检索结果-内蒙古大学图书馆

Techno-economic modeling and analysis of a PV EV charged with battery energy storage system (BESS) on Kalimantan Island

引用

Global Energy Interconnection 2025年第2期8卷 225-239页

作者： Aripriharta Adiguna, Satria Afandi, Arif N. Bagaskoro, Muhammad Cahyo Department of Electrical Engineering and Informatics Faculty of Engineering State University of Malang Malang65145 Indonesia Indonesia

This research examines the optimal combination of solar panel and battery capacity in hybrid systems in 11 cities on the island of Borneo, utilizing the region's significant solar energy potential and high irradiation levels. This research analyses the optimal combination of solar panels and battery capacity in 11 cities in Kalimantan using particle swarm optimization (PSO) and grey wolf optimization (GWO) algorithms to maximize energy output, reduce levelised energy costs, and maximally reduce carbon emissions. Results show Tarakan as the most optimal location, generating 215,804.88 kWh for IDR 916.9/kWh and lowering emissions by 435,884.29 kgCO2e, while Samarinda is the least optimal location. Economically, electricity tariffs of IDR 2,466.78/kWh and IDR 2,000/kWh generate a positive Net Present Value (NPV) with a payback period (PP) of 9–12 years, while a tariff of IDR 1,500/kWh is considered unfavorable. The findings demonstrate the effectiveness of PSO and GWO in optimizing the renewable energy system and confirm the project's financial viability, with a positive NPV and reasonable PP. Implementing renewable energy systems in Kalimantan Island can improve energy efficiency and significantly reduce carbon emissions, supporting environmental sustainability goals. © 2025 Global Energy Interconnection Group Co. Ltd.

关键词： Zero-carbon

来源：评论

学校读者我要写书评

暂无评论

Synthesis of batik motifs using a diffusion - generative adversarial network

引用

Multimedia Tools and Applications 2025年第7期84卷 3407-3438页

作者： Octadion, One Yudistira, Novanto Kurnianingtyas, Diva Informatics Engineering Faculty of Computer Science Universitas Brawijaya Malang Indonesia

This paper presents a novel approach for generating intricate Batik motifs using a modified Diffusion-Generative Adversarial Network (Diffusion-GAN) augmented with StyleGAN2-Ada. Motivated by the rich cultural heritage of Indonesian Batik, our research addresses the challenge of synthesizing high-quality, diverse patterns that capture the artistry and complexity of traditional designs. Traditional generative models often struggle with stability and fidelity in artistic synthesis. We integrate StyleGAN2-Ada and Diffusion techniques to overcome these limitations, optimizing model architecture and employing a curated Batik dataset. Evaluation metrics including Frechet Inception Distance (FID), Kernel Inception Distance (KID), precision, recall, and non-redundancy assess the quality and diversity of generated motifs. Our results demonstrate significant advancements in the realism and authenticity of synthesized Batik patterns, leveraging Diffusion-GAN to enhance detail and artistic fidelity. By exploring the intersection of deep learning and cultural art, this research contributes to the preservation and evolution of Batik as a cultural artifact. References to prior works underscore the evolution of Artificial Intelligence (AI) in cultural heritage preservation, highlighting the potential of modern AI techniques to innovate within traditional art forms like Batik. In summary, this study showcases the efficacy of the proposed Diffusion-GAN methodology in synthesizing original and convincing Batik motifs, while identifying opportunities for further refinement and complexity in motif synthesis. The dataset and code can be accessed here: https://***/octadion/diffusion-stylegan2-ada-pytorch © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Evaluate Recent Numerical Methods for Long-Term Simulation to Study the Effect of Different Shapes of Thermal Bridges in Walls

引用

Defect and Diffusion Forum 2024年 436卷 77-90页

作者： Omle, Issa Kovács, Endre Department of Fluid and Heat Engineering Faculty of Mechanical Engineering and Informatics University of Miskolc Miskolc3515 Hungary Institute of Physics and Electrical Engineering Faculty of Mechanical Engineering and Informatics University of Miskolc Miskolc3515 Hungary

According to previous studies, the most effective, stable, and explicit numerical methods to deal with problems of heat transfer in building walls are the two recently published approaches, which are the modified Dufort-Frankel and leapfrog-hopscotch techniques, which are used in this study to make transient and long-term simulations (three months of the winter season) of 2-D space systems that enable us to execute these simulations with relatively short computational times to evaluate the two most effective versions of these methods. Our solution to a real-world engineering challenge involves investigating thermal bridges of different forms inside multilayer walls of buildings exposed to environmental factors specific to Hungary's climate, such as the outside temperature and sun radiation, to improve energy efficiency. The distributions of temperatures and the total heat loss (across the walls) are calculated for all cases (three layers without a thermal bridge three layers with thermal bridges in straight, bent, and L-shaped shapes). © 2024 Trans Tech Publications Ltd, All Rights Reserved.

关键词： Walls (structural partitions)

来源：评论

学校读者我要写书评

暂无评论

How to get high-efficiency lead chalcogenide quantum dot solar cells?

引用

Science China(Physics,Mechanics & Astronomy) 2023年第1期66卷 34-59页

作者： Chao Ding Qing Shen Faculty of Informatics and Engineering The University of Electro-CommunicationsTokyo 182-8585Japan

Lead chalcogenide colloidal quantum dots(CQDs)are regarded as attractive absorption materials for novel solar cells(SCs).The cost of lead chalcogenide CQD has been decreased to a commercialization target of$5/g due to the direct production of CQD ***,the photoelectric conversion efficiency(PCE)of lead chalcogenide CQDSCs is presently close to 14%,well below the commercialization target(20%),which is only 41%of the theoretical Shockley-Queisser limit *** this study,the different losses of open-circuit voltage(V_(oc)),fill factor(FF),and short circuit current density(J_(sc))for current CQDSCs are systematically discussed,as well as the percentage and likely causes of each *** the primary reasons for the CQDSCs’performance constraints are *** that,we focus on the CQDSCs interfaces(i.e.,CQD/CQD,CQD/HTL,and ETL/CQD)and explore viable ways to reduce device performance ***,based on the discussion above,we propose many enhancements to significantly solve numerous major obstacles impeding device performance to boost the PCE of CQDSCs for future commercialization significantly.

关键词： lead chalcogenide colloidal quantum dots solar cell interface engineering non-radiative carrier recombination charge carrier transport losses

来源：评论

学校读者我要写书评

暂无评论

Self-Learning Model for Pattern Recognition in Vision System Based on Adaptive Kernel

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第14期49卷 157-170页

作者： Aradea Rianto Herlina, Nina Hoeronis, Irani Department of Informatics Faculty of Engineering Siliwangi University Kode Pos Tasikmalaya46115 Indonesia

Recently, the solution for recognizing and understanding an object based on visuals is to integrate the adaptation function (continuous machine-driven process) into the system update function involving humans (continuous human-driven process). However, this has created a gap between the adaptation function and the system. This situation requires understanding the system viewed as a dynamic composition of the learning process. This research introduced a self-learning model in the form of an adaptive kernel equipped with the SpinalNet architecture, and the goal of this study is to increase the Convolutional Neural Network (CNN) accuracy. The model consisted of a domain model, contextual knowledge, and adaptive learner developed based on the CNN with SpinalNet. The combination of Adaptive Kernel and SpiralNet in this CNN has a significant impact, allowing the model to adjust the selection of subsequent kernels based on the optimal input from the previous kernel. Moreover, this combination results in lower memory usage during training. The evaluation results show that our proposed model provides better classification accuracy than the SpiralNet model without the Adaptive Kernel. Furthermore, in terms of inference speed, our model outperforms SpiralNet, as evidenced by the use of fewer parameters. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Thermal Analysis of a Simplified Railway Brake Model with Numerical Simulation

引用

Periodica Polytechnica Transportation engineering 2025年第1期53卷 1-6页

作者： Bolló, Betti Sarka, Ferenc Voith, Katalin Felhő, Csaba Institute of Energy Engineering and Chemical Machinery Faculty of Mechanical Engineering and Informatics University of Miskolc Egyetemváros MiskolcH-3515 Hungary Institute of Machine and Product Design Faculty of Mechanical Engineering and Informatics University of Miskolc Egyetemváros MiskolcH-3515 Hungary Institute of Manufacturing Science Faculty of Mechanical Engineering and Informatics University of Miskolc Egyetemváros MiskolcH-3515 Hungary

The braking system is the most important safety device in all vehicles. When braking, the kinetic energy of the vehicle is converted into thermal energy. The use of friction brakes can cause problems in the long term, as the brake can heat up, reducing its coefficient of friction. Heating and cooling have a harmful effect on all frictional elements, causing material fatigue. As a result of the negative effects, the hot brake cannot reduce the velocity of the vehicle at the correct rate. In this paper, the propagation of frictional heat is analysed in a test specimen made of cast iron material using different numerical simulations. The computational results are validated with the results obtained during measurement. With proper validation, the brake discs are able to be modelled at different designs and materials without having to manufacture a test specimen for each case. In the study, it is important to point physical quantities to carry out the simulation. © 2025 Budapest University of Technology and Economics. All rights reserved.

关键词： Brakes

来源：评论

学校读者我要写书评

暂无评论

Enhancing Decision-making in Uncertain Domains through Optimized Fuzzy Logic Systems

Periodica Polytechnica Electrical Engineering and Computer S...

引用

Periodica Polytechnica Electrical engineering and Computer Science 2025年第1期69卷 63-78页

作者： Sekhi, Ihab Kovács, Szilveszter Nehéz, Károly Institute of Information Science Faculty of Mechanical Engineering and Informatics University of Miskolc MiskolcH-3515 Hungary

Fuzzy logic helps manage human-like reasoning in system control, mainly when traditional analysis does not work due to complex control processes. Despite its usefulness, fuzzy logic faces challenges in decision-making, especially in complex business situations and when combined with expert systems. It struggles with uncertainty and relies on various beliefs and assumptions, which is limiting compared to other methods for handling uncertainty. However, fuzzy logic can improve traditional control systems by adding a layer of intelligence. This study adapts mathematical functions like the straight-line point-slope equation, the absolute value function, and the Gaussian equation to develop accurate and flexible membership functions for fuzzy logic systems. By analyzing 10,000 tasks of different sizes, we found our methods significantly more precise than traditional approaches, especially in determining degrees of membership for uncertain and complex environments. Our MATLAB research shows the potential of using varied membership functions to enhance fuzzy logic systems' accuracy and flexibility. © 2025 Budapest University of Technology and Economics. All rights reserved.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network for Cataract Clasification Using Primary Dataset 9

Convolutional Neural Network for Cataract Clasification Usin...

引用

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Totok Suryawan, I Gede Putra, I Wayan Murmayasa Adi Informatics Engineering Study Program Faculty of Technology and Informatics Denpasar Indonesia

ISBN: (纸本)9798350383010

Cataracts are the main factor causing blindness in Indonesia. Traditional diagnostic methods involving clinical examination by an ophthalmologist using a slit-lamp and visual tests have many challenges such as limited resources, time, and medical expertise may not be available in all locations, especially in less developed areas. Utilizing medical image technology is a wise choice because it allows early detection and monitoring of the development of this cataract disease Technology is needed to identify medical images that have valuable information so that early detection or monitoring of cataract development can be carried out. CNN as a part of deep learning has the ability to perform automatic feature extraction so that it can identify eye images. A CNN model for recognizing cataracts in eye images taken directly from Bhayangkara Hospital in Denpasar Bali has been developed in this research. The model developed is equipped with a dropout layer technique to prevent overfitting. The test results show that the CNN developed in this research produces very good performance with an average accuracy level of 92% on public dataset images, and 94% on primary dataset images. Tested using the primary dataset and public dataset, this CNN model shows very good performance because it can correctly identify an average of 94% of eye images in the primary dataset, and 92% of eye images in the public dataset.. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved LOPCOW-SAW Method for Optimal Supplier Selection in Supply Chain Management 12

Improved LOPCOW-SAW Method for Optimal Supplier Selection in...

引用

12th International Conference on Cyber and IT Service Management, CITSM 2024

作者： Sumanto Sumarna Nurdin, Hafis Asra, Taufik Sobari, Irwan Agus Kuswanto, Herman Chaidir, Indra Akil, Ibnu Handono, Felix Wuryo Universitas Bina Sarana Informatika Informatics Faculty of Engineering and Informatics Jakarta Indonesia Universitas Nusa Mandiri Information System Faculty of Engineering and Informatics Jakarta Indonesia Universitas Bina Sarana Informatika Software Engineering Faculty of Engineering and Informatics Jakarta Indonesia Universitas Nusa Mandiri Universitas Bina Sarana Informatika Information System Faculty of Engineering and Informatics Indonesia Universitas Nusa Mandiri Universitas Bina Sarana Informatika Computer Engineering Faculty of Engineering and Informatics Indonesia

ISBN: (纸本)9798331528799

Supplier selection is a critical component of Supply Chain Management (SCM), as suppliers provide raw materials or services essential for supporting a company's operations. Traditional supplier selection methods often rely on subjective assessments to determine the weighting of criteria, which can lead to biases and suboptimal decision making. To address this issue, this study combines the Logarithmic Percentage Change of Weight (LOPCOW) method with the Simple Additive Weighting (SAW) method to enhance objectivity in the supplier selection process. The LOPCOW method is used to assign criterion weights objectively based on logarithmic percentage changes, which helps minimize subjectivity, These weights are then applied using the SAW method to evaluate and rank suppliers. The results of the study show that this combined approach is more reliable for selecting suppliers objectively and accurately. The study suggests integrating other Multi-Criteria Decision-Making (MCDM) methods to further strengthen the results while recommending the inclusion of real-time data analytics to improve the model's adaptability to dynamic market conditions. The LOPCOW-SAW approach can be applied across various industries for more effective and efficient SCM supplier selection. © 2024 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

An Innovative Bispectral Deep Learning Method for Protein Family Classification

引用

Computers, Materials & Continua 2023年第5期75卷 3971-3991页

作者： Isam Abu-Qasmieh Amjed Al Fahoum Hiam Alquran Ala’a Zyout Biomedical Systems and Informatics Engineering Department Hijjawi Faculty for Engineering TechnologyYarmouk UniversityIrbid21163Jordan

Proteins are essential for many biological *** example,folding amino acid chains reveals their functionalities by maintaining tissue structure,physiology,and *** that quantifiable protein characteristics are vital for improving therapies and precision *** automatic inference of a protein’s properties from its amino acid sequence is called“basic structure”.Nevertheless,it remains a critical unsolved challenge in bioinformatics,although with recent technological advances and the investigation of protein sequence *** protein function from amino acid sequences is crucial in *** study considers using raw sequencing to explain biological facts using a large corpus of protein sequences and the Globin-like superfamily to generate a vector *** power of two representations was used to identify each amino acid,and a coding technique was established for each sequence ***,the encoded protein numerical sequences are transformed into an image using bispectral analysis to identify essential characteristics for discriminating between protein sequences and their families.A deep Convolutional Neural Network(CNN)classifies the resulting images and developed non-normalized and normalized encoding ***,the dataset was split 70/30 for training and ***,the dataset was utilized for 70%training,15%validation,and 15%*** suggested methods are evaluated using accuracy,precision,and *** non-normalized method had 70%accuracy,72%precision,and 71%recall.68%accuracy,67%precision,and 67%recall after ***,the normalized approach without validation had 92.4%accuracy,94.3%precision,and 91.1%*** showed 90%accuracy,91.2%precision,and 89.7%*** that both algorithms outperform the *** paper presents that bispectrum-based nonlinear analysis using deep learning models outperforms standard machine learning methods and other deep learning

关键词： Globin-like superfamily numerical encoding bispectral analysis classification model deep convolutional neural network(CNN)

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：