检索结果-内蒙古大学图书馆

Solving Sparse Reward Tasks Using Self-Balancing Exploration and Exploitation

Journal of Internet Technology 2025年第3期26卷 293-301页

作者： Kong, Yan Wei, Junfeng Hsia, Chih-Hsien School of Computer and Software Nanjing University of Information Science and Technology China Department of Computer Science and Information Engineering National Ilan University Taiwan Department of Business Administration Chaoyang University of Technology Taiwan

A core challenge in applying deep reinforcement learning (DRL) to real-world tasks is the sparse reward problem, and shaping reward has been one effective method to solve it. However, due to the enormous state space and sparse rewards in the real world, a large number of useless samples may be generated, leading to reduced sample efficiency and potential local optima. To address this issue, this study proposes a self-balancing method of exploration and development to solve the issue of sparse rewards. Firstly, we shape the reward function according to the evaluated progress, to guide the agent’s learning of high-reward samples. Secondly, we construct a dual-trajectory exploration network, which provides intrinsic rewards based on the novelty of states and the trajectory difference of sibling agents to encourage the agent to explore and adjust the balance between exploration and exploitation. This method effectively prevents the generation of a large amount of useless training data during the interaction between the agent and the environment, resolves local optimal dilemmas through state novelty, and adjusts the strategy in a timely manner to solve sparse reward tasks. Our method outperforms basic reinforcement learning (RL) and curiosity-driven incentives in these experimental tasks. The self-balancing exploration and exploitation approach in our research provides a new perspective and effective solution for addressing the problem of sparse rewards, thereby advancing the application of DRL in real-world problems and achieving greater success. © 2025 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Domination based graph neural networks

引用

International Journal of computers and Applications 2024年第11期46卷 998-1005页

作者： Meybodi, Mohsen Alambardar Safari, Mahdi Davoodijam, Ensieh Department of Applied Mathematics and Computer Science Faculty of Mathematics and Statistics University of Isfahan Isfahan Iran Department of Software Engineering University of Kashan Kashan Iran

Graph Neural Networks (GNNs) have emerged as a widely used and effective method across various domains for learning from graph data. Despite the abundance of GNN variants, many struggle with effectively propagating messages over long distances. This paper introduces a novel hierarchical message passing framework for graph learning, specifically designed to address the challenge of long-distance message propagation in graphs. By constructing smaller graphs from the main graph using the concept of domination, a fundamental principle in graph theory, we facilitate more efficient message passing within each subgraph. Subsequently, we employ a Graph Attention Network (GAT) to aggregate these features and propagate them to distant nodes across the graph. Experimental results on standard node classification datasets validate that the proposed architecture achieves performance comparable to or better than conventional GNNs. Additionally, our model consistently performs better on graphs with missing edges. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Comparative Performance Analysis of Ethereum and Optimism Smart Contracts in Health Insurance 9

Comparative Performance Analysis of Ethereum and Optimism Sm...

引用

9th International Conference on computer Science and engineering, UBMK 2024

作者： Dedetürk, Beyhan Adanur Dedetürk, Bilge Kagan Abdullah Gul University Department of Computer Engineering Kayseri Turkey Erciyes University Department of Software Engineering Kayseri Turkey

ISBN: (纸本)9798350365887

One type of insurance that people purchase to cover unexpected medical expenses is health insurance. In exchange for premium payments, the insurance company may cover a portion of the insured person's medical expenses, such as prescription medications, hospital stays, and doctor visits. This method makes access to healthcare easier and less expensive. Health insurance systems do, however, have a number of issues, including fair insurance premium calculation, automation, data verification, privacy and security, and cost effectiveness. These issues are starting to be addressed by blockchain technology, particularly with the help of smart contracts. Using a comparison analysis between Ethereum and Optimism smart contracts, this paper demonstrates the performance of health insurance. Simulation of these BC technologies was carried out both on the Sepolia testnet and using Alchemy. Tools and metrics provided to monitor the performance of Alchemy applications, detect errors, and analyze user interactions were used in the measurements. While Ethereum's well-established ecosystem offers robust support for smart contracts, Optimism distinguishes itself as a scalable substitute that delivers quicker transaction speeds and more affordable options. According to the analysis results, the advantages and disadvantages of Ethereum and Optimism are highlighted when it comes to health insurance. © 2024 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Comparison of Geographically Weighted Regression (GWR) and Mixed Geographically Weighted Regression (MGWR) Models on the Poverty Levels in Central Java in 2023

引用

IAENG International Journal of Applied Mathematics 2024年第12期54卷 2746-2757页

作者： Alya, Najma Attaqiya Almaulidiyah, Qothrotunnidha Farouk, Bailey Reshad Rantini, Dwi Ramadan, Arip Othman, Fazidah Engineering Department Data Science Technology Study Program Universitas Airlangga Indonesia Engineering Department Data Science Technology Study Program Faculty of Advanced Technology and Multi-discipline Universitas Airlangga Indonesia Information System Study Program Department of Industrial and System Engineering Telkom University Surabaya Campus Indonesia Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Malaysia

Poverty is considered a serious global issue that must be immediately eradicated by Sustainable Development Goals (SDGs) 1, namely ending poverty anywhere and in any form. As a developing country, poverty is a complex issue faced by Indonesia. Tackling poverty in Indonesia has become a key focus of the government’s strategic priorities. This issue of poverty is experienced by all provinces in Indonesia, including Central Java. The poverty rate in Central Java stands at 10.77% or 3.79 million people. The causes of poverty are explained by several factors. Using these various factors, a mapping model can be conducted to determine the number of poor populations in Central Java. This research employs Geographically Weighted Regression (GWR) and Mixed Geographically Weighted Regression (MGWR) approaches to compare the effectiveness of these models in analyzing the number of poor populations in Central Java in 2023. The kernel function weighting used in this study is Fixed Gaussian. The results showed that the MGWR model outperformed both the OLS regression and GWR models, achieving an Akaike Information Criterion (AIC) of 62.766, an R2 of 82.3%, and a Mean Squared Error (MSE) of 0.177. Consequently, it can be inferred that the MGWR model was more suitable for explaining the poverty levels in Central Java. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Ethical Aspects of ChatGPT in software engineering Research

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 254-267页

作者： Akbar, Muhammad Azeem Khan, Arif Ali Liang, Peng Lappeenranta-Lahti University of Technology Software Engineering Department Lappeenranta15210 Finland University of Oulu M3S Empirical Software Engineering Research Unit Oulu90014 Finland Wuhan University School of Computer Science Wuhan430072 China

ChatGPT can improve software engineering (SE) research practices by offering efficient, accessible information analysis, and synthesis based on natural language interactions. However, ChatGPT could bring ethical challenges, encompassing plagiarism, privacy, data security, and the risk of generating biased or potentially detrimental data. This research aims to fill the given gap by elaborating on the key elements: motivators, demotivators, and ethical principles of using ChatGPT in SE research. To achieve this objective, we conducted a literature survey, identified the mentioned elements, and presented their relationships by developing a taxonomy. Furthermore, the identified literature-based elements (motivators, demotivators, and ethical principles) were empirically evaluated by conducting a comprehensive questionnaire-based survey involving SE researchers. In addition, we employed an interpretive structure modeling approach to analyze the relationships between the ethical principles of using ChatGPT in SE research and develop a level-based decision model. We further conducted a cross-impact matrix multiplication applied to classification analysis to create a cluster-based decision model. These models aim to help SE researchers devise effective strategies for ethically integrating ChatGPT into SE research by following the identified principles by adopting the motivators and addressing the demotivators. The findings of this study will establish a benchmark for incorporating ChatGPT services in SE research with an emphasis on ethical considerations. © 2020 IEEE.

关键词： software engineering

来源：评论

学校读者我要写书评

暂无评论

Review on Image Processing for MRI-Focused Brain Tumor Identification Using Machine Learning 7

Review on Image Processing for MRI-Focused Brain Tumor Ident...

引用

7th Edition Global Conference on Wireless and Optical Technologies, GCWOT 2024

作者： Agha, Dur-E-Shawar Qazi, Farheen Rasheed, Rohail Ali Khan, M. Sadiq Naseem, Muhammad Mubeen, Tauseef Sir Syed University of Engineering & Technology Software Engineering Department Karachi Pakistan Computer Science Department Karachi Pakistan

ISBN: (纸本)9798331534271

Today, image processing plays a significant role in early disease detection, allowing doctors to treat conditions like breast, lung, and brain malignancies. A brain tumor is a serious condition that can be fatal. Brain tumor diagnosis is the most important task for early therapy, and automatic visual classification might be extremely important. It is essential to classify brain cancers in order to assess the tumor's and determine the best course of treatment for each class. To find brain tumors, numerous imaging modalities are used. However, MRI is frequently utilized since it produces superior images and uses no ionizing radiation. This research aims to provide a review of different Machine Learning (ML) techniques for detection and classification of brain tumor. Also, different feature extraction techniques are analyzed and their benefits are discussed. This review is conducted by different research papers which helps new researchers to start immediately a literature review and knowing different machine learning techniques their advantages and disadvantages to classify brain tumor through MRI. Also, they know the accuracy of each algorithm which leads them to directly target the problem not implementing the existing techniques. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Phishing Attacks Detection Using Multiple Datasets

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第5期17卷 71-83页

作者： Aljammal, Ashraf H. taamneh, Salah Qawasmeh, Ahmad Salameh, Hani Bani Department of Computer Science and Applications The Hashemite University Zarqa Jordan Department of Software Engineering The Hashemite University Zarqa Jordan

Nowadays, individuals and organizations are increasingly targeted by phishing attacks, so an accurate phishing detection system is required. Therefore, many phishing detection techniques have been proposed as well as phishing datasets have been collected. In this paper, three datasets have been used to train and test machine learning classifiers. The datasets have been archived by Phish-Tank and UCI Machine Learning Repository. Furthermore, Information Gain algorithm have been used for features reduction and selection purpose. In addition, six machine learning classifiers have been evaluated, namely NaiveBayes, ANN, DecisionStump, KNN, J48 and RandomForest. However, the classifiers have been trained and tested over the three datasets in two stages. The first stage is using all features included in each dataset while the second stage using selected features by IG algorithm. At the first stage RandomForest classifier has shown the best performance over Dataset-1 and Dataset-2, while J48 has shown the best performance over Dataset-3. On the other hand, after features selection, the RandomForest classifier was the superior among the other five classifiers over Dataset-1 and Dataset-2 with accuracy of 98% and 93.66% respectively. While ANN classifier has shown the best performance with accuracy of 88.92% over Dataset-3. Because of the few number of instances as well as features in Dataset-3 comparing to the other two dataset;the performance of the classifiers has been affected © 2023, International Journal of Interactive Mobile *** Rights Reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Test-Driven Development (TDD) in Small software Development Teams: Advantages and Challenges 5

Test-Driven Development (TDD) in Small Software Development ...

引用

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

作者： Ramzan, Hafiz Arslan Ramzan, Sadia Kalsum, Tehmina Institute of Computer and Software Engineering Khwaja Fareed University of Engineering and Information Technology Rahim Yar Khan Pakistan National University of Modern Languages Department of Computer Science Multan Pakistan University of Engineering and Technology Department of Software Engineering Taxila Pakistan

ISBN: (纸本)9798350394764

In the context of small software development teams, this research article gives a thorough investigation of the adoption of test-driven development (TDD) approaches. It aims to highlight the benefits that TDD offers, such as improved code quality through modularization and proactive defect spotting which results in effective debugging and development processes. It also discusses the complex issues that arise when TDD is implemented in smaller teams, such as the learning curve and resource constraints. This study significantly advances the understanding of how TDD can be used to optimize software development techniques in organizations or software houses having small development teams. It also explores the possible advantages and challenges. © 2024 IEEE.

关键词： Modular construction

来源：评论

学校读者我要写书评

暂无评论

Prediction of the Most Common Symptoms in Psychological Illnesses with Language Representation Models 10

Prediction of the Most Common Symptoms in Psychological Illn...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Aygun, Irfan Kaya, Mehmet Celal Bayar University Department of Software Engineering Manisa Turkey Firat University Department of Computer Engineering Elaziǧ Turkey

ISBN: (纸本)9798350363104

It is a known fact as a result of researches that psychological disorders are seen more frequently in society day by day and early diagnosis of these disorders is very important. To detect psychological disorders, it is an important achievement to identify the symptoms in the sentences of potential patients. In the present study, the most frequently used symptoms in the sentences of past psychiatric patients were investigated. The deep learning supported BERT model was used to analyze the texts and the Named Entity Recognition (NER) method was used for symptom detection. Thus, a model is proposed that enables the detection of symptoms even when they are expressed in different ways. The success of the proposed model in detecting the symptoms is between 83.6 and 86.2% and the most common symptoms are shortness of breath, loss of attention and loss of appetite. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation with U-Net for Breast Cancer and Lump Type Prediction

Medical Image Segmentation with U-Net for Breast Cancer and ...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Aygün, Elif Nur Kaya, Mehmet Celal Bayar University Department of Software Engineering Manisa Turkey Firat University Department of Computer Engineering Elaziǧ Turkey

ISBN: (纸本)9798350369106

Today, it is known that, like other types of cancer, breast cancer cases are increasing every year. It is an indisputable fact that early diagnosis and correct diagnosis, which medical literature pays particular attention to, have positive effects on patient health in this field. Therefore, it is a great necessity to identify breast cancer cases correctly and not to confuse malignant masses with benign masses. At this stage, a study was carried out to support the physician's decision, and segmentation was carried out on images containing potential breast cancer with the U-Net model. In addition, a two-class classification model is proposed to determine whether ultrasound images containing masses are benign or malignant. While the detection rate of the current model for benign masses is 99.9%, it reaches 86.6% for malignant masses. In addition, various data augmentation techniques were used hybridly to increase malignant mass images containing fewer samples, and the overall prediction success was increased to 91.13%. © 2024 IEEE.

关键词： Lung cancer

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：