检索结果-内蒙古大学图书馆

Utilizing machine learning algorithms for task allocation in distributed agile software development

Heliyon 2024年第21期10卷 e39926页

作者： Al-Fraihat, Dimah Sharrab, Yousef Al-Ghuwairi, Abdel-Rahman Alzabut, Hamza Beshara, Malik Algarni, Abdulmohsen Department of Software Engineering Faculty of Information Technology Isra University Amman 11622 Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology Isra University Amman 11622 Jordan Department of Software Engineering Faculty of Prince Al-Hussien bin Abdullah for IT The Hashemite University Zarqa 13133 Jordan Department of Computer Science King Khalid University Abha 61421 Saudi Arabia

Distributed agile software development (DASD) has become a prominent software development approach. Proper task allocation is crucial in DASD to avoid undesirable outcomes including project rejection by clients, unfavorable team attitudes, and project failure. Coordination and communication issues occur as businesses embrace the DASD environment more frequently to tap into global talent and knowledge while cutting development expenses. To overcome these challenges, efficient task allocation planning becomes a crucial success component in software project management. The purpose of this study is to utilize machine learning (ML) predictive algorithms to determine the most appropriate role for a given task, with the aim of assisting software managers in making task assignments more efficiently and effectively in DASD environment. Preprocessing steps applied to the dataset include data cleaning, normalization, and partitioning into training, validation, and test sets. Four model classifiers were used in the experiment: Random Forest, Decision Tree, K-Nearest Neighbors (K-NN), and AdaBoost. The results showed that Random Forest outperformed the other classifiers in task allocation prediction, achieving an accuracy of 96.7 %, followed by K-NN (94.2 %), Decision Tree (93.5 %), and AdaBoost (93 %). The study demonstrates that ML models are effective in tackling task allocation issues in DASD settings, and the outcomes are promising. © 2024

关键词： DASD Distributed agile software development Machine learning (ML) software engineering software project management Task allocation

来源：评论

学校读者我要写书评

暂无评论

Identification of selection criteria for blockchain platforms

Identification of selection criteria for blockchain platform...

引用

International Association of Institutes of Navigation World Congress (IAIN)

作者： Shahr Banoo Muradi Yin Kia Chiam Department of Software Engineering Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

Blockchain technology is widely used to develop software systems in different industries such as finance, healthcare, supply chain management, data management, Internet of Things (IoT). To adopt blockchain, some critical challenges such as performance, interoperability, availability, security attacks, sustainability, and latency need to be taken into consideration. If the blockchain platform selected is not appropriate, the functionality and quality of the blockchain-based systems will be affected. Additionally, numerous blockchain platforms with unique properties and specifications are available in the market, and the task of selecting the right platform that best meets the project needs is getting complicated. It is crucial to define significant criteria that can help to shortlist the blockchain platforms for further comparison and selection using multicriteria decision-making methods. This research proposes a set of selection criteria that cover both features and quality attributes of the blockchain platforms. A survey was conducted to get the opinions of blockchain practitioners on the suitability of the selection criteria for the evaluation and selection of blockchain platforms.

关键词： Supply chain management Decision making Medical services software systems Blockchains Internet of Things Security

来源：评论

学校读者我要写书评

暂无评论

A motion-based compression algorithm for resource-constrained video camera traps

arXiv

引用

arXiv 2024年

作者： Ratnayake, Malika Nisal Gallon, Lex Toosi, Adel N. Dorin, Alan Agents and Decision-Making Group Dept. of Data Science and AI Faculty of Information Technology Monash University ClaytonVIC3800 Australia Monash e-Research Centre Monash University ClaytonVIC3800 Australia School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne ParkvilleVIC3052 Australia Dept. of Software Systems and Cybersecurity Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Field-captured video facilitates detailed studies of spatio-temporal aspects of animal locomotion, decision-making and environmental interactions including predator-prey relationships and habitat utilisation. But even though data capture is cheap with mass-produced hardware, storage, processing and transmission overheads provide a hurdle to acquisition of high resolution video from field-situated edge computing devices. Efficient compression algorithms are therefore essential if monitoring is to be conducted on single-board computers in situations where such hurdles must be overcome. Animal motion tracking in the field has unique characteristics that necessitate the use of novel video compression techniques, which may be underexplored or unsuitable in other contexts. In this article, we therefore introduce a new motion analysis-based video compression algorithm specifically designed for camera traps. We implemented and tested this algorithm using a case study of insect-pollinator motion tracking on three popular edge computing platforms. The algorithm identifies and stores only image regions depicting motion relevant to pollination monitoring, reducing overall data size by an average of 87% across diverse test datasets. Our experiments demonstrate the algorithm’s capability to preserve critical information for insect behaviour analysis through both manual observation and automatic analysis of the compressed footage. The method presented in this paper enhances the applicability of low-powered computer vision edge devices to remote, in situ animal motion monitoring, and improves the efficiency of playback during behavioural analyses. Our new software, EcoMotionZip, is available Open Access. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

An Automated Tool for Student Journey Orchestration & Optimization using Machine Learning

An Automated Tool for Student Journey Orchestration & Optimi...

引用

Advancements in Computing (ICAC), International Conference on

作者： Ramanayaka D.Y Liyanagunawardana A.P E.M.T.K. Ekanayake B Weerarathna U.U Thilini Buddhika Jayasingha Thusithanjana Thilakarthna Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398106

The customer journey is a full interaction that a customer has with a business. Every touchpoint of the business is an opportunity to provide good experiences that encourage future opportunities to become customers and consumers to be committed loyal customers through the customer journey. This research paper refers to the student’s journey at university as a customer journey & considers the student’s actions to map the next suitable actions. This paper proposed a machine learning-based novel approach to recommending the suitable next best action for the students based on their past performance at university by using customer journey orchestration and optimization. Customer journey orchestration is the process of coordinating customer experiences in real-time to encourage better engagement with the systems and organization. The journey orchestration of university students is currently a manual flow. The main goal of this research is to convert the manual flow of university journey orchestration into an automated flow. The proposed system orchestrates and optimizes the student journeys at each milestone of the university by recommending the suitable path or next best action as the outcome to help students make a successful path throughout their university journey. This research contributes to achieving the educational goals and professional career goals of university students successfully. Furthermore, from the perspective of the university, this proposed system supports everything to facilitate better directions for the students to complete their studies successfully.

关键词： Machine learning algorithms Manuals Organizations Machine learning Linear programming Real-time systems Systems support

来源：评论

学校读者我要写书评

暂无评论

AD-PU: A Novel Approach for Automated Identification of the Outliers in User Interface Testing (UAT)

AD-PU: A Novel Approach for Automated Identification of the ...

引用

International Automatic Testing Conference, AUTOTESTCON

作者： S.M.N.S.K Seneviratne Victoria Penenco Dharshana Kasthurirathna Faculty of Graduate Studies and Research Sri Lanka Institute of Information Technology Sri Lanka UAT London Stock Exchange Group London Dept. of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Sri Lanka

User acceptance testing (UAT) is the process that validates the system under test (SUT) behaves according to the business requirements. A User would use the graphical user interface to interact with the underlying code. With the improvement of various devices, end-user testing has become even more complex and time consuming. Every user has a unique interaction pattern. Due to this expected test coverage would not be met by focusing only on the functionality itself. This research is to address the issue of UAT test automation coverage and reduce defect leakage in production environments. The proposed automation solution is to identify more defects in the UAT static testing phase and make the system under test more user friendly before handing the product to the consumers. The proposed solution use Machine learning approach to identify user behaviors that does not match the proposed new functionality. The proposed AD-PU model would evaluate non-prominent user behaviours as per perceived usefulness which would effect the decision to accept the functionality as user acceptable or not.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning-based Person Re-identification Across Multi-Cameras 10

A Hybrid Deep Learning-based Person Re-identification Across...

引用

10th International Conference on Digital Arts, Media and technology and 8th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications engineering, ECTI DAMT and NCON 2025

作者： Aonon, Manaschai Charoenkwan, Phasit Singkhamfu, Phudinun Kaewkamol, Porntida Chiang Mai University Data Science Consortium Faculty of Engineering Chiang Mai Thailand Chiang Mai University Modern Management and Information Technology College of Arts Media and Technology Chiang Mai Thailand Chiang Mai University Software Engineering College of Arts Media and Technology Chiang Mai Thailand

ISBN: (纸本)9798331543273

Surveillance systems play an essential role in enhancing security and ensuring safety within society. Public spaces and critical areas are commonly monitored through multi-camera networks for tracking individuals in real-time to enable quick responses to potential security threats. However, variations in lighting, camera angles, and occlusions pose significant challenges to the process of recognizing individuals across multiple camera views. This research proposes a Person Re-Identification (Re-ID) with deep learning and feature extraction method to improve the accuracy of individual matching and identification despite these challenges. This research encompasses multiple neural network topologies, such as ResNet50, ResNet101, and OSNet architectures with traditional computer vision methodologies such as Scale-Invariant Feature Transform (SIFT) to examine the body part weighting coefficients and feature selection mechanisms. The results demonstrated that integrating dimensionality reduction via principal component analysis (PCA) coupled with semantic segmentation techniques yields statistically significant improvements in re-identification accuracy. The ResNet101 architecture emerges as the superior methodology, achieving performance with a Rank-1 accuracy of 0.88 and mean Average Precision (mAP) of 0.94 on the test dataset. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Are EEG-to-Text Models Working?

arXiv

引用

arXiv 2024年

作者： Jo, Hyejeong Yang, Yiqian Han, Juhyeok Duan, Yiqun Xiong, Hui Lee, Won Hee Department of Software Convergence Kyung Hee University Korea Republic of China GrapheneX-UTS HAI Centre Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

This work critically analyzes existing models for open-vocabulary EEG-to-Text translation. We identify a crucial limitation: previous studies often employed implicit teacher-forcing during evaluation, artificially inflating performance metrics. Additionally, they lacked a critical benchmark - comparing model performance on pure noise inputs. We propose a methodology to differentiate between models that truly learn from EEG signals and those that simply memorize training data. Our analysis reveals that model performance on noise data can be comparable to that on EEG data. These findings highlight the need for stricter evaluation practices in EEG-to-Text research, emphasizing transparent reporting and rigorous benchmarking with noise inputs. This approach will lead to more reliable assessments of model capabilities and pave the way for robust EEG-to-Text communication systems. Code is available at https://***/NeuSpeech/EEG-To-Text. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning-based Person Re-identification Across Multi-Cameras

A Hybrid Deep Learning-based Person Re-identification Across...

引用

International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications engineering (ECTI-NCON)

作者： Manaschai Aonon Phasit Charoenkwan Phudinun Singkhamfu Porntida Kaewkamol Data Science Consortium Faculty of Engineering Chiang Mai University Chiang Mai Thailand Modern Management and Information Technology College of Arts Media and Technology Chiang Mai University Chiang Mai Thailand Software Engineering College of Arts Media and Technology Chiang Mai University Chiang Mai Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

关键词： Deep learning Accuracy Surveillance Computer architecture Transforms Feature extraction Cameras Security Identification of persons Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Detection Scheme of Impersonation Attack Based on Sarsa(Lambda) Algorithm in Fog Computing 22

Detection Scheme of Impersonation Attack Based on Sarsa(Lamb...

引用

Proceedings of the 2022 12th International Conference on Communication and Network Security

作者： Aiming Wu Shanshan Tu Junwei Liu Yihe Zhang Yongjie Yang Xuetao Bai Engineering Research Center of Intelligent Perception and Autonomous Control faculty of Information Technology Beijing University of Technology China China Mobile (Suzhou) Software Technology Co. Ltd. China Mobile (Suzhou) Software Technology Co. Ltd. China

ISBN: (纸本)9781450397520

Fog computing is a technology that provides distributed computing, storage and other services between cloud servers and Internet of Things(IoT) devices. It reduces the pressure on cloud servers and utilizes network edges for computing and storage, thereby improving the performance of the entire IoT system. Since fog computing uses traditional security technologies to realize the communication between fog nodes and end users, it is inevitable for fog computing to face some security threats, such as eavesdropping attacks, camouflage attacks and other security threats. Aiming at this problem, this paper proposes a impersonation attack detection scheme based on Sarsa(lambda) algorithm. The scheme first builds a camouflage attack model and a key generation model based on physical layer security technology, then performs hypothesis testing at the receiving end to verify the legitimacy of the training signal, and then obtains the optimal threshold through the proposed algorithm. The optimal threshold realizes the terminal communication security between user nodes and fog nodes. The experimental results show that the algorithm can effectively detect camouflage attacks in a dynamic fog computing environment and have a low average detection error rate. When , AER decreased to 0.4925.

关键词： Fog Computing Sarsa Impersonation Attack Physical Layer Security Hypothesis Testing

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Offloading for Anti-jamming in Fog Computing Networks 22

Deep Reinforcement Learning-Based Computation Offloading for...

引用

Proceedings of the 2022 12th International Conference on Communication and Network Security

作者： Yongjie Yang Shanshan Tu Haishuang Yan Yihe Zhang Aiming Wu Xuetao Bai Engineering Research Center of Intelligent Perception and Autonomous Control faculty of Information Technology Beijing University of Technology China China Mobile (Suzhou) Software Technology Co. Ltd. China Mobile (Suzhou) Software Technology Co. Ltd. China

ISBN: (纸本)9781450397520

With the rapid development of IoT and fog computing, mobile devices can offload computing tasks into the fog layer to reduce energy consumption and transmission delay. However, the communication between fog nodes and end users is vulnerable to malicious jamming attacks. In this paper, we propose a reinforcement learning-based computation offloading strategy to choose fog nodes, offloading rate, and transmit power to address jamming attacks and interference problems. We use dueling deep Q-network to accelerate the learning speed in the system, which can effectively determine the offloading strategy. The simulation results show that this scheme based on DDQN is better than DQN and Q-learning in terms of computational latency and energy consumption.

关键词： Dueling deep Q-network Fog computing Computation offloading Anti-jamming

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：