检索结果-内蒙古大学图书馆

7th EAI International Conference on Innovations and Interdisciplinary Solutions for Underserved Areas, InterSol 2024

作者： Arinaitwe, Irene Jonathan, Ssemakula Nakakawa, Agnes Maiga, Gilbert School of Computing and Informatics Technology Makerere University Kampala Uganda

ISBN: (纸本)9783031864926

Effective waste management relies on active public participation, yet engaging citizens in sustainable waste management remains a challenge. This study introduces a novel approach by developing a mobile application to support public involvement in waste management processes. Drawing upon the Persuasive Systems Design (PSD) framework, the application incorporates persuasive strategies to motivate users to adopt responsible waste handling behaviors. The developed mobile application features a set of functionalities aimed at facilitating user engagement and behavior change. These include a leaderboard to foster competition and motivation among users, a chat room for community interaction, a sorting guide for proper waste categorization, and a module for locating nearby waste collectors, thereby promoting accessibility. To assess the effectiveness and user satisfaction of the application, a structured walkthrough evaluation method was employed, complemented by questionnaire items based on the Attention, Relevance, Confidence, and Satisfaction (ARCS) model. Through this evaluation process, the study measured users’ attention to the application’s features, the relevance of its content to their needs, their confidence in using the application, and their overall satisfaction with the experience. The findings of the evaluation demonstrate the potential of the mobile application in effectively engaging users and promoting positive changes in waste management behaviors. © ICST Institute for Computer Sciences, Social informatics and Telecommunications Engineering 2025.

关键词： Municipal solid waste

来源：评论

学校读者我要写书评

暂无评论

An Examination of Harmonizing Multi-Vendor Cardiac MRI Data for Vendor-Neutral Image Segmentation 5

An Examination of Harmonizing Multi-Vendor Cardiac MRI Data ...

引用

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

作者： Mohideen, Hamdaan Ayoob, Mohamed Nettasinghe, Oshan Sylvester, Vithushan Bowala, Helmini Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331530983

Vendor-specific scanner hardware, software, and image acquisition protocols can introduce systematic biases into MRI scans. This introduces non-biological artifacts which introduce variations across MRI images from different vendors. Further, we ratified such non-biological variances by conducting a discrepancy study on the MnMs-2 Cardiac MRI dataset. Data harmonization is the process of combining datasets from different sources while removing unwanted variations that are not caused by biological differences. This is important because it allows researchers to increase the understanding of biological differences in data, while mitigating vendor-specific biases. We used a domain adaptation methodology (which is a data harmonization method) on the dataset to unlearn domain (or vendor) specific biases by introducing a confusion loss to confuse the encoder. Furthermore, we introduced a 3D segmentation model to this method to capture spatial information. This method demonstrates the performance on the main task (segmentation) and compares the domain predictor, before and after unlearning. This shows the magnitude of mitigating vendor-specific biases of the model. In addition to the model architecture performance, we documented the discrepancy study between inter-vendor model performance to demonstrate the magnitude of impact in which vendor-specific, and non-biological variations of MRI scans can affect the model. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

FlexiSecure - AI-Powered Fraud Detection with Real-Time Alerts and Customizable Security 5

FlexiSecure - AI-Powered Fraud Detection with Real-Time Aler...

引用

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

作者： Mumthas, Nooha Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331530983

The rapid expansion of online financial transactions has escalated the risk of fraud, posing significant challenges for banks and financial institutions, particularly in Sri Lanka. Traditional rule-based fraud detection systems often find it challenging to balance speed and accuracy, rendering them less effective against advanced and evolving fraud schemes. This study proposes a hybrid machine learning model combining decision trees and neural networks to enhance fraud detection performance. The model incorporates advanced preprocessing techniques, including feature scaling and outlier detection, to improve data quality. It employs supervised learning to achieve high accuracy and adapt to emerging fraud patterns. Additionally, explainable AI (XAI) is incorporated to ensure transparency in detection outcomes, where the user would be entrusted to make the final decision on the transaction, thereby fostering user trust and compliance with regulations in the financial sector. The model is designed to process large volumes of transactions efficiently, which demonstrates its scalability and suitability for high-volume banking environments. © 2025 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Music: A Review of Artificial Intelligence in Jazz Reharmonization 5

Transforming Music: A Review of Artificial Intelligence in J...

引用

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

作者： Jayasinghe, Sachindu Bhareti, Kushan Institute of Technology School of Computing Informatics Colombo Sri Lanka

ISBN: (纸本)9798331530983

Jazz reharmonization is a complex musical technique that improves harmonic frameworks by inventive chord progressions, augmenting the depth and emotional resonance of pieces. This paper examines the use of artificial intelligence, namely transformer networks, in the automation of jazz reharmonization, ensuring melodic coherence and artistic fidelity. This review compiles current research to highlight essential approaches, including early rule-based systems, neural networks, and advanced transformer models while emphasizing their benefits and limits. Particular emphasis is placed on the difficulties associated with dataset preparation, assessment measures, and the adaptation of AI systems to the intricacies of jazz harmony. The evaluation, via a critical examination of previous studies, identifies areas for enhancement, including real-time applications, multi-modal data integration, and cross-genre adaptation. The insights provided seek to direct future research and position transformers as a revolutionary instrument in computational musicology. This document is an extensive reference for scholars and professionals investigating the convergence of artificial intelligence and jazz music. © 2025 IEEE.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

A Robust Resource-Aware Framework for YOLO-Based Object Detection in Dynamic and Multi-Platform Resource-Constrained Environments

引用

IEEE Access 2025年 13卷 79977-79995页

作者： Shiddiqi, Ary Mazharuddin Navastara, Dini Adni Studiawan, Hudan Romadhona, Yasinta Azhar, Muhammad Fath Mushaffa Rahma, Fayruz Bramantoro, Arif Alzahrani, Ahmad A. Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Department of Informatics Surabaya60111 Indonesia Informatics Study Program Telkom University Surabaya Campus Surabaya60231 Indonesia Universitas Islam Indonesia Department of Informatics Yogyakarta55584 Indonesia Universiti Teknologi Brunei School of Computing and Informatics Bandar Seri BegawanBE1410 Brunei King Abdulaziz University Faculty of Computing and Information Technology Jeddah21589 Saudi Arabia

Efficient management of resources such as CPU, RAM, and disk storage is a critical challenge for object detection systems that rely on multi-camera video streaming, especially for resource-constrained devices. These constraints frequently result in the risk of overheating and potential system failure during high workloads. This paper presents a novel Resource-Aware Framework (RA-Framework), designed to optimize resource allocation using dynamic adaptation mechanisms. The RA-Framework dynamically manages CPU, RAM, and disk storage resources for YOLO-based object detection, supporting multiple camera streams and scheduling mechanisms. The framework was implemented in resource-constrained environments using various YOLO models with single and dual-camera setups. Experimental results showed that the RA-Framework successfully reduced average CPU usage by up to 68.62%, decreased RAM consumption by approximately 13.47%, and extended the time for disk usage to increase by 1% by more than 500% in specific scenarios. In contrast, systems without the RA-Framework experienced higher resource utilization and greater susceptibility to resource scarcity or even overheating. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Systematic Review of Fine-tuning Approaches for Large Language Models in the Context of Sinhala 5

Systematic Review of Fine-tuning Approaches for Large Langua...

引用

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

作者： Hansaka, Sachin Sumanathilaka, Deshan Informatics Institute of Technology School of Computing Colombo006 Sri Lanka

ISBN: (纸本)9798331530983

The rapid development of large language models (LLMs) such as GPT-3, GPT-4, LlaMA, and mBERT has significantly advanced the natural language processing (NLP) field across many widely spoken languages. However, the effectiveness of these LLMs on low-resource languages such as Sinhala remained unexplored. With the scarcity of high-quality data and linguistic resources, fine-tuning LLMs in Sinhala has gained significant challenges. With a focus on Sinhala specifically, this systematic review addresses the methodologies and outcomes of adapting large language models for underrepresented languages. The purpose of this review is to synthesize existing research, identify effective strategies, contributions, and improvements, and highlight the challenges and opportunities in this domain. By analyzing various approaches, including data augmentation, transfer learning, cross-lingual transfer, parameter-efficient fine-tuning, adapter tuning, and model adaptation likewise, this review provides a comprehensive and precise idea of the current state of LLM fine-tuning on low-resource languages like Sinhala. The results highlight the importance of using creative methods and collaboration to improve LLM performance and usefulness in linguistic environments with limited resources. © 2025 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

SSL400 - A Comprehensive Word Level Dataset for Sinhala Sign Language Recognition 5

SSL400 - A Comprehensive Word Level Dataset for Sinhala Sign...

引用

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

作者： Abhishek, Yohan Sumanathilaka, T.G.D.K. Informatics Institute of Technology School of Computing Colombo006 Sri Lanka

ISBN: (纸本)9798331530983

In the context of increasing digital accessibility and the need for inclusive communication technologies, the demand for automated sign language recognition has grown significantly. However, Sinhala Sign Language (SSL), used by the Sri Lankan deaf community, remains underexplored due to the lack of labelled datasets and the challenges of developing recognition models for low-resource languages. This study addresses this gap by introducing an SSL dataset, specifically curated to support real-time recognition of 384 commonly used words in daily and work-related contexts. The methodology for dataset creation involved expert consultations, a structured data collection process, and multi-step labelling. These steps ensured the accurate labeling of video data, which can be used for machine learning tasks like gesture recognition, sentence formation, and speech translation. The proposed dataset lays the foundation for SSL recognition models that are fast, lightweight, and optimized for low-resource environments. Additionally, we explore the performance of initial recognition models using this dataset, demonstrating its applicability in real-world scenarios. The dataset and research outcomes provide valuable resources for the development of inclusive AI-driven communication tools for the Sinhala-speaking deaf community. This contribution addresses the pressing need for better technological support for underrepresented languages in the field of sign language recognition and processing. © 2025 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pricing Models in E-Commerce: Exploring Machine Learning Techniques to Balance Profitability and Customer Satisfaction

引用

IEEE Access 2025年 13卷 72994-73002页

作者： Guo, Xiaochen Zhang, Lei Anhui Business and Technology College Management School Hefei230041 China Anhui Business and Technology College School of Information Engineering Hefei230041 China Universiti Teknologi MARA College of Computing Informatics and Mathematics Selangor Shah Alam40450 Malaysia

This research investigates the application of Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTM) networks, paired with gradient-based optimization techniques for dynamic pricing in e-commerce. The primary objective is to develop a pricing model that effectively balances profitability with customer satisfaction by leveraging sequential data, such as time-series and customer behavior patterns. The approach utilizes LSTM’s ability to capture long-term dependencies in sequential data, while optimization methods like Stochastic Gradient Descent (SGD) enhance model convergence and performance. Key findings include the superior predictive accuracy of LSTM-based models over traditional approaches like Linear Regression and Decision Trees, particularly in real-time data updates and price elasticity scenarios. Additionally, the analysis revealed that LSTM models could efficiently adapt pricing strategies in response to market dynamics, significantly improving profitability while maintaining customer satisfaction. This study provides valuable insights into the application of advanced machine learning techniques in e-commerce pricing. The results suggest that LSTM-based dynamic pricing models could optimize revenue generation, offering substantial implications for pricing strategy development in modern retail environments. Future work may explore hybrid models and multi-objective optimization techniques to further refine these models. © 2013 IEEE.

关键词： User experience

来源：评论

学校读者我要写书评

暂无评论

Arthropodia-V1: Biodiversity Dataset for Semantic Segmentation, Quality Estimation, and Observation Extraction 5

Arthropodia-V1: Biodiversity Dataset for Semantic Segmentati...

引用

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

作者： Ayoob, Mohamed Maul, Tomas Chandesa, Tissa Informatics Institute of Technology School of Computing Colombo Sri Lanka The University of Nottingham Malaysia School of Computer Science Semenyih Malaysia

ISBN: (纸本)9798331530983

This paper introduces a novel biodiversity image dataset named Arthropodia, which focuses on three crucial tasks: image quality estimation, semantic segmentation, and observation extraction (image similarity). Arthropodia is collected from tropical Malaysian forests and encompasses a diverse range of arthropod species captured under various lighting and environmental conditions. We manually annotate the dataset for each task, making it suitable for benchmarking and developing AI models applicable to biodiversity and environmental monitoring. To demonstrate its utility, we present baseline results using state-of-the-art deep learning models for each task. Our findings indicate that Arthropodia serves as a valuable resource for advancing research in the field of biodiversity conservation and ecological studies through automated image processing and analysis. The open-access availability of Arthropodia fosters further contributions from the research community, paving the way for the development of robust and accurate AI solutions for biodiversity monitoring and preservation. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An enhanced LSTM method for financial market forecasting 2

An enhanced LSTM method for financial market forecasting

引用

2nd International Conference on Big Data, Computational Intelligence, and Applications, BDCIA 2024

作者： Sun, Yu Mutalib, Sofianita Guangdong University of Science and Technology Guangdong Dongguan523083 China School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam40450 Malaysia

ISBN: (纸本)9781510689053

To effectively enhance the prediction accuracy of financial time series and improve the interpretability of the structural parameters of the prediction model, this paper proposes a long short-term memory (LSTM) stock price prediction model optimized in two stages based on Bayesian and Particle Swarm Optimization (BPSO-LSTM). This model represents an innovative advancement of the traditional LSTM framework, specifically designed to address complex nonlinear problems characterized by long-term dependencies, particularly in stock indices. Initially, the Bayesian algorithm is employed to optimize the core parameters of the LSTM model, establishing a foundation for subsequent Particle Swarm Optimization. Following this, an adaptive particle swarm algorithm is utilized to further refine the core parameters obtained through Bayesian Optimization, ensuring a high degree of compatibility between the characteristics of stock data and the network topology, thereby significantly improving the prediction accuracy of stock prices. Results from the prediction of the S&P 500 and Hang Seng Index indicate that the two-stage BPSO-LSTM model not only enhances prediction accuracy but also demonstrates strong universal applicability. © 2025 SPIE.

关键词： Particle swarm optimization (PSO)

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：