检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Kitrungrotsakul, Titinunt Yutaro, Iwamoto Lin, Lanfen Tong, Ruofeng Li, Jingsong Chen, Yen-Wei Healthcare Data Science Zhejiang Lab Hangzhou China Graduate School of Information Science and Engineering Ritsumeikan University Shiga Japan College of Computer Science and Technology Zhejiang University Hangzhou China College of Biomedical Engineering & Instrument Science Zhejiang University Hangzhou China

Deep learning techniques have successfully been employed in numerous computer vision tasks including image segmentation. The techniques have also been applied to medical image segmentation, one of the most critical tasks in computer-aided diagnosis. Compared with natural images, the medical image is a gray-scale image with low-contrast (even with some invisible parts). Because some organs have similar intensity and texture with neighboring organs, there is usually a need to refine automatic segmentation results. In this paper, we propose an interactive deep refinement framework to improve the traditional semantic segmentation networks such as U-Net and fully convolutional network. In the proposed framework, we added a refinement network to traditional segmentation network to refine the segmentation *** results with public dataset revealed that the proposed method could achieve higher accuracy than other state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Markerless 3D Skeleton Pose Estimates with Pop Dance Motion Sequence

Performance Evaluation of Markerless 3D Skeleton Pose Estima...

引用

International Conference on Informatics, Electronics & Vision (ICIEV)

作者： Rollyn T. Labuguen Salvador Blanco Negrete Tonan Kogami Wally Enrico M. Ingco Tomohiro Shibata Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology Kitakyushu City Fukuoka Japan Electronics Computer and Communications Engineering Ateneo de Manila University Quezon City Philippines

ISBN: (数字)9781728193311

ISBN: (纸本)9781728193328

The evaluation of markerless pose estimation performed by OpenPose has been getting much attention from researchers of human movement studies. This work aims to evaluate and compare the output joint positions estimated by the OpenPose with a marker-based motion-capture data recorded on a pop dance motion. Although the marker-based motion capture can accurately measure and record the human joint positions, this particular set-up is expensive. The framework to compare the outputs of the markerless method to the ground truth marker-based joint remains unknown, especially for complex body motion. Synchronization, camera calibration, and 3D reconstruction by fusing the outputs of the markerless method (OpenPose) are discussed. In this case study, the comparison results illustrate that the mean absolute errors for each key points are less than 700 mm. Contribution: This work contributes for human movement science by evaluating the OpenPose markerless 3D reconstruction pose with the marker-based motion-capture data recorded on pop dance motion.

关键词： Cameras Three-dimensional displays Videos Two dimensional displays Calibration Synchronization Pose estimation

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Factors that Influence Learning Experience through Game Based Learning using Visual Novel Game for Learning Pancasila

引用

Procedia computer science 2019年 157卷 353-359页

作者： J Andrew S Henry A.N. Yudhisthira Yulyani Arifin Syarifah Diana Permai Game Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Statistics Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Games are not only used as a means of entertainment but also can be used as a learning tool. Attractive learning tools can increase the interest of young people or millennial generations, especially for learning conceptual or too theoretical. Pancasila as the basis of the Indonesian nation’s life view needs to be understood by the Indonesian people, especially the younger generation. But the way of learning about the Pancasila is currently too theoretical and does not attract young people. Therefore, by making the game that is liked and favorited by young people today is used to study the Pancasila. Through this research the author wants to analyze the factors that can affect learning experience using game-based learning. Researchers use multiple linear regression methods to analyze these factors. The game prototype developed in this study uses the visual novel genre which has an interesting story. There are 101 respondents as samples. The analysis showed that there are two factors that influence game-based learning, namely the gameplay factor and the story of the game. So, it can be concluded that for developing game based learning we need to pay attention to these two factors and through this visual novel prototype game, it can be concluded that the prototype of this game has an interesting game play and a story that is easy to understand.

关键词： Game Based Learning Gamification Visual Novel Pancasila Regression Analysis

来源：评论

学校读者我要写书评

暂无评论

Database Management System Design with Time Series Modification for Child Growth and Malnutrition Monitoring in The Regency of Serdang Bedagai

Database Management System Design with Time Series Modificat...

引用

International Conference on Information Management and technology (ICIMTech)

作者： Reza Rahutomo Ika Nurlaila Anzaludin Samsinga Perbangsa Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia BINUS Online Learning Bina Nusantara University Jakarta Indonesia School of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

A poor data management has led zero stunting strategy in Indonesia moved nowhere. Some justifications on the demography and numbers of affected children remain a matter of plain assumptions without a clear supporting data. We hence develop a database system which enables time series monitoring on the expected increment of children's physical growth. At this initial step, our database system will be implemented at Public Health Office (Dinas Kesehatan) of Serdang Bedagai, South Celebes. This is a modification from Connoly and Begg's principles. Our database was built through 3-steps design started with conceptual followed by logical and at final step was normalizations-enriched physical design. By implementing this proposed system, the assigned healthcare workers will be able record every bit of superficial growth increase. Information obtained in the study is of essence for the efficient and effective intervention formula to achieve national zero stunting goal.

关键词： Pediatrics Monitoring Database systems Dictionaries Drugs Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Supervised sequential pattern mining of event sequences in sport to identify important patterns of play: an application to rugby union

arXiv

引用

arXiv 2020年

作者： Bunker, Rory Fujii, Keisuke Hanada, Hiroyuki Takeuchi, Ichiro RIKEN Center for Advanced Intelligence Project Tokyo Japan Graduate School of Informatics Nagoya University Aichi Nagoya Japan Department of Computer Science Nagoya Institute of Technology Aichi Nagoya Japan

Given a set of sequences comprised of time-ordered events, sequential pattern mining is useful to identify frequent subsequences from different sequences or within the same sequence. However, in sport, these techniques cannot determine the importance of particular patterns of play to good or bad outcomes, which is often of greater interest to coaches and performance analysts. In this study, we apply a recently proposed supervised sequential pattern mining algorithm called safe pattern pruning (SPP) to 490 labelled event sequences representing passages of play from one rugby team’s matches from the 2018 Japan Top League. We compare the SPP-obtained patterns that are the most discriminative between scoring and non-scoring outcomes from both the team’s and opposition teams’ perspectives, with the most frequent patterns obtained with well-known unsupervised sequential pattern mining algorithms when applied to subsets of the original dataset, split on the label. Our obtained results found that linebreaks, successful lineouts, regained kicks in play, repeated phase-breakdown play, and failed exit plays by the opposition team were identified as as the patterns that discriminated most between the team scoring and not scoring. Opposition team linebreaks, errors made by the team, opposition team lineouts, and repeated phase-breakdown play by the opposition team were identified as the patterns that discriminated most between the opposition team scoring and not scoring. It was also found that, by virtue of its supervised nature as well as its pruning and safe-screening properties, SPP obtained a greater variety of generally more sophisticated patterns than the unsupervised models that are likely to be of more utility to coaches and performance analysts. © 2020, CC BY.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Volatile Organic Components and MS-e-nose Profiles of Indonesian and Malaysian Palm Sugars from Different Plant Origins

引用

Chemosensors 2025年第5期13卷 155-155页

作者： Aldia Katherinatama Yonathan Asikin Ryo Amano Siti Hajar-Azhari David Yudianto Dhina Aprilia Nurani Widyahapsari I Wayan Rai Widarta Kensaku Takara Koji Wada Department of Bioscience and Biotechnology Faculty of Agriculture University of the Ryukyus Okinawa 903-0213 Japan United Graduate School of Agricultural Sciences Kagoshima University Kagoshima 890-0065 Japan Department of Food Science Faculty of Food Science and Technology Universiti Putra Malaysia Serdang 43400 Selangor Malaysia Department of Food Industry Quality Assurance Politeknik AKA Bogor Kota Bogor 16154 West Java Indonesia Study Program of Food Technology Faculty of Agricultural Technology Udayana University Kabupaten Badung 80361 Bali Indonesia

The volatile profiles of palm sugar, a traditional sweetener used in Southeast Asia, vary according to its geographic and botanical origin. This study investigated the volatile organic components (VOCs) of Indonesian and Malaysian palm sugars derived from Arenga pinnata, Nypa fruticans, and Cocos nucifera using solid-phase microextraction-GC-MS and MS-e-nose analyses. A total of 42 compounds were detected, including 12 Maillard reaction products, 10 esters, 8 alcohols, 5 ketones, 3 carboxylic acids, 3 phenols, and 1 aldehyde. The Indonesian palm (West Java) and nipa (Central Java) sugars contained VOCs of 39.45 and 38.49 µg/100 g palm sugar, respectively, whereas the Balinese palm and Malaysian coconut sugars contained significantly lower volatiles (18.56 and 11.41 µg/100 g, respectively). Hierarchical clustering and principal component analysis (PCA) revealed diverse composition profiles, with palm-derived sugars rich in pyrazines, nipa sugars dominated by carboxylic acids, and coconut sugars characterized by alcohols such as [R,R]-2,3-butanediol. PCA of the MS-e-nose analysis confirmed these variations, with PAR scaling enhancing their differentiation and providing valuable loading plots, including ion masses m/z 43 and 45 (hydrocarbons or carboxylic acids), m/z 60 (acetic acid), and m/z 108 (dimethyl-pyrazines). These findings highlight the influence of geography and plant origin on palm sugar VOCs, which may affect their sensory attributes.

关键词： palm sugar volatile compound MS-e-nose principal component analysis UV scaling PAR scaling

来源：评论

学校读者我要写书评

暂无评论

Multiplexed DNA detection with DNA tweezers in a one-pot reaction

引用

Materials science for Energy Technologies 2019年第3期2卷 503-508页

作者： Lertanantawong, Benchaporn Krissanaprasit, Abhichart Chaibun, Thanyarat Gothelf, Kurt Vesterager Surareungchai, Werasak Nanoscience and Nanotechnology Graduate Program Faculty of Science King Mongkut's University of Technology Thonburi Bangkok 10140 Thailand and Department of Chemistry Aarhus University DK-8000 Aarhus C Denmark Pilot Plant Development and Training Institute King Mongkut's University of Technology Thonburi Bangkok Thailand School of Bioresources and Technology King Mongkut's University of Technology Thonburi Bangkhuntien Campus Bangkok 10150 Thailand

One of the great challenges for the development of biosensors is to construct a fast, practical and multiplexed detection platform. One promising approach is utilizing the controllable conformation of DNA nanostructures for such biosensing applications. Here, we present tweezer-like DNA (TW-DNA)-assisted multiplexed DNA detection in a one-pot reaction based on fluorescence quenching. The open conformation of the TW-DNA structure can be changed to a closed state by a specific single-stranded DNA target. The fluorophore/quencher pairs decorated on the TW-DNA and the conformation changes were observed by fluorescence quenching. In its initial state, the TW-DNA is maintained in an open state that demonstrates high fluorescence intensity. In the presence of a specific target DNA, the TW-DNA changes to a closed conformation and the emission intensity of the donor is quenched which is directly proportional to the target concentration. Three DNA targets were simultaneously detected using three individually self-assembled TW-DNA that were modified appropriately with fluorophore/quencher pairs for the specific detection of the individual DNA target. The detection range of this assay is at submicromolar concentration of multiple DNA targets with a fast detection time of one minute. Moreover, this biosensor platform provides the significant advantage of being a one-pot reaction for multiplexed DNA detection without any cross-talk, thereby making it a highly applicable assay. © 2019

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

引用

Journal of the Formosan Medical Association 2024年第2期123卷 159-178页

作者： Lee, Pei-Lin Wu, Yen-Wen Cheng, Hao-Min Wang, Cheng-Yi Chuang, Li-Pang Lin, Chou-Han Hang, Liang-Wen Yu, Chih-Chieh Hung, Chung-Lieh Liu, Ching-Lung Chou, Kun-Ta Su, Mao-Chang Cheng, Kai-Hung Huang, Chun-Yao Hou, Charles Jia-Yin Chiu, Kuo-Liang Center of Sleep Disorder National Taiwan University Hospital Taipei Taiwan School of Medicine College of Medicine National Taiwan University Taipei Taiwan Division of Cardiology Cardiovascular Medical Center Far Eastern Memorial Hospital New Taipei City Taiwan School of Medicine National Yang Ming Chiao Tung University Taipei Taiwan Division of Faculty Development Taipei Veterans General Hospital Taipei Taiwan PhD Program of Interdisciplinary Medicine (PIM) National Yang Ming Chiao Tung University College of Medicine Taipei Taiwan Department of Internal Medicine Cardinal Tien Hospital and School of Medicine College of Medicine Fu Jen Catholic University New Taipei City Taiwan Sleep Center Department of Thoracic Medicine Chang Gung Memorial Hospital Linkou Taiwan School of Medicine Chang Gung University Tauyan Taiwan Division of Respirology Department of Internal Medicine Far Eastern Memorial Hospital New Taipei City Taiwan School of Nursing & Graduate Institute of Nursing China Medical University Taichung Taiwan Sleep Medicine Center China Medical University Hospital Taichung Taiwan Division of Cardiology Department of Internal Medicine National Taiwan University Hospital Taipei Taiwan Cardiovascular Center MacKay Memorial Hospital Taipei Taiwan Institute of Biomedical Sciences Mackay Medical College Taipei Taiwan Division of Chest Departments of Internal Medicine MacKay Memorial Hospital Taipei Taiwan MacKay Medical College New Taipei City Taiwan Division of Clinical Respiratory Physiology Department of Chest Medicine Taipei Veterans General Hospital Taipei Taiwan Sleep Center Division of Pulmonary and Critical Care Medicine Department of Internal Medicine Kaohsiung Chang Gung Memorial Hospital Kaohsiung Taiwan Department of Respiratory Care Chang Gung University of Science and Technology Chiayi Taiwan Kao-Ho Hospital Kaohsiung Taiwan Division of Cardiology Department of Internal Medicine E-Da Hospital Kaohsiung Taiwan Division of Cardio

Sleep disordered breathing (SDB) is highly prevalent and may be linked to cardiovascular disease in a bidirectional manner. The Taiwan Society of Cardiology, Taiwan Society of Sleep Medicine and Taiwan Society of Pulmonary and Critical Care Medicine established a task force of experts to evaluate the evidence regarding the assessment and management of SDB in patients with atrial fibrillation (AF), hypertension and heart failure with reduced ejection fraction (HFrEF). The GRADE process was used to assess the evidence associated with 15 formulated questions. The task force developed recommendations and determined strength (Strong, Weak) and direction (For, Against) based on the quality of evidence, balance of benefits and harms, patient values and preferences, and resource use. The resulting 11 recommendations are intended to guide clinicians in determining which the specific patient-care strategy should be utilized by clinicians based on the needs of individual patients. © 2023 Formosan Medical Association

关键词： Atrial fibrillation Continuous positive airway pressure Heart failure Hypertension Sleep disordered breathing

来源：评论

学校读者我要写书评

暂无评论

Forecasting Vegetation Health in the MENA Region by Predicting Vegetation Indicators with Machine Learning Models

Forecasting Vegetation Health in the MENA Region by Predicti...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Sachi Perera Wenzhao Li Erik Linstead Hesham El-Askary Computational and Data Sciences Graduate Program Schmid College of Science and Technology Chapman University Orange CA USA Schmid College of Science and Technology Chapman University Orange CA USA Fowler School of Engineering Chapman University Orange CA USA Faculty of Science Alexandria University Alexandria Egypt

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Machine learning (ML) techniques can be applied to predict and monitor drought conditions due to climate change. Predicting future vegetation health indicators (such as EVI, NDVI, and LAI) is one approach to forecast drought events for hotspots (e.g. Middle East and North Africa (MENA) regions). Recently, ML models were implemented to predict EVI values using parameters such as land types, time series, historical vegetation indices, land surface temperature, soil moisture, evapotranspiration etc. In this work, we collected the MODIS atmospherically corrected surface spectral reflectance imagery with multiple vegetation related indices for modeling and evaluation of drought conditions in the MENA region. These models are built by a total of 4556 and 519 normalized samples for training and testing purposes, respectively and with 51820 samples used for model evaluation. Models such as multilinear regression, penalized regression models, support vector regression (SVR), neural network, instance-based learning K-nearest neighbor (KNN) and partial least squares were implemented to predict future values of EVI. The models show effective performance in predicting EVI values (R 2 > 0.95) in the testing and (R 2 > 0.93) in the evaluation process.

关键词： Vegetation mapping MODIS Atmospheric modeling Remote sensing Predictive models Training Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Features Importance in Classification Models for Colorectal Cancer Cases Phenotype in Indonesia

引用

Procedia computer science 2019年 157卷 313-320页

作者： Tjeng Wawan Cenggoro Bharuno Mahesworo Arif Budiarto James Baurley Teddy Suparyanto Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 BioRealm LLC Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

Recently there has been an interest in predicting complex disease risk using models that combine the effects of many genetic factors together. These are known as polygenic models and are useful in evaluating risk of disease in patients. These models, however, often do not include important non-genetic factors that are important to the prediction of the disease. In this paper, we explore the prediction of colorectal cancer in Indonesia from non-genetic factors using common machine learning algorithms: XGBoost and Elastic Net. The result of this study identified 8 features with strong importance from both XGBoost and Elastic Net. We recommend including these features as covariates in future genetic association studies of colorectal cancer in Indonesia. Ultimately these models may be implemented as tools to screen patients for colorectal cancer risk.

关键词： Feature Importance Feature Selection XGBoost Generalized Linear Model Elastic Net Colorectal Cancer

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：