检索结果-内蒙古大学图书馆

International Conference on informatics and Computational Sciences (ICICoS)

作者： Dewi Arianti Wulandari Tri Retnaningsih Soeprobowati Dinar Mutiara Kusumo Nugraheni Doctoral Program Of Information System Diponegoro University Semarang Indonesia Department of Biology Faculty of Science of Mathematics Diponegoro University Semarang Indonesia Department of Informatics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia

ISBN: (数字)9798350375886

ISBN: (纸本)9798350375893

Using digital literacy in the educational environment can make students more responsible and wiser in using and accessing technology. To find out how prepared the educational environment is in facing this digital era a study that aimed to determine whether there is a correlation between age and gender factors with the number of devices used in the online learning process was conducted at one of the private universities in West Jakarta. The results of this study can contribute to the model developments in both online and offline learning processes to increase student motivation. The data collection method used is qualitative with primary data from survey results, using non-probability sampling, and descriptive analysis. The sample of this study was students at that university with a total of 310 students. Based on the test results using the two-way ANOVA test on the SPSS tool, the result is 0.055. This value is above the significance value requirement of 0.05. The age and gender do not significantly affect device usage, with a Sig value of $\gt0.05$, and the simultaneous relationship between age and gender does not affect device usage. It can be concluded that digital literacy has been applied in that university which can be proven from the test results that 225 students out of 310 or $\mathbf{72.5 \%}$ use more than one device in online learning activities.

关键词： Surveys Portable computers Data analysis Social networking (online) Education Data collection Mobile handsets

来源：评论

学校读者我要写书评

暂无评论

Power Oscillation Damping of a Wind Turbine Generation with Battery Energy to Smoothen Power System Stability

Power Oscillation Damping of a Wind Turbine Generation with ...

引用

IEEE Southeastcon

作者： Ariesa Budi Zakaria Ilham Akbar Mayur Basu Eduard Muljadi Suwano Nanang Hariyanto Graduate Program PLN-ITB PLN Corporate University Auburn USA Electrical and Computer Engineering Auburn University Auburn USA School of Electrical Engineering and Informatics Institut Teknologi Bandung (ITB) Bandung Indonesia

Integrating wind turbine generation (WTG) into the power grid presents challenges due to their variable and unpredictable output, creating instability. The intermittent nature of wind power and the reduced inertia of wind turbines pose significant challenges to maintaining power system stability, especially during grid faults and transient events. Intermittency can impact the electrical grid's stability and requires additional grid balancing and energy storage measures. This study proposes a Power Oscillation Damping (POD) control scheme integrated with battery energy to enhance WTG stability following grid faults. The proposed scheme combines a POD controller for WTG and a battery controller, demonstrating faster oscillation damping than a WTG without batteries. During damping control, the scheme prioritizes active power control of POD, utilizing the wind turbine's kinetic energy. Simultaneously, the reactive power control of POD adjusts based on the synchronous generator's rotational speed to maintain voltage stability. Feedback for both control loops is derived from the nearest synchronous generator, ensuring coordinated and responsive control. Adding a battery into the control scheme helps to smooth out power fluctuations and enhance stability. Therefore, it is possible to compensate for the intermittency of wind power and voltage drop after short-circuit events through various measures, such as advanced control systems and battery power. The effectiveness of this proposed control scheme, with the added integration of Battery Energy, is validated through the PSCAD simulator involving a short-circuit fault in a two-area power system. Results demonstrate a notable improvement in power system stability, particularly after grid faults.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reducing Dependency on Imported Electricity: Utilizing Renewable Energy and Minimizing Fossil Fuel Power Plant Operations in West Kalimantan

Reducing Dependency on Imported Electricity: Utilizing Renew...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Ilham Akbar Ariesa Budi Zakaria Eduard Muljadi Suwarno Nanang Hariyanto Graduate Program PLN-ITB PLN Corporate University Auburn USA Electrical and Computer Engineering Auburn University Auburn USA School of Electrical Engineering and Informatics Institut Teknologi Bandung (ITB) Bandung Indonesia

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

This paper discusses West Kalimantan's dependency on imported electricity and fossil fuels and advocates for integrating renewable energy sources, especially solar power. With abundant solar resources and its equatorial location, West Kalimantan presents a significant solar PV generation opportunity. However, its dependence on imported electricity from the ASEAN Grid initiative poses risks to energy security. By promoting solar power as an alternative energy source and reducing reliance on fossil fuels, the paper aims to improve energy independence and sustainability. Integrating solar PV requires assessing frequency stability to ensure system resilience. Moreover, the interconnection between the two grids enhances system resilience and facilitates renewable energy integration. In summary, integrating solar PV power plants into the West Kalimantan system aims to decrease dependence on electricity imports from Sarawak while preserving the system's frequency stability.

关键词： Photovoltaic systems Renewable energy sources Fault tolerance Electricity Power system stability Fossil fuels Security Sustainable development Thermal stability Research and development

来源：评论

学校读者我要写书评

暂无评论

ML-Agents in Kart Racing Game using Microgame

ML-Agents in Kart Racing Game using Microgame

引用

International Conference on Telecommunication Systems, Services, and Applications (TSSA)

作者： Afina Anfa Ana Vitradisa Pratama Agus Sukoco Ary Setijadi Prihatmanto Rin Rin Nurmalasari Agus Juhana School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Departement of Informatics Universitas Mayasari Bakti Tasikmalaya Indonesia Department of Electrical Engineering UIN Sunan Gunung Djati Bandung Indonesia Multimedia Education Study Program Universitas Pendidikan Indonesia Bandung Indonesia

This paper presents an innovative approach to integrating ML-Agents into a microgame-based kart racing environment, showcasing the potential for enhancing gameplay experiences through AI-driven opponents. Kart Unity Game is a racing game that uses small motorized vehicles but still uses the concept of racing in the real world. One of the racing game development platforms is Unity. Unity has developed a platform, Unity Karting Microgame, which users can modify. Unity Karting Microgame applies self-driving to ML-Agents trained and designed to drive their karts with suitable sensors and actuators. The method used to develop the game is to modify the racetrack and modify ML-Agents to make the game more exciting and fun. As a result of this study, successful implementation of ML-Agents in a microgame-based kart racing environment. The study highlights the potential of using Unity ML-Agents to create AI-driven opponents that enrich gameplay experiences. Games can run well and seem varied. ML-Agents can also control their karts on their lanes. Thus, kart racing games can be implemented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Mining Approach for River Flood Hazard Time-Series: Using a Combination of Triple Exponential Smoothing and Neural Networks, in Demak

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第19期49卷 183-196页

作者： Hakim, Dimara Kusuma Gernowo, Rahmat Nirwansyah, Anang Widhi Haryanto, Totok Department of Informatics Universitas Muhammadiyah Purwokerto 53182 Indonesia Department of Physic Faculty of Mathematics and Natural Sciences Diponegoro University Indonesia Department of Geography Education Universitas Muhammadiyah Purwokerto 53182 Indonesia Bachelor of Management Program Faculty of Economics and Business Universitas Muhammadiyah Purwokerto 53182 Indonesia

Conventional flood hazard maps depict a static perspective on flood risk and are helpful in flood forecasting. Then, time-series flood forecasting research was developed and widely conducted. Still, it has limitations because the univariate method used does not consider the influence of other variables, unlike regression. Also, the determination of flood hazard weights, which is usually conducted through empirical studies using AHP, has a good level of accuracy but has the drawback of expert subjectivity. A new approach is proposed for flood hazard forecasting, combining the Triple ES method with NN and determining weights in a data-driven manner using NN. A combination of time series and regression methods (significantly non-linear), namely Triple ES with NN, results in good accuracy with an MSE value of 3.03, MAE 1.20, RMSE 1.74, R2 0.54, and a MAPE of 32.93%. The evaluation results for flood hazard weight determination with an MSE of 0.0111 and a MAPE of 7.81% show promising results, and the weights can be used in Hazard Flood GIS. Visualization in the form of a GIS Hazard Map can be done after all related raster data have been combined. The computational outcomes, particularly the MSE and MAPE values, demonstrate the effectiveness of the proposed approach, providing a clear understanding of the model's performance. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

YNote: A Novel Music Notation for Fine-Tuning LLMs in Music Generation

arXiv

引用

arXiv 2025年

作者： Lu, Shao-Chien Yeh, Chen-Chen Cho, Hui-Lin Hsu, Chun-Chieh Hsu, Tsai-Ling Wu, Cheng-Han Shih, Timothy K. Lin, Yu-Cheng Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan International Bachelor Program in Informatics Yuan Ze University Taoyuan Taiwan Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan

The field of music generation using Large Language Models (LLMs) is evolving rapidly, yet existing music notation systems, such as MIDI, ABC Notation, and MusicXML, remain too complex for effective fine-tuning of LLMs. These formats are difficult for both machines and humans to interpret due to their variability and intricate structure. To address these challenges, we introduce YNote, a simplified music notation system that uses only four characters to represent a note and its pitch. YNote’s fixed format ensures consistency, making it easy to read and more suitable for fine-tuning LLMs. In our experiments, we fine-tuned GPT-2 (124M) on a YNote-encoded dataset and achieved BLEU and ROUGE scores of 0.883 and 0.766, respectively. With just two notes as prompts, the model was able to generate coherent and stylistically relevant music. We believe YNote offers a practical alternative to existing music notations for machine learning applications and has the potential to significantly enhance the quality of music generation using LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Highly Similar Fish Species Using Machine Learning

Classification of Highly Similar Fish Species Using Machine ...

引用

International Conference on Systems, Signals and Image Processing, IWSSIP

作者： Leandro Magno C. Silva Franklin Cesar Flores Rosilene Luciana Delariva Gustavo Z. Felipe Yandre M. G. Da Costa Graduate Program in Computer Science State University of Maringá Federal Institute of Paraná Maringá Brazil Department of Informatics State University of Maringá Maringá Brazil Center for Biological and Health Sciences State University of Western Paraná Cascavel Brazil Graduate Program in Computer Science State University of Maringá Maringá Brazil

ISBN: (数字)9798350391886

ISBN: (纸本)9798350391893

Fish species inventory and monitoring is a timely concern due to the increasing environmental imbalance. In this sense, the development of machine learning strategies aiming to support automatic fish species identification is an important contribution, both in environmental and scientific terms. This study explores handcrafted features aiming to perform fish species identification in a quite challenging scenario, in which the inter-classes differences are minimal, as the species belong to the same family considering the hierarchy of biological classification (i.e. Characidae). For this purpose, it is proposed a set of features designed properly, aiming to capture visual properties closely related to each species that are difficult to be noted by experts in this domain of investigation. An additional contribution of this work is a dataset of 4870 images taken from 416 individuals from nine fish species. The Region of Interest (RoI) corresponding to the fish body is segmented, and horizontal and vertical histograms are collected from each sample, aiming to capture information related to the body shape, and other characteristics particular to each species. Experiments are performed using the Support Vector Machine (SVM), K-Nearest Neighbours (K-NN), Random Forest and Naive-Bayes classifiers and, in the best scenario, it is obtained an accuracy rate of 99%. This result corroborates the hypothesis that the use of handcrafted features specifically developed for this type of application can be quite effective in addressing this classification problem.

关键词： Support vector machines Image segmentation Visualization Histograms Image recognition Shape Fish

来源：评论

学校读者我要写书评

暂无评论

Detection of CT - Scan Lungs COVID-19 Image Using Convolutional Neural Network and CLAHE 3

Detection of CT - Scan Lungs COVID-19 Image Using Convolutio...

引用

3rd International Conference on Information and Communications Technology, ICOIACT 2020

作者： James, Ronaldus Morgan Sunyoto, Andi Universitas Amikom Yogyakarta Master Program of Informatics Engineering Yogyakarta Indonesia

ISBN: (纸本)9781728173566

Detecting COVID-19 is a significant task for medical professionals today because of its rapid spread. To overcome this problem, medical professionals have used various techniques and methods todetect to inhibit the proliferation of COVID-19. CT (Computed Tomography) Scan is currently the best method for detecting COVID-19. This diagnostic method is very accurate because it can see organs in three dimensions. However, this method requires a radiologist to detect the disease and requiresa long time, which means it will cut valuable time for medical practitioners if a patient is sick. Therefore it is necessary to implement a system to detect the coronavirus automatically as an alternative quickly. This study intends to help medical practitioners to detect computed tomography (CT)Scans of lungs infected with COVID-19. The methods to be used are Limited Adaptive histogram equalization (CLAHE) contrast to improve the quality of CT (Computed Tomography) Scan images of COVID-19 lungs and Convolutional Neural Network (CNN) for the image classification process. The dataset usedis 698 RGB images. This study uses three convolutional layers, 3 Max-Pooling layers, and two fully connected layers, resulting in 83.28% accuracy. © 2020 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

A task-oriented framework for generative AI in design

引用

Journal of Creativity 2024年第2期34卷

作者： Furtado, Lara Sucupira Soares, Jorge Barbosa Furtado, Vasco Department of Transportation Engineering Federal University of Ceará Brazil Applied Informatics Graduate Program University of Fortaleza Unifor Brazil ETICE State of Ceará Information Technology Company Brazil

The intersection of Artificial Intelligence and Design disciplines such as Architecture, Urban Planning, Engineering and Product Design has been a longstanding pursuit, with Generative AI (GAI) ushering in a new era of possibilities. The research presented here explores how GAI can enhance creativity and assist Design practitioners with tasks to create products such as, but not limited to, renderings, concepts, construction techniques, materials, data analytics or maps. We apply a framework of combinational, exploratory and transformational creativity to organize how recent advancements in GAI can support each creative category. We propose a conceptual framework of GAI towards transformational creativity, and identify real-world examples to demonstrate GAI's impact, such as transforming sketches into detailed renders, facilitating real-time 3D model generation, predicting trends through analytics and creating images or reports via text prompts. Our work envisions a future where GAI becomes a real-time collaborator to complete certain automated tasks while liberating Designers to focus on transformational innovation. © 2024

关键词： Creative computing Generative artificial intelligence Product Transformational Creativity

来源：评论

学校读者我要写书评

暂无评论

Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information

SSRN

引用

SSRN 2025年

作者： Li, Yingya Miller, Timothy Bethard, Steven Savova, Guergana Computational Health Informatics Program Boston Children’s Hospital Harvard Medical School 401 Park Drive BostonMA02115 United States College of Information Science The University of Arizona TucsonAZ United States

ObjectiveEven in the era of Large Language Models (LLMs) which are claimed to be solutions for many tasks, fine-tuning language models remains a core methodology used in deployment for a variety of reasons – computational efficiency and performance maximization among them. Fine-tuning could be single-task or multi-task joint learning where the tasks support each other thus boosting their performance. The success of multi-task learning can depend heavily on which tasks are grouped together. Naively grouping all tasks or a random set of tasks can result in negative transfer, with the multi-task models performing worse than single-task models. Though many efforts have been made to identify task groupings and to measure the relatedness among different tasks, it remains a challenging research topic to define a metric to identify the best task grouping out of a pool of many potential task combinations. We propose such *** propose a metric of task relatedness based on task difficulty measured by pointwise V-usable information (PVI). PVI is a recently proposed metric to estimate how much usable information a dataset contains given a model. We hypothesize that tasks with not statistically different PVI estimates are similar enough to benefit from the joint learning process. We conduct comprehensive experiments to evaluate the feasibility of this metric for task grouping on 15 NLP datasets in the general, biomedical, and clinical domains. We compare the results of the joint learners against single learners, existing baseline methods, and recent large language models, including Llama 2 and *** results show that by grouping tasks with similar PVI estimates, the joint learners yielded competitive results with fewer total parameters, with consistent performance across *** domain-specific tasks, finetuned models may remain a preferable option, and the PVI-based method of grouping tasks for multi-task learning could be particularly benefi

关键词： Multi-task learning

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：