检索结果-内蒙古大学图书馆

7th International Conference on Advances in Visual informatics, IVIC 2021

作者： Khan, Ijaz Ahmad, Abdul Rahim Jabeur, Nafaa Mahdi, Mohammed Najah College of Graduate Studies Universiti Tenaga Nasional Kajang Malaysia Information Technology Department Buraimi University College Al-Buraimi Oman College of Computing and Informatics Universiti Tenaga Nasional Kajang Malaysia Computer Science Department German University of Technology Muscat Oman Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Kajang Malaysia

ISBN: (纸本)9783030902346

Classification, a significant application of machine learning, labels each instance of the dataset into one of the predefined classes. Problems occur when the number of instances in the classes is not uniform. The exceptional lyuneven class distribution gives rise to class imbalancing issues which tend to demote the overall performance of the classifier. A set of data-level algorithms are available which are applied to adjust the class distribution. The class imbalancing emerges frequently in datasets from educational domains where the number of students with unsatisfactory performance general appears in low number comparing to the students with satisfactory outcomes. This paper applies a set of data-level sampling algorithms over a dataset taken from an educational domain. It underlines the consequences rising from classification with imbalanced dataset. This research confirms that a classification model achieving higher accuracy may not appear effective in correct identification of instances in minority class. Classification with an imbalance dataset may produce low recall, precision and F-Measure for classes with lower number of instances. The performance of classification model improves with application of data level algorithm. However, it highlights the supremacy of oversampling algorithm over undersampling algorithms. © 2021, Springer Nature Switzerland AG.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Review on Software Deployment Environments for Privacy Protection in an Organizations

A Review on Software Deployment Environments for Privacy Pro...

引用

International Conference on Information Technology and Multimedia (ICIM)

作者： Asmidar Abu Bakar Salman Yussof Fiza Abdul Rahim Ramona Ramli Norsyahirah Khairul Anuar Aishah Abu Bakar College of Computing and Informatics Universiti Tenaga Nasional Kajang Selangor Malaysia Institute of Informatics and Computing Energy Universiti Tenaga Nasional Kajang Selangor Malaysia

ISBN: (数字)9781728173108

ISBN: (纸本)9781728173115

Privacy protection is the main issue in many organizations, especially those handling a large volume of personal data in their daily works such as banks, healthcare, and energy such as electricity. An organization needs to manage the personally identifiable information (PII) such as name, address, identification numbers, etc. as well as sensitive data such as financial or medical data. Departments shared these data for day to day operations. Privacy is a concerning issue as software deployment is no longer on a standalone basis. Organizations now may deploy software on cloud, hybrid cloud, web-based, mobile, and the pervasive environment. Thus, incorporating privacy in an existing system or new software deployment in an organization is essential since it will protect the sensitive data. We have studied literature and discussed privacy and organizations to understand how it relates to each other; we also review various environments where software may deploy with privacy in mind.

关键词： Data privacy Privacy Organizations Medical services Software Task analysis Information technology

来源：评论

学校读者我要写书评

暂无评论

Enhanced Blockchain Scalability for IoT-based Smart Devices -A Generic Model Development

Enhanced Blockchain Scalability for IoT-based Smart Devices ...

引用

International Conference on Computer Applications and Industrial Electronics (ICCAIE)

作者： Mathuri Gurunathan Moamin A. Mahmoud Faisal Hadi Faisal College of Graduate Studies Universiti Tenaga Nasional Kajang Malaysia Department of Computing Institute of Informatics and Computing in Energy College of Computing and Informatics Universiti Tenaga Nasional Kajang Malaysia

Blockchain become well known as there is third-party contribution while doing the exchanges or transactions. Blockchain is the innovation for utilizing digital forms of money. It draws in the consideration of specialists and academicians, along with various highlights of Blockchain it is having the significant issue of versatility and scalability which can be classified into throughput, cost, limit, and systems networking. Scalability influences due to some different components like block size and block interval time which likewise may lessen the security. The system may get powerless against various attacks on the off chance that we indiscriminately change the scalability. To address these challenges, this paper con-ducts an intensive analysis of blockchain scalability challenges in the IoT context and subsequently proposes a generic model to enhance scalability. The investigation covers restrictions on different blockchain stages and how system parameters such as throughput, latency, block size, and network influence a peer-topper system’s effectiveness, security, and energy consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Big Data Technologies with Visual Faceted Search 8

Improving Big Data Technologies with Visual Faceted Search

引用

8th International Conference on Information Technology and Multimedia, ICIMU 2020

作者： Najah Mahdi, Mohammed Rahim Ahmad, Abdul Ismail, Roslan Subhi, Mohammed Ahmed Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Kajang Malaysia College of ComputingInformatics Universiti Tenaga Nasional Kajang Malaysia Universiti Kebangsaan Malaysia Department of Electric Electronics and System Engineering Bangi Malaysia

ISBN: (纸本)9781728173108

Because of the quantity, complexity and speed measurements of big data, access to the data needed for big data applications becomes ever more challenging for both end-users and IT-experts. access. This has however led to problems of overloading information. While progress has been made in search engines, finding the right information still is a struggle due to the exponential increase in the everyday information provided. The need for Big Data Analytic now powers other aspects of modern society, because they can build new linkages and discoveries that help drive tomorrow's innovation. Data visualization of big data applications is an important tool to interpret and understand immense data, making the technology more enticing to use. Visualization of a search result with faceted search is increasingly popular in search engines. This seeks to allow users to easily and effectively find their way through large document collections. FS strategies presume that correct information is required so that the value, importance, and expense of achieving the requested information is optimized. In this work, we propose a new FS framework for visualizing browsing and refinements of search results to allow users to visually build complex search queries. The proposed FS can also solve the problem of lexical uncertainty in current search engines and give users more interest. © 2020 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Cyber-Crime Detection: Experimental Techniques Comparison Analysis

Cyber-Crime Detection: Experimental Techniques Comparison An...

引用

Visualization, informatics and Technology Conference (IVIT), International

作者： Ebraheem Fahad Aljarboua Marina Bte Md. Din Asmidar Abu Bakar Institute of Informatics and Computing in Energy (IICE) Universiti Tenaga Nasional Kajang Selangor Malaysia

ISBN: (纸本)9781665486491

Cyber-crime is one of the main problems the world face, and machine learning plays a key part in contemporary operating systems for giving better transformation in the security environment and cybercrime detection. While detecting cybercrimes is difficult, it is possible to gain advantages from machine learning to generate models to assist in predicting and detecting cybercrimes. The researchers have proven that the majority of the models can work effectively in identifying cybercrime, they can span from 70% to 90% in accuracy measuring. The objective of this research paper is to conduct experimental techniques comparison analysis for cyber-crime detection by reviewing all possible machine learning algorithms for automatic detection. The key focus of the study is on the use of eight classifiers models which are Logistic Regression (LR), Decision Tree (DT), K-nearest Neighbors (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), eXtreme Gradient Boosting (XGBoost) and Multiple layer perception (MLP). From the experiment conducted, the high prediction came from MLP which is 96% accuracy of the cyber-crime methods based on existing cyber-crime data.

关键词： Support vector machines Radio frequency Machine learning algorithms Operating systems Predictive models Security Computer crime

来源：评论

学校读者我要写书评

暂无评论

Simplified Artificial Neural Network Configuration in R Programming for Predictive Modelling 8

Simplified Artificial Neural Network Configuration in R Prog...

引用

8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023

作者： Razak, Tajul Rosli Jarimi, Hasila Ahmad, Emy Zairah Universiti Teknologi MARA School of Computing Sciences College of Computing Informatics and Mathematics Selangor Malaysia University Kebangsaan Malaysia Solar Energy Research Institute Selangor Bangi Malaysia Universiti Teknikal Malaysia Melaka Fakulti Teknologi Dan Kejuruteraan Elektrik Durian Tunggal Malaysia

ISBN: (纸本)9798350315516

The configuration of Artificial Neural Networks (ANNs) in the context of predictive modelling can provide considerable difficulty owing to the complex nature of their arrangements and the need for meticulous hyperparameter adjustment the present study addresses the issue by proposing a more straightforward methodology for configuring Artificial Neural Networks (ANNs) through the R programming language the methodology presented in this study offers a systematic and comprehensive framework, ensuring accessibility and simplicity of implementation. This approach aims to enhance the usability of Artificial Neural Networks (ANNs) for practitioners who need advanced machine learning knowledge. In order to demonstrate the applicability of the proposed methodology, a series of experiments were conducted on a case study in sustainable energy research. This study makes a valuable contribution to academic discipline by establishing a connection between artificial neural network (ANN) theory and its practical application. This study aims to enhance the accessibility of artificial neural network (ANN) setup and provide significant insights to further progress predictive modelling, specifically focusing on sustainable energy research. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Medical Image Analysis Using Deep Learning and Distribution Pattern Matching Algorithm

引用

Computers, Materials & Continua 2022年第8期72卷 2175-2190页

作者： Mustafa Musa Jaber Salman Yussof Amer S.Elameer Leong Yeng Weng Sura Khalil Abd Anand Nayyar Institute of Informatics and Computing in Energy Universiti Tenaga NasionalMalaysia Department of Computer Science Dijlah University CollageBaghdad10021Iraq Biomedical Informatics College University of Information Technology and CommunicationsBaghdadIraq Faculty of Information Technology Duy Tan UniversityDa Nang550000Viet Nam Graduate School Duy Tan UniversityDa Nang550000Viet Nam Department of Computer Science Al-turath University CollegeBaghdadIraq

Artificial intelligence plays an essential role in the medical and health *** convolution networks offer valuable services and help create automated systems to perform medical image ***,convolution networks examine medical images effectively;such systems require high computational complexity when recognizing the same disease-affected ***,an optimized deep convolution network is utilized for analyzing disease-affected regions in this *** disease-relatedmedical images are selected and examined pixel by pixel;this analysis uses the gray wolf optimized deep learning *** method identifies affected pixels by the gray wolf hunting *** convolution network uses an automatic learning function that predicts the disease affected by previous imaging *** optimized algorithm-based selected regions are further examined using the distribution pattern-matching *** pattern-matching process recognizes the disease effectively,and the system’s efficiency is evaluated using theMATLAB implementation *** process ensures high accuracy of up to 99.02%to 99.37%and reduces computational complexity.

关键词： Artificial intelligence medical field gray wolf-optimized deep convolution networks distribution pattern-matching rule

来源：评论

学校读者我要写书评

暂无评论

A Holistic Approach for Establishing Resilient Dams for Malaysia 5th

A Holistic Approach for Establishing Resilient Dams for Mala...

引用

5th International Conference on Water Resources, ICWR 2021

作者： Sidek, Lariyah Mohd Basri, Hidayah Marufuzzaman, Mohammad Jamil, Norziana Kaman, Zeittey Karmilla Khebir, Muhammad Izzat Azhar Omar, Siti Mariam Allias Khambali, Mohd Hazri bin Moh Institute of Energy Infrastructure Universiti Tenaga Nasional Kajang Malaysia College of Computing and Informatics Universiti Tenaga Nasional Kajang Malaysia Universiti Tenaga Nasional Kajang Malaysia Department of Irrigation and Drainage Kuala Lumpur Malaysia

ISBN: (纸本)9789811959462

The dam related disaster caused thousands of people's lives and billions of property damages in the world and in Malaysia. The loss of life and property damages is mostly happened due to dam failure and the lack of timely evacuation procedures. Currently, insufficient integrated and comprehensive research are being done in Malaysia, including the impact of dam failures. The interconnection and interdependence of these elements are vital to ensure holistic solutions for dam safety. In this research, we proposed a resilient and intelligent dam safety management program that integrates engineering, cybersecurity and socioeconomic elements to minimize the risks of dam failure. A comparatively new approach named Risk-Informed Decision-Making is proposed in this research which will use the likelihood of loading, dam fragility, and consequences of failure to estimate the risk related to Batu Dam. Investigation of cyber security in dam data will be portrayed to assist in strengthening the security of dam control systems against sophisticated attacks such as APT. Finally, an effective evacuation procedure will be proposed to complete the holistic solution that benefits the nations, dam owners and other related authorities, but more importantly, it will help keep the community safe. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Arabic Speaker Identification System for Forensic Authentication Using K-NN Algorithm

Arabic Speaker Identification System for Forensic Authentica...

引用

7th International Conference on Advances in Visual informatics, IVIC 2021

作者： Abdulwahid, Sarah Mahmoud, Moamin A. Abdulwahid, Nassren College of Graduate Studies Universiti Tenaga Nasional Kajang Malaysia Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Kajang Malaysia Department of Communication Engineering University of Technology Al-Sina’a Street Baghdad Iraq

ISBN: (纸本)9783030902346

For many years, there was an increasing necessity for being capable of the identification of a person based on his/her voice. Judges, law enforcement agencies, detectives, and lawyers, wanted to be able to use the forensic authentication of voice for investigating a suspect or confirming a judgment of guilt or innocence. This study aims to design and build a comprehensive identification of the forensic speakers for the Arabic language. The suggested system has been utilized for the recognition of forensic speaker’s isolated words for purposes of identification. It comprises two stages;the first stage is training the sentence of the forensic speaker in the case where it is not previously processed and stored;the second stage is testing;it is applied in the case where the sentence of the forensic speaker has been previously processed and stored. Every one of the phases involves utilizing audio features (standard division, mean, amplitude, and zero-crossing), pre-processing with the use of the MFCC, Hamming Window, vector quantization, and data mining classification approaches. The proposed system implementation provides removal of the noise in spoken sentences, processing speech sentences prior to the storing, and a correct classification with the use of a number of algorithms of data mining classification such as the Logistic Model Tree (LMT), and K-nearest neighbor (KNN) algorithms. KNN being given the highest accuracy of 91.53% and 94.56% respectively. © 2021, Springer Nature Switzerland AG.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Adopting Centroid and Amended Trilateration for better accuracy of range-based non-GPS localization

Adopting Centroid and Amended Trilateration for better accur...

引用

International Conference on Computer and Information Sciences (ICCOINS)

作者： Marina Md. Din Norziana Jamil Nik Fariz Nik Ahmad Aziz Institute of Informatics and Computing in Energy Universiti Tenaga Nasional (UNITEN) Jalan Ikram-Uniten Malaysia

There has been massive amount of research have been conducted in the area of indoor positioning systems specifically it's upwards research trending in Localization Based Services (LBS) within a non-open space environment or in the vicinity of high rise buildings due to the incapability of Global Positioning System (GPS) to do so. Most of the indoor localization techniques proposed by researchers to discover an optimized solution for indoor location tracking that has high precision and accuracy. This paper proposes a model for better accuracy on range-based localization algorithm in non-GPS positioning systems. The proposed model adopts the enhanced Kalman Filter (KF) and Centroid Localization Algorithm that can manipulate noise signal from raw Received Signal Strength Indicator (RSSI). There are 12 tests conducted in two different environments; at the area with less-obstacles and at the area with more obstacles. Three different algorithms are deployed with and without KF where a series of observations and comparisons are made to measure the effectiveness and reliability of KF implementation. Our analysis and finding show that the proposed model improves the accuracy percentage by more than 80%.

关键词： Receivers Global Positioning System Computational modeling Estimation Wireless communication Measurement techniques Buildings

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：