检索结果-内蒙古大学图书馆

Cyber science and Technology Congress (CyberSciTech), IEEE

作者： Jianhua Ma Qun Jin Hui-Huang Hsu John Paul C. Vergara Antonio Guerrieri Claudio Miceli Ao Guo Faculty of Computer and Information Sciences Hosei University Japan Department of Human Informatics and Cognitive Sciences Waseda University Japan Department of Computer Science and Information Engineering Tamkang University Taiwan Department of Information Systems and Computer Science Ateneo de Manila University Philippines ICAR-CNR Italy Graduate Program in Systems Engineering and Computer Science Federal University of Rio de Janeiro Brazil Graduate School of Informatics Nagoya University Japan

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

Generative Artificial Intelligence (GenAI) represents a significant milestone in the development of artificial intelligence, bringing sophisticated AI capabilities into daily life and work. As we approach the era of Hyper Intelligence (Hyper-I), a variety of critical challenges and emerging issues have come to light, ranging from computational complexity to ethical concerns. This paper explores the evolution of AI from the perspective of human learning, comparing machine and human intelligence, and identifying key considerations for the development of future AI systems. It also highlights the growing importance of regulating advanced AI models, such as Reinforcement Learning-based Long-Term Planning Agents, to ensure that Hyper-I remains under human control. Additionally, the paper discusses the computational complexity of transformer-based models, their applicability to intractable problems, and their role in cognitive building systems and resource-constrained environments through TinyML. By analyzing these pressing challenges, this work provides insights into the future of AI and the path toward responsible innovation in generative and hyper-intelligent systems.

关键词： Hyper-intelligent systems Ethics Technological innovation Generative AI Computational modeling Tiny machine learning Pressing Transformers Regulation Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Evaluation of an agent-based reinforcement learning framework for model-based testing

Evaluation of an agent-based reinforcement learning framewor...

引用

Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC), V Congreso Internacional en

作者： Jose Ramírez-Méndez Christian Quesada-López Graduate Program in Computing and Informatics University of Costa Rica San Pedro Costa Rica Department of Computer Science and Informatics University of Costa Rica San Pedro Costa Rica

ISBN: (数字)9798350364538

ISBN: (纸本)9798350364545

This study evaluates an agent-based reinforcement learning framework for model-based testing (MBT). The framework’s performance was assessed on three key metrics: effectiveness and efficiency in achieving model coverage objectives, the quantity and uniqueness of generated test cases, and code coverage. The results show improved metrics for the framework compared to traditional testers in model coverage evaluation and test case metrics. Specifically, the framework achieved higher effectiveness and efficiency, generating a higher average number of test cases with a substantial proportion of unique cases, indicating more diverse and thorough testing. Additionally, the framework, along with random and greedy testers, achieved over 70% coverage across branch, method, and line code metrics. The framework showed slightly higher values in method and line coverage compared to other testers. The evaluation highlights the use of agent-based reinforcement learning to support model-based testing in planning test case generation, exploring models using multiple strategies, and learning guided by testing metrics. Future work will focus on further refining the framework learning model, including error coverage evaluation, and testing its applicability across different software systems.

关键词： Measurement Software testing Codes Calculators Refining Reinforcement learning Software systems Planning Testing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Preacher Assignments Using AHC-PCA Algorithm in Kampar Regency

Optimizing Preacher Assignments Using AHC-PCA Algorithm in K...

引用

International Conference on Electrical Engineering, computer and Information Technology (ICEECIT)

作者： Rahmad Kurniawan Nuraina Suhada Sukamto Tisha Melia Zailani Joko Risanto Department of Computer Science Faculty of Mathematics and Natural Sciences Universitas Riau Pekanbaru Indonesia Graduate Program Universitas Islam Negeri Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (数字)9798331504373

ISBN: (纸本)9798331504380

Inefficiencies in assigning preachers for Islamic preaching activities often arise due to distant placements, leading to delays and logistical challenges. In Kampar Regency, geographical diversity intensifies this issue, resulting in suboptimal preacher placements. This study aims to optimize preacher assignments by considering distance and mosque profiles. The dataset, which includes 102 mosques and 148 preachers was obtained from the Indonesian Ulema Council in Kampar. The Agglomerative Hierarchical Clustering (AHC) algorithm was selected for its capacity to cluster data across multiple characteristics. Principal Component Analysis (PCA) was employed to reduce data dimensionality, thereby enhancing clustering outcomes. The optimization of the AHC-PCA algorithm generated an optimal clustering solution with a silhouette score of 0.625524 at three clusters. Furthermore, the elbow method also indicated that three clusters are optimal with a value of 390.234457, while the lowest Davies-Bouldin Index (DBI) score of 0.468573 was achieved with three clusters. Business Intelligence techniques visualized these clusters, providing a spatial distribution of preachers and mosques for detailed analysis. This study improves preacher assignments by reducing travel time and aligning preacher placements with mosque proximity and needs, thus enhancing the efficiency of Islamic preaching in Kampar Regency.

关键词： Measurement Graphical models Clustering algorithms Indexes Business intelligence Elbow Information technology Population density Optimization Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Fake News Classifier with Deep Learning

Fake News Classifier with Deep Learning

引用

Industrial Electrical and Electronics (ICIEE), International Conference on

作者： Michael Febrianto Lu Renaldy Vincent Ciptadi Reyhan Nathanael Kevin Sam Andaria Abba Suganda Girsang Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665486231

In this decade, social media has become more frequently used because it is easy to see some news on the social media for example Instagram, Facebook, and other social media. However, the problem that often arises in social media problems is the accuracy of the news. There are many fake news circulating on social media. This paper aims to classify the fake news using random forest. This research uses data Kaggle “Fake News Dataset Combined Different Sources”. The accuracy of the Fake News Classifier using this model is is 0.9403, the Classification Report on this model is True Recall Score: 0.88 and the Fake Recall score is 0.98 while the Precision Score is 0.96 and 0.93 for each true and fake result, F1-Score is 0.92 and 0.95. At the end the model using self-inputted data is tested

关键词： Deep learning Social networking (online) Multimedia Web sites Forestry Real-time systems Data models Fake news

来源：评论

学校读者我要写书评

暂无评论

Towards Precision Cancer Therapy: Prottrans and Multi-Window Scanning Convolutional Neural Networks Transforming Protein-Peptide Interaction Predictions

SSRN

引用

SSRN 2024年

作者： Van Le, The Zi Zhan, Jun Yu Ou, Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan

This study delves into the prediction of protein-peptide interactions using advanced machine learning techniques, comparing models such as sequence-based, standard CNNs, and traditional classifiers. Leveraging pre-trained language models and multi-view window scanning CNNs, our approach yields significant improvements, with ProtTrans standing out based on 2.1 billion protein sequences and 393 billion amino acids. The integrated model achieves an impressive AUC of 0.855 and 0.822 on Set_1 and Set_2 datasets, outperforming previous methods. Beyond this, we explore the application of this model in cancer therapy, particularly in identifying peptide interactions for selective targeting of cancer cells. The findings of this study contribute to bioinformatics, providing valuable insights for drug discovery and therapeutic development. © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Attention is Everything You Need: Case on Face Mask Classification

引用

Procedia computer science 2023年 227卷 372-380页

作者： Nanda Pratama Dody Harianto Stefan Filbert Harco Leslie Hendric Spits Warnars Maybin K. Muyeba School of Computer Science Bina Nusantara University West Jakarta Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University West Jakarta Jakarta 11480 Indonesia MIST Consulting Manchester M410SA United Kingdom

Automated face mask classification has surfaced recently following the COVID-19 mask wearing regulations. The current State-of-The-Art of this problem uses CNN-based methods such as ResNet. However, attention-based models such as Transformers emerged as one of the alternatives to the status quo. We explored the Transformer-based model on the face mask classification task using three models: Vision Transformer (ViT), Swin Transformer, and MobileViT. Each model is evaluated with a top-1 accuracy score of 0.9996, 0.9983, and 0.9969, respectively. We concluded that the Transformer-based model has the potential to be explored further. We recommended that the research community and industry explore its integration implementation with CCTV.

关键词： Face Mask Classification Convolutional Neural Network Attention Transformer Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Text Classification Using Long Short-Term Memory (LSTM)

Hate Speech Text Classification Using Long Short-Term Memory...

引用

International Conference of computer science and Information Technology

作者： Suminar Ariwibowo Abba Suganda Girsang Diana Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350399080

This paper aims to build hate speech text classification model by applying a combination of LSTM and FastText. The features of hate speech & non-hate speech, target hate speech, and categories of the hate speech. Dataset of those features taken from previous research by Okky Ibrohim. FastText word embeddings is used for formation of text vectors that will be used as input of the LSTM training model. The evaluation results obtained by getting the level of accuracy using confusion matrix. The accuracy value of text classification in this study is 83.52% on the classification of hate speech, 78.44% on the classification of target labels for hate speech, 82.75% on the classification of the label for category of hate speech.

关键词： Training computer science Dictionaries Hate speech Text categorization Bit error rate Information technology

来源：评论

学校读者我要写书评

暂无评论

Twitter-based Sentiment Analysis for Indonesian Drug Products using Supervised Feature Engineering

Twitter-based Sentiment Analysis for Indonesian Drug Product...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Kartika Purwandari Nicholaus Hendrik Jeremy Panji Arisaputra Samuel Philip Derwin Suhartono Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

Social media communications offer valuable feedback to firms about their products. Twitter users share their opinions about e-commerce products on social networking sites. This paper reports a study in sentiment classification for Indonesian drug products for automatically classifying Twitter data as expressing positive or negative sentiments or opinions. The study investigates the effectiveness of using a Decision Tree, Support Vector Machine, Random Forest, Na rve Bayes, and Logistic Regression, along with the term frequency-inverse document frequency used to classify 531 tweets into recommended (positive sentiment) and not recommended (negative sentiment). Among all traditional machine learning models, the highest average accuracy value is 88.6 in the RF model and the lowest average accuracy value is 80.2 when using the LR model. Judging from the average accuracy obtained, the DT and RF model used has a considerable performance

关键词： Drugs Support vector machines Seminars Analytical models Sentiment analysis Social networking (online) Blogs

来源：评论

学校读者我要写书评

暂无评论

Deepepiil13: Deep Learning for Prediction of Il-13 Inducing Epitopes Using Pre-Trained Language Models and Multi-Window Convolutional Neural Networks

SSRN

引用

SSRN 2024年

作者： Chuang, Cheng-Che Ou, Yu-Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan

Interleukin-13 (IL-13) is a key cytokine involved in allergic inflammation and the cytokine storm associated with severe COVID-19. Identifying antigenic epitopes capable of inducing IL-13 holds therapeutic potential for developing epitope-based vaccines and immunomodulatory treatments. However, conventional methods for epitope prediction are often inefficient and inaccurate. This study presents DeepEpiIL13, a novel deep learning framework that integrates pre-trained language models and multi-window convolutional neural networks (CNNs) to rapidly and accurately predict IL-13-inducing epitopes from protein sequences. The ProtTrans pre-trained language model was employed to generate high-dimensional embeddings that capture rich contextual information from protein sequences. These embeddings were then inputted into a multi-window CNN architecture, enabling the efficient exploration of local and global sequence patterns associated with IL-13 induction. The proposed approach was rigorously evaluated using benchmark datasets and an independent SARS-CoV-2 dataset. DeepEpiIL13 achieved superior performance compared to traditional methods, with an impressive Matthews correlation coefficient (MCC) of 0.52 and an area under the receiver operating characteristic curve (AUC) of 0.86 on the benchmark dataset. On the independent SARS-CoV-2 dataset, DeepEpiIL13 demonstrated remarkable robustness, attaining an MCC of 0.63 and an AUC of 0.92, highlighting its potential applicability in the context of COVID-19 research. This study introduces a powerful deep learning framework for accurate epitope prediction, offering new avenues for the development of epitope-based vaccines and immunotherapies targeting IL-13-mediated disorders. The successful identification of IL-13-inducing epitopes paves the way for novel therapeutic interventions against allergic diseases, inflammatory conditions, and potentially severe viral infections like COVID-19. © 2024, The Authors. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Clustering Preachers and Mosques for Effective Religious Outreach in Kampar Using DHC-PCA Algorithm

Clustering Preachers and Mosques for Effective Religious Out...

引用

International Conference on Electrical Engineering, computer and Information Technology (ICEECIT)

作者： Rahmad Kurniawan Natania Adela Surya Fatayat Evfi Mahdiyah Ilyas Husti Arisman Department of Computer Science Faculty of Mathematics and Natural Sciences Universitas Riau Pekanbaru Indonesia Graduate Program Universitas Islam Negeri Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (数字)9798331504373

ISBN: (纸本)9798331504380

Preacher assignments to mosques in Kampar Regency have often been inefficient due to geographical distance and compatibility issues, limiting effective religious outreach. This study aims to optimize preacher assignments by applying the Divisive Hierarchical Clustering (DHC) algorithm. Analysis was conducted on a dataset of 250 records, clustering preachers and mosques based on geographical proximity and relevant attributes. Initial clustering modelling produced the highest silhouette score of 0.336. Dimensionality reduction using Principal Component Analysis (PCA) significantly improved the silhouette score to 0.8197, reflecting enhanced clustering quality. The elbow method validated eight clusters as optimal, with a value of 292.33. Research findings demonstrate that preachers can be effectively placed in geographically closer mosques aligned with their profiles, reducing inefficiencies. Business intelligence techniques visualized the clustering results, providing decision-makers with insights into geographical distribution and facilitating improved assignment strategies. These findings hold substantial implications for optimizing religious outreach in Kampar by minimizing logistical challenges and increasing engagement effectiveness.

关键词： Electrical engineering Dimensionality reduction Visualization Limiting Computational modeling Clustering algorithms Business intelligence Elbow Information technology Principal component analysis

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：