检索结果-内蒙古大学图书馆

International Symposium on Grids and Clouds 2023 in conjunction with HEPiX Spring Workshop, ISGC and HEPiX 2023

作者： Suhardiman, Basuki Hermanto, Benni Rio Directorate of Information Technology Institut Teknologi Bandung Jl Ganesha 10 Bandung Indonesia Master’s Program in Computational Science Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Jl Ganesha 10 Bandung Indonesia Biomedical Engineering Department School of Electrical Engineering and Informatics Institut Teknologi Bandung Indonesia

Forest fires have been detected to occur in Indonesia since 1998. The forest fires mostly resulted from human activities in order to expand their land, especially oil palm lands. Once a land clearing is carried out, it covers areas of tens to hundreds of thousands of hectares. The peak of the forest fires occurred in 2015 when almost half of the world was affected especially by smoke from the fire. In 2011, VIIRS (Visible Infrared Imaging Radiometer Suite) was launched by NOAA (National Oceanic and Atmospheric Administration). In their collected data, there is data on Indonesia issued daily for areas in the islands of Java, Sumatra, Kalimantan, Sulawesi, and the general areas of Indonesia. The VIIRS night data shows the possibility of some burning at night. We need to identify burnings that potentially become fires, which are potentially producing smoke. It is important to observe areas where large-scale forest fires frequently occur, so the authority could do some prevention beforehand. Using existing data released per day per area, we utilize an ANN (Artificial Neural Network) to identify a potential fire. The processes start with data cleaning and processing, Neural Network creation, and finally ANN training and testing. By using the ANN prediction model with the MinMax Scaler, we choose variables Temperature, Radiant Heat Intensity, and Source Footprint. Simulations are made to show the ranges of these variables that predict the possibility of’flame’ status occurring. We conclude that the ANN method can give more accurate results than the existing classification. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Automatic Fish Dryer Prototype 2nd

Design and Analysis of Automatic Fish Dryer Prototype

引用

2nd International Conference on Experimental and Computational Mechanics in engineering, ICECME 2020

作者： Raynaldo, Kevin Andrianto, Richie Darmawan, Steven Study Program of Mechanical Engineering Faculty of Engineering Universitas Tarumanagara Jalan Letjen S. Parman No. 1 Jakarta Barat11440 Indonesia

ISBN: (纸本)9789811607356

Indonesia has lots of natural resources especially in marine sector such as yellowstripe scad and long-jawed mackerel. Those fish are usually dried by fisherman for longer storage using conventional drying by heat from the sun. This conventional drying method takes hours, about two or three days depends on sun heat intensity. Based on that problem, mechanical drying system may overcome the problem. Automatic fish dryer is designed to dry the fish effectively with even heat distribution with palette rotation system which is hoped to increase productivity and economic potential for coastal communities. The prototype is designed theoretically with mechanical design to generate part specification including heater, shaft, electric motor, bearing, pulley and transmission. CFD method to discover the heat distribution inside with 5,239 nodes and STD k-Ε turbulence model. A 400 mm × 500 mm × 420 mm prototype is generated to dry 2 kg of long-jawed mackerels in 5.3 h with 0.00419 g/s for drying mass flow rate from 70 to 30% water content. CFD simulation shows the exhaust fan need to be installed at outlet for better water-vapor flow distribution. This research indicates that automatic fish dryer can dry 4 times faster than conventional drying system. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： CFD Fish dryer Mechanical design Prototype

来源：评论

学校读者我要写书评

暂无评论

Enhancing Search Efficiency: Analyzing Learning Mechanisms in Metaheuristics

Enhancing Search Efficiency: Analyzing Learning Mechanisms i...

引用

Information Technology and Computing (ICITCOM), International Conference on

作者： Teddy Nurcahyadi Christian Blum Mechanical Engineering Study Program Engineering Faculty Universitas Muhammadiyah Yogyakarta Yogyakarta Indonesia Consejo Superior de Investigaciones Científicas Institut d'Investigació en Inielligència Artificial Barcelona Spain

ISBN: (数字)9798350379839

ISBN: (纸本)9798350379846

Metaheuristics have evolved significantly in the last few decades. Nowadays, more complex problems and essential applications are emerging, requiring more powerful metaheuristics to handle them. This article analyzes the characteristics and performance of existing metaheuristics, with particular emphasis on their learning mechanisms. Several critical aspects for improvement are identified, and several promising future research areas are recommended.

关键词： Learning systems Metaheuristics Memory Benchmark testing Maintenance Information technology Standards Faces

来源：评论

学校读者我要写书评

暂无评论

Implementation of AI-Based Support Vector Machine Algorithm for Fraud Detection in Digital Payment Systems

Implementation of AI-Based Support Vector Machine Algorithm ...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Edy Prayitno Rikie Kartadie Uning Lestari Munengsih Sari Bunga Accounting Information Systems Faculty of Information Technology Universitas Teknologi Digital Indonesia Yogyakarta Indonesia Computer Engineering Study Program Faculty of Information Technology Universitas Teknologi Digital Indonesia Yogyakarta Indonesia Informatics Study Program Faculty of Science and Information Technology Universitas Akprind Indonesia Yogyakarta Indonesia Department of Computer Engineering Smart City Information Systems Politeknik Negeri Indramayu Indramayu Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

The increasing use of digital payment systems has led to a rise in fraudulent activities, presenting a significant challenge in ensuring secure transactions. This research focuses on implementing the Support Vector Machine (SVM) algorithm with a Radial Basis Function (RBF) kernel to detect fraud in digital payment systems. One of the main challenges addressed in this study is the severe class imbalance in the dataset, where fraudulent transactions account for only 0.17% of total transactions. To overcome this, the SMOTE (Synthetic Minority Over-sampling Technique) method was applied to balance the dataset, allowing the model to better recognize fraudulent patterns. The results indicate that the SVM model achieved an accuracy of 99.93%, with a precision of 86.23% and a recall of 75.51%. These results demonstrate that SVM, combined with SMOTE and RBF kernel, is highly effective in detecting fraudulent transactions while minimizing false positives. This research provides a strong foundation for improving fraud detection models in the context of digital payment systems, offering enhanced security and trust for users. Further research could explore hybrid models and real-time data analysis to improve performance.

关键词： Support vector machines Seminars Adaptation models Accuracy Data models Real-time systems Fraud Security Kernel Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Technology-Enhanced Learning for User Security Awareness Using AI-based Naive RAG: A Design and Prototype

Technology-Enhanced Learning for User Security Awareness Usi...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： I Putu Agus Eka Pratama I Made Oka Widyantara Linawati Nyoman Gunantara Sinung Suakanto Eka Tresna Irawan Doctoral Program of Engineering Sciences Faculty of Engineering Udayana University Badung Bali Indonesia dept. of Electrical Engineering Faculty of Engineering Udayana University Badung Bali Indonesia dept. of Information System Telkom University Bandung West Java Indonesia Mayar International Pte. Ltd. Singapore

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

The increasing use of Information Technology (IT) in all areas of life, followed by increasing cybersecurity threats on the user side, makes cybersecurity awareness among users an obligation that must be met. Several solutions currently available (guides, discussion forums, workshops) have not been able to provide good results and are lacking in terms of user engagement, adaptability, and optimizing available resources, so technology-based learning is needed, especially AI. This paper introduces the design and prototype of an AI-based learning system, especially with the Naive Retrieval-Augmented Generation (Naive RAG) method with three steps, including Retrieval, Augmented, and Generation. The system combines contextual user questions and answers with internal and domain knowledge systems to explain cybersecurity awareness to users dynamically and personally. The prototype that has been developed is then tested using the Black Box Testing method to evaluate functionality and usability. The test results show that the functionality of the system built has run well with a percentage of success of 100%, so it can be used as a technologybased learning medium for education and learning of user security awareness.

关键词： Electronic learning Retrieval augmented generation Knowledge based systems Prototypes Learning (artificial intelligence) Computer security Usability Information technology Testing Information systems

来源：评论

学校读者我要写书评

暂无评论

Biomedical Image Quality Improvement with Spatial Domains 2

Biomedical Image Quality Improvement with Spatial Domains

引用

2nd International Conference on Innovative and Creative Information Technology, ICITech 2021

作者： Fernando, Erick Siagian, Pandapotan School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Computer Engineering Study Program Del Institute of Technology Faculty of Informatics and Electrical Engineering North Sumatera22381 Indonesia

ISBN: (纸本)9781728197463

Digital image processing aims to improve the quality of an original image so that it can display an image that is relatively better than the original image, so as to obtain the detailed information needed for an analysis need. Quality degradation Biomedical images in computerization usually experience changes in brightness, blur, and contrast stretching. Because of the deterioration in the image quality, doctors and patients cannot obtain the information needed for analysis, therefore the need for biomedical image processing techniques with spatial domain methods to improve the quality and details of information in the image so that it helps doctors in diagnosing. Data analysis is biomedical images like X-ray images, CT-Scan (Computer Tomographic Scan) images, and USG (Ultrasound Graphic) images. A focused study on improving image quality can be done with digital spatial domain image processing techniques. Digital domain image processing is digital image processing based on the manipulation of pixel values in the image directly, in the form of point processing and mask processing. Process testing for each image for Blur level is CT-scan images with a value of 0.98436, ultrasound images with a value of 0.9875, X-ray images with a value of 0.9836. This value is blur level value get near to 1 which means the image becomes clearer. The analysis results prove that the spatial domain method can clarify the object image in this study. The biomedical image quality processing model is proven to be able to improve the quality of the image that is declining due to the digitization process and assist the user in analyzing the biomedical image. © 2021 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Building a Simple COVID-19 Knowledge Graph in Bahasa Indonesia: A Preliminary study

TechRxiv

引用

TechRxiv 2024年

作者： Muharram, Arief Purnama Taufikulhakim, Farhan Hilmi Purwarianti, Ayu Faculty of Medicine Universitas Indonesia Central Jakarta Indonesia Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

COVID-19 is an acute respiratory disease that has become a pandemic worldwide. Many studies have been conducted to enhance our understanding of COVID-19. However, the abundance of information obtained from these studies has resulted in information overload. In this study, we purposed a simple COVID-19 Knowledge Graph in Bahasa Indonesia as a way to reconstruct knowledge to combat this information overload. We used Bahasa Indonesia in our study to explore its potential for constructing a Knowledge Graph (KG). The construction of our KG involved manual curation of medical literatures and annotation of entities and relationships by the domain experts. The KG was implemented using Neo4J version 5. We successfully demonstrated our COVID-19 KG, which consists of 240 nodes and 276 relationships with 15 and 14 node and relationship labels respectively. Accessing the information within the KG is made effortless through the use of Cypher queries in Neo4J. Further research is still needed to develop the KG into a larger and better one. However, our COVID-19 KG can serve as a basis for further development. © 2024, CC BY.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Renewable Energy Generation Forecasting on Smart Home Micro Grid using Deep Neural Network

Renewable Energy Generation Forecasting on Smart Home Micro ...

引用

2021 International Conference on Artificial Intelligence and Mechatronics Systems, AIMS 2021

作者： Purwanto Hermawan Suherman Widodo, Djoko Adi Iksan, Nur School of Postgraduates Studies Universitas Diponegoro Doctoral Program of Environmental Science Faculty of Engineering Department of Chemical Engineering Semarang Indonesia Universitas Negeri Semarang Faculty of Engineering Department of Electrical Engineering Semarang Indonesia

ISBN: (纸本)9781665424820

The implementation of smart grid on a micro scale in this study was for household electricity fulfillment needs. The use of renewable energy sources such as solar power will be integrated through a smart grid so that households can become independent in providing electricity and not depend on state electricity. Besides, it can also reduce monthly electricity costs when integrated with the state electricity network. Smart Micro Grid also enables the availability of energy management services such as monitoring, prediction, forecasting, scheduling and decision-making that was supported by some technologies such as artificial intelligent, smart sensors so that consumer use of electricity was more efficient. In this research, the forecasting method developed using the Deep Neural Network (DNN) and the Gate Recurrent Unit (GRU) as the architectural model. The GRU model was chosen because it has better performance compared to other models, namely LSTM, Auto-LSTM, Auto-GRU with MAE and MSE values of 0.0342 and 0.00245. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparison of Algebraic Reconstruction Technique Methods and Generative Adversarial Network in Image Reconstruction of Magnetic Induction Tomography (MIT)

Comparison of Algebraic Reconstruction Technique Methods and...

引用

2021 International Conference on Biomedical engineering, ICoBE 2021

作者： Lubis, A.J. Nasir, N.F. Mohd Zakaria, Z. Jusoh, M. Azizan, M.M. Zakaria, M.Z. Kazim, M.N.F.M. Rahman, S. Faculty of Engineering and Computer Science Universitas Harapan Medan Medan Indonesia Computer Engineering Program Faculty of Electronic Engineering Technology Universiti Malaysia Perlis Perlis Malaysia Biomedical Electronic Engineering Program Faculty of Electronic Engineering Technology Universiti Malaysia Perlis Perlis Malaysia Universiti Malaysia Perlis Perlis Malaysia Department of Electrical and Electronic Department Faculty of Engineering and Built Environment Universiti Sains Islam Malaysia Negeri Sembilan Malaysia Faculty of Mechanical Engineering Technology Universiti Malaysia Perlis Perlis Malaysia Mechatronic Engineering Program Faculty of Electrical Engineering Technology Universiti Malaysia Perlis Perlis Malaysia

Magnetic induction tomography (MIT) is a technique used for imaging electromagnetic properties of objects using eddy current effects. The non-linear characteristics had led to more difficulties with its solution especially in dealing with low conductivity imaging materials such as biological tissues. Two methods that could be applied for MIT image processing which is the Generative Adversarial Network (GAN) and the Algebraic Reconstruction Technique (ART). ART is widely used in the industry due to its ability to improve the quality of the reconstructed image at a high scanning speed. GAN is an intelligent method which would be able to carry out the training process. In the GAN method, the MIT principle is used to find the optimum global conductivity distribution and it is described as a training process and later, reconstructed by a generator. The output is an approximate reconstruction of the distribution's internal conductivity image. Then, the results were compared with the previous traditional algorithm, namely the regularization algorithm of BPNN and Tikhonov Regularization method. It turned out that GAN had able to adjust the non-linear relationship between input and output. GAN was also able to solve non-linear problems that cannot be solved in the previous traditional algorithms, namely Back Propagation Neural Network (BPNN) and Tikhonov Regularization method. There are several other intelligent algorithms such as CNN (Convolution Neural Network) and K-NN (K-Nearest Neighbor), but such algorithms have not been able to produce the expected image quality. Thus, further study is still needed for the improvement of the image quality. The expected result in this study is the comparison of these two techniques, namely ART and GAN to get the best results on the image reconstruction using MIT. Thus, it is shown that GAN is a better candidate for this purpose. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Self-loop Laplacian Formation Control for Linear Systems

Self-loop Laplacian Formation Control for Linear Systems

引用

Computer Sciences, engineering, and Technology Innovation (ICoCSETI), International Conference on

作者： Ashton Bradley Hendrawan Djati Wibowo Djamari Ignatius Pulung Nurprasetio Harry Septanto Mechanical Engineering Study Program Sampoerna University Jakarta Indonesia Faculty of Mechanical and Aerospace Engineering Institut Teknologi Bandung Bandung Indonesia Research Center for Smart Mechatronics National Agency for Research and Innovation (BRIN) Bogor Indonesia

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

This study works on scalable formation control of general linear system agents which based on self-loop Laplacian method. Self-loop Laplacian method for scalable formation is used when it is desired that the initial states of agents and communication topology of agents affects the formation size directly. Proof is provided demonstrating that the self-loop Laplacian matrix shares spectral properties with the standard Laplacian matrix, and the two can be related through a transformation matrix. Existing works on scalable formation mostly focused on single and double integrator agents, particularly where the control input algorithm uses self-loop Laplacian matrix. Extending the work on self-loop Laplacian matrix, this study proposes a control input algorithm for agents in linear system dynamics. The algorithm uses both self-loop Laplacian formulation and general linear system consensus methods, and the stability of the whole system is proven using Lyapunov direct method. Two numerical examples with 4 and 5 agents are shown to verify the result.

关键词： Linear systems Technological innovation Laplace equations Heuristic algorithms Formation control Topology Collision avoidance Standards Numerical stability Multi-agent systems

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：