检索结果-内蒙古大学图书馆

Multi-class classification of COVID-19 and other infections using machine learning model with wavelet and laws features

引用

AIP Conference Proceedings 2024年第1期2919卷

作者： Shaik Mahaboob Basha Aloísio Vieira Lira Neto Mohamed Abd Elaziz Shaik Hashmitha Mohisin Victor Hugo C. e Albuquerque Department of Electronics& Communication Engg N.B.K.R. Institute of Science &Technology Vidyanagar India Graduation Program in Telecommunication Engineering Federal Institute of Ceará Fortaleza-CE Brazil Faculty of Computer Science and Engineering Galala University Suez 435611 Egypt Department of Avionics Indian Institute of Space Science and Technology Thiruvananthapuram India Department of Teleinformatics Engineering Federal University of Ceará Fortaleza-CE Brazil

Corona virus disease (COVID-19) was responsible for inevitable chaos in the human life due to its inherent nature of high contagious across the globe. This very reason also hindered the physicians and healthcare support systems to provide in-time medical aid to the suffering *** diagnosis of COVID-19 using clinical information is the prime source for detection and treatment. However, computerised tomography (CT) and Chest X-ray (CXR) images have found useful for screening purposes due to the successful usage of image based analysis by physicians which was aided by image processing based *** means of screening, diagnosis and prognostic studies using CT and CXR with the help of comprehensive image processing pipelines could invariably augment the efficiency in the respective tasks. The main objective of this study is to implement multi-class classification of COVID-19, viral-pneumonia (VP) and lung opacity (LO) using threshold-based segmented CXR images further transformed using wavelet transform (WT)and Laws based texture representation. Machine learning (ML) based implementation and comparison was carried using Random Forest (RF) and Logistic regression (LR) techniques with of the WT and Laws features individually as well as with combined feature vectors. The ML based implementation was aimed to classify the CXR image based on the individual or combined features into COVID-19, VP or LO pathology. The validation of the ML techniques was further carried using confusion matrix and other validation measures. The performance of the RF classifier was superior with WT features than Laws texture features on individual category of features than LR technique. Amarginal improvement was observed in the classifier performance when WT and Laws based features were combined.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis and Comparative Between Profile Matching and SAW Method in Decision Support

Analysis and Comparative Between Profile Matching and SAW Me...

引用

International Conference on Cyber and IT Service Management (CITSM)

作者： Helmi Kurniawan Ashari P Swondo Eka Purnama Sari Khairul Ummi Muhammad Rusdi Tanjung Yusfrizal Faculty of Engineering and Computer Science Universitas Potensi Utama Medan Indonesia English Education Study Program Universitas Potensi Utama Medan Indonesia Faculty of Economy and Business Universitas Potensi Utama Medan Indonesia Visual Communication Design Study Program Universitas Potensi Utama Medan Indonesia

ISBN: (数字)9781728177014

ISBN: (纸本)9781728177021

A decision support system is a solution to help provide decision recommendations in determining which options to choose as a solution, in this decision support system research, namely analyzing and comparing the Matching Profile method and the SAW (Simple Additive Weighting) method in providing the best choice solution in the case of determining teaching staff acceptance. Determination of Admission, The selected teaching staff, are teaching staff who are in accordance with the criteria and quality. In an educational institution, namely TPQ Anbata, it is a very important issue to get elected teaching staff. One way to get teaching staff who is in accordance with the cafeteria is determined by selecting or determining prospective teaching staff by paying attention to various assessment criteria so that the selected teaching staff is feasible. From the tests that have been carried out, the results obtained include all test cases, and the testing is appropriate. The results of the system calculation accuracy test show that the calculation of Matching Profile and SAW (Simple Additive Weighting Method carried out by the system with manual calculations is correct and the feasibility test. Appropriate to use in making decisions determining the recruitment of teachers than the profile matching method in Anbata TPQ. The difference is in the highest value in each method. In the profile matching method, the highest value is Salman Al Fariz with a value of 4.70 while in the SAW method the highest value is Ali Gufron with a value of 8,778., it can be concluded that the most appropriate method in determining the recruitment of teaching staff at TPQ Anbata is the Profile Matching Method.

关键词： Education Surface acoustic waves Decision support systems Additives Recruitment Decision making Writing

来源：评论

学校读者我要写书评

暂无评论

Enhanced classification accuracy for cardiotocogram data with ensemble feature selection and classifier ensemble

arXiv

引用

arXiv 2020年

作者： Silwattananusarn, Tipawan Kanarkard, Wanida Tuamsuk, Kulthida Department of Library and Information Science Faculty of Humanities and Social Sciences Prince of Songkla University Hat Yai Thailand Department of Computer Engineering Faculty of Engineering Khon Kaen University Khon Kaen Thailand Information and Communication Management Program Faculty of Humanities and Social Sciences Khon Kaen University Khon Kaen Thailand

In this paper ensemble learning based feature selection and classifier ensemble model is proposed to improve classification accuracy. The hypothesis is that good feature sets contain features that are highly correlated with the class from ensemble feature selection to SVM ensembles which can be achieved on the performance of classification accuracy. The proposed approach consists of two phases: (i) to select feature sets that are likely to be the support vectors by applying ensemble based feature selection methods;and (ii) to construct an SVM ensemble using the selected features. The proposed approach was evaluated by experiments on Cardiotocography dataset. Four feature selection techniques were used: (i) Correlation-based, (ii) Consistency-based, (iii) ReliefF and (iv) Information Gain. Experimental results showed that using the ensemble of Information Gain feature selection and Correlation-based feature selection with SVM ensembles achieved higher classification accuracy than both single SVM classifier and ensemble feature selection with SVM classifier. © 2020, CC-BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal assessment of whole-body center of mass coordination on standard maximum vertical jump

引用

Gait & Posture 2022年 97卷 S208-S209页

作者： Rodrigues, C. Correia, M. Abrantes, J. Rodrigues, B. Nadal, J. Faculty of Engineering- University of Porto Biomedical Engineering Program Porto Portugal INESC TEC - Institute for Systems and Computer Engineering- Technology and Science C-BER - Centre for Biomedical Engineering Research Porto Portugal University of Porto Faculty of Engineering Porto Portugal Lusófona University- CICANT - Centre for Research in Applied Communication- Culture and New Technologies MovLab Laboratory of Technologies for Interactions and Interfaces Lisbon Portugal Federal University of Pernambuco Department of Electronic and Systems Recife Brazil Federal University of Rio de Janeiro Biomedical Engineering Program Rio de Janeiro Brazil

来源：评论

学校读者我要写书评

暂无评论

The matter of deep reinforcement learning towards practical ai applications 12

The matter of deep reinforcement learning towards practical ...

引用

12th International Conference on Ubi-Media Computing, Ubi-Media 2019

作者： Thaipisutikul, Tipajin Chen, Yi-Cheng Hui, Lin Chen, Sheng-Chih Mongkolwat, Pattanasak Shih, Timothy K. Department of Computer Science and Information Engineering National Central University Taiwan Department of Information Management National Central University Taiwan Department of Innovative Information and Technology Tamkang University Taiwan Master's Program of Digital Content and Technologies College of Communication National ChengChi University Taiwan Faculty of Information and Communication Technology Mahidol University Thailand

ISBN: (纸本)9781728128207

Reinforcement Learning (RL) is an extraordinarily paradigm that aims to solve a complex problem. This technique leverages the traditional feedforward networks with temporal-difference learning to overcome supervised and unsupervised real-world problems. However, RL is one of state-of-the-art topic due to the opaque aspects in design and implementation. Also, in which situation we will get performance gain from RL is still unclear. Therefore, This study firstly examines the impact of Experience Replay in Deep Q-Learning agent with Self-Driving Car application. Secondly, The impact of Eligibility Trace in RNN A3C agents with Breakout AI game application is studied. Our results indicated that these two techniques enhance RL performance by more than 20 percent as compared with traditional RL methods. © 2019 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Service Quality Improvement by Using the Quality Function Deployment (QFD) Method at the Government General Hospital 1

Service Quality Improvement by Using the Quality Function De...

引用

1st Workshop on Environmental Science, Society, and Technology, WESTECH 2018

作者： Hasibuan, Abdurrozzaq Parinduri, Luthfi Sulaiman, Oris Krianto Suleman, Abdul Rahman Harahap, Adek Khadijatul Z Hasibuan, Masnilam Rupilele, Frits Gerit John Simarmata, Janner Kurniasih, Nuning Achmad Daengs, G.S. Abdussakir Faculty of Engineering Universitas Islam Sumatera Utara Medan Indonesia Faculty of Computer Science Universitas Victory Sorong Sorong Indonesia Faculty of Economic Universitas Graha Nusantara Padangsidimpuan Indonesia Universitas Negeri Medan Medan Indonesia Faculty of Communication Sciences Library and Information Science Program Universitas Padjadjaran Bandung Indonesia Faculty of Economic Universitas 45 Surabaya Surabaya Indonesia Faculty of Science and Technology Universitas Islam Negeri Maulana Malik Ibrahim Malang Indonesia

In the face of increasingly competitive competition in the hospital industry, RSU managers are required to be able to develop strategies, policies or new breakthroughs related to improving the quality of their services, through improving the characteristics of hospital services, which focus on patient needs, so that the risk of errors or discrepancies between service characteristics that are enhanced by what the patient wants can be avoided or minimized. From the results of research conducted there are 21 variables of patient needs from a health service at the Government General Hospital (RSU). Whereas the patient's research on the service quality of the Government Hospital is 1 variable that has fulfilled the needs of patients, namely that they are satisfied with the quality of hospital services. Variable is the state and completeness of modern medical facilities. Whereas for other variables there are gaps so that they cannot meet patient expectations until the highest quality limit is very satisfied, it is necessary to have a direction of improvement. To obtain the suitability, the technique used to improve the characteristics of the service is the application of the QFD method. The QFD method in this study is in the form of a quality service matrix at the Government General Hospital. From the HOQ matrix, the service quality of the Government Hospital is obtained from the input of the Government Hospital/management that there are priority variables needed to improve their quality, which is generally the patient's needs related to the recovery of patients, including the knowledge and abilities of doctors, medicines the treatment given in the healing of patients, the service of examination, treatment and care that is fast and precise, guarantee of security and trust in the services provided and the completeness of the readiness and cleanliness of the equipment used. So there are 33 service quality characteristics prioritized for further improvement, with the main pr

关键词： Quality function deployment

来源：评论

学校读者我要写书评

暂无评论

Improvement Suggestion Performance of Blowing Machine Line 4 with Total Productive Maintenance (TPM) Method at PT. Coca-Cola Amatil Indonesia MedanUnit 1

Improvement Suggestion Performance of Blowing Machine Line 4...

引用

1st International Conference of SNIKOM 2018, ICoSNIKOM 2018

作者： Irwansyah, Defi Harahap, M.R.F. Erliana, Cut Ita Abdullah, Dahlan Sari, Ayuesteka Siregar, Nurintanasyiah Achmaddaengs, G.S. Indahingwati, Asmara Sumartono, Eko Wilujeng, Sri Nurmawati Subekti, Purwo Kurniasih, Nuning Rosalina, Febrianti Hartono, H. Departement of Industrial Engineering Universitas Malikussaleh Aceh Indonesia Departement of Informatics Universitas Malikussaleh Aceh Indonesia Department of Management STIE Sakti AlamKerinci Jambi Indonesia Department of Management STIE Labuhanbatu Sumatera Utara Indonesia Department of Management Universitas 45 Surabaya Indonesia Department of Management School of Economics Indonesia STIESIA Surabaya Indonesia Faculty of Agriculture Universitas Bengkulu Bengkulu Indonesia Department of Management Faculty of Economy Universitas Kanjuruhan Malang Indonesia Program Study of Industrial Engineering University of 45 Surabaya Indonesia Mechanical Engineering Pasir Pengaraian University Riau Indonesia Faculty of Communication Sciences Library and Information Science Program Universitas Padjadjaran Bandung Indonesia Department of Agrotechnology Universitas Muhammadiyah Sorong Sorong Indonesia Department of Computer Science STMIK IBBI Medan Indonesia

Maintenance is an activity to maintain facilities or equipment of the factory and make repairs or adjustments to the necessary replacement to satisfactory condition of production operations in accordance with what is planned. Companies often experience damage to the Blowing machine so that interconnected machines cannot be operated. The purpose of this study was to improve the performance of Blowing line 4 engines with the Total Productive Maintenance (TPM) method at PT. Coca-Cola Amatil Indonesia Medan Unit, also to determine the level of Blowing machine performance based on the analysis of overall equipment effectiveness (OEE) at PT. Coca-Cola Amatil Indonesia Medan Unit. The method used in this study is the overall equipment effectiveness (OEE) method to measure Ishikawa's treatments and diagrams to compare and propose low engine performance. The results of data processing shows machine maintenance has not comply the OEE standards in July 81.48%, August 81.48%, September 78.07%, October 81.22%, November 78.08%, and those that fill the standards in June amount to 86.48%, with losses that most affect the effectiveness of equipment in line 4 blowroom machine is Equipment Failure Losses of 11.42% based on the results of the study, the proposed improvement in engine performance is to provide training to employees, and increase operator awareness. against engine damage, thus the production process will run smoothly. © Published under licence by IOP Publishing Ltd.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Application of Message Security Application Using Vigenere Cipher Algorithm Utilizing One Time Pad (OTP) Algorithm as a Key Generator 1

Application of Message Security Application Using Vigenere C...

引用

1st Workshop on Environmental Science, Society, and Technology, WESTECH 2018

作者： Pardede, A.M.H. Br Sitepu, Lorena Perbina Zarlis, Muhammad Tulus Iskandar, Akbar Sriadhi, S. Manurung, Rosida Tiurma Siregar, Nurintan Asyiah Sari, Ayu Esteka Yunawati, Sri Mursyidah, M. Mursalin, M. Kurniasih, Nuning Kurniawan, Citra Winarno, Edy STMIK Kaputama Sumatera Utara Binjai Indonesia Department of Computer Science Universitas Sumatera Utara Medan Indonesia Department of Mathematics Universitas Sumatera Utara Medan Indonesia Department of Electrical Engineering Universitas Negeri Medan Indonesia Graduate Program in Scientific Psychology Universitas Kristen Maranatha Indonesia Department of Management STIE Labuhanbatu Sumatera Utara Indonesia Department of Management STIE Sakti Alam Kerinci Jambi Indonesia Program Study of Accounting Pasir Pengaraian University Riau Indonesia Departement of Information Technology and Computer Politeknik Negeri Lhokseumawe Aceh Indonesia Department of Mathematics Education Universitas Malikussaleh Aceh Indonesia Faculty of Communication Sciences Library and Information Science Program Universitas Padjadjaran Bandung Indonesia Department of Electrical Engineering Sekolah Tinggi Teknik Malang Indonesia Faculty of Information Technology Universitas Stikubank Semarang Indonesia

Cryptography is the science and art of maintaining the security of messages when messages are sent from one place to another. One of the ways securing the form of text message information is by the encryption process using the Vigenere Cipher algorithm and utilizing the One Time Pad (OTP) algorithm as a key generator, where the message will be random when it is opened. The message encryption process used the vigenere cipher algorithm while OTP is used to secure the key with the same formula. After this research has been done, an application was designed to secure text messages by converting the text message into a random message so that the message was unreadable due to a secret message that could not be known by others. The results achieved can secure an encrypted message that cannot be reopened and if those messages were reopened, they must be decrypted. © Published under licence by IOP Publishing Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

The Matter of Deep Reinforcement Learning Towards Practical AI Applications

The Matter of Deep Reinforcement Learning Towards Practical ...

引用

IEEE International Conference on Ubi-Media Computing

作者： Tipajin Thaipisutikul Yi-Cheng Chen Lin Hui Sheng-Chih Chen Pattanasak Mongkolwat Timothy K. Shih Department of Computer Science and Information Engineering National Central University Taiwan Department of Information Management National Central University Taiwan Department of Innovative Information and Technology Tamkang University Taiwan Master's Program of Digital Content and Technologies College of Communication National ChengChi University Taiwan Faculty of Information and Communication Technology Mahidol University Thailand

ISBN: (数字)9781728128207

ISBN: (纸本)9781728128214

关键词：

来源：评论

学校读者我要写书评

暂无评论

DEA Model with Hesitant Fuzzy Polyhedral Set in Benchmarking 1

DEA Model with Hesitant Fuzzy Polyhedral Set in Benchmarking

引用

1st International Conference of SNIKOM 2018, ICoSNIKOM 2018

作者： Abdullah, Dahlan Hartono, H. Erliana, Cut Ita Irwansyah, Defi Siregar, Nurintan Asyiah Sari, Ayu Esteka Hasibuan, Abdurrozzaq Abdussakir Kurniasih, Nuning Mas'Ut Rangkuti, Irma Yanti Nurmawati Buston, Erni Abdurrahman, Apridar Handayani, Tita Septi Hadikurniawati, Wiwien Winarno, Edy Department of Informatics Universitas Malikussaleh Aceh Indonesia Department of Computer Science STMIK IBBI Medan Indonesia Department of Industrial Engineering Universitas Malikussaleh Aceh Indonesia Department of Management STIE Labuhanbatu Sumatera Utara Indonesia Department of Management STIE Sakti Alam Kerinci Jambi Indonesia Faculty of Engineering Universitas Islam Sumatera Utara Medan Indonesia Department of Mathematics Education State Islamic University of Malang Malang Indonesia Faculty of Communication Sciences Library and Information Science Program Universitas Padjadjaran Bandung Indonesia Faculty of Economic Universitas Islam Sumatera Utara Medan Indonesia Faculty of Medical Universitas Islam Sumatera Utara Medan Indonesia Faculty of Industry Technique University of 45 Surabaya Indonesia Departement of Nursing Politeknik Kesehatan Kementerian Bengkulu Indonesia Department of Management Universitas Malikussaleh Aceh Indonesia Departemen of Nursing Universitas Dehasen Bengkulu Indonesia Faculty of Information Technology Universitas Stikubank Semarang Indonesia

Data Envelopment Analysis (DEA) method is a linear programming approach that has been widely used as a framework for evaluating efficiency and measurement. DEA decision making is often faced with situations where the existing DMU has input and output that contains fuzzy and hesitant elements so that it is difficult to make efficiency measurements. This study will design a DEA model in the state of inputs and outputs that contain hesitant elements by using polyhedral uncertainty sets. The results of this study are expected to produce a benchmarking model with DEA that can overcome the hesitant element and have the advantage of using a polyhedral uncertainty set that can measure the linearity of the nominal problem. © Published under licence by IOP Publishing Ltd.

关键词： Data envelopment analysis

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：