检索结果-内蒙古大学图书馆

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

作者： Angel Karentia Ferdinand Winaya Derwin Suhartono Computer Science Department BINUS Graduate Program – Master of Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

Sentiment analysis is widely used as a tool to find valuable insight from texts without explicitly expressed. Lots of techniques have already been used to get it but there still have shortcomings in data source or the model strategy itself. Indonesian language approximately has 199 million speakers across the world where 44 million speakers natively. Even with that great number, the resources for the Indonesian language's natural language processing are still limited, and hard to find the perfect way to define sentiment analysis in the Indonesian language. The state-of-the-art sentiment analysis method uses LSTM on a small corpus while the best in town is Transformer where it's easy to transfer learning from the Transformer pre-trained model into specific tasks. From this potential, combining the Transformer pre-trained model with LSTM can be an innovative strategy. This research compared the hybrid model of Transformer-LSTM build using three Indonesian languages’ Transformer-based pre-trained model on sentiment analysis task which can surpass the Transformer model with the highest increased 2.40% accuracy and 3.02% on F1 score.

关键词： Seminars Sentiment analysis Analytical models Accuracy Law Soft sensors Transfer learning Medical services Transformers Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Suitability of Latest Version of YOLOv11 in Drone Development Studies

Suitability of Latest Version of YOLOv11 in Drone Developmen...

引用

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

作者： Mohammad Faisal Riftiarrasyid Ford Lumban Gaol Haryono Soeparno Yulyani Arifin Computer Science Department Binus Graduate Program – Computer Science Bina Nunsantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

Although drones have become increasingly advanced and sophisticated, they still face challenges such as limited computing power and high-power consumption. Optimizing their features is a key strategy to address these limitations. One critical feature that can be further improved is the algorithm for specialized tasks like obstacle detection. Recent studies have primarily relied on earlier versions of YOLO for this purpose. However, with the release of the latest YOLO versions, YOLOv10 and YOLOv11, there is an opportunity to assess their suitability for drone applications. In this study, we trained YOLOv10-nano and YOLOv11-nano using a drone-specific dataset and compared their performance with similar studies. The results indicate that YOLOv11-nano outperforms YOLOv10-nano in bounding-box prediction, achieving a higher mAP of 0.957 with a 0.22 difference, as well as faster inference times with a 74.1 ms improvement, resulting in a frame rate gain of 0.0421 FPS. However, when compared to earlier studies, YOLOv11-nano demonstrates superior precision but lags in real-time processing speed. These findings highlight the trade-off between accuracy and inference time, highlighting the suitability of YOLOv11-nano for applications in drone development where accuracy takes precedence over processing speed.

关键词： YOLO Training Seminars Accuracy Cameras Prediction algorithms Real-time systems Intelligent systems Information technology Drones

来源：评论

学校读者我要写书评

暂无评论

A review: Data pre-processing techniques used for diabetes prediction

引用

Procedia computer science 2024年 245卷 667-676页

作者： Mahmud Isnan Gregorius Natanael Elwirehardja Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Cmputer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

When processing datasets in diabetes classification, common problems included a large number of missing values, outliers, and dataset imbalance. To deal with those issues, this study analyzed 18 studies on diabetes classification with machine learning algorithms over the past 5 years. This revealed the important role of data pre-processing in creating effective classification models, as it was found that by using different data pre-processing techniques, the same model can provide different performance. The study identified K-Nearest Neighbor (KNN) and support vector machine (SVM) as superior methods for filling in missing values, achieving an accuracy of 98.49% and 94.89%, respectively. These approaches outperformed traditional methods such as median or mean replacement. However, the challenge of imbalanced data sets remains in all studies reviewed. The common evaluation metrics used to evaluate the created models in previous studies included accuracy, precision, specificity, sensitivity/recall, and F1 Score. Overall, this review showed that the role of data pre-processing is no less important than algorithm selection to improve the performance of machine learning models in diabetes classification.

关键词： Diabetes Classification Data Pre-Processing Machine Learning Imbalanced Dataset

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

Utilizing Sentiment Insights for Software Evalution with Aspect-Based Sentiment Analysis in App Reviews Using IndoBERT-Lite

Utilizing Sentiment Insights for Software Evalution with Asp...

引用

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

作者： Nikita Ananda Putri Masaling Haryono Soeparno Yulyani Arifin Ford Lumban Gaol Computer Science Department BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

With mobile applications increasingly used daily, understanding user feedback is vital for software improvement. Manual analysis of user reviews on platforms is time-consuming and lacks scalability. This study utilizes aspect-based sentiment analysis with the IndoBERT-Lite model to automate the categorization and sentiment detection of feedback. Despite advancements, precise aspect classification and sentiment detection in Indonesian language reviews remain challenging due to limited resources. Using 5,000 Tokopedia reviews, labeled across five aspects, namely functionality, service, performance, usability, and design, the model achieved optimal results with batch size 32, showing 0.85 accuracy and 0.866 F1 score for aspect classification, and 0.998 across all metrics for sentiment classification.

关键词： Measurement Seminars Sentiment analysis Analytical models Accuracy Reviews Scalability Software Mobile applications Usability

来源：评论

学校读者我要写书评

暂无评论

A review of traffic violation detection technology in reporting mechanism 2

A review of traffic violation detection technology in report...

引用

2nd International Conference on Biospheric Harmony Advanced Research, ICOBAR 2020

作者： Alaydrusl, A. Putra, W.K. Nugroho, Y. Muhammad Surantha, N. Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Traffic Violation Detection system using radio frequency identification (RFID) has been applied to detect vehicles with limited power sources through RFID Tag. Camera sensors are also applied to identify a vehicle and its plate number through image and video processing known as computer vision. On the other hand, vehicular ad hoc network (VANET) to gain information about location, speed, and so on through the vehicle-to-vehicle (V2V) connection. Lastly, the internet-of-things that is backed-up by cloud computing helps to store various information from each of these technologies and process them to get results. Many researchers have proposed and developed algorithms or technology with astonishing experimental results of them. However, there has been no review of the integration and reporting mechanism that correlates them. There has also been no review about how to connect the information to the authority and violator. Therefore, the review was made to explain each technology's method with their experiment's results and issues. Moreover, the future challenge also had been given to further research. © Published under licence by IOP Publishing Ltd.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Telematics Work Field Review Text Classification Using the Naïve Bayes Method

Telematics Work Field Review Text Classification Using the N...

引用

2022 IEEE Creative Communication and Innovative Technology, ICCIT 2022

作者： Maesya, Aries Heryadi, Yaya Arifin, Yulyani Lukas Suparta, Wayan Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Faculty of Engineering Indonesia

ISBN: (纸本)9781665468763

Indonesia will benefit from a demographic boom in 2030 with a higher labor supply than in earlier decades. Then in industrial revolution 4.0 robotics and artificial intelligence will take the place of low-skilled or menial employment that don't require specialized expertise (AI). To aim research is Telematics Work Field Review Text Classification Using the Naïve Bayes Method. The method using Multinomial Naïve Bayes model which is trained to learn from patterns in training data set without being programmed explicitly. Then, based on the Term Frequency - Inverse Document Frequency, consider the weighting of the word used (TF-IDF). The text classification stage is then carried out using the multinominal nave bayes classification method with evaluation using the confusion matrix, following the acquisition of the TF-IDF value. In the study it took data with web crawling techniques on social media sites twitter. The data collected was 936 data consisting of 7,8% negative sentiments, 26,4% positive sentiments, and 65,8% neutrals. The results of accuracy testing using the Confusion Matrix. And from the results of such tests resulted in an accuracy of 66%, precision 73%, and recall 85%. © 2022 IEEE.

关键词： Telematics

来源：评论

学校读者我要写书评

暂无评论

Implementation of the EfficientNet Model for Identification of Wild Edible Plants

Implementation of the EfficientNet Model for Identification ...

引用

science and Information Technology in Smart Administration (ICSINTESA), International Conference of

作者： Maria Susan Anggreainy Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350376111

ISBN: (纸本)9798350376128

Wild plants are plants that are not cultivated but wild plants can be easily found in the neighborhood. However, not all wild plants can be utilized as food crops by the community. Therefore, it is necessary to know what wild plants can be consumed so that people do not have to worry about food availability. The purpose of this study is to determine whether the EfficientNet model can be used to identify wild plants that can be consumed. Experimental results show that the EfficientNet model has an accuracy of 85% in identifying wild plants that can be consumed.

关键词： Training Accuracy Transfer learning Neural networks Crops Data models Information technology Tuning Overfitting Image classification

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Heart Disease Prediction using Kernels in Support Vector Machine Model

Performance Analysis of Heart Disease Prediction using Kerne...

引用

science and Information Technology in Smart Administration (ICSINTESA), International Conference of

作者： Maria Susan Anggreainy Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350376111

ISBN: (纸本)9798350376128

Linear data is a collection of data that is linearly separated by a straight line and nonlinear data is a collection of data that is not separated by a line. Usually, non-linear data is separated by irregular curves. However, for non-linear data. Support Vector Machine (SVM) is difficult to classify data for non-linear data. The solution is to use Kernel Trick. Kernel Trick is a simple method used to map low-dimensional nonlinear data and transform it into a higher-dimensional space. The goal is to make it easier to classify data by finding a hyperplane that can separate the dataset linearly well. This research is to create a program that can predict heart disease using the Support Vector Machine (SVM) model with Kernel Tricks. Heart disease prediction is very important because the heart is one of the most important organs in the human body. The results indicated that the SVM model with the Radial Basis Function (RBF) Kernel achieved the highest accuracy compared to the Linear Kernel and Polynomial Kernel.

关键词： Support vector machines Heart Accuracy Training data Transforms Predictive models Polynomials Kernel Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

BERT and ULMFiT Ensemble for Personality Prediction from Indonesian Social Media Text

BERT and ULMFiT Ensemble for Personality Prediction from Ind...

引用

2022 International Symposium on Information Technology and Digital Innovation, ISITDI 2022

作者： Halimawan, Noptovius Suhartono, Derwin Gema, Aryo Pradipta Yunanda, Rezki Binus Graduate Program-Master Of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School Of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Epigene Labs Paris France

ISBN: (数字)9781665461160

ISBN: (纸本)9781665461160

Predicting personality is a growing topic in the field of natural language processing. The study of personality prediction has been proven to benefit the development of recommender systems and automated personality assessments by previous studies. Additionally, the widespread usage of social media in Indonesia such as Twitter has served as a potential source of data for developing such models. Existing personality prediction models has explored the implementation of both traditional machine learning models and deep learning models, with the latter proven to perform better with more data. Despite so, there is not much development of deep learning-based personality prediction models in the domain of Indonesian text. We propose a deep learning-based ensemble model based on Universal Language Model Fine Tuning (ULMFiT) and Bidirectional Encoder Representations from Transformers (BERT), the state-of-the-art pre-trained models for text classification. The model is trained with Indonesian tweets labelled with Five Factor Model (FFM) personality traits along with the users' metadata. The model is tested with five predetermined scenarios to prove the robustness of its performance. The final evaluation of the model proves that it has successfully achieved optimal performance of 76.41 % macro-average accuracy and 75.55% macro-average F-1 score, exceeding the state-of-the-art BERT and ULMFiT © 2022 IEEE.

关键词： Classification (of information)

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：