检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Kim, Yejin Jeon, Daeseong Park, HyeRim Lee, Changyong Lee, Junghye Ulsan44919 Korea Republic of Ulsan44919 Korea Republic of Technology Management Economics and Policy Program Seoul National University Seoul08826 Korea Republic of Department of Public Administration Korea University Seoul02841 Korea Republic of Technology Management Economics and Policy Program Graduate School of Engineering Practice Seoul National University Seoul08826 Korea Republic of

Detecting anomalies in multivariate time-series data is an important task in various real-world industries, but doing so is non-trivial because both the temporal dependency within the time series and correlations between multiple time series must be considered. Previous studies have only addressed one issue, resulting in limited performance. To address this, we propose a graph convolution-based recurrent encoder-decoder, called GC-RED. The model incorporates intra-dependencies and inter-correlations using a graph-construction process and an encoding-decoding process that encodes the graph with an attention-enhanced graph convolutional LSTM and then restores it. Anomaly detection and root cause identification are performed based on the reconstruction error. Considering that anomalies with various durations can occur in actual situations, the model includes a vanilla model reflecting single scales and a model reflecting multiple scales. The feasibility and usefulness of GC-RED are demonstrated by intensive experiments on several benchmark and real-world datasets with comparisons to other competitive methods. © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Disease Data Modeling by Using Machine Learning Approach

Disease Data Modeling by Using Machine Learning Approach

引用

International Conference on Information technology, Computer and Electrical Engineering (ICITACEE)

作者： Gunawan Wang Rakha Gusti Wardhana Farida Sibuea Anderes Gui Information Systems Management Department BINUS Graduate Program-Master of Information Systems Management Bina Nusantara University Jakarta Indonesia Head of Data Analytics department Data and Information Technology Centre (Pusdatin) Ministry of Health Jakarta Indonesia School of Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350389302

ISBN: (纸本)9798350389319

Since Covid outbreak in 2020, Indonesian Ministry of Health (MoH) has intensively embraced digital transformation initiatives in healthcare management and decision-making process. The latest healthcare digital transformation roadmap 2024, has emphasized the use of AI technology in data analytics and support policy making. The article examines the use of common Machine Learning (AI) algorithms, such as: Logistic Regression, Random Forest, Support Vector Machine (SVM), Decision Tree, and XGBoost. The article applies these algorithms to analyse the common diseases faced by Indonesian such as Measles, Malaria, Leprosy, and Diphtheria. Those diseases are classical diseases, however, still infecting many people in large areas. The article takes a case study of national health profile within period 2017–2022, to study the data model of those diseases. The outcome of the article is expected to be used for further policy making.

关键词： Support vector machines Logistic regression Machine learning algorithms Malaria Measles Medical services Predictive models Prediction algorithms Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Experimentation of Integrating Roadmapping and Sci-Fi Prototyping Methods

Experimentation of Integrating Roadmapping and Sci-Fi Protot...

引用

Portland International Conference on management of Engineering and technology (PICMET)

作者： Miwa Nishinaka Kunio Shirahada Yusuke Kishita Dohjin Miyamoto Hirotaka Osawa Sachiko Kiyokawa Hideaki Takeda The Graduate School of Management Kagawa University Takamatsu Kagawa Japan School of Knowledge Science Transformative Knowledge Management Research Area Japan Advanced Institute of Science and Technology (JAIST) Nomi Ishikawa Japan Department of Precision Engineering The University of Tokyo Tokyo Japan Communication in Science and Technology Education and Research Program Hokkaido University Sapporo Japan Faculty of Science and Technology Keio University Yokohama Kanagawa Japan Graduate School of Education The University of Tokyo Tokyo Japan National Institute of Informatics Tokyo Japan

ISBN: (数字)9781890843458

ISBN: (纸本)9798350369137

In 2023, we proposed a hypothetical knowledge management framework that incorporates science fiction prototyping (SFP) into the traditional roadmapping (RM) method to make RM more innovative and create a future beyond what we can currently imagine. Our main objective is to create a new organizational knowledge co-creation method for generating innovative ideas by incorporating humanistic factors utilizing SFP into RM. In the current article, we present the exploratory study we conducted to examine the hypothetical framework. Experimental workshops were held in November 2023 to compare the integrated method, in which SFP is applied to RM, with the original RM method. We followed a crossover design in the workshops and analyzed the results qualitatively and quantitatively following the perspectives proposed in the hypothetical framework. The qualitative analysis revealed successful integration regarding diverse and broader perspectives. The quantitative analysis utilizing Wilcoxon signed rank tests showed that the scores of the integrated method were significantly higher than those of RM for variables evaluating the effectiveness of the integration, while not for variables related to participants' feelings and satisfaction with the workshops, and sustainability. These findings indicate that the integration was successful in terms of its effectiveness as a method, while participants' subjective feelings toward the workshops were not different in both methods. As for sustainability, which requires a long-term perspective, no apparent differences were observed in these short-term workshops.

关键词： Statistical analysis Conferences Knowledge management Sustainable development Creativity

来源：评论

学校读者我要写书评

暂无评论

Mapping the Scientific Landscape of Integrated Scheduling Towards Industry 5.0 with A Bibliometric Analysis

引用

Procedia Computer Science 2025年 253卷 84-93页

作者： Anak Agung Ayu Putri Ardyanti Zhiqiang Xie Andrea Stevens Karnyoto Bens Pardamean Ni Made Estiyanti School of Computer Science and Technology Harbin University of Science and Technology Harbin 150000 China Faculty of Information Technology and Design Primakara University Bali 80226 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Doctoral School of Management and Business University of Debrecen Debrecen Hungary

The industry is rapidly transitioning from the 4.0 era to the 5.0 era, prompting renewed interest among scholars in scheduling problems. They allow operations to process and assemble various components simultaneously. This bibliometric analysis provides a comprehensive understanding of the diverse research perspectives on the potential challenges of integrated scheduling within the framework. We identified 357 Scopus articles and analysed co-occurrence keyword (CNK) by VOSViewer tools and Global Citation Score (GCS) by Scopus tools. The research data obtained from 1993 to 2023 mainly in the subject areas of Engineering, Computer Science, Maths, and others. CNK identified six cluster keywords, and nine most cited articles based on normalised GCS. These results contribute to our understanding of the development of scheduling algorithms, shifting from an emphasis on manufacturing transfers to contemporary demand-centric research directions. Furthermore, this research provides a valuable perspective for policymakers, plant personnel, and manufacturing managers to make informed decisions.

关键词： integrated scheduling assembly job shop scheduling heuristic algorithm genetic algorithm bibliometric analysis

来源：评论

学校读者我要写书评

暂无评论

Capnesterones A and B, new steroids isolated from the soft coral Capnella imbricata

引用

Phytochemistry Letters 2024年 61卷 115-119页

作者： Cheng, Ting-Yu Yang, Chia-Jung Chen, Po-Jen Chen, Yu-Li Peng, Bo-Rong Kung, Te-An Wen, Zhi-Hong Lai, Kuei-Hung Chung, Hsu-Ming Department of Applied Chemistry National Pingtung University Pingtung 900393 Taiwan Clinical Immunology Laboratory Department of Medical Research E-Da Hospital I-Shou University Kaohsiung 824005 Taiwan Research Center for Chinese Herbal Medicine Graduate Institute of Healthy Industry Technology College of Human Ecology Chang Gung University of Science and Technology Taoyuan 33305 Taiwan Graduate Institute of Biomedical Sciences Graduate Institute of Natural Products College of Medicine Chang Gung University Taoyuan 33305 Taiwan Graduate Institute of Pharmacognosy College of Pharmacy Taipei Medical University Taipei 11031 Taiwan Institute of Food Safety Management National Pingtung University of Science and Technology Pingtung 91201 Taiwan Department of Marine Biotechnology and Resources National Sun Yat-sen University Kaohsiung 804201 Taiwan Institute of BioPharmaceutical Sciences National Sun Yat-sen University Kaohsiung 804201 Taiwan PhD Program in Clinical Drug Development of Herbal Medicine College of Pharmacy Taipei Medical University Taipei 11031 Taiwan Traditional Herbal Medicine Research Center Taipei Medical University Hospital Taipei 11031 Taiwan

Two new non-withanolidal steroids with a cross-conjugated dienone structural unit in ring A, capnesterones A (1) and B (2), were isolated from the soft coral Capnella imbricata in the southeast waters of Taiwan. The compounds' structures were elucidated through a comprehensive analysis of spectroscopic data, including IR, ESIMS, ¹H NMR, and ¹³C NMR, and through comparison with previous literature. At a concentration of 10 μM, steroids 1 and 2 exhibited reductions in iNOS levels (60 % and 82 %) compared to LPS-stimulated control cells, along with increased release (134 % and 110 %) against COX-2 protein expressions. © 2024 Phytochemical Society of Europe

关键词： Capnella imbricata COX-2 INOS Steroid

来源：评论

学校读者我要写书评

暂无评论

Dynamic Terrain Data Exchange in a Collaborative Terrain Editor

Informatica (Slovenia)

引用

Informatica (Slovenia) 2022年第4期46卷 575-582页

作者： Tarigan, Jos Timanta Sitompul, Opim Salim Zarlis, Muhammad Nababan, Erna Budhiarti Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Information Systems Management Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia

In a computer supported cooperative work (CSCW), data consistency between collaborating users is a crucial issue. Based on the type of the application, ensuring data consistency can be a lengthy process that takes time and affects the system’s performance. In most 3D application, terrain data are massive due to its size. Exchanging this data may be expensive and may cause significant delay. In a real-time collaborative terrain editor, this issue becomes more significant due to terrain data exchange is consistently occurred between collaborating users. We present a solution to perform a conflict-free dynamic terrain data exchange in a real-time collaborative terrain editor. Our objective is to develop a method that able to ensure data consistency amongst collaborating peers in real-time manner. The main idea of our method is to split the terrain into smaller patches and synchronize the changes efficiently by only exchanging the modified patches. We applied our solution to a collaborative terrain editor application to test its performance in a real-time collaborative editing session. The tests were done in multiple scenarios, using different patch model, brush size (in the terrain editor), and connection setup between server and collaborating clients. The result shows that our protocol is capable to maintain data consistency between collaborating clients in a real-time terrain edition session. The delay is varied and highly depends on the data size and client-server environment setup. The overall test shows that it is possible to perform a collaborative terrain editing with an acceptable response time delay. In this paper, we present our proposed method, the implementation, and the result data from the test. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Integration of the Use of Conventional technology Towards Smart Home technology for People in the City of Jakarta

Integration of the Use of Conventional Technology Towards Sm...

引用

International Conference on ICT For Smart Society (ICISS)

作者： Tanty Oktavia Febian Wijaya Lintang Gerald Christian Ongko Griselda Valerie Michelle Benedicta Vieri Aska Juneio Sembiring Zaldy Raditya Ananta Takaaki Hosoda Ford Lumban Gaol Information Systems Management Department BINUS Graduate Program - Master of Information Systems Management Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Decision Science Department Advanced Institute of Industrial Technology Tokyo Japan Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

Smart Home technology offers technological concepts that can be controlled through smart devices to make it easier for the community. Therefore, smart home technology is starting to seize the home electronics market in Indonesia, especially in the city of Jakarta. This study aims to determine the integration of conventional technology into smart home technology for people in Jakarta. The research model in this study uses UTAUT2 which analyzes nine variables, namely Perceived Usefulness, Perceived Cost, Perceived Ease of Use, Social Influence, Perceived Compatibility, Trust, Perceived Pleasure, and Effort Expectations, Intention to Use Smart Home technology. After the responses were received, data analysis was carried out using the PLS-SEM approach with the SmartPLS application. The results of this study show that there are many people who live in Jakarta who are helped by the presence of smart home technology. However, there are some people who don't really know how to use a smart home because of a lack of knowledge about this technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessing the Performance of Machine Learning Algorithms for Water Level Prediction in the Chao Phraya River and its Tributaries: A Focus on Low and High Water Levels

SSRN

引用

SSRN 2024年

作者： Priyasiri, Wilmat D.S.M. Rittima, Areeya Kraisangka, Jidapa Sawangphol, Wudhichart Phankamolsil, Yutthana Talaluxmana, Yutthana Graduate Program in Environmental and Water Resources Engineering Department of Civil and Environmental Engineering Faculty of Engineering Mahidol University Thailand Faculty of Information and Communication Technology Mahidol University Thailand Environmental Engineering and Disaster Management Program Mahidol University Kanchanaburi Campus Thailand Department of Water Resources Engineering Faculty of Engineering Kasetsart University Thailand

High precision of hydrological prediction is crucial for real–time operation of flood and drought risk mitigation and strategic planning. This study assessed the predictive performances of three Machine Learning (ML) algorithms;XGBoost, Random Forest (RF), and Multi–Layer Neural Networks (MLNNs) for water level prediction with a focus on low and high water levels. The one–day and one–week water level prediction models for six key gauged stations along the Chao Phraya River and its major tributaries were accordingly developed. Selecting the combination of input features was carried out and structured in the prediction model at all gauged stations based on the physical river–reservoir system using past water level, rainfall, controlled reservoir outflow, and upstream discharges with different travel times. The statistical evaluation indicated that both XGBoost and RF, the tree–based ML models, with rainfall input robustly outperformed than MLNNs, as it strongly achieved higher R2 from 0.957 to 0.999 for model training and from 0.743 to 0.995 for model testing and lower MAE, MSE, and RMSE values for all prediction scenarios. Among these three ML algorithms applied for daily prediction, RF demonstrated the superior performance for low water level prediction exhibiting the smallest percentage error of overestimating lying between +0.0088% and +0.9380%. XGBoost, RF, and MLNNs, demonstrated acceptable performance level for high water level prediction as it shows small percentage error of both overestimating and underestimating lying between –2.2696% and +1.1587%. Additionally, it can capture the entire testing dataset with high precision than weekly model. © 2024, The Authors. All rights reserved.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Uncover Configurational Paths of Streamers' Characteristics Predicting High vs. Low Consumers' Watching Intention to TikTok Live Streaming

Uncover Configurational Paths of Streamers' Characteristics ...

引用

International Conference on Information management and technology (ICIMTech)

作者： Pantas H. Silaban Andri Dayarana K. Silalahi Wen-Kuo Chen Suwandi S. Sangadji Ixora Javanisa Eunike Febiola Panggabean Graduate School Master of Management University of HKBP Nommensen Medan Indonesia Department of Business Administration College of Management Chaoyang University of Technology Taichung Taiwan Department of Money and Banking National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Management Faculty of Economics and Business Universitas Airlangga Surabaya Indonesia Management Program Faculty of Economics and Business University of HKBP Nommensen Medan Indonesia

The recent popularity of live streaming on social media has fascinated scholars' devotion. Though, prior studies have yet to satisfactorily elucidate how continuous watching intentions are enlightened regarding live streaming. This study aims to develop an asymmetrical framework for predicting consumers' watching intentions based on streamers' characteristics, such as beauty, humor, warmth, passion, and expertise. A total of 450 respondents who watched live streaming on TikTok participated in this study. This study attempts to examine propositions that specify models that predict high vs. low watching intentions based on the five streamers' characteristics using the fsQCA 3.0. The findings designate two configurations that signify both high vs. low watching intention. To achieve high watching intention, conditions of humor, warmth, passion, and expertise are required. Meanwhile, consumers will not continue to watch TikTok live streaming when the absence of beauty, humor, passion, and warmth is significant. This study signifies theoretical implication where a configurational model of live streaming watching intention based on streamers' characteristics was well-validated. At the same time, this study also provides marketers with practical guidelines on increasing watching intention using four configurations of streamers' characteristics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grinding wheel specification cybernetic recommendation with multi-task multi-imbalanced learning in smart manufacturing system

引用

Advanced Engineering Informatics 2024年 61卷

作者： Yao, Kuo-Ching Chen, Tzu-Li Chen, James C. Li, Chia-Ruei International Intercollegiate Ph.D. Program National Tsing Hua University Hsinchu30013 Taiwan Kinik Company New Taipei23942 Taiwan Graduate Institute of Intelligent Manufacturing Technology National Taiwan University of Science and Technology Taipei106335 Taiwan Department of Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu300044 Taiwan

Over the years, the grinding wheels industry has played a crucial role in mechanical engineering. Grinding wheel specification is composed of various factors such as abrasive type, wheel grade, bond type, and more, which are derived from customer workpiece operation information. Traditionally, the determination process of grinding wheel specifications is complicated. Experienced engineers need to check out the limitation and consider the interaction of each factor. When the new specification order comes, engineers have to spend a lot of time on historical data search and discussion. Recently, the application of artificial intelligence attracts more and more attention in the manufacturing industry. Through collecting historical data, the model has the ability to extract the domain knowledge, predict the specification that does not exist, and reduce the decision time. However, when training the model, this grinding wheel specification faced multiple imbalanced targets and multi-task issues. In the past, research efforts primarily focused on studying single-task learning (STL) algorithms. Seldom of them has a systematic way to discuss the model determination of multiple targets and correlation influence, especially on the tabular-type dataset. In this study, we proposed a multiple resampling chain multi-task learning framework to address the issue of data science. To tackle the multi-task imbalance resampling problem, we also proposed a resampling strategy called Multiple Resampling Chain. Moreover, we conducted a sensitivity analysis to examine the correlation effect on model improvement. Finally, we proposed a cyber-recommendation system that integrates the training model and interface to provide a more intuitive way of specification prediction. This system not only can help engineers to improve the time spent on making decisions, but also make the whole manufacturing process to be more intelligent. © 2024 Elsevier Ltd

关键词： Grinding (machining)

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：