检索结果-内蒙古大学图书馆

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Michael Ethan I Gede Putra Kusuma Computer Science Department Binus Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

Fatigue in workplace is a common thing shared by all employees. Continuous exposure of fatigue could lead to negative productivity for companies. Current research on fatigue detection mostly focused to detect fatigues from a single 2D image data, meanwhile research on fatigue detection using each frames from video data is needed for better detection for fatigue process. The main advantage of using each timesteps of frames from video data which makes the model is able to predict long term dependency of fatigue person. To solve this problem, a deep learning model is proposed that could detect employee fatigue based on image processing using video data. Three models are used to train data using Convolutional Neural Network (CNN), which are Time Distributed CNN LSTM, 3D CNN, and 3D CNN LSTM. Out of those three models, the best model to detect fatigue person from video data is Time Distributed CNN Model with F-1 Score value of 0.77 and Accuracy Score of 0.76 for testing data. The model that gives best inference time is also Time Distributed CNN Model with the average value of 382 miliseconds to detect fatigues from 58 testing data with each of the data has duration of 3 seconds and 12 frames.

关键词： Deep learning Three-dimensional displays Image processing Computational modeling Distributed databases Fatigue Data models Convolutional neural networks Long short term memory Testing

来源：评论

学校读者我要写书评

暂无评论

Dual Word Embedding Framework for Gender-Based Writing Style Analysis Using Word2Vec and BERT

Dual Word Embedding Framework for Gender-Based Writing Style...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Aditya Riyanto Amalia Zahra Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

Social media has evolved into a vast and multifaceted data repository, presenting valuable opportunities to investigate gender-based variations in writing styles. This study aims to enhance the precision of gender classification on Twitter text by leveraging a combined word embedding approach. The paper proposes a framework that utilizes two distinct word embedding models - a combination of GloVe and BERT, as well as GloVe and Word2Vec - to capture both global and contextual linguistic nuances within the text. The dataset comprises a comprehensive collection of tweets and user profile descriptions harvested from Twitter, which underwent meticulous preprocessing and word representation steps before being further processed using the robust Random Forest algorithm. The experimental findings indicate that the combination of GloVe and BERT outperforms the other combination of GloVe and Word2Vec, and also surpasses the performance of single embedding models, with 62.93% accuracy being the highest achieved result. This study provides valuable insights into the potential of combined word embedding techniques for enhancing the accuracy of gender classification in social media text analysis.

关键词： Biometrics Text analysis Accuracy Social networking (online) Blogs Supervised learning Writing Linguistics Natural language processing Random forests

来源：评论

学校读者我要写书评

暂无评论

An Object-Driven Fuzzy Decision Model for Determining Fuel in Boiler Machines

An Object-Driven Fuzzy Decision Model for Determining Fuel i...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Ditdit Nugeraha Utama Jeremia Widyanto Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

There are many alternative fuel types that can be used by a particular type of engine. Determining which fuel alternative is optimal for an engine presents its own challenges. This is especially true in an industrial setting, where certain standards are necessary to select the best fuel alternative to be used and operated. This study aims to develop a decision model for selecting a fuel type for boiler engines based on specific parameters or criteria. The decision model is designed using an object-oriented approach, utilizing three types of diagrams: object, activity, and sequence. An object-oriented model design approach allows for the decision model to be depicted transparently and very close to reality. Additionally, the analytical hierarchical process (AHP) and fuzzy logic are the core methods employed in constructing the decision model. Then, in developing this decision model, four main criteria or parameters are considered: cost, heating value, safety, and emissions. These four parameters were derived from a literature review and interviews with experts. Among the three evaluated fuel types (i.e., natural gas, industrial diesel oil or IDO, and coal), coal received the highest decision score of 0.78. Thus, based on this decision value―the outcome of the model's recommendation―it can be concluded that coal remains an objective choice as a fuel for use in boiler engines.

关键词： Fuzzy logic Object oriented modeling Oils Coal Analytic hierarchy process Boilers Safety Engines Standards Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Object-Driven Fuzzy Decision Model for Assessing the Employees' Work from Home Eligibility

Object-Driven Fuzzy Decision Model for Assessing the Employe...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Ditdit Nugeraha Utama Christiawan Immanuel Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

Work from Home (WFH), especially in the post-pandemic era, has emerged as an alternative work system adopted by many companies. Efficiency and effectiveness are the two main reasons why WFH is favored. In addition, the implementation of the WFH system in conducting business processes within the company allows for greater flexibility in work methods. For certain types of jobs or specific industry domains, this WFH system can be quite reliable. Workers can perform their tasks from anywhere and at any time. Also, monitoring systems enable employees to be remotely tracked by the company. However, the question remains: is an employee's work environment suitable enough to ensure the successful implementation of WFH? To answer this, a standardized model is needed to assess the level of eligibility for WFH implementation. This study aims to develop a fuzzy-based decision model to evaluate the eligibility of an employee's work environment for implementing WFH. An object-oriented approach is used to describe the design of the decision model, while fuzzy logic serves as the primary method for building the model. The model successfully simulated 24 raw employee data points, yielding a highest eligibility score of 88.61 with a similarity index of 0.78 when compared to the model proposed in previous research.

关键词： Industries Fuzzy logic Object oriented modeling Buildings Companies Data models Reliability Monitoring Business

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

Optimizing Big Data Implementation to Create Business Value and Architecture Proposed in the Banking Industry: A Systematic Review

Optimizing Big Data Implementation to Create Business Value ...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Kristiana, Idha Meyliana, Meyliana Hidayanto, Achmad Nizar Prabowo, Harjanto Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Universitas Indonesia Faculty of Computer Science Depok Indonesia Bina Nusantara University BINUS Business School Undergraduate Program Management Departement Jakarta11480 Indonesia

ISBN: (纸本)9798350320954

The exponential growth of data is compelling organizations to employ data in decision-making. As one of the businesses with an ecosystem that contributes to data growth, banks have challenges in generating insight. A high level of data security is frequently linked to a high level of data access difficulties. This poses a challenge to the implementation of data-driven business, where taking control of our data is one of the best ways to ensure that we not only own data but also have the ability to process and use data to extract business value. Through literature review, a number of challenges to optimizing the implementation of big data analytics in the banking industry were discovered. Data governance refers to the methods and procedures that assist banks in managing and securing data. A big data architecture is presented to address the highlighted issues, particularly with a multi-tiered approach to big data structures. With the adoption of this architecture, it will be simpler to generate business-value-generating insights for the banking industry using big data with accessibility and protection of data. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

The Learning Outcomes Achievement and User Experience Analysis of a Cryptography Education Web Game

The Learning Outcomes Achievement and User Experience Analys...

引用

HCI and UX Conference in Indonesia (CHIuXiD), International

作者： Helmi Yusuf Susanto Yulyani Arifin Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350380439

ISBN: (纸本)9798350380446

The rising threat of cybercrimes in Indonesia, including a significant breach of the national data center, reveals the urgent need for effective cybersecurity education. Cryptography, a key component of cybersecurity, is often difficult for beginners to grasp. To address this, we developed an interactive web game that blends puzzle-solving with a visual novel to make cryptographic concepts more accessible. This study analyzes the game’s user experience (UX) using the ARCS model—Attention, Relevance, Confidence, Satisfaction—and assesses learning outcomes by comparing pre-test and post-test results. The findings show significant improvements in participants’ understanding and high levels of engagement, demonstrating a strong correlation between positive user experience and enhanced learning outcomes. However, some aspects of the educational content still need refinement. Future updates will offer multilingual support and personalized learning paths, with pre-and post-tests targeting specific cryptography and cybersecurity sub concepts, and analysis of UX features through targeted surveys and in-game analytics to enhance learning experiences.

关键词： Surveys Visualization Analytical models Data centers Correlation Education Games User experience Multilingual Cryptography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Software Quality Through Defect Prediction

Enhancing Software Quality Through Defect Prediction

引用

Creative Communication and Innovative Technology (ICCIT), IEEE

作者： Nyoman Ayu Gita Gayatri Haryono Soeparno Ford Lumban Gaol Yulyani Arifin Dept. of Computer Science BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350367492

ISBN: (纸本)9798350367508

Prediction of software defects is an important aspect of software quality assurance, aiming to identify defective modules to improve reliability and reduce costs in the maintenance process. A systematic literature review (SLR) on software defect prediction is presented in this study, focusing on identifying commonly used datasets, methods, and frameworks in this domain between 2014 and 2023. The review follows established SLR guidelines to synthesize data from primary studies, providing insight into research trends as well as methodological advances. The results show a significant reliance on public datasets such as the NASA Metrics Data program (MDP) and the PROMISE repository. Various machine-learning techniques have been used, with Neural networks, support vector machines, and random forests becoming the most popular techniques. This review aims to guide future research by highlighting key trends and gaps in the existing literature.

关键词： Support vector machines Measurement Neural networks NASA Software quality Machine learning Market research Software reliability Maintenance Guidelines

来源：评论

学校读者我要写书评

暂无评论

Trend Intelligent Tutoring System 2018-2022 : Systematic Literature Review 3

Trend Intelligent Tutoring System 2018-2022 : Systematic Lit...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Suwita, Jaka Prabowo, Harjanto Hendric Spits Warnars, Harco Leslie Meyliana, Meyliana Binus Graduate Program Computer Science Bina Nusantara University Departement of Computer Science Jakarta11480 Indonesia Stmik Insan Pembangunan Department of Information System Tangerang15810 Indonesia Binus Business School Undergraduate Program Bina Nusantara University Management Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia

ISBN: (纸本)9798350381931

ITS is a method of teaching that uses technology to give lessons without the need for an instructor to be there. A systematic literature review (SLR) was conducted in this research to identify the components of an intelligent tutoring system, and the results are presented. The method used in this literature review is the prism method. The steps in the prism method are slr protocol, search for literature, select literature, summarize evidence and disseminate results. The slr protocol stage, it consists of determining a research question, searching for scientific reference sources with the keyword intelligent tutoring system, then sorting out the appropriate articles and making final conclusions. This article gives a detailed look at how the intelligent tutoring system changed over time during the pandemic epoch. Our contribution is complete information on the components of ITS in times of epidemic at universities, with the goal of improving their learning and practical use of the technology. © 2024 IEEE.

关键词： Prisms

来源：评论

学校读者我要写书评

暂无评论

Virality Prediction on Twitter Using Combined CNN and BERT Models

Virality Prediction on Twitter Using Combined CNN and BERT M...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Hilarius Ryan Auxilio Benedecas Abba Suganda Girsang Computer Science Department Binus Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

Nowadays, social media serves as a platform for sharing and receiving information. One indicator of the importance of information is its virality. Virality is an interesting topic in the world of Natural Language Processing (NLP), including the prediction of virality and identifying features that influence it. Research in this area has utilized Bidirectional Encoder Representations from Transformers (BERT) models and yielded promising results. Previous studies aimed to predict virality based on specific features. This research aims to predict virality by combining the abilities of Convolutional Neural Network (CNN) and BERT models. The BERT model transforms textual data into numerical and adds new features, while the CNN model excels in numerical classification. Data for this study is sourced from Twitter and in Indonesian language. The proposed model demonstrates improvements compared to the model from previous research. Specifically, it shows a 7.1% increase in precision, a 9.9% increase in recall, a 3.8% increase in accuracy, and an 8.1% increase in F1-Score compared to the previous model. These findings contribute to future research on similar topics, particularly in leveraging multiple models for prediction tasks. Overall, the study provides insights into effectively utilizing the strengths of various models and combining them in prediction tasks.

关键词： Measurement Social networking (online) Blogs Bidirectional control Predictive models Encoding Data models Natural language processing Numerical models 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：