检索结果-内蒙古大学图书馆

21st IEEE Student Conference on Research and Development, SCOReD 2023

作者： Alqushaibi, Alawi Ragab, Mohammed Gamal Sumiea, Ebrahim Hamid Al-Selwi, Safwan Mahmood Hasan, Mohd Hilmi Abdulkadir, Said Jadid Alhussian, Hitham Al-Asbahi, Mahmoud Mustafa Universiti Teknologi PETRONAS Computer and Information Sciences Perak Malaysia Universiti Teknologi PETRONAS Centre for Research in Data Science Perak Malaysia Universiti Malaysia Terengganu Faculty of Ocean Engineering Technology and Informatics Terengganu Malaysia

ISBN: (纸本)9798350318821

Detection of heart disease is critical, as it is a common and serious health condition. Predicting its occurrence is vital in the healthcare domain, and machine learning techniques are increasingly being utilized to accurately identify patients at risk. To evaluate how well machine learning models can effectively predict heart disease, we used a pre-existing dataset from the UCI repository's Cleveland database. Though the dataset originally contained 303 records and 76 attributes, we followed the literature by narrowing the focus to 14 relevant attributes in order to improve the precision of various algorithmic approaches. Our study employed five machine learning classifiers, namely KNearest Neighbors (KNN), CatBoost Classifier (CBC), Decision Tree Classifier (DT), XGBClassifier (XGBC), and Support Vector Classifier (SVM). We evaluated their performance using different metrics like accuracy, precision, AUC, and F1 score on the heart disease dataset. We found that the CatBoost Classifier had the best performance, achieving high accuracy and AUC with 0.88% and 0.94% values, respectively. This suggests that machine learning algorithms could aid in identifying heart disease at an early stage and have significant implications for improving patient outcomes in healthcare. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Preliminary Study on the Effect of Traffic Representation on Accuracy Degradation in Machine Learning-based IoT Device Identification

Preliminary Study on the Effect of Traffic Representation on...

引用

2022 IEEE International Conference on Computing, ICOCO 2022

作者： Aqil, Nik Afifi, Firdaus Zaki, Faiz Anuar, Nor Badrul Faculty of Computer Science and Information Technology Universiti Malaya Department of Computer System and Technology Kuala Lumpur50603 Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu21030 Malaysia

ISBN: (纸本)9781665489966

The Internet of Things (IoT) has gained attention for its rapid growth in the past few years. IoT devices such as temperature and humidity sensors and voice controllers are implemented widely, from household appliances to industrial machines. However, with the rapid growth and benefits IoT offers, we are exposed to various security vulnerabilities, such as data breaches and IoT-specific malware. Researchers are using IoT device identification as a solution for IoT security issues. IoT device identification helps network administrators identify network traffic into its originating devices. However, researchers often overlook an important issue in IoT device identification, which is accuracy degradation over time. Thus, this paper explores the severity of accuracy degradation in IoT device identification on different traffic representation approaches, which are flow, sub-flow, and packet. This paper utilizes a private, and the UNSW IoT Traffic Traces public dataset. Based on the experimental findings, the sub-flow-based approach recorded the best overall performance, with only 8% degradation in the private dataset and 1% degradation in the public dataset. Meanwhile, even though the packet-based approach only degraded 5% on the private dataset, it recorded up to an 11% accuracy decrease in the public dataset. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Assessing and solving multicollinearity in sediment transport prediction models using principal component analysis

引用

ISH Journal of Hydraulic engineering 2021年第S1期27卷 343-353页

作者： Sulaiman, Mohd Sofiyan Abood, Manal Mohsen Sinnakaudan, Shanker Kumar Shukor, Mohd Rizal You, Goh Qiu Chung, Xiang Zhi School of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Terengganu Malaysia Faculty of Engineering and Technology Infrastructure Infrastructure University Kuala Lumpur Kajang Malaysia Faculty of Civil Engineering Universiti Teknologi MARA Permatang Pauh Malaysia

Predicting sediment transport in a river system is necessary when attempting to monitor river changes due to incoming particle deposition from upstream reaches. Previous studies have used various techniques such as probabilistic, regression, and equal mobility approaches to make predictions. However, issues associated with multicollinearity occur when using the regression approach. Significant correlations between the explanatory variables in a regression equation can increase the coefficient variance estimates, which make these estimates very sensitive to minor changes. Thus, we propose the use of principal component analysis as a solution to these issues. We observed that the variance inflation factor is less than 10, which indicates the nonexistence of issues associated with multicollinearity. Fitting components to the regression equation create a new prediction model for sediment transport, which improves upon previous equations using the same technique. © 2019 Indian Society for Hydraulics.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Single Valued Neutrosophic VIKOR and Its Application to Wastewater Treatment Selection

引用

Neutrosophic Sets and Systems 2021年 47卷 250-272页

作者： Mohd Kamal, Nor Liyana Amalini Abdullah, Lazim Yee, Fu Ming Abdullah, Ilyani Vafaei, Nazanin Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia UNINOVA-CTS and Faculty of Sciences and Technology Nova University of Lisbon Caparica2829-516 Portugal

The fuzzy VIsekriterijumska optimizacija i KOmpromisno Resenje (VIKOR) has been used in solving various multi-criteria decision-making problems where triangular fuzzy numbers are utilized in defining decision-makers' linguistic judgements. Most of the fuzzy VIKOR are built from linguistic variables based on fuzzy sets and its generalization such as intuitionistic fuzzy sets. Recent literature suggests that single-valued neutrosophic sets (SVNSs) can offer a better alternative particularly when fuzzy sets have some extent of limitations in handling indeterminacy and uncertainty. This paper proposes the SVNS-VIKOR where single-valued neutrosophic numbers are utilized in defining linguistic variables of VIKOR. Differently from the typical fuzzy VIKOR which directly utilizes fuzzy numbers with a single membership, the proposed method introduces three independent memberships of truth, indeterminacy and false to enhance judgments in the group decision-making environment. The obtained solutions would help policy makers in identifying the best solution that could enhance the efficiency of treating wastewater. © 2021. All Rights Reserved.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Properties and Filtration Performance of Porous Clay Membrane Fabricated at Various Sintering Temperatures

引用

Macromolecular Symposia 2025年第1期414卷

作者： Zulkifli, Rumaizah Che Azaman, Fazureen Razali, Mohd Hasmizam Ali, Asmadi Hassan, Mohd Faiz Nor, Mohd Al Amin Muhamad Faculty of Science and Marine Environment Universiti Malaysia Terengganu Terengganu Kuala Nerus 21030 Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Kuala Nerus 21030 Malaysia

A porous clay membrane is fabricated using natural ball clay and sintered at various temperatures ranging from 800 to 1100 °C. The properties of the porous clay membrane are characterized, including shrinkage, water absorption, porosity, density, compressive strength, pure water permeation, and turbidity removal from aquaculture wastewater. A clear trend is observed from the findings. As the sintering temperature increases, the water absorption, porosity, and membrane permeation decreases from 62.25% to 43.67%, 57% to 43%, and 4356 to 2235 L h−1 m−2 bar−1, respectively. Conversely, shrinkage, density, compressive strength, and turbidity removal show an opposite correlation, increasing from 9.09% to 18.18%, 0.84 to 1.0 kg m−3, 0.95 to 4.11 MPa, and 79% to 94%, respectively. In summary, the sample sintered at 1000 °C emerges as the optimal choice for aquaculture wastewater filtration. It strikes a balance between the desired density and strength while maintaining an appropriate porosity level and exceptional turbidity removal capacity. This cost-effective ceramic filter exhibits promising properties in producing clear effluent. © 2025 Wiley-VCH GmbH.

关键词： Turbidity

来源：评论

学校读者我要写书评

暂无评论

An assessment of water pollutions area in Terengganu River, Malaysia using unsupervised machine learning 4th

An assessment of water pollutions area in Terengganu River, ...

引用

4th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2022

作者： Zamri, Nurnadiah Pairan, Mohammad Ammar Azman, Wan Nur Amira Wan Abdullah, Lazim Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Besut Campus Terengganu Besut22200 Malaysia Management Science Research Group Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Kuala Nerus21030 Malaysia

River, which supply 90% of the readily accessible water, are key elements of universal water source system. Terengganu River situated in Terengganu, Malaysia is a modern busy city known for tourism, fishing, and industry. Due to that, it has increased risk of water pollution exposure. Therefore, this paper proposes unsupervised ML include Autoencoder and Self-Organizing Map (SOM) for clustering water pollution area along the Terengganu River. Then, uses Silhouette analysis to assess the total of optimum clusters in a dataset. Next, applies Adjusted Rank Index (ARI) to discover the finest comparing within original data with Autoencoder and SOM. Lastly, applies Elbow method to double verify the most excellent clusters for each clustering algorithm. Lastly, lists of polluted area in each cluster are retrieved from 14 main sampling stations with 24 water quality parameters, including 405 water samples. Result shows different cluster with different water samples. Thus, offer different strategies to manage polluted area for Terengganu River. © 2023 The Authors. Published by Elsevier B.V.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

Rayleigh–Bénard Convection in a Bi-viscous Bingham Fluid with Weak Vertical Harmonic Oscillations: Linear and Non-linear Analyses

引用

International Journal of Applied and Computational Mathematics 2023年第3期9卷 1-15页

作者： Keerthana, S. Siddheshwar, P.G. Tarannum, Sameena Idris, Ruwaidiah Department of Mathematics Centre for Mathematical Needs CHRIST (Deemed to be University) Bengaluru 560029 India Department of Professional Studies CHRIST (Deemed to be University) Bengaluru 560029 India Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Kuala Nerus 21030 Malaysia

Linear and weakly non-linear stability analyses of Rayleigh–Bénard convection in a bi-viscous Bingham fluid layer are performed in the presence of vertical harmonic vibrations. In the linear analysis, expression is obtained for the correction Rayleigh-number arising due to the vibrations. The non-linear-analysis based on the Ginzburg–Landau equation is used to compute the Nusselt-number in terms of the correction Rayleigh-number. The mean-Nusselt-number is then obtained as a function of the scaled-Rayleigh-number, the frequency and the amplitude of modulation, the Prandtl number, and the bi-viscous Bingham fluid parameter. The non-autonomous amplitude-equation is numerically solved using the Runge–Kutta–Fehlberg45 method. It is found that the influence of increasing the amplitude of modulation is to result in a delayed-onset situation and thereby to an enhanced-heat-transport situation. For small and moderate frequencies, the influence of increasing the frequency of oscillations is to decrease the critical Rayleigh-number. However, the mean-Nusselt-number decreases with increase in the frequency of oscillations only in the case of small frequencies. An increase in the value of the bi-viscous Bingham fluid parameter leads to advanced-onset and thereby to an enhanced-heat-transport situation. At very large frequencies, the effect of modulation on onset and heat-transport ceases. © 2023, The Author(s), under exclusive licence to Springer Nature India Private Limited.

关键词： Bi-viscous Bingham fluid Ginzburg–Landau method Rayleigh–Bénard convection Vertical harmonic oscillation and Nusselt-number

来源：评论

学校读者我要写书评

暂无评论

A Survey on Product Promotion via E-commerce Platforms - Case Study in Malaysia

A Survey on Product Promotion via E-commerce Platforms - Cas...

引用

2021 IEEE International Conference on Automatic Control and Intelligent Systems, I2CACIS 2021

作者： Alomari, Mohammad Ahmed Ahmed Al-Qasem Al-Hadi, Ismail Yusoff, M. Hafiz Sulaiman, Ibrahim Mohammed Universiti Tenaga Nasional Institute of Informatics and Computing in Energy Malaysia Faculty of Ocean Engineering Technology Informatics Malaysia School of Informatics and Computing Malaysia Faculty of Informatics and Computing Malaysia

ISBN: (纸本)9781665403436

A survey by Malaysian Communication and Multimedia Commission (MCMC) has shown that Internet users in Malaysia has increased up to 88.7% in year 2020 compared to 76.9% in year 2016 which is quite high increase in percentage. The pervasive use of smartphones and computers nowadays as well as the availability of high-speed Internet access has brought a new way of promoting products. E-commerce is a buy and sell system that can be accessed globally around the world. This system can provide efficient strategies for promoting products and services. It is widely agreed that even small enhancements in promotion techniques can increase the profitability of any e-commerce system. In this paper, a research has been conducted to study methods to enhance product promotion among Malaysians. The study investigates through a survey the factors affecting users' WTP (willing-to-pay) during performing e-commerce transaction as well as factors what attract/repel them more. To achieve the study aim, a group of 385 respondents throughout Malaysia have been involved in this research through questionnaire study. Detailed analysis has been introduced to clarify the results. The study has identified the top e-commerce platforms that are used by Malaysians to execute product promotion. The results show that promotion through e-commerce platforms could increase profitability and help businesses to expand rapidly. This is due to the fast market penetration of online promoting compared to conventional one. © 2021 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

A Review: Heart Disease Prediction in Machine Learning & Deep Learning 19

A Review: Heart Disease Prediction in Machine Learning & Dee...

引用

19th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2023

作者： Bakar, Wan Aezwani Wan Abu Josdi, Nur Laila Najwa Bt Man, Mustafa B Zuhairi, Muhammad Amierusyahmi B Universiti Sultan Zainal Abidin Gong Badak Campus Pusat Asasi Sains Dan Perubatan UniSZA Terengganu Kuala Nerus21030 Malaysia Universiti Sultan Zainal Abidin Besut Campus Faculty of Informatics and Computing Besut Terengganu22200 Malaysia Universiti MalaysiaTerengganu Faculty of Ocean Engineering Technology and Informatics Terengganu Kuala Nerus21030 Malaysia

ISBN: (纸本)9781665476928

The whole world has come to know the fact that heart disease is not a trivial issue. Although the years have changed, throngs of patients are diagnosed with this lethal disease and not only is it not decreasing, but increasing and this is evident from the analysis of death rates across the country. Heart disease is caused by several main factors such as negligence in taking care of diet and daily life. Causes such as age and genetics cannot be fully controlled by humans. So it is the responsibility of each individual to take care of critical risk factors that can be controlled by humans. Innovation and data mining technology should also help to reduce the death rate caused by heart disease. Existing data should be used to find hidden relationships, which are very useful for early diagnosis, which can be a new advanced technology and potentially improve the level of the national health system. This paper underlines previous studies that leverage machine learning and deep learning expertise to predict heart disease. Each algorithm produces variations in accuracy and this study will examine the variables that enable these results. At the end of the study, the results achieved by deep learning proved to be ahead of machine learning by showing consistency in a satisfactory range between 84% to 99%. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Ameliorating the re/dehydrogenation behaviour of MgH2 by zinc titanate addition

引用

Journal of Magnesium and Alloys 2023年第6期11卷 2205-2215页

作者： N.A.Ali N.A.Sazelee M.F.Md Din M.M.Nasef A.A.Jalil Haizen Liu M.Ismail Energy Storage Research Group Faculty of Ocean Engineering Technology and InformaticsUniversiti Malaysia Terengganu21030 Kuala NerusTerengganuMalaysia Department of Electrical and Electronic Engineering Faculty of EngineeringNational Defence University of MalaysiaKem Sungai BesiKuala LumpurMalaysia Center of Hydrogen Energy Institute of Future EnergyUniversiti Teknologi Malaysia81310 UTM Johor BahruJohorMalaysia Department of Chemical and Environmental Engineering Malaysia Japan International Institute of TechnologyUniversiti Teknologi MalaysiaJalan Sultan Yahya PetraKuala Lumpur 54100Malaysia Faculty of Chemical and Energy Engineering Universiti Teknologi Malaysia81310 UTM Johor BahruJohorMalaysia Guangxi Novel Battery Materials Research Center of Engineering Technology State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite StructuresSchool of Physical Science and TechnologyGuangxi UniversityNanning 530004China State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures Nanning 530004China

Magnesium hydride(MgH_(2))is the most feasible and effective solid-state hydrogen storage material,which has excellent reversibility but initiates decomposing at high temperatures and has slow kinetics ***,zinc titanate(Zn_(2)TiO_(4))synthesised by the solid-state method was used as an additive to lower the initial temperature for dehydrogenation and enhance the re/dehydrogenation behaviour of MgH_(2).With the presence of Zn_(2)TiO_(4),the starting temperature for the dehydrogenation of MgH_(2)was remarkably lowered to around 290℃–305℃.In addition,within 300 s,the MgH_(2)–Zn_(2)TiO_(4)sample absorbed 5.0 wt.%of H_(2)and 2.2–3.6 wt.%H_(2)was liberated from the composite sample in 30 min,which is faster by 22–36 times than as-milled MgH_(2).The activation energy of the MgH_(2)for the dehydrogenation process was also downshifted to 105.5 k J/mol with the addition of Zn_(2)TiO_(4)indicating a decrease of 22%than as-milled MgH_(2).The superior behaviour of MgH_(2)was due to the formation of Mg Zn_(2),MgO and MgTiO_(3),which are responsible for ameliorating the re/dehydrogenation behaviour of MgH_(2).These findings provide a new understanding of the hydrogen storage behaviour of the catalysed-MgH_(2)system.

关键词： Hydrogen storage Solid-state storage MgH_(2) Additive Zn_(2)TiO_(4)

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：