检索结果-内蒙古大学图书馆

International Conference on Applied System Innovation (ICASI)

作者： Yu-Chen Tu Hsuan-Chih Wang Chien-Pin Liu Chia-Yeh Hsieh Chia-Tai Chan Department of Biomedical Engineering National Yang Ming Chiao Tung University Taipei City Taiwan Bachelor's Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City Taiwan

ISBN: (数字)9798350394924

ISBN: (纸本)9798350394931

Fall incidents among the elderly represent a significant global concern, often resulting in physical injuries and psychological distress. It is crucial to develop reliable fall detection systems which are capable of identifying fall events immediately and triggering alerts for assistance. However, real-world fall occurrences are infrequent, leading to a highly imbalanced class situation. Training a model with imbalanced datasets may result in biased models with poor performance in fall detection. To address this challenge, various techniques such as data transformation and Synthetic Minority Oversampling Technique (SMOTE) have been proposed. However, these methods are constrained by issues such as limitations in input data size or sensitivity to outliers. Compared to other methods, variational autoencoder (VAE) can generate data with a similar probability distribution to the original input data while constraining the latent representation in a Gaussian distribution. This study proposes a VAE-based data augmentation method for wearable-based fall detection system. The proposed method is validated on the FallAllD public dataset, achieving a F-score of 99.46%. The performance has been increased by 2.21%. The results demonstrate the effectiveness of VAE-based data augmentation technique in enhancing fall detection systems and its superior performance compared with other traditional data augmentation methods.

关键词： Training Technological innovation Sensitivity Psychology Data augmentation Probability distribution Reliability

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory Networks for Predicting LQ45 Index Trends in Infrastructure Stocks*

Long Short-Term Memory Networks for Predicting LQ45 Index Tr...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： C. Maximiliano E. E. Surbakti R. Winantyo Jantianus M. Vasty W. Istiono Department of Informatics Universitas Multimedia Nusantara Tangerang Banten Indonesia Department of Electrical Engineering Universitas Multimedia Nusantara Tangerang Banten Indonesia Banking and Accounting Program Politenik Negri Medan Medan North Sumatra Indonesia

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

The capital market plays a crucial role in the nation’s economy by serving as a platform for trading long-term financial products. Among the securities, stock is favored by investors due to their high potential for profitability. With the advancement of technology, to minimize the risks associated with stocks, the utilization of technical analysis using the long short-term memory (LSTM) algorithm has become increasingly prevalent. Investors show keen interest in the LQ45 index, which comprises 45 stocks characterized by high liquidity and capitalization. The infrastructure sector within the index, including “***,” “***,” “***” and “***,” is particularly attractive due to its promising outlook, steady growth, and government backing. Hence, the utilization of the LSTM algorithm for forecasting the stock prices of the infrastructure sector within the LQ45 index aims to offer a competitive edge to investors in the stock market. Based on tests with 36 parameter combinations for each stock, highly accurate forecasting was achieved on each stock model with MAPE values below $10 \%$. The *** stock model stood out with a MAPE of $1.43 \%$ and an RMSE of 78.16031. It utilized 64 neurons on two hidden layers, a batch size of 32, and a dropout rate of 0.2.

关键词： Training Accuracy Neurons Predictive models Transformers Indexes Forecasting Long short term memory Tuning Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Unitig-centered pan-genome machine learning approach for predicting antibiotic resistance and discovering novel resistance genes in bacterial strains

引用

Computational and Structural Biotechnology Journal 2024年 23卷 1864-1876页

作者： Do, Duyen Thi Yang, Ming-Ren Vo, Tran Nam Son Le, Nguyen Quoc Khanh Wu, Yu-Wei Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Business Administration College of Management Lunghwa University of Science and Technology Taoyuan City Taiwan Professional Master Program in Artificial Intelligence in Medicine College of Medicine Taipei Medical University Taipei Taiwan Clinical Big Data Research Center Taipei Medical University Hospital Taipei Taiwan TMU Research Center for Digestive Medicine Taipei Medical University Taipei Taiwan

In current genomic research, the widely used methods for predicting antimicrobial resistance (AMR) often rely on prior knowledge of known AMR genes or reference genomes. However, these methods have limitations, potentially resulting in imprecise predictions owing to incomplete coverage of AMR mechanisms and genetic variations. To overcome these limitations, we propose a pan-genome-based machine learning approach to advance our understanding of AMR gene repertoires and uncover possible feature sets for precise AMR classification. By building compacted de Brujin graphs (cDBGs) from thousands of genomes and collecting the presence/absence patterns of unique sequences (unitigs) for Pseudomonas aeruginosa, we determined that using machine learning models on unitig-centered pan-genomes showed significant promise for accurately predicting the antibiotic resistance or susceptibility of microbial strains. Applying a feature-selection-based machine learning algorithm led to satisfactory predictive performance for the training dataset (with an area under the receiver operating characteristic curve (AUC) of > 0.929) and an independent validation dataset (AUC, approximately 0.77). Furthermore, the selected unitigs revealed previously unidentified resistance genes, allowing for the expansion of the resistance gene repertoire to those that have not previously been described in the literature on antibiotic resistance. These results demonstrate that our proposed unitig-based pan-genome feature set was effective in constructing machine learning predictors that could accurately identify AMR pathogens. Gene sets extracted using this approach may offer valuable insights into expanding known AMR genes and forming new hypotheses to uncover the underlying mechanisms of bacterial AMR. © 2024 The Authors

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Creating Mathematical Models to Help Formulate Company Strategies for Knowledge Management System Implementation

Creating Mathematical Models to Help Formulate Company Strat...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Wahyu Sardjono Widhilaga Gia Perdana Dewi Sagita Pranata Information Systems Management Department BINUS Graduate Program Master of Information Systems Management Bina Nusantara University Jakarta Indonesia Post Graduate Program of Management Science State University of Jakarta Jakarta Indonesia Department of Informatics Cyber Security Studi Program Faculty of Natural Mathematical & Engineering Sciences King's College London Strands West Minster UK

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

This research aims to build a mathematical model to formulate the problems of implementing knowledge management systems in companies that often face obstacles in achieving the desired objectives and goals. With increasing competition in the business sector, organizations or organizations realize the importance of utilizing the knowledge assets that reside in each individual and organization. If this knowledge can be managed optimally, it can become a competitive advantage for the company due to the emergence of innovative ideas by the concepts of knowledge management theory. By implementing optimal knowledge management (KM), companies can design innovative solutions to improve business operations and increase overall revenue. The factor analysis method will be used to find the determining factors for the success of the implementation of knowledge management systems (KMS) and the regression analysis method will also be used to form a mathematical model of several new factors which are formed as independent variables with the current level of community understanding of KMS as the dependent variable. The research results provide insight into strategies to improve success factors to successfully facilitate KMS implementation. This study contributes to existing knowledge management by providing insight into dynamics that go beyond the technical aspects of KMS, ultimately developing strategies for more effective and efficient utilization of knowledge and organizational growth and supporting competitive advantage for companies.

关键词： Performance evaluation Knowledge acquisition Collaboration Companies Knowledge management Mathematical models Regression analysis Information management Problem-solving System implementation

来源：评论

学校读者我要写书评

暂无评论

Mammogram Breast Cancer Classification Based on Deep-Convolutional Neural Network

Mammogram Breast Cancer Classification Based on Deep-Convolu...

引用

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Avissa Aurellia Amadea Christy Atika Sari Eko Hari Rachmawanto Wellia Shinta Sari Mohammed S. Noori Mohamed Ayad Alkhafaji Study Program in Informatics Engineering University of Dian Nuswantoro Semarang Indonesia Study Program in Information Systems University of Dian Nuswantoro Semarang Indonesia Department of Computer Engineering Technology Northern Technical University Mosul Iraq Department of Computer Science National University of Science and Technology DhiQar Iraq

Based on WHO’s data, breast cancer is one of the most deadly diseases that has claimed many victims, especially women. This disease begins with the presence of an undetected and eventually turns into malignant (cancer). This happens due to ignorance of the importance of having a medical check-up even though in good health. Doctors and researchers can prevent the development of tumor cells through treatment that begins with radiological examinations to identify the possibility of a person being affected by this disease. One of the most frequently used techniques is Mammography. This technique can detect the presence of tumor cells using advanced technology and several methods in displaying the patient’s diagnostic results on low-dose X-rays in the form of mammogram images. The technology is inseparable from the methods used to identify the presence of tumor cells. In this study, we have proposed the CNN method based on the deep-CNN model to identify mammogram images in the detection of breast cancer cells with average evaluation results in terms of accuracy, precision, recall, specificity, and f-measure on mammogram image datasets of 99.52%, 99.72%, 99.31%, 99.72%, and 99.5%. These results showed that this method has a good performance in breast cancer detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Classification Using A Hybrid and Efficient MobileNetV2-SVM Model

Diabetic Retinopathy Classification Using A Hybrid and Effic...

引用

2020 IEEE Region 10 Conference, TENCON 2020

作者： Taufiqurrahman, Shidqie Handayani, Astri Hermanto, Beni Rio Mengko, Tati Latifah Erawati Rajab Institut Teknologi Bandung Biomedical Engineering Program School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9781728184555

Deep learning has been proposed as one of the automated solutions for diabetic retinopathy (DR) severity classification problem. However, most of the successful deep learning models are based on large convolutional neural network (CNN) architectures, requiring a vast volume of training data as well as dedicated computational resources. In this study, we used MobileNetV2 architecture, which was considered a small-scale architecture (4.2 million trainable parameters), to perform DR classification task in APTOS 2019 dataset (3662 color retinal images). We used the generic MobileNetV2 pre-trained weights from ImageNet as initialization and implemented data augmentation and resampling during training. We further optimized our model by combining it with an SVM classifier, resulting a hybrid and computationally efficient deep learning model, MobileNetV2-SVM. This model obtained quadratic weighted kappa score of 0.925, 85% accuracy, and area under receiving operating characteristic (AUROC) of 1.00, 0.82, 0.94, 0.94, 0.93 for normal, mild, moderate, severe, and proliferative DR classes, respectively;which is better or at least comparable with the larger architecture performance on the same dataset. Our result shows that with proper optimization strategy, a relatively small and generic CNN architecture, can achieve promising DR classification performance, and even outperform the performance of CNN model with larger architecture. © 2020 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Towards an Automated Dissemination Process of Cyber Threat Intelligence Data using STIX 6

Towards an Automated Dissemination Process of Cyber Threat I...

引用

6th International Workshop on Big Data and Information Security, IWBIS 2021

作者： Briliyant, Obrina Candra Tirsa, Nusranto Pratama Hasditama, Maulana Andika Politeknik Siber Dan Sandi Negara Cyber Security Engineering Program Department of Cyber Security Bogor Indonesia National Cyber and Crypto Agency Depok Indonesia Faculty of Electrical Engineering and Informatics Budapest Computer Engineering Budapest Hungary

ISBN: (数字)9781665424516

ISBN: (纸本)9781665424516

Cyber Threat Intelligence (CTI) is an actionable, evidence-based knowledge management system of cyber threats data. CTI consists of 3 (three) major parts, namely information gathering, analysis, and dissemination. To carry out dissemination in CTI, Structured Threat Information Expression (STIX) and Trusted Automated Exchange of Intelligence Information (TAXII) have been developed as open and interoperable standards for the CTI dissemination. An effective CTI is a CTI that can be integrated into the organization's security operations processes. Many organizations today runs CTI with a mechanism for reporting and distributing information in the dissemination process or known as cyber threat information sharing which has significant effects on security operations performance. In this study, user requirements analysis and design of cyber threat information sharing processes were carried out. From the results of the requirement analysis, a suitable business process re-engineering were proposed to accelerate the automation of CTI, especially in the information sharing part. Lastly, the designed processes were tested by simulating the processes using STIX and TAXII-based platform. The results of this study indicate that the designed processes can be run on STIX and TAXII-based platforms, ergo a step toward to a fully automated CTI. © 2021 IEEE.

关键词： Information dissemination

来源：评论

学校读者我要写书评

暂无评论

IoT: Monitoring Temperature, Water pH, and Automatic Water Drainage Systems for Gurami Cultivation

IoT: Monitoring Temperature, Water pH, and Automatic Water D...

引用

Networking, Electrical engineering, Computer Science, and Technology (IConNECT), International Conference on

作者： Heni Sulistiani Wijaya Saputra Dedi Darwis Auliya Rahman Isnain Ardy Rimanda Putra Yosi Khairunisa Study Program of Accounting Information System Universitas Teknokrat Indonesia Lampung Indonesia Study Program of Computer Engineering Universitas Teknokrat Indonesia Lampung Indonesia Study Program of Informatics Universitas Teknokrat Indonesia Lampung Indonesia Regional Research and Development Agency Lampung Province (Balitbangda) Lampung Indonesia

Gurami is a native fish from Indonesian waters that is much-loved by Indonesian people for daily food consumption. The gurami inhabits still waters such as swamps, lakes, and ponds. Besides that, carp cannot live in a water content that is too alkaline or acidic, the oxygen content in the water must be stable. Water quality is a very important factor and can affect the survival of cultivated fish. Several parameters must be considered in improving the development of carp, one of which is the temperature and pH of the water and automatic drainage of water. In this paper, we conduct IoT-based research that focuses on controlling water temperature and pH and automatically draining pool water. Water temperature and pH control such as a pH sensor temperature sensor and a water turbidity sensor will later be connected to the ESP 32 microcontroller which already has a wi-fi module. A system that is linked to electrical power and the internet then the sensor will read the water quality including the pH temperature value and water turbidity from inside the fish pond, after getting the data, the data will go to ESP 32. This research can help gurami cultivating farmers to make it easy to control the pH temperature and perform automatic pool water draining. The results of sensor testing with actual data are pretty accurate with the average error value of the ds18b20 sensor being 0.05% while the value of the pH sensor itself is 0.07%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Web Based GIS for Distribution of Freshwater Fish Ponds 9

An Implementation of Web Based GIS for Distribution of Fresh...

引用

9th International Conference on Cyber and IT Service Management, CITSM 2021

作者： Yulfiperius Herawan Hayadi, B. Utami, Risnita Tri Firman Zulkhasyni Pardiansyah, Dedi Universitas Prof. Dr. Hazairin SH Aquaculture Study Program Faculty of Agriculture Bengkulu Indonesia Universitas Prof. Dr. Hazairin SH Informatics Study Program Faculty of Engineering Bengkulu Indonesia

ISBN: (纸本)9781665435482

Geographical Information System is a term in the field of mapping which has a scope of how a system can unify geographic objects and their information. Freshwater fishery is the business of the majority of residents of South Bengkulu Regency covering tilapia and catfish. The solution is to create a web-based Freshwater Fish Pond GIS application using the PHP programming language. Making a database using MySQL, and for geolocation storage using Google Fusion Tables. The web that will be created will later display the GIS Web-based Freshwater Fish Pond Distribution Mapping in South Bengkulu Regency. Each pond will be accompanied by information such as the name of the owner, type of fish, type of pond, and location of the pond. It is known that the number of ponds in 4 villages in 2 districts in South Bengkulu Regency has reached 100 ponds consisting of 80 tilapia fish ponds, 20 catfish ponds. © 2021 IEEE.

关键词： Geographic information systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Cyber Security: Deephoax Detection

Deep Learning for Cyber Security: Deephoax Detection

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： SY. Yuliani Yakub Rivo Juicer Wowor David Agustriawan Irmawati Dinar Ajeng Kristiyanti P.M. Winarno Rosilah Hassan Roshayu Mohamad Randy Zahran Razzaq Department of Informatics Universitas Multimedia Nusantara Tangerang Indonesia Information System Study Program Universitas Multimedia Nusantara Tangerang Indonesia Center for Cyber Security (CYBER) Universiti Kebangsaan Malaysia Selangor Malaysia College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Department of Informatics UIN Sultan Maulana Hasanuddin Banten Indonesia

ISBN: (数字)9798331506995

ISBN: (纸本)9798331507008

The increasing prevalence of deep hoaxes, such as fake news and phishing schemes, poses a significant threat to cybersecurity, undermining trust and spreading misinformation. In Indonesia, surveys indicate that more than 60% of people exposed to hoax news believe that it is true, emphasizing the urgent need for robust detection methods. Traditional cybersecurity approaches often struggle to keep pace with the growing scale and sophistication of these attacks. To address this challenge, this research investigates the use of deep learning techniques, specifically focusing on text-based hoax detection in the Indonesian language. The study fine-tunes IndoBERT, a pretrained deep learning model optimized for Indonesian text, to enhance the accuracy and scalability of hoax detection. The IndoBERT model was trained on a balanced dataset of 29,552 articles, comprising both hoax and real news content, collected from the Mafindo API and Kaggle's Indonesia News Dataset. The model was fine-tuned using supervised learning and evaluated using several key metrics, including accuracy, F1-score, precision, and recall. The results demonstrate that IndoBERT outperforms existing state-of-the-art approaches, achieving an accuracy of 98.51%, an F1-score of 98.44%, and a precision of 98.23% on the test set. These results highlight the effectiveness of IndoBERT for hoax detection, which offers a scalable solution to improve cybersecurity defenses against deceptive content. This research contributes to the integration of advanced deep learning models into cybersecurity systems, addressing the evolving landscape of cyber threats.

关键词： Deep learning Measurement Training Surveys Adaptation models Technological innovation Accuracy Computer security Fake news Videos

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：