检索结果-内蒙古大学图书馆

6th International Conference on Computer and Informatics Engineering, IC2IE 2023

作者： Rumahorbo, Brilyan Nathanael Pardamean, Bens Elwirehardja, Gregorius Natanael Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia

ISBN: (纸本)9798350345162

Major Depressive Disorder (MDD) is a prevalent mental disorder, affecting a significant number of individuals, with estimates reaching 300 million cases worldwide. Currently, the diagnosis of this condition relies heavily on subjective assessments based on the experience of medical professionals. Therefore, researchers have turned to deep learning models to explore the detection of depression. The objective of this review is to gather information on detecting depression based on facial expressions in videos using deep learning techniques. Overall, this research found that RNN models achieved 7.22 MAE for AVEC2014. LSTM models produced 4.83 MAE for DAIC-WOZ, while GRU models achieved an accuracy of 89.77% for DAIC-WOZ. Features like Facial Action Units (FAU), eye gaze, and landmarks show great potential and need to be further analyzed to improve results. Analysis can include applying feature engineering techniques. Aggregation methods, such as mean calculation, are recommended as effective approaches for data processing. This Systematic Literature Review found that facial expressions do have relevant patterns related to MDD. © 2023 IEEE.

关键词： deep learning facial expression GRU LSTM major depressive disorder

来源：评论

学校读者我要写书评

暂无评论

Implications of the Usage of Three-Mode Principal Component Analysis with a Fixed Polynomial Basis 15th

Implications of the Usage of Three-Mode Principal Compone...

引用

15th International KES Conference on Intelligent Decision Technologies, KESIDT 2023

作者： Monden, Rei Nagai, Isamu Yanagihara, Hirokazu Informatics and Data Science Program Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Higashi-Hiroshima739-8521 Japan Faculty of Liberal Arts and Science Chukyo University Aichi Nagoya466-8666 Japan Mathematics Program Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Higashi-Hiroshima739-8526 Japan

ISBN: (纸本)9789819929689

When I subjects answer questions regarding J variables K times, the data can be stored in a three-mode data set of size I× J× K. Among the various component analysis approaches to summarize such data, Three-mode Principal Component Analysis (3MPCA) is often used. 3MPCA expresses a three-mode data set by means of A-, B-, and C-mode components and a core array, but this approach is not suitable for predicting data at unobserved time points. To handle this issue, the current study suggests a fixed orthonormal polynomial basis for the 3MPCA model. Briefly, we fix the C-mode component matrix with an orthonormal polynomial basis. More specifically, i) measurement time points, and ii) log transformation of the measurement time points were used as an orthonormal polynomial basis. The use of our proposed methods was demonstrated by applying them to a longitudinal data set collected from patients with depression. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Performance prediction in major league baseball by long short-term memory networks

引用

International Journal of data science and Analytics 2023年第1期15卷 93-104页

作者： Sun, Hsuan-Cheng Lin, Tse-Yu Tsai, Yen-Lung Center for Information Systems and Technology Claremont Graduate University Claremont United States Data Science Degree Program National Taiwan University Taipei Taiwan Department of Mathematical Sciences National Chengchi University Taipei Taiwan

Player performance prediction is a serious problem in every sport since it brings valuable future information for managers to make important decisions. In baseball industries, there already existed variable prediction systems and many types of researches that attempt to provide accurate predictions and help domain users. However, it is a lack of studies about the predicting method or systems based on deep learning. Deep learning models had proven to be the greatest solutions in different fields nowadays, so we believe they could be tried and applied to the prediction problem in baseball. Hence, the predicting abilities of deep learning models are set to be our research problem in this paper. As a beginning, we select numbers of home runs as the target because it is one of the most critical indexes to understand the power and the talent of baseball hitters. Moreover, we use the sequential model Long Short-Term Memory as our main method to solve the home run prediction problem in Major League Baseball. We compare models’ ability with several machine learning models and a widely used baseball projection system, sZymborski Projection System. Our results show that Long Short-Term Memory has better performance than others and has the ability to make more exact predictions. We conclude that Long Short-Term Memory is a feasible way for performance prediction problems in baseball and could bring valuable information to fit users’ needs. © 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Baseball

来源：评论

学校读者我要写书评

暂无评论

E-Government Interoperability: Provincial-Level Architecture Model to Enable Fast Healthcare Interoperability Resources (FHIR) 9

E-Government Interoperability: Provincial-Level Architecture...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Wijayanti, Diana Urbaya, Satriawansyah Sitompul, Taufiq Adrian, Verry BINUS Graduate Program Bina Nusantara University Department of Information Systems Jakarta11480 Indonesia Program USAID Indonesia Jakarta12930 Indonesia University of Oslo Department of Informatics Oslo0316 Norway Binus Graduate Program - Doctor Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Jakarta Provincial Health Office Center of Data and Information Technology Jakarta10160 Indonesia

ISBN: (纸本)9798350390025

The process of using ICT to provide services to the public is known as the Indonesian e-Government system, or Sistem Pemerintahan Berbasis Elektronik (SPBE). The e-Government initiative in Jakarta Provincial Health Office involves enhancing collaboration among public health entities for efficient data exchange and streamlined processes, especially between the Provincial and District Health Offices, public hospitals, government clinics, and primary health care centers (Puskesmas). Achieving interoperability requires standardized protocols and a well-defined architectural model to integrate data seamlessly. This study presents a provincial-level architectural model focused on improving electronic health records interoperability, aiming to promote the adoption of the national Fast Healthcare Interoperability Resources (FHIR) health information exchange platform and enhance the integrity of health data in Jakarta. The study methodology involves conducting literature reviews, observations, and discussions with representatives from healthcare facilities to develop the e-Government architecture model and prototype of the infrastructure layer aiming to facilitate the interoperability of Electronic Health Records (EHRs) across 93 healthcare facilities, all of which are part of the SPBE users. © 2024 IEEE.

关键词： e-government

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of CNN Models for Multiclass Detection on Colon Disease 9

Comparative Analysis of CNN Models for Multiclass Detection ...

引用

9th International Conference on Information Technology and Digital Applications, ICITDA 2024

作者： Sulistyawan, Jason Sebastian Nugroho, Kuncahyo Setyo Isnan, Mahmud Pardamean, Bens Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331510732

Gastrointestinal diseases are significant health concerns that mostly affect the digestive and biliary tracts. These can only be observed internally through endoscopy, or a modern approach named Wireless Capsule Endoscopy. Though the approach has proven to work, the process relies heavily on medical experts, which is prone to error when given a considerably large load. The use of deep learning in detecting diseases with images has been proven to work in various cases and can be implemented for gastrointestinal diseases. This study compared four deep learning models based on Convolutional Neural Network architectures consisting of the VGG16, ResNet152V2, InceptionV3, and Xception for classifying colon disease images. The experiment showed that the ResNet152V2 performed the best, compared to the other three with a testing accuracy score of 0.9837. On the other hand, the VGG16 had the lowest performance with around accuracy score of 0.89 while the Xception and InceptionV3models yielded similar accuracy scores of 0.9587 and 0.9549, respectively. The results highlight the effectiveness of ResNet152V2 in handling the complexity of colon disease detection © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Multiple Choice Question Generation: A Systematic Literature Review 9

Automatic Multiple Choice Question Generation: A Systematic ...

引用

9th International Conference on Information Technology and Digital Applications, ICITDA 2024

作者： Henry, Matthew Martianus Heryanto, Nur Adhianti Isnan, Mahmud Nugroho, Kuncahyo Setyo Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331510732

Despite their drawbacks, multiple-choice questions (MCQ) have been widely used to assess the students' understanding of lectures through examinations. The development of automatic MCQ generation is beneficial, especially for educators. As a starting point for further development, a Systematic Literature Review (SLR) is conducted to uncover current trends, future challenges, and opportunities in automatic MCQ generation. Previously, an SLR was conducted, but it lacks coverage of the utilization of transformer-based models. This SLR covers the development of automatic MCQ generation using either traditional or advanced approaches such as Transformers. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used to gather the data from Scopus, IEEE Xplore, SpringerLink, arXiv, and Semantic Scholar. The included articles must be open-access computer science conference papers or journal articles and written in English less than five years ago. Four independent reviewers analyzed the research workflow, evaluation metric, and dataset used in each study. There are 18 included studies, where 17% (n = 3) studies are from 2024, 33% (n = 6) studies are from 2023, 22% (n = 4) studies are from 2022, 11% (n = 2) studies are from 2021, and 17% (n = 3) studies are from 2020. There are 33% (n = 6) of the studies used the traditional feature-based engineering approach, 39% (n = 7) of the studies used the Transformer-based model fine-tuning approach, and the remaining used novel approaches. The study found that BERT variants are the most utilized Transformer-based model in automatic MCQ. The research notes some challenges, but also open various opportunities for further research, including Large Language Model (LLM) utilization for automatic MCQ generation, the utilization BERT-based models for standardized machine-learned evaluation metrics, and the initiative for the creation of an MCQ dataset benchmark. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Automatic question generation for bahasa indonesia examination using copynet 9th

Automatic question generation for bahasa indonesia examinati...

引用

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

作者： Henry, Matthew Martianus Elwirehardja, Gregorius Natanael Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

In educational institutions, an educator is responsible for assessing the student's knowledge grasp through examination. Creating exam questions, even the low-level factoid questions, is time-consuming, especially for inexperienced educators. Therefore, this study aims to create a sequence-to-sequence model using CopyNet by exploiting its copying mechanism advantage to automatically generate Bahasa Indonesia factoid questions to ease the educator's burden. Indonesian records in the TyDi QA dataset are used as the model input. GRU and Bi-GRU are employed as the CopyNet encoder, while LSTM is used as the CopyNet decoder. The model that utilizes GRU as the encoder achieves BLEU1, BLEU2, BLEU3, BLEU4, and ROUGE-L scores of 0.28, 0.19, 0.14, 0.1, and 0.32, respectively. Bi-GRU utilization as the model encoder achieves BLEU1, BLEU2, BLEU3, BLEU4, and ROUGE-L scores of 0.26, 0.17, 0.12, 0.09, and 0.30, respectively. Models using either encoder still achieve low scores. However, compared with the previous work, the result is still on par regarding the BLEU score. Further examination found that the generated questions do not adhere to semantic and syntactical correctness. Adding more records to the dataset and utilizing a more advanced architecture like CopyBERT are encouraged to improve the model performance in future work. Despite the result, this study has shown that CopyNet, primarily designed for text summarization or single-turn dialogue, can be tailored for factoid question generation. © 2024 The Authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cancer Prediction using Clinical and Genomic data Fusion: A Systematic Review 6

Cancer Prediction using Clinical and Genomic Data Fusion: A ...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Julian, Kelvin Nugroho, Kuncahyo Setyo Nirwantono, Rudi Pardamean, Bens Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Biotechnology Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

This systematic review provides a comprehensive overview of the methods used to integrate genomic and clinical data in cancer prediction. The review includes 19 studies across various cancers, including breast, colorectal, melanoma, lung, pancreatic, and thyroid. The studies employed different methods to combine genomic and clinical data, including weighted polygenic risk scores, genetic and non-genetic risk scores, and different machine learning algorithms. The results show significant improvements in model prediction performance accuracy across multiple studies. The review highlights the potential benefits of integrating genetic and phenotypic information to improve disease risk prediction models and inform personalized healthcare strategies. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Consideration of Constructing a Weed Detection Method for an Agricultural Robot in Perilla Fields 23

Consideration of Constructing a Weed Detection Method for an...

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Sugie, Tatsuya Takagi, Noboru Motoyoshi, Tatsuo Sawai, Kei Masuta, Hiroyuki Graduate School of Intelligent Robotics Program Toyama Prefectural University Toyama Japan Toyama Prefectural University Department of Data Science Toyama Japan Toyama Prefectural University Department of Intelligent Robotics Toyama Japan

ISBN: (纸本)9798331528041

In recent years, the number of farmers in Japan has been decreasing, and the automation of agriculture using robots, AI, and IoT, known as 'smart agriculture,' is being promoted. In this context, Toyama city is promoting a project to build a robot for automatic weeding between plants in a perilla fields. In this research, we are in charge of the system part that detects weeding regions and informs the weeding mechanism. In the field, a wide variety of weeds form vegetation, and it is necessary to prevent food crops from being cut. Therefore, we detect crop regions and the rest of the area should be the weeding regions. In this study, we construct a system to detect crop regions by transfer learning the object detection model YOLO-v8, which is a convolutional neural network (CNN), and evaluate the system in terms of detection accuracy and processing speed. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigation of Robot's Eye Gaze Affecting Human Pedestrian Behavior by Robot in Virtual Space 23

Investigation of Robot's Eye Gaze Affecting Human Pedestrian...

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Takata, R.Y.O. Fuse, Yotaro Takagi, Noboru Myagmardulam, Bilguunmaa Motoyoshi, Tatsuo Sawai, K.E.I. Masuta, Hiroyuki Graduate School of Intelligent Robotics Program Toyama Prefectural University Toyama Japan Toyama Prefectural University Department of Data Science Toyama Japan Toyama Prefectural University Department of Intelligent Robotics Toyama Japan

ISBN: (纸本)9798331528041

We investigate the effects of robot's gaze on human behavior when a human and a robot pass each other in a virtual reality space (VR). Nonverbal communication, particularly eye contact, influences physical proximity between individuals in human-to-human interaction. Results of a study indicate that the robot's gaze affects the physical distance between a human and a robot in human-robot communication. Studies on robot's gaze tend to focus on experimental scenarios in which robots and humans communicate. However, robot's gaze in environments with interactions, such as crossing paths, has not been extensively investigated. Therefore, we hypothesize that the robot's gaze exhibits an influence on the physical distance between humans and robots during encounters. In our experiment, we compare three conditions: a robot with a rotating neck and gaze directed at the subject, a faceless robot with a rotating neck, and a faceless robot with a rotating neck and gaze directed at the subject. We analyze the subject's paths of movement and physical distance between the subjects and the robot. Results suggest that the hypothesis that 'intimacy equilibrium model' works when humans and robot's cross paths in the VR environment is not supported. © 2024 IEEE.

关键词： Human robot interaction

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：