检索结果-内蒙古大学图书馆

An LSTM Based Forecasting for Major Stock Sectors Using COVID Sentiment

Computers, Materials & Continua 2021年第4期67卷 1191-1206页

作者： Ayesha Jabeen Sitara Afzal Muazzam Maqsood Irfan Mehmood Sadaf Yasmin Muhammad Tabish Niaz Yunyoung Nam Department of Computer Science COMSATS University IslamabadAttock CampusPakistan Department of Media Design and Technology Faculty of Engineering&InformaticsUniversity of BradfordBradfordBD71AZUK Department of Smart Device Engineering School of Intelligent Mechatronics EngineeringSejong UniversitySeoulKorea Department of Computer Science&Engineering Soonchunhyang UniversityAsan36538Korea

Stock market forecasting is an important research area,especially for better business decision *** stock predictions continue to be significant for business *** short-term stock market forecasting is usually based on historical market data analysis such as stock prices,moving averages,or daily ***,major events’news also contains significant information regarding market *** effective stock market forecasting system helps investors and analysts to use supportive information regarding the future direction of the stock *** research proposes an efficient model for stock market *** current proposed study explores the positive and negative effects of coronavirus events on major stock sectors like the airline,pharmaceutical,e-commerce,technology,and *** use the Twitter dataset for calculating the coronavirus sentiment with a Long Short-Term Memory(LSTM)model to improve stock *** LSTM has the advantage of analyzing relationship between time-series data through memory *** performance of the system is evaluated by Mean Absolute Error(MAE),Mean Squared Error(MSE),and Root Mean Squared Error(RMSE).The results show that performance improves by using coronavirus event sentiments along with the LSTM prediction model.

关键词： Business intelligence decision making stock prediction long short-term memory COVID-19 event sentiment

来源：评论

学校读者我要写书评

暂无评论

Kco: Balancing Class Distribution in Just-in-Time Software Defect Prediction Using Kernel Crossover Oversampling

SSRN

引用

SSRN 2023年

作者： Ismail, Ahmad Muhaimin Hamid, Siti Hafizah Ab Sani, Asmiza Abdul Daud, Nur Nasuha Mohd Department of Software Engineering Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Faculty of Ocean Engineering Technology and Informatics University Malaysia Terengganu Kuala Terengganu Terengganu21030 Malaysia

ContextThe performance of the defect prediction model by using balanced and imbalanced datasets makes a big impact on the discovery of future defects. Current resampling techniques only address the imbalanced datasets without taking into consideration redundancy and noise inherent to the imbalanced *** address the imbalance issue, we propose Kernel Crossover Oversampling (KCO), an oversampling technique based on kernel analysis and cross-over interpolation. Specifically, the proposed technique aims to generate balanced datasets by increasing data diversity in order to reduce redundancy and *** first represents multidimensional features into two-dimensional features by employing Kernel Principal Component Analysis (KPCA). KCO then divides the plotted data distribution by deploying spectral clustering to select the best region for interpolation. Lastly, KCO generates the new defect data by cross-interpolating different data templates within the selected data *** to the prediction evaluation conducted, KCO consistently produced F-scores ranging from 21% to 63% across six datasets, on average. According to the experimental results presented in this study, KCO provides more effective prediction performance than other baseline *** experimental results show that KCO within project and cross project predictions especially consistently achieve higher performance of F-score results. © 2023, The Authors. All rights reserved.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Review on Advance Monitoring of Electrical and Mechanical Failure in Submersible Pump

Review on Advance Monitoring of Electrical and Mechanical Fa...

引用

International Conference on Electrical, Control and Instrumentation engineering (ICECIE)

作者： T. S. N. F. Tuan Mohamad N. Afrizal M.Z. Daud M.R. Awal Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Terengganu Terengganu Malaysia

ISBN: (纸本)9781665480772

Electrical Submersible Pump (ESP) is one of the most efficient and reliable devices for lifting moderate to high volumes of fluids from wellbores. It is commonly used in the oil and gas industry, where it provides high volumes of lifting with the flexibility to cover a range of sizes output flow capacities at various well conditions. Due to its challenging operation environment, ESP prompt to face a fatigue failure, undesirables disruption that lead to shorten its life time. Hence, this work attempts to review and summarise recent research and development in ESP performance monitoring and early fault detection focusing on mechanical and electrical failures. The paper starts with a brief explaination of pump operating mechanism followed by detail discussion on ESP failures and detail explanation of various methods on ESP performance monitoring. A recent and advance failure detection methods applied on ESP also discussed including the main principles of the motor currents signature analysis (MCSA) method. Finally, the authors discuss practical aspects and challenges related to data processing and real-world implementation on ESP monitoring condition.

关键词： Shafts Condition monitoring Vibrations Induction motors Fluids Fault detection Pumps

来源：评论

学校读者我要写书评

暂无评论

Design and Implement of REST API for Data Integration 8

Design and Implement of REST API for Data Integration

引用

8th International Conference on engineering and Emerging Technologies, ICEET 2022

作者： Yusof, Mohd Kamir Man, Mustafa Ismail, Azli Universiti Sultan Zainal Abidin Faculty of Informatics and Computing Terengganu Besut 22200 Malaysia Universiti Malaysia Terengganu Faculty of Ocean Engineering Technology and Informatics Terengganu Kuala Nerus21030 Malaysia Wisma Dataran Rimba Square Lieos SDN BHD Lot 37744 Tingkat 1 Terengganu Kuala Nerus21300 Malaysia

ISBN: (纸本)9781665491068

Data integration is currently most important to organization to integrate data from different data sources using different platform or programming languages. A suitable approach is required to allow one system send the data to another system using standard data format. REST API is one approach can used for data integration using JSON format. Three processes are involved in this approach. There are extract data, send data, received and dump data. In this approach, SAP system will be sending the data in JSON to FEMS system. FEMS system will be exploded and dump the data into database FEMS. Based the experiment, the result indicates, REST API is successfully implemented by showing less response time and CPU usage during sending and receiving the data in JSON format. © 2022 IEEE.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

MalCov: Covid-19 Fake News Dataset in the Malay Language

MalCov: Covid-19 Fake News Dataset in the Malay Language

引用

Visualization, informatics and technology Conference (IVIT), International

作者： N. H. Abd Rahim M. S. H. Basri Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu Malaysia

ISBN: (纸本)9781665486491

The COVID-19 pandemic has drastically changed the world's atmosphere. The virus itself has spread worldwide, so the misinformation related to COVID-19 also created chaos in society. The inaccurate use of infodemic terminology created misleading info about the disease. This tragedy caused panic, confusion among the public, and miscommunication between government information and the public. Several attempts using automated classification via machine learning models have been recently made to avoid the spread of this fake news. These methods require the use of labeled data. However, the scarcity of available corpora for predictive modeling, particularly in languages other than English, is a big barrier challenge in this area. To date, our proposed research may be the first step in an extensive study of fake news detection in the Malay language. We introduce MalCov (Malaysia Covid) fake news dataset for the purpose. The MalCov which contains 79.5% fake articles or approximately 171 statements are gathered from main social media platforms. The remaining statements are valid articles that have been checked and manually validated by the local authorities. All these articles are gathered from a single portal called "***" Since we are using a non-English language for this dataset, the data has been separated into contents and titles. The most frequent words used are then analyzed. Several machine learning models such as Naïve Bayes, SVM, and Logistic Regression are utilized to build the classifiers. As a result, the decision tree achieves the highest performance, which is 93.48%. Keywords—dataset; fake news; fake news detection; machine learning classification; Malay language.

关键词： COVID-19 Support vector machines Terminology Social networking (online) Pandemics Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of unsaturated polyester/epoxidized palm oil/Kenaf fibre composite at different styrene content

Mechanical properties of unsaturated polyester/epoxidized pa...

引用

Innovative Manufacturing, Mechatronics & Material Forum 2022, iM3F 2022

作者： Rahman, Ahmad Syafiq Ridzuan Mustapha, Rohani Mustapha, Siti Noor Hidayah Advanced Biopolymer Group Faculty of Industrial Sciences and Technology Universiti Malaysia Pahang Lebuhraya Tun Razak Gambang Kuantan Pahang26300 Malaysia Environmental Sustainable Material Research Interest Group Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Kuala Nerus21030 Malaysia

Polyester resin (UPE) is petroleum-based polymer that most generally utilized as matrix system in fibre-reinforced plastic (FRP) products due to its high properties per price ratio. Currently, researchers are interested in partial blends of UPE resin with vegetable oil reinforced with natural fibre to produce renewable and sustainable composite products. However, the mechanical properties of this new blending bio-composite are highly related to the curing and crosslinking process of the UPE resin;which contributed by the styrene concentration as the crosslinking agent. Thus, this research aims to investigate the effect of styrene contents on the mechanical and thermal properties of unsaturated polyester (UPE)/epoxidized palm oil (EPO)/kenaf composites. The kenaf fibres were initially treated with an alkaline solution, and the composites were prepared by the direct mixing method and fabricated by hand lay-up technique. In this research, the amount of EPO and styrene varied at 0, 10, 20, 30 wt% and 25, 35, and 45 %, respectively. The characterization of found that increasing styrene content in UPE/EPO/kenaf composites improved the crosslinking and chemical interactions in the composites. In addition, increasing styrene content also improved the tensile modulus, tensile strength, Izod impact strength and elongation at break of the UPE/EPO/kenaf composites. © 2022 Elsevier Ltd. All rights reserved.

关键词： Palm oil

来源：评论

学校读者我要写书评

暂无评论

Water Absorption Behaviour of Epoxy/Acrylated Epoxidized Palm Oil (AEPO) Reinforced Hybrid Kenaf/Glass Fiber Montmorillonite (HMT) Composites 1

Water Absorption Behaviour of Epoxy/Acrylated Epoxidized Pal...

引用

1st International Conference on Green Materials, Processing and Characterization 2021, ICoGMPAC 2021

作者： Mustapha, Rohani Mustapha, Siti Noor Hidayah Suriani, M.J. Ruzaidi, C.M. Awang, M. School of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Terengganu Malaysia Faculty of Industrial Sciences and Technology Universiti Malaysia Pahang Gambang Malaysia

The use of fiber-reinforced vegetable oil - polymer composites has increased in various technical fields. However, the long-term operating performance of these materials is still not well understood, limiting the development of these composites. In this study, the water absorption performance of hybrid composites, which consist of kenaf fiber and glass fiber as reinforcement, epoxy resin and acrylated epoxidized palm oil (AEPO) as a matrix, and montmorillonite (MMT) nano clays as a filler was evaluated with the function of different fibers layering order. The hand lay-up method is used to produce the composites with the variable number of kenaf fibers and glass fibers layer sequences. The water absorption kinetics of epoxy/AEPO reinforced hybrid kenaf/glass fiber-filled MMT composites are described in this paper. It has been observed that the water absorption rate of the composites depends on the fiber layering sequences. The alternative sequence of Glass-Kenaf-Kenaf-Glass and Kenaf-Glass-Kenaf-Glass composites layers exhibited the lowest moisture absorption rates of 7.61% and 7.63%, respectively. © 2021 Institute of Physics Publishing. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Analysis and Circuit Design of a New 3D Highly Chaotic System and its Application to Pseudo Random Number Generator (PRNG) and Image Encryption

引用

SN Computer Science 2024年第4期5卷 420页

作者： Sambas, Aceng Benkouider, Khaled Kaçar, Sezgin Ceylan, Nurdoğan Vaidyanathan, Sundarapandian Sulaiman, Ibrahim Mohammed Mohamed, Mohamad Afendee Ayob, Ahmad Faisal Mohamad Muni, Sishu Shankar Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Campus Besut Terengganu Kuala 22200 Malaysia Department of Mechanical Engineering Universitas Muhamadiyah Tasikmalaya Tamansari Gobras Tasikmalaya 46196 Indonesia Department of Electronics Faculty of Technology Badji-Mokhtar University B.P. 12 Sidi Ammar Annaba 23000 Algeria Department of Electrical and Electronics Engineering Sakarya University of Applied Sciences Serdivan Sakarya 54050 Turkey Department of Mechanical Engineering Adıyaman University Merkez Adıyaman 02040 Turkey Centre for Control Systems Vel Tech University Tamil Nadu Chennai 600062 India School of Quantitative Science University Utara Malaysia Sintok Kedah Bukit Kayu Hitam 06010 Malaysia Faculty of Education and Arts Sohar University Sohar 311 Oman Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Gong Badak Terengganu Kuala Terengganu 21300 Malaysia Department of Physical Sciences Department of Physical Sciences Indian Institute of Science Education and Research Mohanpur Kolkata 741246 India

In this paper, a new 3D dynamical system with four quadratic nonlinear terms is presented. It is shown that the proposed chaotic system has two saddle-foci, unstable, equilibrium points. Thus, the proposed chaotic system exhibits self-excited chaotic attractors. Dynamical analysis methods such as Lyapunov exponents spectrum, bifurcation diagrams, and phase portraits are used to explore the complex dynamical behaviors of the proposed chaotic system and analyze its basic qualitative properties. It is shown that the maximal Lyapunov exponent (MLE) of the new chaotic system is 7.196, which is a high value. The proposed highly chaotic system exhibits high complexity and it will be very useful for applications in cryptography, encryption and secure communications. The physical feasibility of the proposed system is verified by implementing its electronic circuit schematic using Multisim software. Additionally, a PRNG has been developed using the derived state variables and analyze with NIST-800–22 test. Lastly, we developed a PRNG-based image encryption and employ it for an encryption. The experimental outcomes obtained prove that the 3D chaotic system-based encryption application presented in this section has a very good performance. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Chaos Image encryption Pseudo random number generator

来源：评论

学校读者我要写书评

暂无评论

On preimages of the quasi-treed HNN groups

On preimages of the quasi-treed HNN groups

引用

2021 International Conference on Information technology, ICIT 2021

作者： Aljamal, Khaled Mustafa Ghani, Ahmad Termimi Ab Saleh, Rasheed Mahmood Universiti Malaysia Terengganu Faculty of Ocean Engineering Technology and Informatics Terengganu21030 Malaysia Irbid National University Department of Mathematics Irbid Jordan

ISBN: (纸本)9781665428705

We say that a group G acts on a graph X with inversions if there exist an element g∈G and an edge e∈X such that g transfers e to its inverse e, that is, g(e) = e. A group is called a quasi-treed HNN (treed HNN) group if there exists a tree on which the group acts on with inversion (without inversions) and fixing no elements of the tree. The aim of the paper is to prove that if H and G are two groups and p: H→G is an epimorphism such that G is a quasi-treed HNN group (treed HNN), then H is a quasi-treed HNN group (treed HNN). As an application, we show that if N is a normal subgroup of the group G such that the quotient group G/N is a quasi-treed HNN group (or is a treed HNN group), then H is a quasi-treed HNN group (or is a treed HNN group). © 2021 IEEE.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Ensemble Feature Selection Method Based on Bio-inspired Algorithms for Multi-objective Classification Problem 1st

Ensemble Feature Selection Method Based on Bio-inspired Algo...

引用

1st International Conference of Advanced Computing and informatics, ICACIN 2020

作者： Basir, Mohammad Aizat Hussin, Mohamed Saifullah Yusof, Yuhanis Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Terengganu Malaysia School of Computing Universiti Utara Malaysia Sintok Malaysia

ISBN: (纸本)9789811560477

Feature selection is a challenging task, specifically in achieving an optimal solution. This is due to the difficulties in choosing the most suitable feature selection method as they tend to work individually and cause incorrect feature selection, which in turn affect the classification accuracy. The objective of this research was to utilise the potential of ensemble methods (boosting) with bio-inspired techniques in improving the performance of multi-objective algorithms (ENORA and NSGA-II) in term of optimum features set. The vital stage in this research was the optimisation of both algorithms using suitable bio-inspired search algorithms with an ensemble method. The next step was the confirmation of the optimal selected feature set by performing a classification task. The evaluation metrics were determined based on the number of selected features with good classification accuracy. Eight benchmark datasets with various sizes were carefully chosen to experiment. Experimental results revealed that both algorithms that used the selected bio-inspired search algorithms with an ensemble method have successfully achieved a better solution with an optimum set of features, that is, less number of features with higher classification accuracy on the selected datasets. This discovery implies that the combination of bio-inspired algorithms with an ensemble method (boosting) improves the performance of both algorithms in attribute selection and classification task. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

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：