检索结果-内蒙古大学图书馆

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

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

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. © 2022 Elsevier B.V.. All rights reserved.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Service Oriented Fuzzy Decision Model for Road Traffic Engineering 9

Service Oriented Fuzzy Decision Model for Road Traffic Engin...

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Utama, Ditdit Nugeraha Zaki, Fauzan Affan Munjeri, Intan Juliani Putri, Nidya Utami Bina Nusantara University BINUS Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia UIN Syarif Hidayatullah Information Systems Department Jakarta Indonesia

ISBN: (纸本)9798350370126

A number of attempts have already been implemented formally to solve road traffic congestion. However, the objective strategy type of road traffic engineering could not be proven truly. Try and error is one inefficient way in road traffic engineering to degrade the level of congestion. The study was conducted to propose a new service-oriented model (SOM) that combines fuzzy-logic and water flow algorithm methods (called FWFA). The method combination was operated as the main method to construct the decision model for selecting the objective strategy in road traffic engineering. Also, service-oriented architecture (SOA) is realized to implement such a constructed model practically. The Model can suggest the most optimal strategy decision in road traffic engineering. Here, a main traffic road of Juanda in area Ciputat, Tangerang Selatan, province Banten, Indonesia;was selected as a research object in this study. The constructed SOM for road traffic engineering was structurally delivered in this paper. © 2023 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Computational Analysis of Jazz Music: Estimating Tonality through Chord Progression Distances 23

Computational Analysis of Jazz Music: Estimating Tonality th...

引用

7th International Conference on computer science and Application Engineering, CSAE 2023

作者： Yamamoto, Yuta Mizutani, Tetsuya Master's Program in Computer Science University of Tsukuba Tsukuba Japan Department of Computer Science University of Tsukuba Tsukuba Japan

ISBN: (纸本)9798400700590

Currently, research in music informatics focuses extensively on music theory, particularly on the theoretical systems of Western classical music dating back to the 19th century. However, contemporary popular music genres such as pop, rock, and jazz often rely on jazz music theory, which is an evolution from classical music theory. To make music informatics research more practical and relevant to modern music composition, it is essential to explore music analysis based on jazz music theory using computational methods. In this study, we attempt to perform jazz music analysis computationally. Jazz music theory primarily centers around chord progressions. Therefore, Tonal Pitch Space (TPS) and its extension to jazz music theory, TPS-ExJ, are valuable tools for our investigation. We implement and modify these computational music theories to calculate the "chord distance,"a metric indicating the naturalness of chord progressions. This allows us to estimate the "key"of a piece of music, a concept determined by human sensibility, using computational techniques. Although the experimental results for key estimation are not particularly high, we believe that the theoretical framework proposed in this study forms a solid foundation for complex chord progressions' key estimation in jazz music. © 2023 ACM.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Analysis of Performance Expressions Using Sequential Tension Values 23

Analysis of Performance Expressions Using Sequential Tension...

引用

7th International Conference on computer science and Application Engineering, CSAE 2023

作者： Miura, Shingo Mizutani, Tetsuya Master's Program in Computer Science University of Tsukuba Tsukuba Japan Department of Computer Science University of Tsukuba Tsukuba Japan

ISBN: (纸本)9798400700590

Human performers interpret and perform a piece of music based on their own musical sensibilities and the musical characteristics they read from the information in the score. In doing so, the changes in speed and volume that appear in the performance are called performance expressions. This performance expression changes each time the music piece or performer changes, and we believe that formalizing this expression will make it possible to perform more human-like performances on a computer. In this study, we focused on the fact that Generative Theory of Tonal Music (GTTM) [1], one of the cognitive music theories, uses a parameter called tension value to analyze a piece of music. However, one method of calculating tension values, hierarchical tension values, is not suitable for automatic analysis because it requires consideration based on advanced musical knowledge when calculating them. Therefore, this study uses a parameter called sequential tension value, which is obtained by a different calculation method. Although sequential tension values are less accurate than hierarchical tension values, they have the advantage of being easy to calculate and suitable for automatic analysis. This paper discusses how to improve the accuracy of analysis of musical pieces using sequential tension values and how each component of the musical structure that makes up the sequential tension value affects the analysis results. Multiple regression analysis is used for this analysis, with the musical expression obtained from the local tempo and volume changes for each event calculated from the score data as the objective variable and the musical symbols in each event as the explanatory variables. The accuracy of the obtained regression model is compared with the methods used in previous studies, indicating that the analysis using sequential tension values is useful for music analysis. © 2023 ACM.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

UML Design for Decision Support Model in Determining the Sustainability of Online Course Materials 6

UML Design for Decision Support Model in Determining the Sus...

引用

6th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2022

作者： Sihotang, Erna Fransisca Angela Kurniawan, Afdhal Utama, Ditdit Nugeraha Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798350399615

The scenario of online learning is a very urgent need in the world of future knowledge. Since the Corona Virus Disease-19 pandemic, the world economy has started to plummet and caused many adults to lose their jobs. The advantage is the flexibility and rapid development of the internet. In 2020, the number of unemployed increased significantly. This reason makes people strive to improve their ability to meet job requirements by taking online courses. Online courses are a way that people can choose to improve their skills anywhere and anytime. The sustainability of online course material that is offered to the course user and issued by the company will be discussed in this study. The novelty of this research is to obtain a decision support model based on fuzzy logic for determining online courses. The method used is decision-making based on UML and fuzzy logic for the final decision. The fuzzy inference model process begins by determining the decision parameters then using fuzzification with absolute input then refracted with fuzzy criteria, and ends with defuzzification with absolute output. There are two groups of parameters in this study, company profits which consist of 5 parameters and user benefits, which consist of 9 parameters. Once the model is verified and valid, the final decision is useful for users looking for online course and also useful for the decision unit of online course companies in determining the sustainability of online course materials. © 2022 IEEE.

关键词： Decision support model fuzzy logic online course UML

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 7

BERT base model for toxic comment analysis on Indonesian soc...

引用

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

作者： Nabiilah, Ghinaa Zain Prasetyo, Simeon Yuda Izdihar, Zahra Nabila Girsang, Abba Suganda Computer Science Department Binus Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 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. © 2022 Elsevier B.V.. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Optimized LightGCN for Music Recommendation Satisfaction 6

Optimized LightGCN for Music Recommendation Satisfaction

引用

6th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2022

作者： Hansel, Aaron Christian Adrianus Pradana, Lunardi Suganda, Abba Girsang Nugroho, Ariadi Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798350399615

With the large amount of information available on the internet, recommendation tasks have grown to be more crucial than ever. Businesses that store digital media on the internet such as video streaming and music streaming platforms, benefit a lot from recommendation systems. A simple yet powerful recommendation system that can give better recommendation performance is always being sought after. Light Graph Convolution Network (LightGCN) is a simplified version of Graph Convolution Network (GCN) for collaborative filtering in recommendation systems. LightGCN architecture includes only the most essential part of GCN for collaborative filtering that is the neighborhood aggregation, it removes the feature transformation and nonlinear activation because both of them contribute little to no effect to the recommendations. The focus of this research is to optimize LightGCN by tuning the hyperparameters using exhaustive search (grid search). The optimized LightGCN model is able to out-perform LightGCN by more than 140% in music recommendation © 2022 IEEE.

关键词： exhaustive search hyperparameter tuning LightGCN music recommendation Recommendation system

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Powered Intent Classification for Indonesian E-Wallet Customer Service Chatbots 4

Artificial Intelligence-Powered Intent Classification for In...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Owen, Christopher Suhartono, Derwin Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331506490

The rapid expansion of e-wallet services in Indonesia has significantly heightened the need for efficient customer service solutions, making chatbots an essential tool for user support. However, many providers continue to rely on rule-based chatbots, resulting in rigid interactions that struggle to meet diverse user needs or handle the linguistic complexities of the Indonesian language. This study addresses these limitations by developing an AI-powered intent classification model specifically tailored for Indonesian e-wallet customer service, aimed at delivering a more accurate, adaptive, and user-centered experience. A custom dataset was created from user comments on social media associated with Indonesia's top e-wallet providers, followed by data pre-processing and clustering using the BERTopic model. To improve interpretability, OpenAI's GPT-4 was employed for label refinement, resulting in enhanced clarity. Various models were tested, including IndoBERT, RoBERTa, and Convolutional Neural Network (CNN) architectures in both 2D and 3D configurations. The highest-performing model combined IndoBERT embeddings with a 3D CNN classifier, achieving an accuracy of 84.30%, precision of 84.33%, recall of 84.30%, and an F1-score of 84.24%. This study contributes a unique Indonesian-specific dataset and demonstrates the potential of AI to transform customer service interactions in Indonesia's e-wallet sector, offering a clear advancement over traditional rule-based approaches. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Utilisation of convolutional neural network on deep learning in predicting digital image to tree damage type

引用

International Journal of Internet Manufacturing and Services 2024年第1期10卷 77-90页

作者： Safe’i, Rahmat Andrian, Rico Maryono, Tri Nopriyanto, Zuhri Forestry Master Study Program Faculty of Agriculture University of Lampung Lampung Indonesia Department of Computer Science Faculty of Mathematics and Natural Science University of Lampung Lampung Indonesia Department of Agrotechnology Faculty of Agriculture University of Lampung Lampung Indonesia

Damage is often defined as a condition where there is a change in an object or shape. Damage does not only occur to objects, it can occur to living things, including trees. Damage to trees is seen in the physical shape of the tree that has changed shape, to find out it requires deep learning. One way that can be used is by modelling through computers through artificial intelligence, namely creating a deep learning model that can retrieve image information to recognise objects. This research aims to utilise convolutional neural network algorithm in deep learning to identify tree damage. The research stages carried out are input, feature extraction and classification, and output. The final result obtained is the successful identification of trees in deep learning on the model with an accuracy of 99.06% with a detection error of 0.94%. Detection errors occur due to similarities in terms of patterns, etc. This can be minimised by combining hyperparameters. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Error detection

来源：评论

学校读者我要写书评

暂无评论

Comparison of Spelling Error Correction Algorithms for the Indonesian Language 11

Comparison of Spelling Error Correction Algorithms for the I...

引用

11th International Conference on Information and Education Technology, ICIET 2023

作者： Yanfi, Yanfi Setiawan, Reina Soeparno, Haryono Budiharto, Widodo Bina Nusantara University BINUS Graduate Program Computer Science Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9781665465489

Edit distance as a string measurement metric is often used to help detect misspellings in languages. This paper aims to compare two string spelling error correction algorithms for the Indonesian language. The N-gram, Jaro-Winkler distance, and Levenshtein distance algorithms are used to determine whether they can accurately correct typological errors in the Indonesian language. Moreover, this study utilized KNIME tools to process the data from beginning to end. The data was retrieved from news in Indonesia. After the experiment on N from 1 to 12, the results obtained for the comparative analysis proved that Jaro-Winkler distance performed better than Levenshtein distance for comparing smaller strings like words and names. However, Levenshtein distance performs as well as Jaro-Winkler distance started from four strings. Finally, both Jaro-Winkler distance and Levenshtein distance algorithm got the best performance accuracy for eight strings with an accuracy of 99.52 percent. The result of this study is also presented that both algorithms can support word error correction for the Indonesian language. © 2023 IEEE.

关键词： Error correction

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：