检索结果-内蒙古大学图书馆

Comparative study of test on covariance performance in two outlier scenarios

AIP Conference Proceedings 2024年第1期2895卷

作者： Sharifah Sakinah Syed Abd Mutalib Siti Zanariah Satari Wan Nur Syahidah Wan Yusoff Centre for Mathematical Sciences College of Computing & Applied Sciences Universiti Malaysia Pahang Lebuh Persiaran Tun Khalil Yaakob 26300 Kuantan Pahang Malaysia Faculty of Computer Media and Technology Management University College TATI Jalan Panchur Teluk Kalong 24000 Kemaman Terengganu Malaysia

In practice, multivariate data frequently include outliers. Since outliers can cause incorrect conclusions, a robust estimator must be used to analyze the data as the robust estimator is designed to be resistant to outliers. One of the latest robust estimators for multivariate data is the Test on Covariance (TOC). The performance of TOC has been investigated via simulation studies and historical datasets in few studies. The simulation studies from past researchers used two outlier scenarios, mean shift (Outlier Scenario 1) and covariance shift (Outlier Scenario 2). However, the focus of previous studies is on the number of variables, p ≤ 5 with small to large sample sizes and percentage of outliers ranging from 1% to 25% only. Thus, the objective of this study is to investigate further the performance of TOC with existing robust estimators in these two outliers’ scenarios, however focusing on the number of variables, p ≥ 5, small and moderate sample sizes, and percentage of outliers ranging from 5% to 25%. Measurements used to evaluate the performance of TOC and the existing robust estimators are pout, pmask, and pswamp. The pout is the probability of all outliers successfully detected, pmask is the probability of masking effect, and pswamp is the probability of swamping effect. It is found that, TOC exhibits better results in Outlier Scenario 1 than Outlier Scenario 2, especially when the separation between outliers and inliers is large for pout and pmask. However, the performance of TOC is excellent in both outlier scenarios for pswamp as TOC shows the lowest probability of swamping.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simple Blood Vessel Detection on Retinal Image Using Image Processing Technique

引用

Journal of Physics: Conference Series 2021年第1期1874卷

作者： Siti Nursyafiqah Wan Azani Mustafa Syed Zulkarnain Syed Idrus Mohd Aminudin Jamlos Faculty of Electrical Engineering Technology UniCITI Alam Campus Universiti Malaysia Perlis 02100 Padang Besar Perlis Malaysia Advanced Computing Engineering (AdvComp) Centre of Excellence (CoE) Universiti Malaysia Perlis (UniMAP) Pauh Putra Campus 02600 Arau Perlis Malaysia Faculty of Applied and Human Sciences Universiti Malaysia Perlis 01000 Kangar Perlis Malaysia Faculty of Electronic Engineering Technology UniCITI Alam Campus Universiti Malaysia Perlis 02100 Padang Besar Perlis Malaysia

Detection of blood vessel plays an important stage in different medical areas, such as ophthalmology, oncology, neurosurgery and laryngology. The significance of the vessel analysis was helped by the continuous overview in clinical studies of new medical technologies intended for improving the visualization of vessels. In this paper, a new blood vessel detection using a simple method of image processing was proposed. The main objective is to propose new method in order to detect the blood vessel on the degraded retinal input image (DRIVE dataset). A few Image Quality Assessment (IQA) such as sensitivity, specificity and accuracy was obtained to prove the effectiveness of detection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Metal-oxide nanocatalysts for spontaneous sequestration of endocrine-disrupting compounds from wastewater

引用

Chemosphere 2024年 367卷 143569页

作者： Bamisaye, Abayomi Abati, Shakirudeen Modupe Ige, Ayodeji Rapheal Etafo, Nelson Oshogwue Alli, Yakubu Adekunle Bamidele, Muyideen Olaitan Okon-Akan, Omolabake Abiodun Adegoke, Kayode Adesina Abiola-Kuforiji, Olajumoke T. Idowu, Mopelola Abidemi Bello, Olugbenga Solomon Department of Chemistry Faculty of Natural and Applied Sciences Lead City University Ibadan Nigeria Faculty of Civil Engineering and Environmental Sciences Bialystok University of Technology Wiejska 45E Bialystok15-351 Poland Programa de Posgrado en Ciencia y Tecnología de Materiales Facultad de Ciencias Químicas Universidad Aut'onoma de Coahuila Ing. J. C'ardenas Valdez S/N Republica Coahuila Saltillo25280 Mexico UPR8241 Universit'e de Toulouse UPS INPT Toulouse Cedex 4 ToulouseF-31077 France Department of Chemical Sciences Faculty of Science and Computing Ahman Pategi University Patigi-Kpada Road Kwara State Patigi Nigeria Department of Manufacturing and Materials Engineering Kulliyyah of Engineering International Islamic University Malaysia Jalan Gombak Kuala Lumpur53100 Malaysia Department of Food Research Faculty of Chemical Sciences Universidad Aut'onoma de Coahuila Ing. J. C'ardenas Valdez S/N Republica Coahuila Saltillo25280 Mexico Department of Pure and Applied Chemistry Ladoke Akintola University P. M. B. 4000 Ogbomoso Nigeria Wood and Paper Technology Department Federal College of Forestry Jericho Ibadan Nigeria Department of Industrial Chemistry First Technical University Ibadan Nigeria Department of Molecular Biology and Biotechnology Chrisland University Abeokuta Nigeria Department of Chemistry College of Physical Sciences Federal University of Agriculture Abeokuta Nigeria

The quest for a good life, urbanization, and industrialization have led to the widespread distribution of endocrine-disrupting chemicals (EDCs) in water bodies through anthropogenic activities. This poses an imminent threat to both human and environmental health. In recent years, the utilization of advance materials for the removal of EDCs from wastewater has attracted a lot of attention. Metal-oxide nanocatalysts have emerged as promising candidates due to their high surface area, reactivity, and tunable properties, as well as enhanced surface properties such as mesoporous structures and hierarchical morphologies that allow for increased adsorption capacity, improved photocatalytic activity, and enhanced selectivity towards specific EDCs. As a result, they have shown extraordinary efficacy in removing a wide range of EDCs from aqueous solutions, including pharmaceuticals, agrochemicals, personal care items, and industrial chemicals. This study give insight into the unique physicochemical characteristics of metal-oxide nanocatalysts to effectively and efficiently remove harmful EDCs from wastewater. It also discussed the advances in the synthesis, and properties of metal-oxide nanocatalysts, and insight into understanding the fundamental mechanisms underlying the adsorption and degradation of EDCs on metal-oxide nanocatalysts using advanced characterization techniques such as spectroscopic analysis and electron microscopy. The findings of the study present metal-oxide nanocatalysts as a good candidate for the spontaneous sequestration of EDCs from wastewater is an intriguing approach to mitigating water pollution and safeguarding public health and the environment. © 2024 Elsevier Ltd

关键词： Emerging contaminants Endocrine disruptor chemicals Environment Metal-oxide nanocatalysts Wastewater

来源：评论

学校读者我要写书评

暂无评论

The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach

引用

AIP Conference Proceedings 2024年第1期3123卷

作者： Muhammad Ammar Shafi Mohd Saifullah Rusiman Siti Afiqah Muhamad Jamil Mohd Arif Mohd Zim Faculty of Technology Management and Business Universiti Tun Hussein Onn Malaysia Batu Pahat Johor Malaysia Faculty of Applied Sciences and Technology Universiti Tun Hussein Onn Malaysia Panchor Johor Malaysia College of Computing Informatics and Media School of Mathematical Sciences Universiti Teknologi MARA Shah Alam Selangor Malaysia KPJ Healthcare Berhad Damansara Specialist Hospital 2 Damansara Kuala Lumpur Malaysia

Colorectal cancer (CRC) is a type of cancer that develops in the human colon and rectum. The body’s cells proliferating out of control, which is the cause of colorectal cancer, results in these symptoms. Nevertheless, there is still disagreement on the precise signs of a high-risk CRC. The linear regression model struggles with erroneous and ambiguous data. Because the idea of fuzzy set theory can deal with data that does not refer to a precise point value, fuzzy machine learning, a new hybrid linear fuzzy regression with symmetric parameter clustering with a support vector machine model (FLRWSPCSVM), is used in this study to predict the high-risk symptoms causing the development of colorectal cancer in Malaysia (uncertainty data). After analysing secondary data from 180 colorectal cancer patients who underwent treatment in a general hospital, 25 separate symptoms with diverse combinations of variable types were considered in the analysis. Together with the model’s parameters, errors, and justifications, two statistical measurement errors were also included. The least values of mean square error (MSE) are 100.605 and root mean square error (RMSE) is 10.030 for FLRWSPCSVM, which were determined to be ovarian and a history of cancer symptoms to be the high-risk symptom for developing colorectal cancer. To monitor and control the high-risk symptoms that can affect colon cancer and lower patient mortality, the hospitality industry could also benefit from this study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detoxification of heavy metals from E. affinis using chelation technique

引用

AIP Conference Proceedings 2022年第1期2454卷 050012页

作者： Nurul Syahmin Amir Hamzah Nurasmat Mohd Shukri Wan Nazwanie Wan Abdullah Nur Fatien Muhamad Salleh Noor Zuhartini Md Muslim Farah Shahirah Mohd Fairuz Norshahidatul Akmar Mohd Shohaimi Nor Hakimin Abdullah Ahmad Zamani Ab Halim School of Health Sciences Universiti Sains Malaysia Health Campus 16150 Kubang Kerian Kelantan Malaysia School of Chemical Sciences 11800 Universiti Sains Malaysia Pulau Pinang Malaysia Faculty of Applied Sciences Universiti Teknologi MARA Pahang 24600 Bandar Tun Razak Jengka Pahang Malaysia Advanced Materials Research Cluster (AMRC) Faculty of Bioengineering and Technology Universiti Malaysia Kelantan (UMK) 17600 Jeli Kelantan Malaysia Faculty of Industrial Sciences and Technology College of Computing and Applied Science Universiti Malaysia Pahang 26300 Gambang. Kuantan Pahang Malaysia

Euthynnus affinis (E. affinis) or mackerel tuna is one of the common fish species consumed in Malaysia. There is a limited study conducted to remove heavy metals from contaminated fish species, especially E. affinis. This study aims to investigate the effectiveness of the chelation technique for heavy metals removal, which are lead (Pb), copper (Cu), cadmium (Cd) and nickel (Ni) from fish species. In this study, heavy metal analysis was conducted using flame atomic absorption spectroscopy (FAAS). The initial concentrations of heavy metals in E. affinis species were recorded above the World Health Organization (WHO) and Malaysian Food Regulation (MFR 1985). Three types of chelating agents applied were labelled as trisodium citrate (TSC), disodium oxalate (DSO) and sodium acetate trihydrate (SAT). The optimum conditions yielded in this study were 400 mg/L of trisodium citrate at 1 hour of treatment at temperature 36.50±0.50°C. Therefore, this chelation technique proved that this optimum condition could remove 90% of all heavy metals from E. affinis which concurrently complied with the permissible limit set by WHO and MFR 1985.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Memetic multiobjective particle swarm optimization-based radial basis function network for classification problems” [Inform. Sci. 239 (2013) 165–190]

引用

Information Sciences 2014年 279卷 914-914页

作者： Sultan Noman Qasem Siti Mariyam Shamsuddin Siti Zaiton Mohd Hashim Maslina Darus Eiman Al-Shammari Computer Science Department College of Computer and Information Sciences Al Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz Yemen Soft Computing Research Group Faculty of Computer Science and Information System Universiti Teknologi Malaysia 81310 Skudai Johor Malaysia School of Mathematical Sciences Faculty of Science and Technology Universiti Kebangsaan Malaysia Malaysia Information Science Department College of Computing Sciences and Engineering Kuwait University Kuwait

来源：评论

学校读者我要写书评

暂无评论

Numerical solution of van der Pol equation via fix and variable step size methods

引用

AIP Conference Proceedings 2023年第1期2746卷

作者： Noor Julailah Abd Mutalib Norhayati Rosli Noor Amalina Nisa Ariffin Centre for Mathematical Sciences College of Computing and Applied Sciences Universiti Malaysia Pahang Malaysia Lebuhraya Tun Razak 26300 Gambang Pahang Malaysia Faculty of Electrical & Automation Engineering Technology University College TATI 24000 Kemaman Terengganu Malaysia Faculty of Computer and Mathematical Sciences Universiti Teknologi MARA Jengka Campus 26400 Bandar Tun Razak Pahang Malaysia

This paper devotes to the numerical simulation of Van der Pol equation using fix and variable step size methods. The solution is obtained via two different methods of Runge-Kutta of order 5 (RK5) for fix step size and Runge-Kutta Fehlberg method (RKF) of order 5 for variable step size. The algorithms of fix and variable step size of RK5 and RKF methods, respectively are developed and coded in Matlab for model simulation. Local and global errors are computed for non-stiff and stiff problem of Van der Pol equation. RKF method using variable step size show low values of error for stiff problem with less number of iteration, hence indicate good performance of the method in approximating the solution of the Van der Pol model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Employing derivatives for creating texture masks for digital images

引用

AIP Conference Proceedings 2024年第1期2898卷

作者： Taha Basheer Taha Ruzelita Ngadiran Dujan B. Taha IT Department Faculty of Applied Science Tishk International University Erbil Kurdistan Region Iraq Faculty of Electronic Engineering Technology Universiti Malaysia Perlis 02600 Arau Perlis Malaysia Centre of Excellence Advanced Computing (AdvComp) Universiti Malaysia Perlis 02600 Arau Perlis Malaysia Software Engineering Department College of Computer Science and Mathematics Mosul University Mosul Iraq

Texture masking has been used as a significant factor in creating perceptual maps that simulates human vision system in observing noise in digital images. In this paper, the possibility of creating texture masks using first and second derivatives is investigated and tested. Results shows that after applying the derivatives, areas of higher texture were highlighted and recognized, which will lead to simple implementation of texture masks using numerical analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Adversarial Learning: Vector-Quantized Common Latent Space for Multi-Sequence MRI

arXiv

引用

arXiv 2024年

作者： Han, Luyi Tan, Tao Zhang, Tianyu Wang, Xin Gao, Yuan Lu, Chunyao Liang, Xinglong Dou, Haoran Huang, Yunzhi Mann, Ritse Department of Radiology and Nuclear Medicine Radboud University Medical Centre Geert Grooteplein 10 Nijmegen6525 GA Netherlands Department of Radiology The Netherlands Cancer Institute Plesmanlaan 121 Amsterdam1066 CX Netherlands Faculty of Applied Sciences Macao Polytechnic University Macao Special 999078 China GROW School for Oncology and Developmental Biology Maastricht University Medical Centre P. Debyelaan 25 Maastricht6202 AZ Netherlands Center for Computational Imaging and Simulation Technologies in Biomedicine School of Computing The University of Leeds LeedsLS2 9JT United Kingdom School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China

Adversarial learning helps generative models translate MRI from source to target sequence when lacking paired samples. However, implementing MRI synthesis with adversarial learning in clinical settings is challenging due to training instability and mode collapse. To address this issue, we leverage intermediate sequences to estimate the common latent space among multi-sequence MRI, enabling the reconstruction of distinct sequences from the common latent space. We propose a generative model that compresses discrete representations of each sequence to estimate the Gaussian distribution of vector-quantized common (VQC) latent space between multiple sequences. Moreover, we improve the latent space consistency with contrastive learning and increase model stability by domain augmentation. Experiments using BraTS2021 dataset show that our non-adversarial model outperforms other GAN-based methods, and VQC latent space aids our model to achieve (1) anti-interference ability, which can eliminate the effects of noise, bias fields, and artifacts, and (2) solid semantic representation ability, with the potential of one-shot segmentation. Our code is publicly available 7 Copyright © 2024, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

A Quantum Beta Distributed Multi-Objective Particle Swarm Optimization Algorithm for Twitter Fake Accounts Detection

TechRxiv

引用

TechRxiv 2022年

作者： Aboud, Ahlem Rokbani, Nizar Mirjalili, Seyedali Hussain, Amir Chabchoub, Habib Alimi, Adel M. University of Sousse ISITCom Sousse4011 Tunisia BP 1173 Sfax3038 Tunisia High Institute of Applied Science Technolgy of Sousse University of Sousse Tunisia Centre for Artificial Intelligence Research and Optimisation Torrens University Australia Brisbane Australia Yonsei Frontier Lab Yonsei University Seoul Korea Republic of Edinburgh Napier University School of Computing EdinburghEH10 5DT United Kingdom College of Business Al Ain University of Science and Technology Abu Dhabi United Arab Emirates Department of Electrical and Electronic Engineering Science Faculty of Engineering and the Built Environment University of Johannesburg South Africa University of Sousse Tunisia

Fake account detection is a topical issue when many Online Social Networks encounter several issues caused by the growing number of unethical online activities. This study presents a new Quantum Beta-behaved Multi-Objective Particle Swarm Optimization (QB-MOPSO) algorithm for machine learning based Twitter fake accounts detection. The proposed approach aims to improve the learning process of deep neural networks, random forest, through minimizing simultaneously the feature dimensionality and the classification error rate. The main contribution consists in proposing a quantum beta MOPSO to handle the training phase of neural and deep architectures. The QB-MOPSO is used to perform a multi-objective training of the random forest algorithm. The QB-MOPSO has two optimization profiles: the first one uses a quantum-behaved equation for improving the exploratory behaviour of PSO, while the second one uses a beta function to enhance PSO’s exploitation. An extensive experimental study is carried out using two open Twitter datasets with 1982 and 928 accounts. The new proposal is a random forest QB-MOPSO. Results showed that random forest QB-MOPSO accuracy is about 99.19% and 97.52% accounts on datasets 1 and 2. Comparative analysis of the prosed architecture toward the original architecture showed that the use of QB-MOPSO for learning enhances the random forest algorithm which perform then the original ones. © 2022, CC BY-NC-SA.

关键词： Social networking (online)

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：