检索结果-内蒙古大学图书馆

A Robust Resource-Aware Framework for YOLO-Based Object Detection in Dynamic and Multi-Platform Resource-Constrained Environments

引用

IEEE Access 2025年 13卷 79977-79995页

作者： Shiddiqi, Ary Mazharuddin Navastara, Dini Adni Studiawan, Hudan Romadhona, Yasinta Azhar, Muhammad Fath Mushaffa Rahma, Fayruz Bramantoro, Arif Alzahrani, Ahmad A. Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Department of Informatics Surabaya60111 Indonesia Telkom University Informatics Study Program Surabaya Campus Surabaya60231 Indonesia Universitas Islam Indonesia Department of Informatics Yogyakarta55584 Indonesia Universiti Teknologi Brunei School of Computing and Informatics Bandar Seri BegawanBE1410 Brunei King Abdulaziz University Faculty of Computing and Information Technology 21589 Saudi Arabia

Efficient management of resources such as CPU, RAM, and disk storage is a critical challenge for object detection systems that rely on multi-camera video streaming, especially for resource-constrained devices. These constraints frequently result in the risk of overheating and potential system failure during high workloads. This paper presents a novel Resource-Aware Framework (RA-Framework), designed to optimize resource allocation using dynamic adaptation mechanisms. The RA-Framework dynamically manages CPU, RAM, and disk storage resources for YOLO-based object detection, supporting multiple camera streams and scheduling mechanisms. The framework was implemented in resource-constrained environments using various YOLO models with single and dual-camera setups. Experimental results showed that the RA-Framework successfully reduced average CPU usage by up to 68.62%, decreased RAM consumption by approximately 13.47%, and extended the time for disk usage to increase by 1% by more than 500% in specific scenarios. In contrast, systems without the RA-Framework experienced higher resource utilization and greater susceptibility to resource scarcity or even overheating. © 2013 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Prediction of Corrosion Inhibition Efficiency of Expired Pharmaceuticals: Model Development and Application

引用

Journal of Bio- and Tribo-Corrosion 2025年第1期11卷 1-12页

作者： Putra, Dzaki Asari Surya Ardyansyah, Nibras Bahy Putranto, Nicholaus Verdhy Trisnapradika, Gustina Alfa Akrom, Muhamad Rustad, Supriadi Dipojono, Hermawan Kresno Maezono, Ryo Faculty of Computer Science Study Program in Informatics Engineering Universitas Dian Nuswantoro Semarang50131 Indonesia Research Center for Materials Informatics Faculty of Computer Science Universitas Dian Nuswantoro Semarang50131 Indonesia Quantum and Nano Technologies Research Group Faculty of Industrial Technology Institut Teknologi Bandung Bandung40132 Indonesia School of Information Science Japan Advanced Institute of Science and Technology Ishikawa923-1292 Japan

Corrosion poses a significant challenge in industries due to material degradation and high maintenance costs, making effective inhibitors essential. Recent studies suggest expired pharmaceuticals as alternative corrosion inhibitors, but identifying the most efficient compounds can be time-consuming. This study applies machine learning models, particularly Gradient Boosting Regressor (GBR), to predict corrosion inhibition efficiency (CIE). The developed model is integrated into a web-based application, enabling real-time, accurate CIE predictions. Results show GBR as the more precise model for predicting CIE, with low error rates. The streamlit-based web application offers a user-friendly platform, facilitating quick identification of suitable inhibitors. It is flexible, supporting analysis beyond corrosion inhibitors, and significantly enhances the efficiency of the evaluation process. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Drivers of the Sustainability Performance of Induction Stove Conversion program in Indonesia

引用

International Journal of Sustainable Energy Planning and Management 2025年 43卷 5-30页

作者： Damayanti, Retno Wulan Safira, Silvia Dhea Laksono, Pringgo Widyo Setiadi, Haryono Entifar, Nisa Aqilla Ellenahaya Industrial Engineering Study Program Sebelas Maret University Ir.Sutami 36A Surakarta57121 – 57162 Indonesia Center of Technology Development and Industrial Collaboration Institute for Research and Community Service Sebelas Maret University Ir.Sutami 36A Surakarta57121 – 57162 Indonesia Informatics and Science Data Study Program Sebelas Maret University Ir.Sutami 36A Surakarta57121 – 57162 Indonesia Smart Green Technology Engineering Department Pukyong National University 45 Yongso-ro Nam-Gu Busan Korea Republic of

In 2022, Indonesia initiated a pilot project to transition from liquid petroleum gas (LPG) stoves to induction stoves, targeting 8.2 million households by 2025. While LPG is considered a clean cooking fuel by the World Health Organization due to its low PM2.5 emissions, this program aims to further reduce CO2 emissions from cooking activities, aligning with Indonesia’s clean energy transition and 2060 Net Zero Emission goals. Throughout the program, doubts and criticisms arose among various sectors of society, particularly concerning the sustainability of this program. This research aims to determine and analyze the driving factors that support the sustainability of the induction stove transition program. Five sustainability aspects, namely, economic, social, environmental, technical, and institutional, were analyzed. A total of 315 Indonesian citizens participated as respondents in this research survey. The Partial Least Squares-Structural Equation Model (PLS–SEM) method was utilized as the analytical approach for the study. The results revealed that nine factors significantly influenced program sustainability, with the strongest impacts from technology costs (path coefficient = 0.859), contextual factors (0.803), electrical infrastructure (0.792), and community perception (0.773). Economic sustainability was driven by technology costs and business opportunities (0.643), while environmental sustainability was strongly influenced by electrical infrastructure. Post-installation support (0.307) and financial management (0.391) significantly impacted technical and institutional sustainability respectively. These empirical findings improve previous research on the sustainability of an energy transition program, which provides insights for researchers and stakeholders in the energy management field, especially in developing countries, for policy determination and decision-making. © 2025, Aalborg University Press. All rights reserved.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Herb compounds screening as meningitis inhibitor candidates using neural network and random forest methods

引用

AIP Conference Proceedings 2025年第1期3250卷

作者： Riska Aprilia Mohammad Hamim Zajuli Al Faroby Muhammad Adib Kamali Muhammad Dzulfikar Fauzi Information Technology Study Program Faculty of Information Technology and Business Institut Teknologi Telkom Surabaya Surabaya Indonesia Data Science Study Program Faculty of Information Technology and Business Institut Teknologi Telkom Surabaya Surabaya Indonesia Informatics Study Program Faculty of Information Technology and Business Institut Teknologi Telkom Surabaya Surabaya Indonesia

Meningitis is an inflammation of the meninges that occurs in the protective lining of the brain and spinal cord caused by bacterial, viral, or fungal infections. This disease is difficult to recognize because it has initial symptoms like the flu where the patient has a fever and headache. Current efforts to prevent the disease by strengthening antibodies. Meanwhile, drug candidates for the treatment of this disease still have not found optimal results in reducing mortality due to meningitis. This study aims to find and analyses herbal compound candidates that might be inhibitors of meningitis. Compound data was acquired from a validated open database. The data acquired are smiles of the chemical bond structure of the compounds. In the data processing process, compound feature extraction is required by applying the concept of molecular fingerprint. The results of feature extraction are used as datasets to build classification models by applying the Multilayer Perceptron (MLP) and Random Forest algorithms. The two models are compared, and a more robust model is selected to be used as a prediction model for herbal compound search. The MLP model has a better accuracy of 0.97 compared to the Random Forest model. The results of screening using the MLP learning model obtained Symphytine, cis-Linalool oxide, and 3-O-Methylcalopocarpin compounds have the highest probability compared to thousands of other herbal compounds. This candidate compound can be used as a recommendation for drug discovery to treat patients who contract Meningitis.

关键词：

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

Empirical mode decomposition of near-infrared spectroscopy signals for predicting oil content in palm fruits

引用

Information Processing in Agriculture 2023年第3期10卷 289-300页

作者： Inna Novianty Ringga Gilang Baskoro Muhammad Iqbal Nurulhaq Muhammad Achirul Nanda Computer Engineering Study Program College of Vocational StudiesIPB UniversityBogor 16680Indonesia Informatics Management Study Program College of Vocational StudiesIPB UniversityBogor 16680Indonesia Technology and Plantation Production Management Study Program College of Vocational StudiesIPB UniversityBogor 16680Indonesia Department of Agricultural and Biosystem Engineering Faculty of Agro-Industrial TechnologyUniversitas PadjadjaranJatinangor 45363Indonesia

Oil content estimation in palm fruits is a precious property that significantly impacts oil palm production,starting from the upstream and *** content can be used to monitor the progress of the oil palm fresh fruit bunch(FFB)and be applied to identify product *** on the near-infrared(NIR)signals,this study proposes an empirical mode decomposition(EMD)technique to decompose signals and predict the oil content of palm ***,350 palm fruits with Tenera varieties(Elaeis guineensis ***),at various ages of maturity,were harvested from the Cikabayan Oil Palm Plantation(IPB University,Indonesia).Second,each sample was sent directly to the laboratory for NIR signal measurements and oil content ***,the EMD analysis and arti-ficial neural network(ANN)were employed to correlate the NIR signals and oil ***,a robust EMD-ANN model is generated by optimizing the lowest possible *** on performance evaluation,the proposed technique can predict oil content with a coefficient of determination(R2)of 0.933±0.015 and a root mean squared error(RMSE)of 1.446±*** results demonstrate that the model has a good predictive capacity and has the potential to predict the oil content of palm fruits directly,without neither solvents nor reagents,which makes it environmentally ***,the proposed technique has a promising potential to be applied in the oil palm *** like this will lead to the effective and efficient management of oil palm production.

关键词： Artificial neural network Empirical mode decomposition Oil palm Oil content prediction

来源：评论

学校读者我要写书评

暂无评论

Securing elliptic curve based El-Gamal against Pollard Rho attack using elliptic curve based Diffie-Hellman key exchange

Securing elliptic curve based El-Gamal against Pollard Rho a...

引用

7th International Conference for Internet technology and Secured Transactions, ICITST 2012

作者： Zani, Tafta Barmawi, Ari Moesriami Abdurohman, Maman Informatics Study Program Graduate School of Telkom Institute of Technology Bandung Indonesia

ISBN: (纸本)9781908320087

Elliptic Curve based El-Gamal (ECEG) cryptosystem is one of many widely used public key cryptosystems that makes use the elliptic curve discrete logarithm problem (ECDLP). For breaking ECDLP, Pollard Rho is currently the fastest attack. In this study a hybrid of Elliptic Curve based Diffie-Hellman Key Exchange (ECDHKE) and ECEG, is modified as an attempt to make harder for an attacker to reveal ECEG's private key by executing Pollard Rho attack using information from the public key gained by eavesdropping. This study examine the modified ECEG strength increase and the feasibility for implementing the modified ECEG. © 2012 Infonomics Society.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Finding the Best Techniques for Predicting Term Deposit Subscriptions (Case study UCI Machine Learning Dataset) 4

Finding the Best Techniques for Predicting Term Deposit Subs...

引用

4th International Conference on Sustainable Engineering and Creative Computing, ICSEC 2022

作者： Setiyani, Lila Indahsari, Ayu Rosalina Wansen, Tjong President University Master of Science Information Technology Study Program Bekasi Indonesia President University Informatics Study Program Bekasi Indonesia

ISBN: (纸本)9798350322002

Knowing a lot about attributes, such as bank client data, marketing campaigns, social and economic context, and so on, is necessary to predict which bank customers are likely to sign up for time deposits. The direct marketing campaigns dataset for the bank institution was made available by the UCI machine learning repository. This dataset had previously been used in studies to forecast customers who would sign up for time deposits, but the outcomes of the two studies were different. The purpose of this study is to determine which machine learning methods are most effective for predicting customers who will sign up for time deposits. In this study, researchers used machine learning methods like random forests, K-nearest neighbors, decision trees, naive bayes, logistic regression, SVM, and XGBoost to uncover the truth. Results showed that XGBoost had the highest accuracy (91.73%), followed by the DT classifier (88.79%), LR classifier (91.2%), NB classifier (84.78%), KNN classifier (90.6%), SVM (89.6%), and XGBoost (91.44%). © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Annotated Data for Semantic Role Labeling of Crisis Events in Indonesian Tweets

引用

Data in Brief 2025年

作者： Amelia Devi Putri Ariyanto Diana Purwitasari Bilqis Amaliah Chastine Fatichah Muhammad Ghifari Taqiuddin Haikal Department of Informatics Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya 60111 Indonesia Information Technology and Systems Study Program Widya Husada University Semarang 50146 Indonesia Department of Public Health Faculty of Health Science Universitas Dian Nuswantoro Semarang 50131 Indonesia

Social media platforms like Twitter provide essential real-time information about crisis events. Although the text data generated is rich, its vast volume and unstructured format make manual analysis challenging. Information extraction technologies such as Semantic Role Labeling (SRL) are needed to identify a sentence's semantic roles, such as who is the victim, what happened, when and where the event occurred, and what objects are affected in the crisis text to speed up and facilitate the emergency response process. However, the availability of public SRL datasets, especially for Indonesian, still considered a low-resource language, is very limited. We aim to develop an Indonesian-language SRL dataset based on Twitter text focusing on crisis events. This dataset includes entity labels for Named Entity Recognition (NER), another information extraction technique besides SRL. Text data was obtained through a crawling process on Twitter using specific keywords from 2018–2023, then preprocessed to obtain clean and relevant data for crisis events in Indonesia. The cleaned text data was then manually annotated by two experts based on guidelines designed to maintain consistency, resulting in 99,206 tokens labeled with SRL and NER. The high inter-annotator agreement value (Cohen's Kappa >0.90) indicates reliable data quality. This dataset is designed to support the development of automated models for information extraction, such as SRL and NER. The results of this extraction will be used for disaster impact analysis, mapping affected areas, and planning for crisis mitigation. By providing this dataset, the research opens up new opportunities for developing Natural Language Processing (NLP) in Indonesian, especially in crisis event analysis.

关键词： Semantic Role Labeling Named Entity Recognition Crisis Event Twitter Data Low-resource Languages Indonesian Tweets

来源：评论

学校读者我要写书评

暂无评论

Influence of blended learning on learning result of algorithm and programming 3

Influence of blended learning on learning result of algorith...

引用

3rd International Conference on informatics and Computing, ICIC 2018

作者： Anggrawan, Anthony Ibrahim, Nurdin Suyitno, M. Satria, Christofer Informatics Engineering Study Program of College of Informatics Management and Computer Science Bumigora West Nusa Tenggara Indonesia Education Technology Study Program of Jakarta State University Jakarta Indonesia Education Technology Study Program of Jakarta State University Jakarta Indonesia Visual Communication Design Study Program of College of Informatics Management and Computer Science Bumigora West Nusa Tenggara Indonesia

ISBN: (纸本)9781538669204

The advancement of today's learning technology makes the learning process no longer fully bases on face to face learning, but can achieve by online learning. Online learning is not only useful in overcoming deficiencies in conventional classroom learning, but also a means to meet the learning styles of students who are less fond of and/or dislike face-to-face learning. On the other hand, the main disadvantage of online learning is the lack of face-to-face interaction, while the strength of face-to-face learning is the intensity of student interaction with teachers, the ease of cooperative learning and the clarity of learning materials. In turn, the superiorities on face-to-face learning and online self-learning can be acquired by blended learning. However, blended learning is a learning solution by taking the best advantage of face-to-face classroom learning and online learning. Blended learning has been a learning solution of today's learning. In this study, two blended learning that has different learning content portions between the portion of face-to-face learning materials and online self-learning was conducted to find out which blended learning results produce better pedagogy between two blended learning, and how well the learning outcomes of blended learning are, especially for Algorithm and programming subject. The research results showed the blended learning with 60% face-to-face learning content and 40% online self-learning content delivers learning cognitive competency outcomes worse than 40% face-to-face learning content and 60% online self-learning content. The learning outcome of both blended learning is good, that is greater than 60% from the ideal number. © 2018 IEEE.

关键词： Students

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：