检索结果-内蒙古大学图书馆

Computer Science, information Technology and Engineering (ICCoSITE), International Conference on

作者： Yaya Heryadi Bambang Dwi Wijanarko Dina Fitria Murad Cuk Tho Kiyota Hashimoto Computer Science Department BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Prince of Songkla University Phuket Thailand

Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of two models: the Long Short-term Memory and the Bidirectional Long Short-term Memory models as machine language translation models involving Bahasa Indonesia and the Sundanese language. The empiric results showed that the Bidirectional Long Short-term Memory model achieves higher performance as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.95 and 0.95 average training accuracy respectively; and 0.90 and 0.89 average testing BLEU scores respectively) than the Long Short-term Memory model as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.93 and 0.92 average training accuracy respectively; and 0.91 and 0.88 average testing BLEU scores). These results validate some previously reported studies that claim the Bidirectional Long Short-term Memory model potentially outperform the Long Short-term Memory model when it is used to process a sequence dataset.

关键词： Training Computer science Computational modeling Instruments Machine translation Task analysis information technology

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Network-based Models as Bahasa Indonesia-Sundanese Language Neural Machine Translator

Recurrent Neural Network-based Models as Bahasa Indonesia-Su...

引用

Computer Science, information Technology and Engineering (ICCoSITE), International Conference on

作者： Bambang Dwi Wijanarko Yaya Heryadi Dina Fitria Murad Cuk Tho Kiyota Hashimoto Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Prince of Songkla University Phuket Thailand

Sequential data are available in many domains including weather observation data, stock price, gene sequence, and many others. Sequential data processing is very instrumental as a solution to a variety of downstream tasks in Natural Language Processing such as language translation. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, language translation is not an easy computation task when there is a language-resource gap. This paper presents some empirical results from the exploration of the Recurrent Neural Network (RNN), the Gated Recurrent Unit (GRU), the Long Short-term Memory (LSTM), and the Bidirectional Long Short-term Memory (Bi-LSTM) models as machine translation models from Bahasa Indonesia to the Sundanese language. These empirical results show that the Bi-LSTM achieved the highest performance (0.95 average training accuracy and 0.92 average testings BLEU score) compared to the RNN (0.93 average training accuracy and 0.91 average testings BLEU score), the GRU (0.88 average training accuracy and 0.89 average testings BLEU score), and the LSTM (0.92 average training accuracy and 0.91 average testings BLEU score) models. These results validate some previously reported studies that claim the Bi-LSTM model potentially outperforms the other recurrent neural network-based models when it is used to process sequence datasets.

关键词： Training Recurrent neural networks Computational modeling Instruments Data processing Machine translation Task analysis

来源：评论

学校读者我要写书评

暂无评论

Revalidating the Encoder-Decoder Depths and Activation Function to Find Optimum Vanilla Transformer Model

Revalidating the Encoder-Decoder Depths and Activation Funct...

引用

Computer Science, information Technology and Engineering (ICCoSITE), International Conference on

作者： Yaya Heryadi Bambang Dwi Wijanarko Dina Fitria Murad Cuk Tho Kiyota Hashimoto Computer Science Department BINUS Graduate Program– Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Prince of Songkla University Phuket Thailand

The transformer model has become a state-of-the-art model in Natural Language Processing. The initial transformer model, known as the vanilla transformer model, is designed to improve some prominent models in sequence modeling and transduction problems such as language modeling and machine translation. The initial transformer model has 6 stacks of identical encoder-decoder layers with an attention mechanism whose aim is to push limitations of common recurrent language models and encoder-decoder architectures. Its outstanding performance has inspired many researchers to extend the architecture to improve its performance and computation efficiency. Despite many extensions to the vanilla transformer, there is no clear explanation of the encoder-decoder set out depth in the vanilla transformer model. This paper presents exploration results on the effect of combination encoder-decoder layer depth and activation function in the feed-forward layer of the vanilla transformer model on its performance. The model is tested to address a downstream task: text translation from Bahasa Indonesia to the Sundanese language. Although the value difference is not significantly large, the empirical results show that the combination of depth = 2 with Sigmoid, Tanh, and ReLU activation function; and d = 6 with ReLU activation shows the highest average training accuracy. Interestingly, d = 6 and ReLU show the lowest average training and validation loss. However, statistically, there is no significant difference between depth and activation functions.

关键词： Training Computer science Computational modeling Computer architecture Transformers Computational efficiency Machine translation

来源：评论

学校读者我要写书评

暂无评论

Gamification in the Learning Community for Culinary Basics Course at Higher Education 8

Gamification in the Learning Community for Culinary Basics C...

引用

8th International Conference on ICT for Smart Society, ICISS 2021

作者： Winanti Meyliana Sestri Goestjahjanti, Francisca Lumban Gaol, Ford Prabowo, Harjanto Ferdiyatmoko Cahya Kumoro, Dwi STMIK Insan Pembangunan Information System Departement Tangerang15810 Indonesia Bina Nusantara University School of Information Systems Information Systems Department 11480 Indonesia STIE Insan Pembangunan Management Departement Banten Tangerang15810 Indonesia Bina Nusantara University BINUS Graduate Program-Computer Science Computer Science Department Jakarta11480 Indonesia Computer Science Department Doctor of Computer Science Bina Nusantara University 11480 Indonesia

ISBN: (纸本)9781665416979

This paper discusses basic culinary learning in universities using gamification techniques. The learning objectives are carried out to improve maximum learning outcomes, create a sense of pleasure and joy (satisfaction), and increase motivation. Although the author realizes that gamification is not the only learning technique that must be applied. The success of learning can be influenced by various factors including the internal factors of students and lecturers which until now have become the most important factors. Apart from the curriculum, social environment, and methods used, gamification is an alternative to produce maximum value, satisfaction, and motivation. The gamification technique is done by dividing students into several groups, each group consisting of 4 to 6 students. Each half-semester group is given learning by conventional methods and the next half-semester is given learning by gamification. Both will be evaluated through the results of the assessment in the form of statistics. The results obtained by using gamification on average have 10 to 20 points better than conventional methods. Students and lecturers become satisfied, motivated and get maximum test scores and they become more creative and innovative due to direct student involvement and fast interaction between lecturers and students. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Business Intelligence Dashboard for Project Control at the Port Harbor-Company 12th

Design and Implementation of Business Intelligence Dashboard...

引用

12th Asian Conference on Intelligent information and Database systems, ACIIDS 2020

作者： Lumban Gaol, Ford Syahir, Arsyan Matsuo, Tokuro Computer Science Department BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Information System Bina Nusantara University Jakarta Indonesia Advanced Institute of Industry Technology Tokyo Japan

ISBN: (纸本)9789811533792

This study aims to assist resource management and the project controller at Port Harbor Company. Port Harbor Company is an IT Consulting. Problems that often occur in IT Consulting are related to the project cost, resource management and control of each project. Problems that occur at the Port Harbor Company are poor resource management, spending costs that exceed a predetermined budget and how to see the status of ongoing projects. Using Business Intelligence and the dashboard as a front end will help the project controller and resource management manage resources, manage project costs and monitor ongoing projects. In this study, the development and implementation of Business Intelligence and dashboards using the ASAP method are expected to be more structured and can solve the Port Harbor Company problem. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Modeling of development of performance evaluation on health information systems implementation

Modeling of development of performance evaluation on health ...

引用

International Conference on Physics and Mathematics for Biological Science 2019, ICOPAMBS 2019

作者： Sardjono, W. Selviyanti, E. Perdana, W.G. Maryani Information Systems Management Department BINUS Graduate Program Master of Information Systems Management Bina Nusantara University Jakarta11480 Indonesia Health Department State Polytechnic of Jember Jember Jawa Timur68124 Indonesia Post Graduate Program of Environmental Science School of Environmental Science University of Indonesia Jakarta11480 Indonesia Information System Department School of Information System Bina Nusantara University Jl. K.H. Syahdan no.9 Kemanggisan Jakarta Barat11480 Indonesia

In any organization, the appropriate use of information systems will have an impact on the effectiveness of day-to-day operations. To find out how the performance of an information system is necessary to do an evaluation of the implementation of which has been run. This study evaluates the implementation of information systems in the Maternity Hospital St. Yosef. By adopting PIECES framework as an evaluation, primary data collection is done through questionnaires distributed. Of the some respondents who collected the data used factor analysis to get factors and indicators affect the successful implementation of system and get right model for evaluation of the Maternity Hospital in St. Joseph. The results showed that the factor of ease use and suitability to needs of a positive effect on the success, while reliability of system negatively affect the success. On a scale of 0-100 obtained an un-expected value of system performance is at 45.75 and the expected value of performance of the system is equal to 83.77. © Published under licence by IOP Publishing Ltd.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Interpretable classification of categorical time series using the spectral envelope and optimal scalings

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 13513-13543页

作者： Zeda Li Scott A. Bruce Tian Cai Paul H. Chook Department of Information System and Statistics Baruch College The City University of New York New York NY Department of Statistics Texas A&M University College Station TX Ph.D. Program in Computer Science The Graduate Center The City University of New York New York NY

This article introduces a novel approach to the classification of categorical time series under the supervised learning paradigm. To construct meaningful features for categorical time series classification, we consider two relevant quantities: the spectral envelope and its corresponding set of optimal scalings. These quantities characterize oscillatory patterns in a categorical time series as the largest possible power at each frequency, or spectral envelope, obtained by assigning numerical values, or scalings, to categories that optimally emphasize oscillations at each frequency. Our procedure combines these two quantities to produce an interpretable and parsimonious feature-based classifier that can be used to accurately determine group membership for categorical time series. Classification consistency of the proposed method is investigated, and simulation studies are used to demonstrate accuracy in classifying categorical time series with various underlying group structures. Finally, we use the proposed method to explore key differences in oscillatory patterns of sleep stage time series for patients with different sleep disorders and accurately classify patients accordingly.

关键词： categorical time series classification optimal scaling multiple time series spectral envelope

来源：评论

学校读者我要写书评

暂无评论

AI-Based Feature Extraction and Cosine Similarity for Automation of Student Learning Assessment

AI-Based Feature Extraction and Cosine Similarity for Automa...

引用

information Technology (ACIT)

作者： Bambang Dwi Wijanarko Bachtiar Rosilah Binti Hassan Dina Fitria Murad Ridho Bramulya Ihsan Yaya Heryadi Engkos Achmad Kuncoro Eka Julianti Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Master of English Education Graduate School Universitas Terbuka Jakarta Indonesia Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor Malaysia Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Manajemen Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Information System Department Universitas Terbuka Jakarta Indonesia

This research is ongoing research into the student learning process which aims to develop artificial intelligence-based technology to calculate essay exam scores automatically, based on the textual proximity of students' answers to the answer key. This research uses an approach based on natural language processing (NLP) and text analysis. Feature extraction was carried out using the BERT model and similarity comparison using the Cosine distance method. Model evaluation was carried out using sensitivity and specificity tests. The model evaluation results show a sensitivity of 98.21%, which means this assessment model is able to detect positive cases well.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Governance information system Using Framework Cobit 5 in Banking Company

Evaluation of Governance Information System Using Framework ...

引用

2019 International Conference on Sustainable Engineering and Creative Computing, ICSECC 2019

作者： Legowo, Nilo Christian Bina Nusantara University BINUS Graduate Program-Master in Information System Management Information System Department Jakarta11480 Indonesia

ISBN: (纸本)9781728151922

The majority of organizations or companies both public and private already use information technology as a support in improving the effectiveness and efficiency of business performance, it can impact on not achieving the business goals of the company. Every banking company in Indonesia is obliged to report monthly reports to Bank Indonesia for financial supervision, but on the use of reporting systems is perceived to be less than optimal. The IS audit control mechanism using this COBIT framework not only provides an evaluation of IT governance in the company, but also provides inputs that can be used to improve its management. COBIT 5 is therefore a benchmark for the process of appraising and improving IT governance. After the mapping obtained 7 processes for the measurement that is EDM02, APO02, APO11, BAI06, DSS01, DSS02, and DSS03. Result of each process, obtained the level of capability of each process EDM02 = Level 1, APO02 = Level 2, APO11 = Level 2, BAI06 = Level 2, DSS01 = Level 2, DSS02 = Level 2, and DSS03 = Level 1. The IT governance gap analysis is done by comparing the current level of IT governance capability with the target level to be achieved. © 2019 IEEE.

关键词： information use

来源：评论

学校读者我要写书评

暂无评论

Customer satisfaction in using the quick response code Indonesian standard (QRIS) on the menu list

引用

AIP Conference Proceedings 2024年第1期3148卷

作者： Wahyu Sardjono Justin Arden Tanuwijaya Erna Selviyanti Information System Management Department BINUS Graduate Program – Master of Information Systems Management Bina Nusantara University Jakarta Indonesia Health Department Polytechnic Negeri Jember Jember Jawa Timur Indonesia 68124

A coffee shop is a place of business that offers a variety of beverages, including coffee, as well as snacks or pastries for customers to enjoy. In addition to providing coffee and beverage products, coffee shops usually offer facilities such as Wi-Fi access, power plugs, and comfortable seating. Customers at Coffee Toffee take a long time to order drinks and meals since they must wait in line as the server enters their order before it is delivered. As a result of no numbers at each table, servers are also extremely perplexed about where clients are seated. The ordering information system on the menu uses web-based Customers to easily order menus at each table utilizing the QR code system by scanning it with their smartphone’s camera or scanner. This research aims to evaluate the Barcode system Menu List implementation in Coffee Toffee to satisfy customers. A Quantitative method was used, and data were analyzed using statistical analysis t-test, F-test, and linear regression to test hypotheses. The result is the QRIS Payment Variable has a significant positive influence on Customer Satisfaction.

关键词：

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：