检索结果-内蒙古大学图书馆

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Ismael Seidel André Filipe da Silva Fernandes José Luis Güntzel Dept. of Computer Science and Statistics (INE) Embedded Computing Lab. (ECL) Computer Science Graduate Program (PPGCC) Federal University of Santa Catarina (UFSC) Florianópolis Brazil

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

Light Fields (LFs) are a plenoptic image modality that provides more information on light rays, making them an excellent representation for immersive media. To compress such a modality, the Joint Photographic Experts Group (JPEG) committee created the JPEG Pleno Part 2 standard with two profiles. This work focuses on the reference encoder implementation for the Baseline Block-Based Profile (BBBP), called JPEG Pleno Model (JPLM). Our main contribution lies in the proposal and analysis of a parallel implementation of JPLM using OpenMP. We show that it is possible to accelerate encoding from nearly 2 to 10 times when using 2 to 16 threads, with a memory overhead ranging from 15% up to 78%, depending on the LF size. Moreover, the speedup comes with no cost in terms of coding efficiency, i.e., the LFs encoded with the proposed parallel version are bit-exact matches to ones encoded with the sequential version.

关键词： Costs Instruction sets Transform coding Transforms Encoding Light fields Software Decoding Proposals Standards

来源：评论

学校读者我要写书评

暂无评论

E-Govchurch as a Digital Transformation Initiative for Nation-wide Christianity Organization 1

E-Govchurch as a Digital Transformation Initiative for Natio...

引用

1st International Conference on Technology Innovation and Its Applications, ICTIIA 2022

作者： Paramita, Adi Suryaputra Prabowo, Harjanto Ramadhan, Arief Sensuse, Dana Indra Graduate Program Universitas Ciputra Surabaya Bina Nusantara University Surabaya Indonesia/Jakarta Information Systems Department/Doctor Of Computer Science Indonesia Doctor Of Computer Science Graduate Program Bina Nusantara University Jakarta Indonesia Universitas Indonesia Faculty Of Computer Science Depok Indonesia

ISBN: (数字)9781665488266

ISBN: (纸本)9781665488266

The process of digital transformation is part of the 4.0 industrial revolution. Through digital transformation, it is hoped that all processes inside an organization will function more efficiently. Internet technology is the major driver of an organization's digital transformation effort. Information Systems for the statewide scope of the two main religion-based organizations in Indonesia are required to satisfy the Indonesian government's National Medium-Term Development Plan for the years 2020-2024 in accordance with Indonesian President Decree No. 18 of 2020. The regulation mandates that the ministry of religious affairs provide information and data services. E-Govchurch, an abbreviation for Electronic-Governmental Church, is the suggested framework. E-Govchurch is a digital program for Information Systems that incorporates a framework for data governance. E-Govchurch will develop utilizing SSM, RBV, the Zachman Framework, and the DAMA framework. The purpose framework in research will lead the next phase of framework development process. © 2022 IEEE.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Ensemble-Stacking Machine Learning Model for Multi-Class Skin Diseases Identification 5

Ensemble-Stacking Machine Learning Model for Multi-Class Ski...

引用

5th International Conference on Biomedical Engineering, IBIOMED 2024

作者： Tandelon, Dennis Christiono, David Lawrence Andryani, Nur Afny Catur Gondokaryono, Srie P. Rahardja, July I. Danarti, Retno School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Doctor of Computer Science Department Jakarta Indonesia Indonesian Society of Dermatology & Venereology Padjadjaran University Faculty of Medicine Indonesia Dermatovenereology Department Indonesia Indonesian Society of Dermatology & Venereology Gadjah Mada University Faculty of Medicine Indonesia Dermatovenereology Department Indonesia

ISBN: (纸本)9798350389265

Algorithm development on skin diseases identification with high cardinality classification is still very challenging. In addition, the high similarity appearance among diseases makes the computer vision approach meet high difficulties on providing clear distinct feature representation. In general, some literature shows that the performance of single machine learning or single deep learning techniques can be further improved when merged by ensemble mechanism. This approach has been applied on binary skin's cancer diseases diagnosis prediction and successfully improve the prediction ability. This paper elaborates the potential of ensemble machine learning approaches using stacking techniques on conducting feature extraction and classification model for identifying more general skin diseases based on dermoscopy images and mobile phone images. The proposed model combines three different CNN architectures, ResNet50, Xception, and VGG16 to extract features from the image then stacked as input for the model trained using five different algorithms, which are logistic regression, support vector machines, multi-layer perceptron, k-nearest neighbors, random forests and the combination of these algorithm in stacking classifier as the base estimators and final estimator. The simulation results present the proposed ensemble - stacking model succeeds to improve the identification ability in all utilized datasets. In addition, the proposed ensemble - stacking models show better recall which indicates good sensitivity on handling false negative. It is beneficial for medical application. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Automation testing using silk test workbench for website

引用

Procedia computer science 2023年 216卷 128-135页

作者： Feliks Abedyoga Chandra Parapat Gede Putra Kusuma Muhammad Rizki Nur Majiid Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Automation testing is essential to carry out functional testing quickly and precisely. Software testing is beneficial for testers doing many testing processes according to the existing scenarios. So, there is an urgency to explore a more advanced solution to replace the traditional approach. Silk Test Workbench is a tool for automation testing that can accelerate the functional testing of complex applications. For this research, we proposed automation testing on website applications with various testing scenarios that have been made. The visual test recording method is used for automation testing with Silk Test Workbench. Silk Test Workbench can speed up testing time, make a good test asset testing scenario, make it easier for users to do testing, and speed up the process to get the result in the form of a screen capture of the testing process. A comparison of testing time has been performed. The automatic testing time with the scenarios is 2 hours 46 minutes. The automatic testing time will be 2 hours 36 minutes using the all-in-one scenario. This study also used questionnaires from colleagues in the Quality Assurance field to get maximum User Acceptance Test results.

关键词： Automation Testing Silk Test Workbench Testing Strategy Testing Environment Web Application

来源：评论

学校读者我要写书评

暂无评论

Using synthetic data to develop machine learning models to predict the performance of fiber-reinforced concrete

引用

Asian Journal of Civil Engineering 2025年第5期26卷 2209-2221页

作者： Silva, Victor Hugo Peres Pessoa, Carolina Luiza Emereciana Sousa, Derica dos Santos Stefani, Ricardo Graduate Program in Materials Science Federal University of Mato Grosso Campus Araguaia MT Cuiaba 78605-091 Brazil Center for Agricultural and Veterinary Sciences University for the Development of Santa Catarina State (UDESC) Campus Lages SC Florianópolis 88520-000 Brazil Departament of Chemistry Federal University of Ouro Preto MG Ouro Preto 35402-136 Brazil

Concrete is a widely used construction material owing to its high compressive strength. However, its durability is often compromised by the development of cracks caused by tensile stress within the structures. These cracks can occur during the drying process, leading to water infiltration and corrosion of the concrete reinforcement, which subsequently require repair. Consequently, innovative technologies, such as self-repairing concrete and crack control, have become crucial for reducing the costs associated with structural repairs. In this context, this study investigated novel crack-control technologies in concrete structures using a machine-learning model that can accurately predict the performance of a specific fiber in fiber-reinforced concrete using a comprehensive dataset. The dataset was compiled from 18 studies and further augmented using synthetic data-generation techniques. It encompasses 13 different fiber types and 1953 fiber-reinforced concrete formulations. The computational model was implemented in Python, and multiple linear regression (MLR), support vector regression (SVR), random forest, and gradient boosting techniques were employed to develop the prediction model. The results showed that the Random Forest (R² = 0.887 and RMSE = 0.110), gradient boosting (R² = 0.868 and RMSE = 0.368), and SVR models (R² = 0.856 and RMSE = 0.376) outperformed their MLR counterparts (R² = 0.587 and RMSE = 0.637). Moreover, the Random Forest method showed a lower RMSE, making it more suitable for accurately predicting the performance of fiber-reinforced concrete. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Crack control Fiber-reinforced concrete Machine learning

来源：评论

学校读者我要写书评

暂无评论

BERT base model for toxic comment analysis on Indonesian social media

引用

Procedia computer science 2023年 216卷 714-721页

作者： Ghinaa Zain Nabiilah Simeon Yuda Prasetyo Zahra Nabila Izdihar Abba Suganda Girsang Computer Science Department Binus Graduate Program Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

Social media is an online media that functions as a platform for users to participate, share, create, and exchange information through various forums and social networks. The rapid increase in social media activity causes an increase in the number of comments on social media. This is prone to triggering debate due to the easy formation of open discussions between social media users. However, the debate often triggers the emergence of negative things, causing great fights on social media. Social media users often use comments containing toxic words to argue and corner a party or group. This study conducted an experiment to detect comments containing toxic sentences on social media in Indonesia using a Pre-Trained Model that was trained for Indonesian. This study performed a multilabel classification and evaluated the classification results generated by the Multilingual BERT (MBERT), IndoBERT, and Indo Roberta Small models. The optimal result of this study is to use the IndoBERT model with an F1 Score of 0.8897.

关键词： Toxic Comment MBERT IndoBERT IndoRoBERTa Small Indonesian social media

来源：评论

学校读者我要写书评

暂无评论

Performance of MIMO Visible Light Communication Under Consideration of Recommended Illumination Levels

Performance of MIMO Visible Light Communication Under Consid...

引用

Optics and Photonics Conference (SBFoton IOPC), SBFoton International

作者： David Esteban Farfán-Guillén Alexandre De Almeida Prado Pohl Graduate Program in Electrical and Computer Engineering (CPGEI) Federal University Technology-Parana Curitiba Brazil

This work compares illumination and communication performance of 2 × 2, 3 × 2 and 4 × 2 MIMO-OFDM VLC links. Results show that not every configuration complies with the recommended illumination levels (... 详细信息

ISBN: (数字)9798350388176

ISBN: (纸本)9798350388183

关键词： Spatial diversity Lighting Optics MIMO Robustness Photodetectors Indoor environment Antennas Visible light communication Photonics

来源：评论

学校读者我要写书评

暂无评论

Frequency-Voltage-var Function for VFD in Oil and Gas Platform with Wind Power 8

Frequency-Voltage-var Function for VFD in Oil and Gas Platfo...

引用

8th Southern Power Electronics Conference and the 17th Brazilian Power Electronics Conference, SPEC / COBEP 2023

作者： De Sousa Medeiros, Kassiane Da Rocha, Lorrana Faria Soares Callegari, João Marcus Brandão, Danilo Iglesias Universidade Federal de Minas Gerais Graduate Program in Electrical Engineering Belo Horizonte Brazil Norwegian University of Science and Technology Department of Electric Energy Trondheim Norway

ISBN: (纸本)9798350321128

Renewable energy resources emerge as a sustainable alternative to augmenting the energy supply of Floating Production Storage and Offloading (FPSO) platforms. However, the increased generation based on converter-interfaced energy decreases the system-equivalent inertia constant, which becomes more susceptible to frequency deviations. This paper proposes and evaluates the performance of the combined frequency-voltage-var control to mitigate frequency variation in a typical FPSO unit with penetration of wind power systems. The control functions are communication-free and embedded in two active front-end variable frequency drives (AFE- VFDs) set on water injection pumps. The FPSO's electrical power system model is developed in MATLAB/Simulink®. Comparative results with the AFE-VFD equipped with volt-var, freq-var, and combined freq-volt-var functions are shown to highlight the merits of the proposed solution. © 2023 IEEE.

关键词： Floating production storage and offloading freq-var control isolated power system power quality volt-var control

来源：评论

学校读者我要写书评

暂无评论

Serverless utilization in microservice e-learning platform

引用

Procedia computer science 2023年 216卷 204-212页

作者： Bryan Andreas Nday Gede Putra Kusuma Renaldy Fredyan Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Since cloud computing becoming the trend, the way servers being implemented slowly moves to the cloud. Companies did not need to buy a physical server machine to deploy an app. Having a private server on cloud infrastructure indeed already reduce some cost for on-premise server maintenance. However, there is still a cost for usage when the server is inactive or having low to no traffic at all. Serverless deployment offer function as a service where application is deployed as a function and cost is billed per function call. This paper proposed a solution where there are two deployment that works in turn between infrastructure as a service and function as a service deployment. This dual deployment offered the system to use the virtual private server or deployed instance on active hours, and switch to serverless functions on inactive hours. Switching to serverless on low traffic hours will cut the usage and cost of the microservice app by the least 25%, while having performance slightly comparable to microservice app deployed to instances.

关键词： Cloud Computing E-Learning Function as a Service Hybrid Deployment REST API

来源：评论

学校读者我要写书评

暂无评论

Digital Transformation: Challenges About Iot and Ai in High Pressure Die Casting (HPDC)

Digital Transformation: Challenges About Iot and Ai in High ...

引用

International Symposium on Applied Computational Intelligence and Informatics ( SACI)

作者： Patricia D. M. Plentz Thaynara M. M. Ribeiro Heinz F. C. Rahmig Renato F. Bulcão-Neto Iwens Gervasio Sene Analucia S. Morales Graduate Program in Computer Science Federal University of Santa Catarina Florianópolis Brazil Institute of Informatics Federal University of Goiás Goiânia Brazil Advanced Knowledge Center in Immersive Technology Federal University of Goiás Goiânia Brazil Graduate Program in Energy and Sustainability Federal University of Santa Catarina Araranguá Brazil

ISBN: (数字)9798331515478

ISBN: (纸本)9798331515485

This study explores and systematically reviews advancements in applying artificial intelligence (AI) and Internet of Things (IoT) technologies to the high-pressure die casting (HPDC) process. Widely utilized in aluminum automotive part production, HPDC presents significant challenges, including defect reduction, process optimization, and predictive maintenance. The primary objective of this research is to examine how AI and IoT can address these challenges by enhancing decision-making, improving quality control, and increasing operational efficiency. The systematic review, based on PRISMA guidelines, analyzed 16 peer-reviewed studies that focus on the integration of machine learning (ML) and deep learning (DL) techniques in HPDC. The findings reveal critical applications, such as defect detection, predictive modeling for optimizing the solidification cycle, and fault diagnosis. Despite the potential benefits, challenges remain, including high implementation costs, data quality issues, and the limited interpretability of AI models. Furthermore, the analysis underscores the predominance of private datasets and highlights the need for public, anonymized repositories to foster collaborative research. This study contributes by providing a comprehensive overview of AI applications in HPDC, identifying existing barriers, and proposing directions for future research. These findings reinforce the transformative potential of AI in advancing Industry 4.0 and offer valuable insights for academia and industry, paving the way for more sustainable and efficient HPDC operations.

关键词： Deep learning Technological innovation Costs Collaboration Production Companies Fourth Industrial Revolution Internet of Things Die casting Predictive maintenance

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：