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

Neural Machine Translation Approach for Low-resource Languages using Long Short-term Memory Model

Neural Machine Translation Approach for Low-resource Languag...

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

Communication is a form of translation that human learns naturally since early childhood. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. One example of high-impact language translation is translating health protocols from the World Health Organization to many national languages to prevent the spread of the Covid-19 virus. 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 the Long Short-term Memory model as a machine translation involving Bahasa Indonesia and the Sundanese languages. Performance of the Sundanese language to Indonesian language translation is 0.93 average training and validation accuracy and 0.91 average testings BLEU score. Whilst, Indonesian language to Sundanese language translation is 0.92 average training and validation accuracy and 0.88 average testings BLEU score. Both models achieve 0.39 average training loss and 0.38 average validation loss.

关键词： Training Pediatrics Protocols Computational modeling Instruments Organizations Machine translation

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

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

Extended E-Learning Model to Support Home Schooling with Collaboration Between Teacher, Parents and Student

Extended E-Learning Model to Support Home Schooling with Col...

引用

International Conference of computer Science and information Technology

作者： Inayatulloh Harjanto Prabowo Harco Leslie Hendric Spits Warnars Togar Alam Napitupulu Khairil Holly Deviarti Information Systems Department School of Information system Bina Nusantara University Jakarta Indonesia Computer Science Department Program Doctor of Computer Science Bina Nusantara University Jakarta West Jakarta Indonesia Fakultas Ilmu Komputer Universitas Dehasen Bengkulu Indonesia Accounting Department School of Accounting Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350399080

Homeschooling is a family and environmental/informal education path. Homeschooling is the practice of instructing one's children in one's own home rather than sending them to a school or other institution that follows a more conventional model of teaching and learning in a group setting. Problems for children who follow homeschooling are related to child psychology and boring learning methods. collaborative learning is a learning concept by involving several parties to increase the effectiveness and efficiency of learning. By involving many parties who have different competencies, they can solve homeschooling children's problems. On the other hand, e-learning with the Learning Management System can manage the learning process, teaching materials and collaborative processes in homeschooling in a more systematic and structured manner. With some of the phenomena above, this research aims to increase the effectiveness and efficiency of the homeschooling learning process by integrating the concept of collaborative learning and the Learning Management System. The research method uses a qualitative approach through observation to identify problems related to the learning process with homeschooling. Observations and literature reviews were also carried out to find alternative solutions with an information technology approach

关键词： Learning management systems Electronic learning Federated learning Education Collaboration Psychology Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Learning Pairwise Preferences from Movie Ratings 7

Learning Pairwise Preferences from Movie Ratings

引用

7th International Conference on ICT for Smart Society, ICISS 2020

作者： Qomariyah, Nunung Nurul Fajar, Ahmad Nurul Bina Nusantara University Faculty of Computing and Media Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program-Master of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781665404228

Preference Elicitation is now considered a crucial stage in recommender system. That is the stage where we collect and query preferences of the users as part of interactive decision support system. Preference elicitation can be performed using many ways, such as asking the user explicitly to give ratings or feedbacks for some products, or implicitly observing their behaviour. Once this preference has been collected by the system, it can then be used to generate item recommendation. Using explicit feedback itself, such as rating only, has several drawbacks. Using ratings is very subjective. Two users with similar taste might give different rating to the same item. A user also may not be consistent in giving number to express their liking. In other case, a user may like an item more than the other items, but feels difficult to give lower rating on the other item, because it means that the particular item is just as bad as the one he/she does not like. By showing two different items as a pair, it will be easier for the users to pick which one is the best. In this paper, we show the result of our experiment in predicting user pairwise preferences by using their movie ratings data. We evaluated five different machine learning algorithms to predict the data in pairwise preference format. The result shows that K-Nearest Neighbour and Random Forest outperformed the other algorithms. © 2020 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

The Online Test application uses Telegram Bots Version 1.0 3

The Online Test application uses Telegram Bots Version 1.0

引用

3rd International Conference on Science and Technology 2019, ICST 2019

作者： Parlika, Rizky Pratama, Arista Informatics Engineering Study Program Faculty of Computer Science Indonesia Information Systems Study Program Faculty of Computer Science National Development University Veteran East Java Raya Rungkut Madya Road Gunung Anyar Surabaya Indonesia

The development of the smartphones that rapidly increasing, and high smartphone Users as a tool to make a lot of information, make emergence of instant messaging applications with a variety of options for use. Telegram, as one of the instant messaging application that is fairly new, offering in its various features compared to other instant messaging applications, so it can grow rapidly and much in demand in only 2 years. One of the interesting features is the Bot telegram, a special account without number that can handle Command from the User and gives answers appropriate to Command functionality. The account serves as the interface of the running system that communicate via Telegram Bot API. This study seeks to build a Bot telegram with database to built The Online Test application uses Telegram Bots Version 1.0. In each lecture meeting, a Lecturer can make a short test in the form of multiple choices to review the material at the previous meeting and get information about what percentage of students understand the material that has been taught before. We can use the application to send realtime messages to facilitate the test. Of course, which supports the creation of bots easily to add features that did not yet exist. Of the many we chose Telegram to be an online test environment by utilizing the Bot creation facilities provided by Telegram. This article will be a guide that makes it easier for lecturers to give a simple test at the beginning of the meeting, so that they can attract students' daily grades. And in order to be more interactive there are features of student value progress reports that can also be accessed individually so that students can know the progress of their learning outcomes. © Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Research on Data Security and Privacy of Smart Grids

引用

International Journal of Network Security 2024年第5期26卷 901-910页

作者： Hwang, Min-Shiang Chang, Yung-Ling Lin, Ko-Yu Lin, Iuon-Chang Yang, Cheng-Ying Department of Computer Science & Information Engineering Asia University 500 Lioufeng Rd. Wufeng Taichung Taichung41354 Taiwan Fintech and Blockchain Research Center Asia University 500 Lioufeng Rd. Wufeng Taichung Taichung41354 Taiwan The Ph.D. Program in Artificial Intelligence Asia University Taiwan Department of Management Information Systems National Chung Hsing University 500 Lioufeng Rd. Wufeng Taichung Taichung41354 Taiwan Department of Computer Science University of Taipei Taipei Taiwan

Developing a smart grid is a trend nowadays and an indispensable basic necessity of life. In recent years, the electricity demand has risen rapidly due to economic development and quality of life improvement. The power grid in significant cities is unstable due to old equipment, and power outages occur frequently. The smart grid can adjust the grid’s distribution strategy through the consumer’s real-time electricity demand so that the consumer’s electricity consumption data is always transmitted to the grid. Failure to protect the privacy and security of such information will expose consumers’ habits and even make the grid unnecessarily wasteful. The smart grid’s abnormality detection efficiency determines the overall grid’s stability. Failure to detect anomalies or power theft in the grid promptly will not only lead to the selection of the wrong distribution strategy for the smart grid but also reduce the transmission efficiency of the grid. This research ensures the privacy and security of transmitted data to enhance the efficiency of abnormality detection in the smart grid. The research issues are divided into privacy of transmitted data, data security authentication, and anomaly detection efficiency. © (2024), (International Journal of Network Security). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare

arXiv

引用

arXiv 2025年

作者： Zhang, Hang Lou, Qian Wang, Yanshan Intelligent Systems Program School of Computing and Information University of Pittsburgh PA United States Department of Computer Science University of Central Florida OrlandoFL United States Department of Health Information Management University of Pittsburgh PA United States Department of Biomedical Informatics University of Pittsburgh PA United States Clinical and Translational Science Institute University of Pittsburgh PittsburghPA United States University of Pittsburgh Medical Center PittsburghPA United States

Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study systematically assesses the vulnerabilities of seven LLMs to three advanced black-box jailbreaking techniques within medical contexts. To quantify the effectiveness of these techniques, we propose an automated and domain-adapted agentic evaluation pipeline. Experiment results indicate that leading commercial and open-source LLMs are highly vulnerable to medical jailbreaking attacks. To bolster model safety and reliability, we further investigate the effectiveness of Continual Fine-Tuning (CFT) in defending against medical adversarial attacks. Our findings underscore the necessity for evolving attack methods evaluation, domain-specific safety alignment, and LLM safety-utility balancing. This research offers actionable insights for advancing the safety and reliability of AI clinicians, contributing to ethical and effective AI deployment in healthcare. © 2025, CC BY-NC-SA.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Fusion of Mixture of Experts and Generative Artificial Intelligence in Mobile Edge Metaverse

arXiv

引用

arXiv 2024年

作者： Liu, Guangyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Mao, Shiwen Kim, Dong In The College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Auburn University Auburn United States The School of Electrical and Computer Engineering University of Sydney Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is slowed down by the challenges of content creation, scalability, and dynamic user interaction. Our study investigates an integration of Mixture of Experts (MoE) models with Generative Artificial Intelligence (GAI) for mobile edge computing to revolutionize content creation and interaction in the Metaverse. Specifically, we harness an MoE model's ability to efficiently manage complex data and complex tasks by dynamically selecting the most relevant experts running various sub-models to enhance the capabilities of GAI. We then present a novel framework that improves video content generation quality and consistency, and demonstrate its application through case studies. Our findings underscore the efficacy of MoE and GAI integration to redefine virtual experiences by offering a scalable, efficient pathway to harvest the Metaverse's full potential. © 2024, CC BY.

关键词： Augmented reality

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：