检索结果-内蒙古大学图书馆

5th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2022

作者： Ogwok, Daniel Ehlers, Elizabeth Marie Academy of Computer Science and Software Engineering University of Johannesburg South Africa

ISBN: (纸本)9781450397612

Many methods have been applied to image segmentation, including unsupervised, supervised, and even deep learning-based models. Semantic and instance segmentation are the two most widely researched forms of segmentation. It is of value to use multiple methods to segment an image. In this paper, we present an image segmentation ensemble methodology. Multiple image segmentation methods are applied to an image and merged to create one segmentation using the proposed method. The technique uses the Jaccard index algorithm, sometimes called the Jaccard similarity coefficient and commonly known as Intersection over Union (IoU). This resulted in better segmentation results than the respective individual segmentation methods. This experiment was applied to mathematical expression recognition (MER), with the expressions taken from blackboards with varying degrees of noise, and lighting conditions, from different classroom environments. A summary of empirical results from the segmentation of multiple images is presented in the paper. © 2022 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Actor-Oriented Self-Organizing Maps: A novel distributed design for Self-Organizing Systems 22

Actor-Oriented Self-Organizing Maps: A novel distributed des...

引用

10th International Conference on computer and Communications Management, ICCCM 2022

作者： Thomas, Penelope Clara Coulter, Duncan Anthony Academy of Computer Science and Software Engineering University of Johannesburg South Africa

ISBN: (纸本)9781450396349

This paper explores the implementation of a distributed model of the Self-Organizing Map (SOM) and its subsequent validation through the implementation of a proof-of-concept prototype using the Typed-Akka tool kit. This work is a part of an on-going study into the intersection of the actor-model and SOMs following on from previous work on lattice initialization. A comprehensive software architecture model is given using various UML diagrams, specifically the behavioral and finite state-oriented aspects of the design are given using activity and state diagrams respectively. A parameter-study was conducted that focused specifically on the neighborhood definition function in the context of an actor-oriented SOM. © 2022 ACM.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

A Gene Expression Programming Inspired Evolution Symbiont Agent for Real-Time Strategy Generation 5

A Gene Expression Programming Inspired Evolution Symbiont Ag...

引用

5th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2022

作者： Sithungu, Siphesihle P. Ehlers, Elizabeth M. Academy of Computer Science and Software Engineering University of Johannesburg South Africa

ISBN: (纸本)9781450397612

AdaptiveSGA is a method for achieving Adaptive Game Artificial Intelligence-Based Dynamic Difficulty Balancing through the Symbiotic Game Agent Model. Previous work has shown that AdaptiveSGA can achieve Dynamic Difficulty Balancing in simulated soccer by effectively changing a team's strategy based on the opponent's performance. AdaptiveSGA pre-existing strategies and switches between them during runtime to increase the game's replayability by adapting the challenge it poses to the human player. Although this method works, its limitation is that if the human player surpasses the most intelligent strategy of the computer opponent, there is no way for the model to generate a new strategy during runtime that can potentially overcome the human player. AdaptiveSGA can only maintain engagement with the human player if the human player has not overcome the best strategy for the pool of pre-existing strategies. Current work addresses this limitation by introducing an Evolution Symbiont Agent whose purpose is to generate new strategies in real-time (during gameplay) through evolutionary mechanisms using Gene Expression Programming. Experimental results show that the presence of the evolution symbiont agent can use Gene Expression Programming to generate strategies capable of outperforming an opposing strategy. © 2022 ACM.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Human-Centric Considerations in Deploying Biometric Modalities: A Multi-Modal Approach for Public Services Application

Human-Centric Considerations in Deploying Biometric Modaliti...

引用

International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD)

作者： Elisa Maeko Dustin Van Der Haar Academy of Computer Science and Software Engineering University of Johannesburg Johannesburg South Africa Academy of Computer Science and Software Engineering name University of Johannesburg Johannesburg South Africa

ISBN: (数字)9798350387902

ISBN: (纸本)9798350387919

This research aims to aid public service organizations in selecting effective multi-modal authentication technology to mitigate authentication risks and facilitate informed decision-making, preventing financial burdens associated with unsuccessful system implementations. It has become a financial burden for organisations to deploy inappropriate technology in an environment that ultimately goes unused and may lead to unsuccessful system implementations. Different biometric attributes, characteristics, qualities, and criteria - the environment (organisation), budget and business requirements, specifications, design, system performance, the information technology infrastructure, operations, and post-deployment functions - must be compared. The research methodology also encompasses the execution of a survey, concomitant with factor analysis, which serves as the cornerstone for assessing the model. The model evaluation survey, conducted with participants aged 18 to 55, garnered a response rate of 99.4% from respondents who positively consented to participate in the study. In order to analyse and evaluate the proposed model, this research incorporates a spectrum of intricate statistical techniques, including descriptive statistics, factor analysis, chi-square for goodness of fit, Mardia's coefficient, multivariate kurtosis, and path model analysis. This study contributes to the body of knowledge by studying the human factors that impact public awareness, perception, and the usability of multi-modal biometrics. The formalised model proposed in the study will be of value to the public services environment that may need to deploy multi-modal biometric authentication technologies to minimise future failed deployments.

关键词： Surveys Analytical models Biological system modeling System performance Authentication Organizations Kurtosis

来源：评论

学校读者我要写书评

暂无评论

The Emergence of IIoT and its Cyber Security Issues in Critical Information Infrastructure 21

The Emergence of IIoT and its Cyber Security Issues in Criti...

引用

21st European Conference on Cyber Warfare and Security, ECCWS 2022

作者： Bhaiyat, Humairaa Yacoob Sithungu, Siphesihle Philezwini Academy of Computer Science and Software Engineering Faculty of Science University of Johannesburg South Africa

ISBN: (纸本)9781914587405

The emergence of the Industrial Internet of Things (IIoT) can transform and improve industrial domain processes. This is achieved by IIoT’s ability to collect and process vast amounts of data using technology such as sensors. IIoT capabilities can improve the manufacturing processes of these sectors and contribute to the improved functioning of critical information infrastructure. In addition, current trends - such as the Fourth Industrial Revolution (4IR) - use IIoT to realise specific goals. While the emergence of IIoT systems does introduce many benefits, such as improved efficiency and sustainability, it can also introduce security concerns. These security concerns pose a significant threat to the industrial domain, including critical information infrastructures. The resulting threats emphasise the need to implement solutions to secure IIoT systems. The paper aims to discuss the emergence of IIoT and its cyber security issues within the context of critical information infrastructure. The research paper follows a theoretical research methodology to provide an improved understanding of the emergence of IIoT and its cyber security issues in critical information infrastructure. The paper contains an exhaustive discussion of what is IIoT. A discussion on where IIoT fits within the context of critical information infrastructure and its impact on 4IR is also highlighted in the paper. Due to the many vulnerabilities that IIoT systems can contain, the paper also discusses security concerns surrounding the emergence of IIoT. The security concerns make IIoT systems attractive targets for cyberattacks. Therefore, different approaches that can be applied to secure IIoT systems is also provided. Since IIoT capabilities can impact the critical information infrastructure of businesses and nations, the authors’ stance on how IIoT systems could transform the current understanding of critical information infrastructure is also discussed. © 2022 Curran Associates Inc.. All rights r

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Integrating Modern Portfolio Theory into Information Security Control Selection Optimisation

Integrating Modern Portfolio Theory into Information Securit...

引用

IT Innovation and Knowledge Discovery (ITIKD), International Conference on

作者： Muhammad Zaid Abrahams Josef J Langerman Academy of Computer Science and Software Engineering University of Johannesburg Johannesburg South Africa

ISBN: (数字)9798350355468

ISBN: (纸本)9798350355475

Risk management and optimised security control selection in information technology, particularly information security, is crucial for identifying and mitigating organisational threats. Information security control selection and planning are challenging due to limited resources such as funding, time and staffing. This research article is an academic exposition in which a quantitative method of evaluating cyber security risk and utilizing principles of Modern Portfolio Theory (MPT) to optimize the allocation of resources and funding to select security controls to mitigate an organization's specific security risk and in addition reduce and organisations attack surface as the identified Return on Investment (ROI). This article details and illustrates a novel model that uses quantitative risk evaluation methods such as Monte Carlo simulations as opposed to the widely used qualitative methods in the aim to provide organisations with empirical data to make informed decisions, using Modern Portfolio Theory (MPT), when selecting and managing a portfolio of security controls such as Anti-DDOS solutions, Endpoint Detection and Response (EDR) and Cloud Access Security Broker (CASB) solutions.

关键词： Technological innovation Monte Carlo methods Information security Organizations Planning Resource management computer crime Portfolios Risk mitigation Investment

来源：评论

学校读者我要写书评

暂无评论

ECG-Signals-based Heartbeat Classification: A Comparative Study of Artificial Neural Network and Support Vector Machine Classifiers 22

ECG-Signals-based Heartbeat Classification: A Comparative St...

引用

2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics, SAMI 2024

作者： Ugwu, Chukwuemeka Malachi Pierrette Mukamakuza, Carine Tuyishimire, Emmanuel Carnegie Mellon University Africa College of Engineering Kigali Rwanda University of Johannesburg Academy of Comp. Science and Software Eng. Johannesburg South Africa

ISBN: (纸本)9798350317206

This research conducts a comparative performance of artificial neural networks (ANNs) and support vector machines (SVMs) models for heartbeat classification using Electrocardiogram (ECG) signals, which diagnose various cardiovascular diseases and abnormalities. The study scrutinizes various combinations of feature extraction and classification algorithms to identify the most effective methodology in terms of accuracy and other performance metrics. The experiment focuses on classifying five classes of ECG signals using the MIT-BIH database as the data source. Each signal is initially preprocessed into beats using Discrete Wavelet Transform (DWT), followed by Independent Component Analysis (ICA) for enhanced feature extraction. Results show that the SVM performs better than ANN with an overall accuracy of 98.7% to 98.4%. However, there are nuanced differences in their performance across different classes and configurations. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Cyber security skills development in South Africa: Addressing the Gender Gap in the Industry 8

Cyber security skills development in South Africa: Addressin...

引用

8th Conference on Information Communication Technology and Society, ICTAS 2024

作者： Ramonyai, Tebogo Motlatso Mpekoa, Noluntu Tom, Sheethal University of Johannesburg Academy of Computer Science & Software Engineering Cape Town South Africa IIE Varsity College School of Information Technology Cape Town South Africa

ISBN: (纸本)9798350314892

This paper investigates the gender gap in South Africa's cybersecurity sector and its effects on both the sector and the nation's economic growth. There is a significant shortage of skilled workers in the sector, and women are notably underrepresented. The main research question examines how the gender gap affects the industry's development, innovation, and national security posture, emphasizing the importance of utilizing the nation's talent pool to its fullest capacity to combat the evolving cyber threats. Insights and perspectives on the gender disparity in the cybersecurity sector were gathered through a questionnaire circulated amongst cybersecurity professionals and academics. These participants were chosen due to their knowledge and direct engagement in the subject, which offers valuable insights into the obstacles that women encounter in their workplace. The study highlights a number of problems, including gender stereotypes, a lack of access to education and training, and a non-inclusive workplace culture, that contribute to the gender gap. The paper makes the case that in order to solve these problems and advance diversity and inclusivity in the workplace, all stakeholders must work together to close the gender gap. In order to overcome the gender gap in cybersecurity in South Africa, the study suggests special programs aimed at expanding access to education and training opportunities, promoting gender diversity and inclusivity, and creating a more hospitable and equal work environment. This will boost the country's economic growth and strengthen security against cyberattacks. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Ethical implications of using artificial intelligence for multimodal biometric selection model evaluation 6

Ethical implications of using artificial intelligence for mu...

引用

6th International Conference on Information and computer Technologies, ICICT 2023

作者： Maeko, Elisa Van Der Haar, Dustin Academy of Computer Science and Software Engineering and University of Johannesburg Cnr University Road and Kingsway Avenue Auckland Park Gauteng2006 South Africa

ISBN: (纸本)9798350300956

In today's digital world, information security, and person In today's digital world, information security, and personal authentication are major concerns. As technology has advanced, so have the methods used to authenticate users. Multimodal biometric selection combines several biometric methods to authenticate users. However, before any biometric system can be used in the public domain, it must be analysed and evaluated to ensure that it is usable and that the system considers the ethical aspect of the end-user. This process is necessary to ensure that all individuals affected by the implementation are aware of the ethical implications of biometric use and that any risks are properly assessed. To ensure the accuracy of the selection process, survey and evaluation techniques have been implemented to enhance the multimodal biometric selection processes for public domain authentication. Furthermore, the paper discusses the ethical implications and the potential impact of the use of multimodal biometrics in the public domain. The model was assessed using a confirmatory factor analysis quantitative research survey. In the experimental study, 352 eligible responses were received, where more than 200 participants were expected to complete the survey to evaluate the model and determine what is important to the public end-user when using biometric systems in this context. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for Alzheimer's Disease Diagnosis and Mini-Mental State Examination Score Prediction

引用

Big Data Mining and Analytics 2024年第3期7卷 828-842页

作者： Jin Liu Xu Tian Hanhe Lin Hong-Dong Li Yi Pan Hunan Provincial Key Lab on Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410083China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of SoftwareXinjiang UniversityUrumqi 830091China School of Science and Engineering University of DundeeDundeeDD14HNUK Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Accurately diagnosing Alzheimer's disease is essential for improving elderly ***,accurate prediction of the mini-mental state examination score also can measure cognition impairment and track the progression of Alzheimer's ***,most of the existing methods perform Alzheimer's disease diagnosis and mini-mental state examination score prediction separately and ignore the relation between these two *** address this challenging problem,we propose a novel multi-task learning method,which uses feature interaction to explore the relationship between Alzheimer's disease diagnosis and minimental state examination score *** our proposed method,features from each task branch are firstly decoupled into candidate and non-candidate parts for ***,we propose feature sharing module to obtain shared features from candidate features and return shared features to task branches,which can promote the learning of each *** validate the effectiveness of our proposed method on multiple *** Alzheimer's disease neuroimaging initiative 1 dataset,the accuracy in diagnosis task and the root mean squared error in prediction task of our proposed method is 87.86%and 2.5,*** results show that our proposed method outperforms most state-of-the-art *** proposed method enables accurate Alzheimer's disease diagnosis and mini-mental state examination score ***,it can be used as a reference for the clinical diagnosis of Alzheimer's disease,and can also help doctors and patients track disease progression in a timely manner.

关键词： multi-task learning Alzheimer's disease diagnosis mini-mental state examination score prediction

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：