检索结果-内蒙古大学图书馆

9th IEEE Information Technology International Seminar, ITIS 2023

作者： Lucky, Raymasterio Vera Herkanyaka, Baladiffa Aurora Basuki, Vieri Ferdian Putra Parmonangan, Ivan Halim Diana School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350306835

The Javanese language faces challenges due to its complexity and decreasing usage as Indonesian becomes more prevalent. This study highlights the importance of preserving Javanese as a crucial cultural heritage by developing a sentiment analysis model tailored to the language. Two datasets, Indonesian hotel reviews, and "kuliah online"(Online Lectures) comments/tweets, were manually translated into Javanese by three bilingual speakers, creating the Javanese sentiment analysis corpus. Through text preprocessing, word embedding, and utilizing Bi-LSTM and BERT methods. While Bi-LSTM and Bi- LSTM + fastText achieved similar results in predicting negative and positive sentiments. The sentiment data comprising natural cases, mixed sentiment polarities, and conflicting or similar target sentiment face challenges for the models. The most successful model, BERT, achieved an F1-score of 77%. The result obtained from the study will contribute to the preservation of Javanese language and literature on NLP for the Javanese language, with future prospects involving training and testing on original Javanese datasets. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality of Historical Relics in the British Museum 8

Augmented Reality of Historical Relics in the British Museum

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Kurniawan, Daniel Kevin Sademi, Steven Maulana, Fairuz Iqbal Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Museums are one of the tourist attractions that are in great demand by the public. Museums can be used as a place to increase knowledge for many people;many people visit museums during the holiday season or on tourist tours, causing severe congestion when they want to visit the museum during that season. This hinders people from enjoying and learning about historical relics. Therefore, our group decided to help people to learn about the historical relics in the museum by using other media. Our group will create an Augmented Reality (AR) application in the form of historical relics in the British Museum. Augmented Reality (AR) will be created using the SDLC (Software Development Life Cycle) method to be able to produce maximum results so that users can use this Augmented Reality (AR) application more easily. The expected result of making this Augmented Reality (AR) application is to reduce the density in the museum, helping people to recognize and gain information about relics, paintings, sculptures, and others in the British Museum without having to visit the museum, as well as to assist students in learning about British historical heritage with a more fun method in a 3D View. © 2023 The Authors. Published by Elsevier B.V.

关键词： Augmented Reality Britannia Historical Museum Relics

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Music: A Systematic Literature Review 8

Deep Learning for Music: A Systematic Literature Review

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Kurniawan, Daniel Kevin Alexander, Gregorius Revyanno Sidharta, Sidharta School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350326093

Recently, Artificial Intelligence development and implementation are becoming faster and more popular. Artificial Intelligence has appeared to help humans in their daily activities. Several examples that are currently hype are Chat-GPT, and AI Art. With the emergence of applications like Chat-GPT many people have started using applications that have Artificial Intelligence in it. However, there are still rare applications or research that discuss the implementation of Artificial Intelligence or deep learning in music. Therefore, this research will conduct a systematic literature review (SLR) on Deep Learning in music. In this systematic literature review we will research and answer three research questions. Those research question are, What kind of deep learning architecture that most widely used for developing, classifying, and making music;What implementations of deep learning can be done in music, Whether the existence of Artificial Intelligence / Deep learning can help musicians or composers in making music. Predetermined research questions will be answered using the Kitchenham & Cochrane method. From the results of the analysis that has been carried out we concluded that the deep learning methods that are widely used for training deep learning in music are CNN and RCNN, While the implementation of deep learning in music is used for classification and recommendation systems. For conclusion in this paper, we conclude that deep learning can be used to help musicians and composers in creating music. © 2023 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Analysis of Machine Learning Algorithms in Predicting Chronic Kidney Diseases Based on Performance: A Systematic Literature Review 4

Analysis of Machine Learning Algorithms in Predicting Chroni...

引用

4th International Conference on Artificial Intelligence and Data sciences, AiDAS 2023

作者： Alpaullivarez, Angelique Aurielle Aurelia, Miracle Monica, Sheila Suri, Puti Andam School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350318432

Chronic Kidney Disease (CKD) has been increasing nowadays from 750 million cases in 2019 to 850 million in 2023. Lack of access and late detection are one of the reasons why CKD cases have been increasing for all these years. Various Machine Learning (ML) algorithms have been studied to detect CKD and this paper will discuss and compare different types of algorithms to detect CKD early before progressing to advanced stages based on its performance. Although the use of ML to predict chronic kidney disease in the medical world is still hard to find, in other literature reviews with similar topic, it is found that various ML algorithms have been developed with the goal of assisting medical professionals in predicting CKD. Highly accurate ML algorithms have also been discovered using Artificial Neural Network, Random Forest, and XGBoost, despite needing further improvement in quality to be able to be applied on a large scale. In this paper, 5 commonly used ML algorithms namely XGBoost, Random Forest, Support Vector Machine (SVM), Artificial Neural Networks (ANN), and logistic regression were analyzed. Using Systematic Literature Review as this paper's methodology, this paper provides detailed explanation on how the algorithms work, implemented, and their performance were also analyzed by using 5 parameters: AUC, accuracy, precision, recall or sensitivity, and F1-Score. It was found that XGBoost achieved the highest score among all parameters except for AUC, which highest score was possessed by Artificial Neural Network. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

DeepLyric: Predicting Music Emotions through LSTM-GRU Hybrid Models with Regularization Techniques 8

DeepLyric: Predicting Music Emotions through LSTM-GRU Hybrid...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Angelica, Felicia Hydro, Romington Sulistiya, Zefanya Delvin Muliono, Yohan Prasetyo, Simeon Yuda Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Music is a powerful medium that has the potential to evoke strong emotional responses in humans. Researchers have investigated the relationship between music and emotions and the growing interest in developing precise techniques for recognizing emotions in music. Growing interest among researchers in developing more precise techniques for recognizing emotions in music has evoked numerous studies to be conducted. The researchers trained LSTM and GRU (Gated Recurrent Unit) hybrid model on a dataset of 1,160 songs tagged with sadness, compassion, and tension. They were able to attain a test accuracy of 72.51%, although overfitting was discovered because of insufficient training data, a choice of dropout, and learning rate. The research proves the potential of machine learning methods for musical emotion recognition and recommends the use of regularization techniques to alleviate overfitting. It may be possible to create software that can recognize and respond to emotional states in musical contexts because of the research, which contributes to the growing body of knowledge on the connection between music and machine learning. © 2023 The Authors. Published by Elsevier B.V.

关键词： GRU Hybrid Model LSTM Music Emotion Recognition Natural Language Processing Song Lyrics

来源：评论

学校读者我要写书评

暂无评论

Building Serious Game Design to Prepare University Students for The World of Work 9

Building Serious Game Design to Prepare University Students ...

引用

9th International HCI and UX Conference in Indonesia, CHIuXiD 2023

作者： Steven Malik, Victor C. Harefa, Jeklin Alexander Chowanda, Andry School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350304084

Pandemic hits the world catastrophically, leading to the disruption on our everyday life including how students learn in the pandemic era. Most of the students nowadays have difficulties preparing the way to face the world of work. This research proposes a serious game design to prepare university students for the world of work by combining the Six Facets of Serious Game Design and Adam's Ernest Game Design. Six Facets of Serious Game Design is the design pattern for serious games (e.g., pedagogical games) [1]. Two systems (i.e. the serious game and the baseline system) were designed, deployed and evaluated to evaluate the effectiveness of the proposed serious game design. The serious game design was built on an Android mobile phone. Moreover, a simple simulation that has identical scenarios with the serious game was also built as the baseline in the evaluation process. Thirty-seven respondents who will be or have been entering the workplace for their first time participated in the evaluation process. A Wilcoxon rank test was applied to the data as the data does not come from a normal distribution. The results show that the proposed serious game design provides more effective results than the baseline. The user experiences' score provided by the serious game design system is statistically higher than the baseline system. Moreover, the serious game system increases the learners' motivation compared to the baseline system. © 2023 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Based Decision Support Model for Health Insurance Claim

引用

Informatica (Slovenia) 2022年第7期46卷 119-130页

作者： Susanto, Sumiatie Utama, Ditdit Nugeraha Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Insurance industry in Indonesia has shown promising result based on premium growth in 2014-2018, as recorded in Indonesia General Insurance Market Update 2019. With the increase of premium, the claim rate also grows. Insurance companies face challenges in processing the claims. Many factors need to be carefully considered before making a claim decision. This paper proposes a decision support model (DSM) to score claim cases and to propose claim risk category (CRC) and claim decision (CD). The model was built with 13 parameters, divided into non-fuzzy group and fuzzy group. The analytic hierarchy process (AHP) method was used to determine the priority weight (PW) among parameters. The Tsukamoto’s fuzzy logic (FL) method was applied to process the fuzzy parameters. A simple mathematics method (SMM) was exercised to calculate the non-fuzzy parameters, and to aggregate the result into claim risk score (CRS). Finally, CRC and CD were derived from the CRS using a rule base. The model was tested using 19611 actual claim history records. The result was: 6171 (31.47%) accepted with CRC= low, 3459 (17.64%) pending (CRC medium), and 9981 (50.89%) pending (CRC high). The DSM model was implemented in python with Google COLAB and Datapane to create various graphics. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Privacy and Security in the Use of Voice Assistant: An Evaluation of User Awareness and Preferences 8

Privacy and Security in the Use of Voice Assistant: An Evalu...

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Dhiya'mardhiyyah, Alya Latif, Jazlyn Jan Keyla Tho, Cuk School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350326093

Recently, voice assistants have become increasingly popular with millions of users relying on them to complete daily tasks and access information. While it may be convenient to use, some may question its security and are concerned about their privacy. While the users are attracted to the beneficial services provided by voice assistants, they are risking their personal information. This study aims to evaluate user awareness regarding the privacy and security aspects of voice assistants, and their preferences for future development of voice assistants. The literature review in this study obtained three vulnerabilities of privacy and security in the use of voice assistants and the countermeasures that can be taken. The user-centric countermeasures to mitigate the vulnerability of voice assistants were chosen for analysis by systematically evaluating 151 relevant journal and conference articles from 6 databases and 52 were chosen for analysis. To evaluate user awareness and preferences regarding the use of voice assistants, a questionnaire with a total of 37 participants who have experience in using voice assistants was done. The results showed that the participants were aware of the voice assistant's vulnerability and were concerned that their data might be misused. © 2023 IEEE.

关键词： privacy privacy and security security user awareness user preferences voice assistant

来源：评论

学校读者我要写书评

暂无评论

Learning Media for Introduction of Traditional Weapons in Indonesia Using Augmented Reality Technology 8

Learning Media for Introduction of Traditional Weapons in In...

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Andriawan, Deny Pujianputra, Naufal Humam Risqullah Budi, Marcelino Hans Setia Maulana, Fairuz Iqbal Permana, Frihandhika School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350326093

Augmented Reality (AR) is a technology that can visualize 3D objects to make them more realistic with the help of interactive digital images. This technology can be combined with various kinds of digital information so that it becomes more interesting. The Pusakaku application is an AR-based application that was created to introduce traditional weapons in Indonesia. This application is developed using the ADDIE framework, which consists of the Analysis, Design, Development, Implementation, and Evaluation stages. This framework helps in creating applications in accordance with the appropriate flow to produce an application that can be used in general. With this AR technology, it is expected to attract the attention of young people to learn various kinds of Indonesian cultural wealth in the field of traditional weapons. The application was tested before based on a phone and tablet. The result questionnaire of this application display is fairly clear and good, accompanied by traditional songs and combined with digital information containing the history of traditional weapons, which makes this AR traditional weapon more interesting. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Does Deflate Outperform Huffman Lossless Compression? 9

Does Deflate Outperform Huffman Lossless Compression?

引用

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

作者： Sutomo, Vincent Dava Cenon, Neo Kang, Aloysius Bandjar, I. Dewa Agung Kayana Abhipraya Putra Kurniadi, Felix Indra Riccosan Bina Nusantara University School of Computer Science Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350370126

Lossless compression is a compression technique used to store data with higher quality compared to its counterpart, lossy compression. This study explores two specific lossless compression techniques to investigate and address the research questions that motivated this experiment. Deflate, an algorithm derived from Huffman and LZ77, is one of the techniques under examination. This algorithm is particularly intriguing due to the amalgamation of the two preceding compression techniques. Consequently, a crucial inquiry arises: does Deflate surpass its original algorithm? In this paper, Huffman and Deflate are compared to analyze whether combining algorithms yields superior or inferior results. The conducted test provides evidence supporting the superiority of Deflate over Huffman. Deflate demonstrates advantages in terms of compression ratio and, notably, compression and decompression speed. However, it is important to note that this case is not conclusively closed, as the experiment can still be extended to include other algorithms. The present paper exclusively focuses on Deflate and does not guarantee that all combination-based algorithms outperform the algorithms they incorporate. Nevertheless, this comparative analysis makes a valuable contribution to the future development of lossless compression techniques. Additionally, it fulfills the objective of understanding the factors that enable an algorithm like Deflate to effectively implement multiple compression techniques. © 2023 IEEE.

关键词： Deflate Huffman code lossless compression

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：