检索结果-内蒙古大学图书馆

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Mokgethi, Chandapiwa Sigwele, Tshiamo Selvaraj, Rajalakshmi Department of Computing and Informatics Palapye Botswana

ISBN: (纸本)9798331518981

The proliferation of computationally intensive mobile applications like Augmented Reality (AR), Speech Recognition, and Mobile Gaming has led to an alarming rise in mobile energy consumption, raising the need for frequent recharging of mobile devices. This frequent recharging leads to degradation of mobile device's battery health resulting in reduced battery capacity, shorter usage cycles, and ultimately increased costs associated with battery replacements. The current mobile energy optimization frameworks are unable to effectively handle the dynamic and realtime nature of mobile environments with unpredictable variables. This research proposes a Deep Reinforcement Learning (DRL) model to optimize energy efficiency in mobile devices using Mobile Edge computing (MEC) to handle varying workloads and dynamic environment while maintaining Quality of Service (QoS) where computationally intensive applications are optimally offloaded to edge cloud servers. The result shows that the proposed outperforms current works by reducing energy consumption and average latency by 27.5% and 35% respectively. © 2024 IEEE.

关键词： Mobile edge computing

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

A Gap Analysis On Blockchain Frameworks For Managing Academic Transcripts 4

A Gap Analysis On Blockchain Frameworks For Managing Academi...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Bayani, Pelontle Sigwele, Tshiamo Kuthadi, Venumadhav Department of Computing and Informatics Palapye Botswana

ISBN: (纸本)9798331518981

Academic transcript systems have traditionally been managed independently by educational institutions, leading to challenges in interoperability, security, and data integrity. Blockchain technology, characterized by decentralization, immutability, and transparency, presents a promising solution to these issues. The introduction of blockchain technology offers a transformative approach to managing academic transcripts, providing a unified, secure, and transparent platform. This literature review examines current blockchain based academic transcript frameworks then critically and graphically analyses them based on the identified research objectives and gaps. The review's critical analysis resulted in significant trends, patterns and insights as follows. The current research's major objectives and their adoption percentages are enhancing security (33%), improving scalability (27%), ensuring transparency (23%) and addressing interoperability (17%). The major gaps identified are lack of interoperability (42%), security issues (42%) and high cost (11%) and others. Based on these insights, this work recommends current researchers to concentrate more on enhancing security and interoperability in academic transcript frameworks. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

The Integration of Deep Learning Techniques and Big Data Analytics for Improved Breast Cancer Diagnosis and Treatment: A Systematic Review

The Integration of Deep Learning Techniques and Big Data Ana...

引用

2024 International Conference on Information and Communication Technology for Development for Africa, ICT4DA 2024

作者： Gebre, Hambisa Mitiku Wegari, Getachew Mamo Jimma University Faculty of Computing and Informatics Department of Information Science Jimma Ethiopia Jimma University Faculty of Computing and Informatics Department of Information Technology Jimma Ethiopia

ISBN: (纸本)9798331527792

Background:- Breast cancer is one of the most common and lethal diseases in the world. Traditional breast cancer diagnostic and prognosis procedures usually involve significant human talent and can be time-consuming and subjective, leading to potential errors and treatment delays. Two recent technical advancements, deep learning, and big data analytics are promising to improve breast cancer diagnosis and therapy. As a result, this systematic review aims to examine specific papers that describe deep learning techniques and big data analytics in the context of breast cancer diagnosis and ***: Using Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), peer-reviewed articles published in the English language from January 2020 to August 2023 were selected from electronic databases such as PubMed, ACM, Digital Library, and Science Direct, as well as citations and manual searches. This review paper takes into account papers about deep learning algorithms, big data analytics, the efficacy of deep learning and big data analytics, as well as the problems and limitations of merging deep learning methods with big data analytics. Articles that were not original or in English were not ***: - Ten articles were identified for this review. The finding showed that deep-learning techniques play a great role in analyzing vast datasets to identify malignant cells or tumors, aiding radiologists in accurate diagnoses and improving patient outcomes. Big data analytics in breast cancer diagnosis and treatment can improve accuracy, efficiency, and patient-centered care. Deep learning techniques are utilized with big data, enhancing screening test accuracy and guiding diagnostic procedures, especially for image-based scanning that leads to early breast cancer identification, improving patient outcomes, and potentially enhancing diagnostics. Obtaining huge volumes of high-quality data for training deep learning models is a challenge and limita

关键词： big data analytics breast cancer diagnosis and treatment Deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

DiabetCare - A Classifier based Mobile Application for Predicting the Risk of Prediabetes Mellitus, Gestational Diabetes Mellitus and Type 2 Diabetes Mellitus

DiabetCare - A Classifier based Mobile Application for Predi...

引用

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

作者： Pathiranage, Nirmani Jayaprabha Asanka Sanjaya Suraweera, S.M.D. Informatics Institute of Technology Department of Computing Colombo Sri Lanka

ISBN: (纸本)9798350375688

Diabetes mellitus, commonly referred to as diabetes, poses a significant global public health challenge. According to the International Diabetes Federation, the number of people affected by this condition is projected to rise from 415 million to 642 million by 2040. This chronic ailment disrupts the body's ability to absorb glucose, making early risk prediction essential for diagnosis and prevention. This research aims to introduce an innovative AI-driven method for early risk assessment of three distinct types of diabetes. Utilizing medical data from the University of Kelaniya, two different ensemble learning techniques are implemented. These predictions will be accessible through an automated mobile application named "DiabetCare,"enabling risk evaluation irrespective of age. The objective is to identify and manage diabetes in its early stages, thereby reducing potential future complications. The experimentation process encompassed the training of 12 machine learning base classifiers and three ensemble techniques for each component. Optimal parameters for each algorithm were determined using the random search cv hyper-parameter tuning method. Ultimately, the most effective base and ensemble models, based on evaluation metrics, were chosen for integration into the final product. In terms of predicting the risk of type 2 diabetes or prediabetes, the Random Forest classifier achieved perfect training accuracy (1.0000), a testing accuracy of 0.8715, an AUC-ROC score of 0.9811, and a Cohen's Kappa of 0.8037. For forecasting the risk of gestational diabetes, the Stacking classifier attained a perfect training accuracy (1.0000), a testing accuracy of 0.9650, an AUC-ROC score of 0.9963, and a Cohen's Kappa of 0.9288. The implementation of such a system holds immense potential within the field of diabetes medicine and can serve as a valuable validation tool for medical experts. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review for Facilitating Authentication for the Disabled 20

A Systematic Literature Review for Facilitating Authenticati...

引用

20th IEEE International Conference on e-Business Engineering, ICEBE 2024

作者： Cropley, David Whittington, Paul Dogan, Huseyin Bournemouth University Department of Computing and Informatics Poole United Kingdom

ISBN: (纸本)9798350365856

In the modern world today, many online services require user authentication of some kind to log in to access its features, be it social media, banking, work or entertainment. For most people, the process of completing this task is straightforward, even if occasionally challenging or time consuming. However, disabled people can face additional challenges;whether through not being able to complete a verification due to lack of speed in responding, lack of necessary information provided to them or from security vulnerabilities that become exposed because of the nature of their disability. This paper aims to address these issues with a potential solution that provides a usable system for a disabled person to be able to access services easily without compromising on security. By way of a systematic literature review, this paper reinforces the need for such a system by highlighting fundamental shortfalls, and areas where advancements can occur and thereby advocating firm business incentives for doing so. Part of this review involved research for a proposed system architecture which illustrates how an authentication system can operate for disabled people while retaining both usability and security, along with a supporting business perspective to provide a sustainable lifecycle for the system. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Classification of Privacy Preserved Medical Data with Fractional Tuna Sailfish Optimization Based Deep Residual Network in Cloud

引用

Annals of Data Science 2025年第3期12卷 829-854页

作者： Shikalgar, Shabanam K. Kumar, N. V. S. Pavan Singh, Gavendra Rashid, Faizur Sharad Institute of Technology College of Engineering Yadrav India Koneru Lakshmiah Education Foundation Vijayawada India Department of Software Engineering College of Computing and Informatics Haramaya University Dire Dawa138 Ethiopia College of Computing and Informatics Haramaya University Dire Dawa138 Ethiopia

Nowadays, with the growth of emerging technologies, increased attention has been paid to the classification of privacy-preserved medical data and development of various privacy-preserving models for the promotion of online medical pre-diagnosis systems. Medical data is highly sensitive and it is essential to ensure privacy of medical records from third-party users to increase service quality, satisfy patients and earn trust. The classification of medical preserved data is helpful to build a clinical decision system by classifying patients based on their disease and symptoms. In this article, a hybrid optimization-based deep learning model named Fractional Tuna Sailfish Optimization–Deep Residual Network (FractionalTSFO-DRN) is designed to precisely classify the privacy preserved medical data. A privacy utility coefficient matrix is used to ensure the privacy of medical data by generating a key matrix using Tuna Sailfish Optimization (TSFO) algorithmic technique. The privacy-preserved medical data is allowed for the classification process using DRN and the introduced Fractional TSFO is used to optimize and enhance the classification in DRN. The assessment followed by using heart disease prediction databases proved that the employed classification technique recorded an accuracy of 94.67%, a True Positive Rate of 93.56%, and a True Negative Rate of 89.68% respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A NEWBORN EMBODIED TURING TEST FOR COMPARING OBJECT SEGMENTATION ACROSS ANIMALS AND MACHINES 12

A NEWBORN EMBODIED TURING TEST FOR COMPARING OBJECT SEGMENTA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Garimella, Manjulata Pak, Denizhan Wood, Justin N. Wood, Samantha M.W. Department of Informatics School of Informatics Computing & Engineering Department of Psychological & Brain Sciences Cognitive Science Program Program in Neuroscience

Newborn brains rapidly learn to solve challenging object perception tasks, including segmenting objects from backgrounds and recognizing objects across new viewing situations. Conversely, modern machine learning (ML) algorithms are "data hungry," requiring more training data than brains to reach similar performance levels. How do we close this learning gap between brains and machines? Here, we introduce a new benchmark-a Newborn Embodied Turing Test (NETT) for object segmentation-in which newborn animals and machines are raised in the same environments and tested with the same tasks, permitting direct comparison of their learning. First, newborn chicks were raised in controlled environments containing a single object rotating on a single background, then their recognition performance was tested across new backgrounds and viewpoints. Second, we performed "digital twin" experiments in which artificial agents were reared and tested in virtual environments that mimicked the rearing and testing conditions of the chicks. We inserted a variety of ML "brains" into the artificial agents and measured whether those algorithms learned common object recognition behavior as chicks. All newborn chicks solved this one-shot object segmentation task, successfully learning background-invariant object representations that generalized across new backgrounds and viewpoints. In contrast, none of the artificial agents solved the task, instead learning background-dependent representations that failed to generalize across new backgrounds and viewpoints. This digital twin design exposes core limitations in current ML algorithms in developing brain-like object perception. Our NETT is publicly available for comparing ML algorithms with newborn chicks. We argue that NETT benchmarks can help researchers build embodied AI systems that learn as efficiently and robustly as newborn brains. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Factors of organizational adoption of enterprise architecture in Malaysian public sector: a multi group analysis

引用

Journal of Systems and Information Technology 2022年第4期24卷 331-360页

作者： Ahmad, Nor Azizah Mohd Drus, Sulfeeza Kasim, Hairoladenan Department of College of Computing and Informatics UNITEN Putrajaya Malaysia

Purpose: The relevant importance of enterprise architecture (EA) to an organization has gained the attention of the public sector. However, its adoption rate remains slow on the uptake. Thus, this study aims to investigate the various factors associated with adoption intention based on the technological, organizational and environmental framework for federal and state types of public organizations to provide greater predictive accuracy and relevance of EA adoption in Malaysia’s public sector (MPS) context. Design/methodology/approach: An empirical study was conducted through an online survey in Malaysia. Based on 255 samples from public organizations throughout Malaysia, a multigroup analysis with partial least square structural equation modeling was performed to identify the respective influencing factors for adopting EA by federal and state organizations in the Malaysian public sector. Findings: Five organizational factors (clear communication, normative pressure, expected benefit, good governance and organization size) and two environmental factors (coercive pressure and mimetic pressure) were found to be significant factors influencing adoption intention for EA. Additionally, clear communication and coercive pressure were noted to be significant factors influencing adoption for both federal and state organizations. Other significant factors for federal organizations include expected benefit and normative pressure, whereas for state organizations, another significant influencing factor was good governance. The predictive accuracy for federal organizations was slightly higher at 74.6% than that of state organizations, that is, at 65%. Research limitations/implications: These findings imply that federal and state organizations respond to different factors that motivate their intention to adopt EA. These findings guide future intentional practice and ensure greater motivation for EA adoption. Practical implications: The identification of specific factors that matter

关键词： Factor analysis

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：