检索结果-内蒙古大学图书馆

A comparison of unsupervised and supervised machine learning algorithms to predict water pollutions

Procedia Computer Science 2022年 204卷 172-179页

作者： Nurnadiah Zamri Mohammad Ammar Pairan Wan Nur Amira Wan Azman Siti Sabariah Abas Lazim Abdullah Syibrah Naim Zamali Tarmudi Miaomiao Gao Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Besut Campus Besut Terengganu Malaysia Management Science Research Group Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu Malaysia Management Science Research Group Computer and Information Sciences University of Strathclyde Glasgow United Kingdom Universiti Technology MARA Johor Branch Segamat Johor Malaysia Faculty of Biology Medicine and Health School of Medical Siences University of Manchester Manchester United Kingdom

Clean and safe water is vital for our lives and public health. In recent decades, population growth, agriculture, industries, and climate change have worsened freshwater resource depletion and clean water pollution. Several studies have focused on water pollutions risk simulation and prediction in the presence of pollution hotspots. However, the increase and complexity of big data caused by uncertain water quality parameters led to a new efficient algorithm to trace the most accurate pollution hotspots. Therefore, this study proposes to offer different algorithms and comparative studies using Machine Learning (ML) algorithms. Ten different most widely used algorithms, including unsupervised and supervised ML, will be employed to categorize the pollution hotspots for the Terengganu River. Besides, we also validate algorithms’ accuracies by improving and changing each parameter in ML algorithms. Our results list all the accurate and efficient ML algorithms for the classification of river pollutions. These results help to facilitate river prediction using efficient and accurate algorithms in various water quality scenario.

关键词： Machine Learning Deep Learning Water Pollutions Terengganu River

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Gradient-Based Optimization Techniques Using Multidimensional Surface 3D Visualizations and Initial Point Sensitivity

arXiv

引用

arXiv 2024年

作者： Asadi, Saeed Gharibzadeh, Sonia Zangeneh, Shiva Reihanifar, Masoud Rahimi, Morteza Abdullah, Lazim Department of Civil Engineering The University of Texas at Arlington ArlingtonTX United States Department of Computer Engineering South Tehran Branch Islamic Azad University Tehran Iran Faculty of Engineering University of Malayer Malayer Iran Department of Civil and Environmental Engineering University of California at Berkeley BerkeleyCA United States Department of Civil and Environmental Engineering BarcelonaTech Technical University of Catalonia Barcelona Spain Knight Foundation School of Computing and Information Sciences Florida International University MiamiFL United States Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Malaysia

This study examines several renowned gradient-based optimization techniques and focuses on their computational efficiency and precision. In the study, the steepest descent, conjugate gradient (Fletcher-Reeves and Polak-Ribiere variants), Newton-Raphson, quasi-Newton (BFGS), and Levenberg-Marquardt techniques were evaluated. These methods were benchmarked using Rosenbrock's, Spring Force Vanderplaats', Ackley's, and Himmelblau's functions. We emphasize the critical role that initial point selection plays in optimizing optimization outcomes in our analysis. It is also important to distinguish between local and global optima since gradient-based methods may have difficulties dealing with nonlinearity and multimodality. We illustrate optimization trajectories using 3D surface visualizations in order to increase understanding. While gradient-based methods have been demonstrated to be effective, they may be limited by computational constraints and by the nature of the objective functions, necessitating the use of heuristic and metaheuristic algorithms in more complex situations. Copyright © 2024, The Authors. All rights reserved.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Analysis of intelligent solar ICU water ambulance to optimize energy

引用

Annals of Medicine and Surgery 2022年 80卷 104141-104141页

作者： Hasan, Tawheed Jamaludin, Shahrizan Nik, WB Wan Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus 21030 Malaysia Industrial Center of Excellence (ICoE) Universiti Malaysia Terengganu Kuala Nerus 21030 Malaysia

To enhance health and medical facilities, some authorities have recently introduced an emergency special water vehicle known as a ‘water ambulance’. This vehicle is distinct for remote areas. To operate the ambulance service, environmental issues and energy resources have become major concerns. This is a scope of research to address the issues. First, the possibility of using solar energy as the sole power source for a vessel is a perfect solution to these issues. Second, solar vessels operate everywhere without polluting the environment. In addition, another contribution of the research is to integrate a control unit in a water ambulance which is called an ‘intelligent unit’. This unit will prioritize the source of energy to ensure uninterrupted power to emergency medical equipment and ambulances. This paper proposes a dynamic design of a solar water ambulance that is subject to replacing small conventional fuel-run watercraft vehicles. © 2022 The Authors

关键词： ICU Recue Smart solar Solar system Solar water ambulance

来源：评论

学校读者我要写书评

暂无评论

Libraries on metaverse, do they exist?

引用

Library Hi Tech News 2023年第6期40卷 1-2页

作者： Nove E. Variant Anna Dessy Harisanty Noraini Ismail Nove E. Variant Anna nove.anna@vokasi.unair.ac.id is based at the Faculty of Vocational Studies Universitas Airlangga Surabaya Indonesia Dessy Harisanty dessy.harisanty@vokasi.unair.ac.id is based at the Faculty of Vocational Studies Universitas Airlangga Surabaya Indonesia Noraini Ismail noraini@umt.edu.my is based at the Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Malaysia

Purpose This paper aims to explore the existence of Metaverse or 3D virtual libraries and how they use Metaverse to expand library services. Design/methodology/approach The authors use literature to search projects and research papers that discuss the metaverse library. They also did observations on metaverse libraries. Findings There are some virtual realities or metaverse platforms that a library or virtual community can use to build their 3D virtual world. Some libraries already create a virtual world library or metaverse library. However, those initiatives are still in the prototype stage and are used for exhibitions and projects. Originality/value This paper overviews and builds a simple understanding of the metaverse library. The value of the paper is giving motivation when building the metaverse library. This initiative shows that big hi-tech companies do not dominate Metaverse.

关键词： Virtual reality Metaverse Libraries Education Virtual library Literacy

来源：评论

学校读者我要写书评

暂无评论

Aesthetic user interfaces ranking using fuzzy analytic hierarchy process (FAHP) approach

引用

AIP Conference Proceedings 2023年第1期2484卷

作者： Fatin Sarah Salim Zuriana Abu Bakar Noor Maizura Mohamad Noor Rosmayati Mohemad Ily Amalina Ahmad Sabri Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia

In decision making, multiple approach can be applied to solve a problem according to its nature. Analytic Hierarchy Process (AHP) approach is one of them. AHP is widely used in both qualitative and quantitative problem solving. AHP however is unable to handle problem that are vague in nature, thus this is where fuzzy set is essential. Fuzzy refers to the uncertainty in decision making, it reflects the criteria of human that can be very ambiguous in deciding their preferences. Fuzzy Analytic Hierarchy Process (FAHP) method determine weight criteria and priorities of alternative in a structured manner through pair wise comparison thus eliminating the fuzziness of a problem. The aim of this study is to rank aesthetic user interfaces using the FAHP method in five (5) design attributes: contrast, consistency, balance, emphasis and alignment. The interfaces are very subjective; it could vary from a user to another. Thus, this study proposes a model using FAHP as a method to calculate the weight of each alternative in relation to each criterion to get the most aesthetic interface. The result of the study shows that contrast is the most important criteria in deciding aesthetic interface from five (5) experts that involve in user interface design domain. The model produce can act as a guideline in designing interface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trend of decision support system frameworks from 2010-2021

引用

AIP Conference Proceedings 2023年第1期2746卷

作者： Mohammad Jazli Shafizan Jaafar Noor Maizura Mohamad Noor Noraida Ali Rosmayati Mohemad Noor Azliza Che Mat Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Terengganu Terengganu Malaysia

A current literature review of several academic papers and articles available on the internet, research carried out to assess the Decision Support System (DSS) Framework in the context of an overview of the goals for the period 2010 to 2021. We present a descriptive analysis of the current state of the Decision Support System Framework domain based on studies published in the following databases: Science Direct, Springer Link, ProQuest, Web of Science, and EBSCO reports on the Decision Support System Framework. We utilized the following keyword sequence for this project: Years 2010 to 2021; The titles is “Decision Support System Framework.” 21 DSS framework studies published between January 2010 and September 2021 were kept and evaluated using the previously mentioned inclusion and exclusion criteria. DSS framework are intended to enable various unstructured decision-making processes and will evolve and adapt in response to new problems and environments. Through a detailed survey, we identify possible gaps in determining the trend and framework of risk management DSS framework in teaching and learning. The number of publications in the DSS framework has increased due to these publication since 2017, but the absolute frequency of publications has remained low.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An intelligent autonomous surface vehicle manoeuvring analysis in restricted waters via neuroevolutionary method

引用

AIP Conference Proceedings 2023年第1期2484卷

作者： N. I. Jalal A. F. Ayob J. S. Norbakyah A. R. Salisa 1Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Terengganu Malaysia

Autonomous surface vehicle (ASV) is beneficial to complete tasks that are beyond human limits such as offshore target detection, search-and-rescue (SAR) mission and offshore surveillance. The use of ASV may cater to lower the risks exposed to human operators in the shipping business for transporting cargo, handling congestion in waterways and harbours. Manoeuvring operations are complex and challenging for human pilots to conduct, in which with a slight error, may lead to marine incidents such as capsizing, grounding and collision. The application of ASV is advantageous as a human surrogate to operate in heavy traffic and restricted waters, therefore preserving human pilot safety and economic factors. ASV control is akin to the operation of human operators owing to the combination of mathematical models and artificial neural networks. This paper presented the capability of an ASV for decision-making to perform course-keeping and course-changing manoeuvring in restricted water. The neuroevolutionary method (combination single-layer artificial neural network (ANN) and genetic algorithm (GA)) is demonstrated in this work to utilize a simulation environment to train an ASV to operate without human intervention. The performance of the ASV to accomplish the piloting task faster compared to a human operator is highlighted as the result of the work. In this work, the movement of the ASV's rudder owing to an ANN bias due to imbalanced waterway turns setup (either to port or starboard direction). In future work, the training of the ASV may develop with implement the combination algorithms of multiple layer feedforward ANN and GA to perform autonomous navigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PREFACE: Proceedings of the 1st International Conference on Material Processing and technology (ICMProTech, 2021) 14-15 July 2021

引用

Journal of Physics: Conference Series 2021年第1期2129卷

作者： Muhammad, Noorhafiza Bin Wan Ibrahim, Wan Abdul Rahman Assyahid Bin Abd Rahim, Irfan Rosli, Muhamad Farizuan Bin Mat Saad, Mohd Nasir Omar, Mohd Firdaus Rahman, Rozyanty Salleh, Mohd Arif Anuar Mohd Fathullah, Mohd Shuaib, Norshah Afizi Leman, Abdul Mutalib Bin Kamarudin, Khairu Maarof, Mohd Rashidi Bin Ali, Mohd Basri Saad, Mohd Sazli Suhaimi, Mohd Azlan Sharif, Safian Zaharuddin, Mohd Faridh Ahmad bin Ghazali, Che Mohd Ruzaidi Centre of Excellence Geopolymer and Green Technology Universiti Malaysia Perlis Malaysia Faculty of Chemical Engineering Technology Universiti Malaysia Perlis Malaysia Faculty of Mechanical Engineering Technology Universiti Malaysia Perlis Malaysia Faculty of Engineering Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia Faculty of Mechanical Engineering Universiti Malaysia Pahang Malaysia Faculty of Mechanical and Manufacturing Engineering Technology Universiti Teknikal Melaka Malaysia School of Mechanical Engineering Universiti Teknologi Malaysia Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Malaysia

来源：评论

学校读者我要写书评

暂无评论

Synthesis of copper supported on diapers char as green catalyst for the carboxylation of glycerol

引用

AIP Conference Proceedings 2023年第1期2746卷

作者： Najaa Rozulan Nurul Razali Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu 21030 Kuala Nerus Terengganu Malaysia

The commercialization of biodiesel as an alternative fuel has generate large amount of glycerol as by-product reaching 2.7 billion in 2020 while the concentration of CO2 has continuously increased to 418 ppm in June 2021. The combination of these two materials has gained attention in the industry for commercial and environmental concern. This study focusing on synthesize glycerol carbonate via carboxylation of glycerol using copper oxide as a heterogeneous catalyst supported on diapers char using impregnation method. Four different catalyst loading ratio of Cu/DC was prepared. The best result obtained with the use of Cu/DC with ratio of 0.1:0.9 resulted in 59.7% glycerol conversion and 9.7% selectivity of glycerol carbonate under condition of 150°C, 35 bar of CO2, 100 mmol glycerol, 200 mmol acetonitrile, 6 wt.% to glycerol ratio and was carried out for 5 hours. The result for glycerol carbonate, monoacetin and diacetin yield of Cu/DC with ratio 0.1:0.9 are 5.8%, 5.7% and 0.7% respectively. The morphology and properties of the catalyst was analyzed using scanning electron microscopy and Brunauer Emmett Teller (BET).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Latent Fingerprint Imaging by Spectroscopic Optical Coherence Tomography

SSRN

引用

SSRN 2022年

作者： Strąkowski, Marcin Robert Strąkowska, Paulina Pluciński, Jerzy Department of Metrology and Optoelectronics Faculty of Electronics Telecommunications and Informatics Gdańsk University of Technology 11/12 G. Narutowicza Str. Gdańsk80-233 Poland Institute of Ocean Engineering and Ship Technology Faculty of Mechanical Engineering and Ship Technology Gdańsk University of Technology 11/12 G. Narutowicza Str. Gdańsk80-233 Poland

Optical coherence tomography (OCT) is a non-contact and non-invasive optical method for evaluating semitransparent and scattering objects. Its unique features, such as non-destructive 3D measurements of tested objects with a fast scanning rate, make this technique interesting for latent fingerprint reading, which is the subject of this paper. So far, OCT has not found widespread use for reading fingerprints directly from surfaces due to its insufficient axial resolution. This problem has been overcome by applying spectroscopic analysis to the OCT measurements, which is based on retrieving the spatially resolved spectral characteristics of the recorded backscattered light directly from the OCT measurement data. The spectroscopic analysis is very sensitive to thin film thickness variations, improving the readability of the latent fingerprints by OCT, which is reported here as well. This study includes a description of spectroscopic analysis in combination with OCT and indicates the benefits for thin film evaluation, in particular, latent fingerprints. The example of latent fingerprint OCT measurements enhanced by spectroscopic analysis has been shown, as well as a brief discussion of the method’s applicability. Finally, improving fingerprint OCT imaging contrast and readability by applying spectroscopic analysis have been confirmed. © 2022, The Authors. All rights reserved.

关键词： Thin films

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：