检索结果-内蒙古大学图书馆

Automatic essay scoring for discussion forum in online learning based on semantic and keyword similarities

Asian Association of Open Universities Journal 2023年第3期18卷 262-278页

作者： Dhini, Bachriah Fatwa Girsang, Abba Suganda Sufandi, Unggul Utan Kurniawati, Heny Department of Multimedia Teaching Material Production Center Universitas Terbuka Tangerang Selatan Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia Faculty of Sains and Technology Universitas Terbuka Tangerang Selatan Indonesia

Purpose: The authors constructed an automatic essay scoring (AES) model in a discussion forum where the result was compared with scores given by human evaluators. This research proposes essay scoring, which is conducted through two parameters, semantic and keyword similarities, using a SentenceTransformers pre-trained model that can construct the highest vector embedding. Combining these models is used to optimize the model with increasing accuracy. Design/methodology/approach: The development of the model in the study is divided into seven stages: (1) data collection, (2) pre-processing data, (3) selected pre-trained SentenceTransformers model, (4) semantic similarity (sentence pair), (5) keyword similarity, (6) calculate final score and (7) evaluating model. Findings: The multilingual paraphrase-multilingual-MiniLM-L12-v2 and distilbert-base-multilingual-cased-v1 models got the highest scores from comparisons of 11 pre-trained multilingual models of SentenceTransformers with Indonesian data (Dhini and Girsang, 2023). Both multilingual models were adopted in this study. A combination of two parameters is obtained by comparing the response of the keyword extraction responses with the rubric keywords. Based on the experimental results, proposing a combination can increase the evaluation results by 0.2. Originality/value: This study uses discussion forum data from the general biology course in online learning at the open university for the 2020.2 and 2021.2 semesters. Forum discussion ratings are still manual. In this survey, the authors created a model that automatically calculates the value of discussion forums, which are essays based on the lecturer's answers moreover rubrics. © 2023, Bachriah Fatwa Dhini, Abba Suganda Girsang, Unggul Utan Sufandi and Heny Kurniawati.

关键词： Discussion forum Essay scoring Keyword similarity Semantic similarity

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

Intelligence Tutorial System for Learning Cultures and Local Languages in Indonesia 2

Intelligence Tutorial System for Learning Cultures and Local...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Veron, Juan Sebastian Tantry, Calvin Fladico, Naxwell Warnars, Harco Leslie Hendric Spits Bina Nusantara University School of Computer Science Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665400527

Indonesia has so many local cultures and languages that spread from Sabang to Merauke, and most Indonesians do not know how to speak two or more regional languages in Indonesia. Most Indonesians only know familiar tribes that are only commonly heard. Because of this problem, governments in the Indonesian provinces have included lessons on Indonesian culture. The lesson will explain Indonesia's national and local culture for their area. In this way, the government can also help Indonesians learn more about their local language. This paper proposes a solution to create a learning portal website for users, both from Indonesia and other countries, to learn Indonesian culture and regional languages. In this way, the author hopes that users can learn about Indonesian local culture and language and contribute to preserving Indonesian local culture and language. This application was built on a web-based basis by applying the following HTML, CSS, and javascript using Personal Home Pages (PHP) for database connection using MySQL. The built application was designed using a use case diagram and class diagram to describe the database relations. © 2022 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Drowsiness Detection in Low-Light Conditions Using YOLO and CLAHE Augmentation for Real-Time Applications

Drowsiness Detection in Low-Light Conditions Using YOLO and ...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Sella Joanita Nur Aprilia Devi Fitrianah Computer Science Department Binus Graduate Program–Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

In the era of advancing technology, deep learning, particularly within the realm of computer vision, has emerged as a critical tool for enhancing human safety. This research focuses on developing a drowsiness detection system for car drivers using the YOLOv5 algorithm, aimed at mitigating the risks associated with microsleep, a temporary loss of attention that poses a significant threat on the roads. The prevalence of traffic accidents attributed to drowsy driving is alarming, with statistics indicating that over 9.5% of accidents in Indonesia during late 2019 were linked to drowsiness. To address this pressing issue, our study employs the YOLOv5 model to classify driver states into ‘Drowsy’ and ‘Awake’ categories, enhanced by the Contrast Limited Adaptive Histogram Equalization (CLAHE) augmentation technique, which optimizes performance in low-light conditions. The drowsiness detection system is designed as a user-friendly application that provides real-time alerts to drivers upon detecting signs of drowsiness. The implementation process includes data collection, preprocessing, and model training, leading to the evaluation of the system’s accuracy. Evaluation results demonstrate a detection accuracy of 94%, with precision and recall both reaching 93%. These findings underscore the efficacy of integrating YOLO and CLAHE in developing a reliable drowsiness detection system, contributing to road safety by reducing the risk of accidents related to driver fatigue.

关键词： YOLO Deep learning Training Adaptation models Accuracy Real-time systems Sensor systems Intelligent sensors Vehicles Accidents

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

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

Detection of Employee Fatigue Based on Image Processing Using Deep Learning Model

Detection of Employee Fatigue Based on Image Processing Usin...

引用

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

Indonesian Tweet Emotion Detection Using IndoBERT

Indonesian Tweet Emotion Detection Using IndoBERT

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Nikita Ananda Putri Masaling Ricky Reynardo Siswanto Abba Suganda Girsang Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

This study investigates emotion detection on tweets written in the Indonesian language, using the IndoBERT model that has been trained for 50 epochs. The examination conducted in this study provides a comprehensive analysis of the performance dynamics shown by the model. The assessment results provide an accuracy score of 0.74, indicating the model's proficiency in identifying sentiments within the collection of tweets. By using assessment criteria such as accuracy, recall, and the F1-score, the model's comprehensive analytical ability is validated, emphasizing its effectiveness in deciphering various emotional circumstances. The accuracy, recall, and F1-score of the model, with average values of 0.79, 0.78, and 0.78 respectively, combined demonstrate its resilience in accurately capturing subtle emotional subtleties. This study enhances our comprehension of language model applications in the field of emotional intelligence by exploring the complexities of sentiment analysis. It emphasizes the practical value of these applications in real-world scenarios.

关键词： Analytical models Sentiment analysis Emotion recognition Accuracy Prevention and mitigation Stability criteria Ecosystems Robustness Information management Resilience

来源：评论

学校读者我要写书评

暂无评论

Object Driven Fuzzy Decision Model for Evaluating the Cryptocurrency's Performance

Object Driven Fuzzy Decision Model for Evaluating the Crypto...

引用

International Conference on ICT For Smart Society (ICISS)

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

ISBN: (数字)9798350389654

ISBN: (纸本)9798350389661

The assessment of cryptocurrency performance has been subject to criticism due to the lack of a standardized approach, leaving the evaluation process without clear guidance. In this research, an innovative object-driven decision model based on fuzzy logic (OFDM) conception was developed to systematically analyze cryptocurrency performance. Object-oriented operated as the main method in analyzing and designing the model. In this context, the model elements deeply observed and functioned to become fundamental thinking for constructing the model. Then, fuzzy logic with curve membership function form was also used as the primary method to avoid the bias value of three key parameters; trend line (and then used to see the slope distance), price consistency, and transaction volume consistency. The constructed model is a novel decision model that was successfully constructed for assessing the determined cryptocurrency performance. Utilizing six months of real data from three major cryptocurrencies (Bitcoin, Ethereum, and Dogecoin), the model conclusively demonstrates that Bitcoin exhibits the strongest performance, scoring 36.39 performance points.

关键词： Fuzzy logic Analytical models Object oriented modeling OFDM Bitcoin Market research Data models Context modeling

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

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：