检索结果-内蒙古大学图书馆

11th International Conference on Information Technology, computer and Electrical Engineering, ICITACEE 2024

作者： Sulistio, Bambang Suhartono, Derwin Soeparno, Haryono Budiharto, Widodo Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Program Jakarta11480 Indonesia

ISBN: (纸本)9798350389289

The advancement of Artificial Intelligence (AI), notably in Natural Language Processing (NLP), has been remarkable. Among its applications, Question-Answering (QA) systems stand out, assisting users in accessing pertinent information across various topics, including religious contexts. Religion plays a significant role in providing guidance on moral values to modern society, such as tolerance, compassion and social norms. Religious practices taught by religion serve as significant foundations for addressing the increasingly advancing influence of technology. The primary goal of this paper is to create a question-answering system proficient in analyzing user inquiries and precisely extracting data from translated Indonesian Hadith datasets. This research endeavors to enhance question-answering accuracy through Deep Learning techniques. Employing pre-processing methods, the system interprets user query intents. Furthermore, the Text-to-Text Transfer Transformer (T5), a text-based language Transformer model, is utilized to streamline the retrieval process for Hadith-related queries based on relevant subjects. The research findings demonstrate the precision of answers through BLEU and ROUGE scores. The novelty of this study lies in the creation of a dataset of hadith translations in Indonesian and the fine-tuning of the T5 model that has been trained using a dataset of questions and answers based on these translations. This research demonstrates the following evaluation scores: BLEU: 0.606, ROUGE-1: 0.702, ROUGE-2: 0.548, and ROUGE-L: 0.701, indicating that the answers generated by this particular research model are better compared to those produced using the standard mT5 model. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Experiments to Review Literature on Topic Trends in Technology Development in Educational Information Systems 7

Experiments to Review Literature on Topic Trends in Technolo...

引用

7th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2023

作者： Santiko, Irfan Soeprobowati, Tri Retnaningsih Surarso, Bayu Universitas Amikom Purwokerto Faculty of Computer Science Informatic Departement Indonesia School of Post Graduate Diponegoro University Information System Departement Semarang Indonesia School of Post Graduate Diponegoro University Faculty of Science and Mathematic Semarang Indonesia

ISBN: (纸本)9798350382266

The smart campus is a phenomenon that occurs in the industrial era 4.0. Many people understand that a smart campus is a campus where all resources can work and produce learning with high effectiveness and maximum efficiency. Everyone talks about elements of information technology that play a role in the sustainability of smart campuses. However, what actually makes the definition of a smart campus itself is not defined with certainty. This is because the world of education itself is experiencing major disruption. This causes innovation in the world of education, especially learning, to pay less attention to the actual aspects of education. This means that education has relied too much on technology which will actually cause a shift in the essence of education itself. In this paper, we will review how effective and efficient learning concepts actually are using information technology. The method used is an analysis of the literature review with an experimental survey and bibliometric analysis. As a result, it will be known that information technology that is in accordance with the essence of education is a matter that does not only focus on technical aspects but also needs to pay attention to aspects of methods, materials, and media. So that the results that are known will provide insight into the development of learning models on an ongoing basis according to the true essence of education. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Investigation of player emotion and instinct on racing video game using 6-11 framework (case study: split second (2010) single player modes) 9th

Investigation of player emotion and instinct on racing video...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Pratama, Galih Dea Novika, Andien Dwi Ardiyanto, Elshad Ryan Game Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Binus Graduate Program Bina Nusantara University Jakarta11480 Indonesia

Racing is one of the most prominent genres in the modern video game industry, where the games within the genre enable players to use any vehicle of their choice and win through doing series of action within gameplay. Thus, it made the genre popular over the years, spawning many famous titles such as Split Second back in 2010. Like every other video game title, Split Second also invokes the player emotion and instinct during its gameplay session. To understand the emotion and instinct aspect present in players of the game, we will use 6-11 framework which focuses on the two aspects. As part of the conclusion, Split Second game involves instincts such as Competition, Collecting, and Survival, with emotions including Fear, Pride, Joy, and Excitement, which can be found from its vast single player game modes. © 2024 The Authors.

关键词： 6-11 framework game analysis racing video games video games

来源：评论

学校读者我要写书评

暂无评论

Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation 61

Jointprop: Joint Semi-supervised Learning for Entity and Rel...

引用

61st Annual Meeting of the Association for Computational Linguistics, ACL 2023

作者： Yandan, Zheng Anran, Hao Tuan, Luu Anh School of Computer Science and Engineering Interdisciplinary Graduate Program-HealthTech Nanyang Technological University Singapore

ISBN: (纸本)9781959429722

Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples. Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data. © 2023 Association for Computational Linguistics.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

TaxDiff: taxonomic-guided diffusion model for protein sequence generation

引用

science China(Information sciences) 2025年第4期68卷 385-386页

作者： Zongying LIN Hao LI Liuzhenghao LV Yu WANG Bin LIN Junwu ZHANG Zijun CHEN Calvin Yu-Chian CHEN Li YUAN Yonghong TIAN School of Electronic and Computer Engineering Peking University AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Peng Cheng Laboratory School of Chemical Biology and Biotechnology Peking University

Protein design aims to generate protein variants with targeted biological functions, which is significant in multiple biological areas, including enzyme reaction catalysis, vaccine design, and fluorescence intensity. Protein design contains two paradigms: sequence generation and structure generation. Recently, EvoDiff [1] proposed a universal designing paradigm, combining structure and sequence generation using the diffusion framework, which improves the protein design efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Negation Handling on XLNet Using Dependency Parser for Sentiment Analysis 4

Negation Handling on XLNet Using Dependency Parser for Senti...

引用

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

作者： Winaya, Ferdinand Girsang, Abba Suganda Binus Graduate Program Bina Nusantara University Jakarta Indonesia School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331506490

Negation handling is often overlooked in Indonesian sentiment analysis, making it difficult to automatically and accurately determine the polarity of sentences containing negation words. Negation is a challenging issue in natural language processing, as it can drastically alter the meaning of a sentence. For example, common Indonesian negation words such as 'tidak' (no/not), 'belum' (not yet), or 'jangan' (do not) can reverse the sentiment polarity in a text. Previous studies have proposed rule-based approaches, relying on linguistic rules or dependency parse trees to handle negation. However, negation is a complex problem that cannot be effectively addressed by simple rules alone, as they often lack flexibility in handling diverse sentence structures and negation complexities. Therefore, a more dynamic approach is needed, such as combining a dependency parser with an embedding layer, which can map syntactic relationships between words and learn vector representations of negation. This allows the model to flexibly determine the scope of negation words, enabling more accurate sentiment analysis even in complex sentences. This study evaluates the impact of negation handling on a transformer-based model, specifically XLNet, in Indonesian sentiment analysis. Using the proposed method, the model's F1 score increased by 2.13%, from 71.42% to 73.55%, compared to the baseline model. This demonstrates that the proposed negation handling strategy enhances sentiment prediction accuracy, making the model more effective at handling texts with negation. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

An Augmented Reality Game's User Experience and Its Effect on Immersion Leading to Intention 11

An Augmented Reality Game's User Experience and Its Effect o...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Oktavia, Tanty Utomo, Kawang Gaol, Ford Lumban Hosoda, Takaaki Bina Nusantara University Binus Graduate Program - Information System Management Information Systems Management Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Advanced Institute of Industrial Technology Decision Science Department Tokyo Japan

ISBN: (纸本)9798350389654

Since the emergence of Pokémon Go in 2016, the world has been introduced to Augmented Reality (AR) games. Many IT companies have begun developing augmented reality (AR) games due to the great commercial potential in this industry. Certain products may have managed to remain viable in the market, while others were forced to close due to one or two factors. Since the emergence of Pokémon Go, no other game has managed to surpass its unprecedented success. The company responsible for developing Pokémon Go has decided to shut down one of their games due to a lack of consumer interest. The technology of augmented reality (AR) is consistently associated with the concept of immersion. Immersion is a key aspect of the game that allows users to deeply engage and feel fully involved in the experience. This study will employ a quantitative methodology, utilising a questionnaire that will be distributed to and completed by those who have engaged in augmented reality (AR) games. The data will be analysed using Smart PLS to examine the impact of user experience on immersion, which in turn influences intention. After gathering over 200 participants by spreading google form questionnaires and doing data analysis, the findings indicate that only a few aspects of user experience, namely Brand Experience and User Need Experience, have an impact on reasons. Niantic, the developer of Pokémon Go, was unable to replicate their success with a similar augmented reality game called Harry Potter: Wizards Unite. The initial release occurred on June 21, 2019, and the shutdown took place on December 21, 2021. In the beginning, they shown a profound enthusiasm for the game but were unable to sustain it, much as Pokémon Go. According to Niantic CEO John Hanke, the primary reason for the game's shutdown was its immersion. Immersion has a notable impact on User Confirmation, which in turn has a notable impact on Satisfaction, and Satisfaction has a notable impact on Intention. Moreover, there have be

关键词： Plant shutdowns

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fake News Detection with Sentiment Analysis Using Machine Learning 7

Enhancing Fake News Detection with Sentiment Analysis Using ...

引用

7th International Conference on Electronics, Materials Engineering and Nano-Technology, IEMENTech 2023

作者： Bose, Shreea Roy, Reek St Xavier's College Department of Post Graduate and Research Computer Science Kolkata India Belda College Department of Computer Science Paschim Medinipur India

ISBN: (纸本)9798350305517

In the digital age we live in today, fake news has become a serious problem because it has the power to sway public opinion, affect policy decisions, and upend social harmony. Sentiment analysis, which evaluates the content's emotional tone, is essential for spotting and stopping the spread of false information. In this work, we leverage machine learning techniques for sentiment analysis to increase the detection accuracy of fake news. To scrutinize the affective milieu present in news pieces and headlines, we investigate the amalgamation of various sentiment analysis instruments, such as VADER, TextBlob, and NLTK. By translating textual input into numerical properties, TF-IDF vectorization is utilized in conjunction with sentiment analysis to increase the predictive power of machine learning models. Enhancing the feature set through the use of TF-IDF vectorization is essential for teaching machine learning models to discern between authentic and fraudulent news. As classification models, Decision trees, SVM, and Logistic regression are used;each has advantages when it comes to processing tasks involving sentiment-based classification. In this study, we try to classify the emotions that the fake news mainly shows after the prediction. We have seen the trend that mainly Negative emotion is conveyed with fake news. The models have been compared and we're getting 98% accuracy. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis and Remediation of Insecure Direct Object References (IDOR) Vulnerabilities in Android APIs 1

Comprehensive Analysis and Remediation of Insecure Direct Ob...

引用

1st IEEE International Conference on Cryptography, Informatics, and Cybersecurity, ICoCICs 2023

作者： Yulianto, Semi Abdullah, Roni Reza Soewito, Benfano Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia National Institute of Science and Technology Faculty of Informatics Engineering Jakarta12630 Indonesia Bina Nusantara University Binus Graduate Program. Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350339437

The escalating visibility of secure direct object reference (IDOR) vulnerabilities in API security, as indicated in the compilation of OWASP Top 10 API Security Risks, highlights a noteworthy peril to sensitive data. This study explores IDOR vulnerabilities found within Android APIs, intending to clarify their inception while evaluating their implications for application security. This study combined the qualitative and quantitative approaches. Insights were obtained from an actual penetration test on an Android app into the primary reasons for IDOR vulnerabilities, underscoring insufficient input validation and weak authorization methods. We stress the frequent occurrence of IDOR vulnerabilities in the OWASP Top 10 API vulnerability list, highlighting the necessity to prioritize them in security evaluations. There are mitigation recommendations available for developers, which recognize its limitations involving a possibly small and homogeneous selection of tested Android applications, the testing environment that could cause some inaccuracies, and the impact of time constraints. Additionally, the study noted insufficient threat modeling and root cause analysis, affecting its generalizability and real-world relevance. However, comprehending and controlling IDOR dangers can enhance Android API security, protect user data, and bolster application resilience. © 2023 IEEE.

关键词： Sensitive data

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：