检索结果-内蒙古大学图书馆

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

AI Chatbot Technology to Predict Disease: A Systematic Literature Review 4

AI Chatbot Technology to Predict Disease: A Systematic Liter...

引用

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

作者： Velasco, Vincent Dedy Setiawan, Kevin Robert Sanjaya, Renaldo Susan Anggreainy, Maria Kurniawan, Afdhal School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350318432

Artificial Intelligence (AI) and chatbot technology have emerged as promising solutions to improve healthcare services. AI chatbots can mimic human-like interactions and assist with tasks such as triaging patients and providing medical advice. This review focuses on the use of AI chatbots in predicting diseases, aiming to explore their effectiveness and potential for early intervention and treatment. The purpose of this systematic literature review is to analyze studies related to AI chatbot technology in disease prediction. A systematic literature review was conducted, analyzing a total of 24 selected journals based on predefined inclusion and exclusion criteria. The review protocol involved examining studies published from various years, with a particular emphasis on articles from 2020. The findings indicate that AI chatbots have the potential to play a significant role in predicting diseases and assisting healthcare professionals in making informed decisions. AI chatbot technology shows tremendous potential in disease prediction. By utilizing machine learning algorithms and techniques, chatbots can enhance the accuracy and quickness of disease diagnosis. Continued research and development efforts are necessary to refine AI chatbots' capabilities and revolutionize healthcare delivery for improved patient outcomes and disease management. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Predicting Stock Market Movements Using Long Short-Term Memory (LSTM) 4

Predicting Stock Market Movements Using Long Short-Term Memo...

引用

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

作者： Fauzan, Achmad Susananggreainy, Maria Nathaniel, Nicholas Kurniawan, Afdhal School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350318432

This paper explores using artificial intelligence (AI) to predict stock market movements and build optimal portfolios. The research methodology involves using LSTM networks to predict stock performance. The study aims to combine AI with human expertise to develop an intelligent trading system. The findings emphasize the importance of selecting appropriate AI approaches for accurate predictions and optimal portfolio management. The results of this study state that with LSTM, we can predict stock prices that are very close to their real prices. The average LSTM method in predicting stock prices is about 97.2938%. Average error obtained when using LSTM was 2.3223%. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Scheduling Production in the Flexible Packaging Industry Using Mathematical Models and Genetic Algorithms

Scheduling Production in the Flexible Packaging Industry Usi...

引用

2023 International Conference on Informatics Engineering, science and Technology, INCITEST 2023

作者： Tarigan, Masmur Gaol, Ford Lumban Mauritsius, Tuga Budiharto, Widodo Esa Unggul University Bina Nusantara University Computer Science Department / Computer Science Graduate Program Jakarta Indonesia Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta Indonesia Management Bina Nusantara University Department of Information System Jakarta Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350317862

Minimizing time wastage is a crucial objective for all production operations. Reliable manufacturing scheduling The objective is to mitigate time-based production waste caused by excessive processing, waiting, and transportation. Industry 4.0 promotes technological innovation across all industrial sectors to increase efficiency and effectiveness while preserving high competitiveness. The implementation of artificial intelligence in Industry 4.0 is expected to result in a reduction in time wastage. Non-dominance sequencing genetic algorithms (NSGA), genetic algorithms (GA), and evolutionary algorithms (EA) are the three most common scheduling approaches, according to literature-indexed research summaries from the past five years. The examination of production scheduling in the flexible packaging business, which involves the utilization of different machines and processes and is produced on demand, had not been conducted before in this study. A mathematical scheduling model will be developed in this research to ascertain the shortest production time span in the flexible packaging industry. As a form of technological innovation, this mathematical model will be utilized in experiments employing a genetic algorithm approach. For the genetic algorithm to generate a minimum makespan in the flexible packaging industry's production scheduling process. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of Sundanese Stemmer Based on Morphophonemics 10

Development of Sundanese Stemmer Based on Morphophonemics

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Maesya, Aries Arifin, Yulyani Zahra, Amalia Budiharto, Widodo BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Computer Science Binus Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350339543

The Stemming Process is used to get the base word by removing the word affixes. The purpose of this study is to improve the algorithm in previous research by incorporating the Stemming Process into a morphophonemic approach for language processing based on rules (Rule Based) which is named AM Sundanese Stemmer (AMS). The AM Sundanese stemmer algorithm will utilize morpheme information to perform stemming on Sundanese words and analyze the phonemes in a word to identify the morphemes therein contained. The experimental process was carried out with 11,885 existing data and a sample of 546 words were taken to be stemmed. The test was carried out by comparing the algorithms of Nazief and Adriani, UG 18 and AMS. The test results showed that the AMS Algorithm was better than the Nazief Andriani Algorithm and the UG18 Algorithm with a high F-1 score of 87.52% and the comparison of the execution time of the AMS Stemmer Algorithm was 0.041403 seconds faster than the Nazief Andriani and UG 18 Algorithms. © 2023 IEEE.

关键词： Rule Based Stemming Sundanese Stemmer

来源：评论

学校读者我要写书评

暂无评论

The Model of Personalized Machine Learning to Enhance Students’ Achievements 6th

The Model of Personalized Machine Learning to Enhance Studen...

引用

6th International Conference on Intelligent Sustainable Systems, ICISS 2023

作者： Rusdi, Mikail Rifqi Enrico, T. S. Gregorio Salomo, Austin Ordell Gaol, Ford Lumban Matsuo, Tokuro Bina Nusantara University Undergraduate Program-Computer Science Jakarta Indonesia Computer Science Department Binus University BINUS Graduate Program – Doctor of Computer Science Jakarta11480 Indonesia Advanced Institute of Industry Technology Tokyo Japan

ISBN: (纸本)9789819917259

Global technological improvements are accelerating and influencing numerous industries, including education. Using machine learning, technological innovations can be utilized in the education industry. Machine learning is a subset of artificial intelligence (AI) that enables computers or teaching machines to make intel-ligent decisions by learning from all past data. The framework for machine learning involves acquiring and retaining a large quantity of data and translating it into orga-nized knowledge. AI advancements enable educators to acquire a deeper knowledge of their students’ learning progression. Using Personalized Machine Learning can increase the efficiency of student learning by analyzing their performance in real time and modifying teaching techniques and the curriculum based on this information. It helps to have a tailored approach that adapts to the individual in order to provide a better education. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review on IT Strategic Workspaces: Approach to Develop an Ideal Environment 9

Systematic Literature Review on IT Strategic Workspaces: App...

引用

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

作者： Putra, Alden Ardiwinata Fusanto, Princessa Fortunata Valonika, Nebrisca Anggreainy, Maria Susan Kurniawan, Afdhal Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Graduate Program Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11530 Indonesia

ISBN: (纸本)9798350370126

Technology and information will always develop dynamically;this statement demands programmers to always be creative and keep up with the times. Despite this, their work ethic is always the same and tends to stagnate. programmers' perspectives on their workplace: this perspective is rarely seen as important and the opportunity for a comprehensive study is still widely open. This study aims to conduct a systematic literacy study to ascertain that the workplace has a crucial relationship with a programmer's performance. The focus of the study includes a discussion of how programmers relate to their workplace in a tech company, benchmarking between various office layouts, and criteria that can be derived from the literature review regarding a degree of whether such a workplace is good or bad. The proper base facts are obtained. Nevertheless, the two entities are proven to be interrelated to each other. Such correlations are derived into tangible metrics and parameters (e.g., human cognitive, cultural, physical, behavioral, etc.). Relating issues regarding these topics are also presented. © 2023 IEEE.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Level Prediction in Jakarta Using Artificial Neural Network 4

Air Pollution Level Prediction in Jakarta Using Artificial N...

引用

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

作者： Ferdinan, Roger Margareta, Krestella Christyan, Stevan Anggreainy, Maria Susan Kurniawan, Afdhal School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350318432

Air pollution has emerged as a critical issue in several major urban areas, including Jakarta. To address this problem, the study explores the utilization of the Artificial Neural Network (ANN) method. Three distinct approaches are investigated in this research: the Support Vector Classifier (SVC), Deep Artificial Neural Network (Deep ANN), and Long Short-Term Memory (LSTM). The available Air Quality data were utilized to train and assess the performance of the proposed ANN models. The research findings reveal that the Deep ANN model surpasses the other methods, achieving an impressive accuracy of approximately 96.57% and a cross-entropy value of 0.1103. In predicting air quality in Jakarta, Deep ANN has demonstrated superior performance when compared to SVC and LSTM. These results highlight the significant potential of deploying Deep Artificial Neural Network (ANN) methodologies for air quality prediction. Such an approach could play a pivotal role in the development of monitoring and early warning systems aimed at effectively addressing air quality issues in the Jakarta region. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Authorship Attribution in Bahasa Indonesia Using Twitter Dataset on Political Topic 4

Authorship Attribution in Bahasa Indonesia Using Twitter Dat...

引用

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

作者： Muliono, Yohan Gaol, Ford Lumban Chowanda, Andry Budiharto, Widodo Bina Nusantara University Binus Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350318432

Fake news so called made-up news intended to cause misinformation is identified as Hoax. In Indonesia, hoaxes could not be ignored, fairly low literacy rate is the cause of hoaxes could spread quickly in Indonesia, to make it even worse, there are so many people would believe in hoaxes without any intention to make sure of the integrity of the news. even the media in Indonesia are competing with one another to provide content with provocative names in the hopes of increasing their rating and reaching as many people as possible. In the course of this research, a method for identifying authors on the basis of their writings will be developed to reduce the spread of hoaxes and encourage people to re-evaluate their decision to create harmful content and hoax news in the future. In this investigation, a transformer-based methodology focusing on IndoBERTbase, IndoBERTbase-uncased, and IndoBERTtweet will be employed in conjunction with the self-collected Indonesian tweet data that will be crawled from Indonesian Social Actor Focused on politicians in Twitter and will be combined with another topic in the future study. This research has shown a promising 98,93% in Training Accuracy using IndoBERTtweet. © 2023 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Hate Speech Detection Techniques 4

An Analysis of Hate Speech Detection Techniques

引用

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

作者： Krisdianto, Ricky Apriani, Ivana Halim, Peter Miracle Anggreainy, Maria Susan Kurniawan, Afdhal School of Computer Science Bina Nusantara University Computer Science Departement Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Departement Jakarta11480 Indonesia

ISBN: (纸本)9798350318432

Hate speech is any act of provoking or insulting another person or group based on their ethnicity, religion, race, gender, sexual orientation, physical ability, or other characteristics. This can be done in a variety of ways. Because of this, a study was conducted that focused on ascertaining the most effective technique for identifying hate speech. It was discovered that LSTM, a form of recurrent neural network (RNN) that is particularly good at modeling sequential data, is the most successful technique to apply. Many natural language processing (NLP) activities may be performed with it, including hate speech detection, which makes LSTM have advantages over other techniques, both in terms of long-term memory mechanisms. LSTM, also able to handle long and complex text sequences, capable of recognizing more complex patterns, able to understand and consider the context in the text, to recognize the meaning of a word or phrase in a broader context. Then, based on the dataset obtained from the Kaggle website with a total of 24783 data, then the dataset is divided into training data and validation data, with a ratio of training data to validation data. of 80%: 20%. Then, the testing step results in an accuracy value of 87.10%. © 2023 IEEE.

关键词： Speech recognition

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：