User Experience in Mobile Travel Applications: A Study on Personalized Routing, Thematic Content, and Cultural Engagement 6

Optimizing User Experience in Mobile Travel Applications: A ...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Perera, Tharusha Samarahewa, Nawanjana Jinasena, Yasithri Thilakarathna, Dinuka Kasthurirathna, Dharshana Rupasinghe, Shalini Sri Lanka Institute of Information and Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798331517878

This paper presents an AI-powered personalized trip planner designed to enhance travel experiences in Sri Lanka. The platform integrates advanced machine learning techniques, including K-Nearest Neighbor (KNN) and Ant Colony Optimization (ACO), to generate customized travel itineraries that align with user preferences, budgetary considerations, and optimal seasonal factors. The system incorporates Natural Language Processing (NLP) for precise location-based promotions and synchronization with users' schedules. Furthermore, an augmented reality (AR) tour guide, developed using Unity and Vuforia, enriches tourist interaction with local heritage sites. The research also employs sentiment analysis and topic categorization to refine recommendations based on user feedback and expenditure patterns. The findings indicate that the proposed system has significant potential to enhance tourist satisfaction and contribute to sustainable tourism development in Sri Lanka. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Queue Management System for Multi-Cashier Supermarkets Using IoT and Real-Time Monitoring 6

Dynamic Queue Management System for Multi-Cashier Supermarke...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Perera, Wuwani Perera, Hiruni Perera, Hasini Suraweera, Savindee Rathnayake, Samadhi Karunathilaka, Supipi Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798331517878

Optimizing consumer satisfaction and operational efficiency in supermarkets hinges on effective queue management at cashier counters. In multi-cashier systems, customers often choose lines based on the number of people waiting, ignoring the number of items in each cart. This behavior leads to inefficient queue distribution, resulting in longer waits at counters with higher item counts and underutilized counters with fewer items, detracting from the shopping experience. This study proposes a dynamic queue management system leveraging Closed-Circuit Television (CCTV) cameras and Internet of Things (IoT) devices for real-time monitoring to enhance checkout efficiency. Our approach uses a robust object detection model, developed with PyTorch and Hugging Face Transformers, to accurately determine queue lengths and cart contents from CCTV footage, identifying and categorizing customers and cashiers. IoT sensors count the items in each customer's cart, and this data is combined with CCTV footage to calculate the optimal cashier allocation. This system dynamically assigns customers to cashier counters based on the number of customers and the complexity of their transactions, distributing the checkout load more evenly and efficiently. Processed images, including visual annotations of queue lengths and optimal cashier assignments, are uploaded to Firebase for real-time viewing and access. This technology streamlines the checkout process, enhancing customer satisfaction and optimizing queue management by reducing wait times. The results demonstrate that dynamic queue assignment and real-time item counting significantly improve operational efficiency and customer happiness. This study provides valuable insights and advances in retail queue management, offering a more efficient and customer-focused approach to supermarket operations. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A Generative Adversarial Network to Upscale the Resolution of Low-Resolution Galaxy Images 6

A Generative Adversarial Network to Upscale the Resolution o...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Hettiarachchi, Anuththara Rathnayake, Samadhi Dissanayaka, Kapila Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798331517878

High-resolution galaxy images play a crucial role in astronomy and astrophysics, enabling detailed morphological analysis, the identification of faint structures, and distance measurements. However, limitations in telescope technologies, atmospheric conditions, and the vast distances of observed objects often result in low-resolution images. In this research, we leveraged advanced deep-learning methods to enhance the resolution of low-resolution galaxy images. We introduced a Generative Adversarial Network (GAN) specifically developed to upscale galaxy images taken at suboptimal resolutions, with the Enhanced Super Resolution Generative Adversarial Network (ESRGAN) serving as the foundational model. Our self-attention multi-scale GAN architecture utilized deep learning to produce super-resolution images by learning from a dataset of high-resolution galaxy images. Additionally, we incorporated an Explainable AI technique to open the black box of our GAN model, providing insights into its intrinsic decision processes and feature learning mechanisms. This advanced approach not only enhanced image resolution but also improved model transparency and built trust in the model's predictions. Our results demonstrated a significant improvement in the Peak Signal-to-Noise Ratio and Structural Similarity Index Measure and provided a better understanding of the model's operations, which is highly important for scientific analysis and validation in astronomical research. © 2024 IEEE.

关键词： Generative adversarial 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：