检索结果-内蒙古大学图书馆

Data Mining for the Global Multiplex Weekly Average Income Analysis

Procedia computer science 2023年 219卷 52-59页

作者： Nicholas Dominic Gregorius Natanael Elwirehardja Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

The box office (BO) income had significantly declined up to 80% in 2020, as the COVID-19 pandemic emerged. To minimize further financial risks, multiplex (multiple cinema complexes) owners need to analyze their potential income for each movie, each week. Therefore, we developed a proper data mining strategy that allows multiplex owners to analyze and discover insights on how successfully produced movies could be. The methodology comprises (1) data loading and exploration, (2) data cleaning, (3) data selection, integration, and transformation using Pentaho, (4) data mining in which the results were stored in the MySQL database, and (5) pattern evaluation and presentation using Qlik Sense as the Business Intelligence (BI) dashboard. Based on our data mining methodology, we revealed that drama, comedy, action, and thriller are favorite genres. We also found that DreamWorks Animation and Pixar Animation Studios are both the most popular production houses, even Apatow Productions and Escape Artists still have the biggest revenue on average.

关键词： movie multiplex income data mining Business Intelligence dashboard

来源：评论

学校读者我要写书评

暂无评论

Long short-Term memory (LSTM) model-based reinforcement learning for nonlinear mass spring damper system control 7

Long short-Term memory (LSTM) model-based reinforcement lear...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Wijaya, Santo Heryadi, Yaya Arifin, Yulyani Suparta, Wayan Lukas Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta55281 Indonesia Universitas Katolik Indonesia Atma Jaya Jakarta12930 Indonesia

The Neural Networks (NN) model which is incorporated in the control system design has been studied, and the results show better performance than the mathematical model approach. However, some studies consider that only offline NN model learning and does not use the online NN model learning directly on the control system. As a result, the controller's performance decreases due to changes in the system environment from time to time. The Reinforcement Learning (RL) method has been investigated intensively, especially Model-based RL (Mb-RL) to predict system dynamics. It has been investigated and performs well in making the system more robust to environmental changes by enabling online learning. This paper proposes online learning of local dynamics using the Mb-RL method by utilizing Long Short-Term Memory (LSTM) model. We consider Model Predictive Control (MPC) scheme as an agent of the Mb-RL method to control the regulatory trajectory objectives with a random shooting policy to search for the minimum objective function. A nonlinear Mass Spring Damper (NMSD) system with parameter-varying linear inertia is used to demonstrate the effectiveness of the proposed method. The simulation results show that the system can effectively control high-oscillating nonlinear systems with good performance. © 2022 Elsevier B.V.. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches in Detecting Autism Spectrum Disorder

引用

Procedia computer science 2023年 227卷 1070-1076页

作者： Daniel Nicholas Dominic Tjeng Wawan Cenggoro Bens Pardamean Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480

Early detection of Autism Spectrum Disorder (ASD) needs to be increased to prevent further adverse impacts. Thus, the classifi-cation between ASD and Typically Development (TD) individuals is an intriguing task. This review study has collected 26 related papers to answer four research questions, i.e., what are the most used data inputs, brain atlases, and machine learning models for ASD classification, as also to discover the significant parts of the brain correlated with the ASD. It was eventually found that functional connectivity matrix, Support Vector Machine, and CC200 are the most frequently used data input, model, and brain atlas, respectively. Researchers also concluded that the posterior temporal fusiform cortex, intracalcarine cortex, cuneal cortex, subcallosal cortex, occipital pole, and lateral occipital cortex are the brain regions highly correlated with ASD.

关键词： autism spectrum disorder brain atlas brain region machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of time-series database on microservice architecture for health monitoring system

Evaluation of time-series database on microservice architect...

引用

2022 International Symposium on Electronics and Smart Devices, ISESD 2022

作者： Simanjuntak, Eko Surantha, Nico Isa, Sani Muhamad Bina Nusantara University Binus Graduate Program-Master of Computer Science Computer Science Department Jakarta11480 Indonesia Tokyo City University Electronic and Communication Engineering Faculty of Engineering Department of Electrical Tokyo Japan

ISBN: (数字)9798350396607

ISBN: (纸本)9798350396607

Recently, the research on daily health monitoring using a wearable sensor has been continually evolving. In the future, when this system is actually implemented, a vast amount of data transmission will be conducted from multiple sensors to the cloud server. A system capable of transmitting, storing, processing, and visualizing massive volumes of data is necessary for health monitoring. This research aims to develop a health monitoring system that can accommodate a high amount of data with high performance. The proposed techniques include numerous modifications to system architecture and technology. In the system architecture, a multi-database is proposed to enhance the reliability of the system. As an enhancement to the technology aspect, a time series database and MQTT server are proposed. As the result, the proposed system achieves significantly better performance in terms of throughput, database-writing speed, and database-reading speed compared to the existing system. © 2022 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effect of Activation Function on Transformer Model Performance for Official Announcement Translator from Indonesian to Sundanese Languages

Exploring the Effect of Activation Function on Transformer M...

引用

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Bambang Dwi Wijanarko Dina Fitria Murad Yaya Heryadi Cuk Tho Kiyota Hashimoto Computer Science Department BINUS Online Learning Jakarta Indonesia Information Systems Department BINUS Online Learning Jakarta Indonesia Computer Science Department BINUS Graduate Program-Doctor of Computer Science Jakarta Indonesia Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Prince of Songkla University Phuket Campus Phuket Thailand

Automated language translation involving low-resource language has gained wide interest from many research communities in the past decade. One lesson learned from the past COVID-19 pandemic, particularly in Indonesia, is that many local Governments have to release regular public announcements to keep people following health protocol especially when they are in public areas. Many studies showed some evidence that rural people in Indonesia which covers a large proportion of Indonesia’s population, feel more convenience receiving official announcements in their local language. However, translating official announcement from the national language to many local languages in Indonesia require many experienced bilingual translators and time. This paper presents exploration results in developing an automated language translator model to translate texts in Bahasa Indonesia to the Sundanese language. In particular, this study aims to explore the effect of ReLU, Sigmoid, and Tanh activation functions of the Vanilla Transformer Model on its translation performance. The experiment results showed that the activation function under study gives similar training accuracy (0.98). However, ReLU achieves better performance than Tanh in terms of validation accuracy, training loss, and validation loss.

关键词： Training COVID-19 computer science Protocols Pandemics Local government Sociology

来源：评论

学校读者我要写书评

暂无评论

Analysis of Enterprise Architecture Research Trends for Higher Education Institutions Using Systematic Literature Review and Vos Viewer

Analysis of Enterprise Architecture Research Trends for High...

引用

Informatics Engineering, science & Technology (INCITEST), International Conference on

作者： Yudistira Soegoto Harjanto Prabowo Harco L H Spits Warnars Agung Trisetyarso Computer Science Departemen BINUS Graduate Program Doctor Computer Science - School of Computer Science Bina Nusantara University Jakarta Indonesia Mathematics Departement School Of Computer Sicence Bina Nusantara University Jakarta Indoensia

Enterprise Architecture Framework (EAF) is a commonly used framework and the best solution for addressing and defining the transformation that needs to be built to support business operations. To be able to make the transition quickly, many higher education institutions (HEIs) are starting to adopt EAF. This research aims to help the evolution and transpiration of enterprise architecture research in higher education. This research uses a systematic literature review (SLR) research method which includes several steps, namely identifying research questions, identifying research sources, using keywords to complete the data discovery process, disseminating data, and analyzing the results to answer research questions. The data used comes from digital libraries, especially Emerald Insight, IEEE Xplore Digital Library, and science Direct. Data taken from 2019 to 2023 in RIS format will then be analyzed and visualized using VosViewer. The results of this research are to find the growth of research publications over five years, find research trends on enterprise architecture frameworks, identify relationships between scientific concepts, and determine the knowledge network of enterprise architecture frameworks based on keywords.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Machine Learning on Smart Home Data for Prediction of Electrical Energy Consumption

Evaluation of Machine Learning on Smart Home Data for Predic...

引用

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Mochammad Haldi Widianto Alexander Agung Santoso Gunawan Yaya Heryadi Widodo Budiharto Computer Science Department BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Electrical energy consumption is always increasing, and this causes the supply of electrical energy to be increased to compensate. One solution is to predict electricity energy consumption using Artificial Intelligence (AI) technology in Smart Homes. Several studies' solutions for predicting electrical energy consumption usually focused only on performance but rarely evaluated Machine Learning (ML) by correlation for feature selection and utilized interpretability model. This study uses an ML model for predicting utilization (Linear Regression, Decision Tree, Random Forest, and XGBoost). Then, Feature Selection utilizes correlation to choose the best feature. After that, the interpretability model utilizes Local Interpretable Model-agnostic Explanations (LIME). The results show that XGBoost has the best Root Mean Squared Error (RMSE) value (0.318) with a percentage of the number of train and test data (90/10). After that, by eliminating features that correlate with 0.01, XGBoost improves with an increase of (0.018) to become (0.3). Then from LIME. This work also gets positive feature from XGBoost such as: "Furnance, Well dan Living Room".

关键词： Energy consumption Correlation Linear regression Smart homes Predictive models Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Blockchain and API Development to Improve Relational Database Integrity and System Interoperability 7

Blockchain and API Development to Improve Relational Databas...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Ramadhan, Andhika Naafi Pane, Kharisma Naufal Wardhana, Kun Rifki Suharjito Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Industrial Engineering Department BINUS Graduate Program-Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia

Technological developments have resulted in a trend of cryptocurrencies that use a technology called blockchain to create and record all transactions made into a digital ledger. Along with the emergence of the trend of cryptocurrencies, this development has also resulted in crimes that hit the digital world, such as data leakage and cyber espionage. This threat can be prevented by applying blockchain technology to the database that has been used. Therefore, we need a system that can facilitate the use of blockchain technology and can process data from an existing relational database into a blockchain-based database. The system developed in this study was built with the FastAPI framework that uses the Python programming language and the React framework that uses the Javascript programming language. This system was tested using Katalon and Wireshark software to perform throughput testing and man-in-The-middle attacks. Evaluation of this system is assessed based on the average throughput time and also the results of Wireshark packet capture. The system designed in this research is expected to help overcome interoperability problems when using blockchain and improve relational database integrity. The results of the test show that the system is safe from man-in-The-middle attacks while sending data through API and has a faster throughput time than BigchainDB system by 4.151 seconds. © 2022 Elsevier B.V.. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Analyzing STEM Women’s Employability: A Machine Learning Framework with Clustering and Multi-Target Classification

Analyzing STEM Women’s Employability: A Machine Learning Fr...

引用

computer sciences, Engineering, and Technology Innovation (ICoCSETI), International Conference on

作者： Nadzla Andrita Intan Ghayatrie Wina Permana Sari Devi Fitrianah Esyin Chew Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Cardiff School of Technology Cardiff Metropolitan University Cardiff United Kingdom

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

The gender gap in science, Technology, Engineering, and Mathematics (STEM) fields highlights significant research opportunities, particularly in examining the employability of female graduates. This study introduces a novel machine learning framework integrating Clustering and Multi-target Classification to analyze employment waiting time and job linearity among women STEM alumni. Using K-Means Clustering and Multi-Target Logistic Regression, the framework achieved a classification accuracy of 77% and a silhouette score of 0.61, demonstrating its effectiveness in predictive analysis. Beyond these results, the framework offers a robust methodology for integrating Clustering with Classification, enabling a nuanced understanding of the employability challenges faced by women in STEM. This approach identifies key patterns in employment data, paving the way for targeted interventions and actionable insights. Furthermore, the findings aim to inform data-driven policymaking and future research to improve employability outcomes. This work contributes to addressing systemic challenges and fostering gender diversity in STEM careers while enhancing opportunities for women.

关键词： Logistic regression Technological innovation Accuracy Computational modeling Employment Linearity Machine learning Predictive analytics STEM Gender issues

来源：评论

学校读者我要写书评

暂无评论

Energy Sector Stock Price Prediction Using The CNN, GRU & LSTM Hybrid Algorithm

Energy Sector Stock Price Prediction Using The CNN, GRU & LS...

引用

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Bambang Sulistio Harco Leslie Hendric Spits Warnars Ford Lumban Gaol Benfano Soewito Computer Science Department Binus Graduate Program – Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Nowadays, many people are starting to care about early investment. One of the most popular investments lately, especially for millennials, is a stock investment. In investing, there are advantages and risks of loss. One way to reduce the risk of loss is by using price predictions before investing in stocks. This paper proposes the use of deep learning in making stock predictions. We conducted research by calculating the performance of six deep-learning algorithms to predict stock closing prices. The application of the CNN-LSTM-GRU hybrid algorithm combination produces the best performance compared to other methods, based on the value: Root Mean Squared Error (RMSE) decreased by 1.100 by 14%, Mean Absolute Error (MAE) was successfully reduced by 0.798 by 13.4%, and R Square increased by 0.957 by 3.9%. In predicting stock prices on the Indonesian Stock Exchange, especially in the energy sector, CNN-LSTM-GRU is more appropriate for investors than using a single algorithm to make decisions in investing in stocks..

关键词： Deep learning computer science Recurrent neural networks Sociology Prediction methods Prediction algorithms Convolutional neural networks

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：