检索结果-内蒙古大学图书馆

Early Detection of Diabetes Mellitus using Feature Selection and Fuzzy Support Vector Machine

Procedia computer science 2019年 157卷 46-54页

作者： Rian Budi Lukmanto Suharjito Ariadi Nugroho Habibullah Akbar Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

The number of patients that were infected by Diabetes Mellitus (DM) has reached 415 million patients in 2015 and by 2040 this number is expected to increase to approximately 642 million patients. Large amount of medical data of DM patients is available and it provides significant advantage for researchers to fight against DM. The main objective of this research is to leverage F-Score Feature Selection and Fuzzy Support Vector Machine in classifying and detecting DM. Feature selection is used to identify the valuable features in dataset. SVM is then used to train the dataset to generate the fuzzy rules and Fuzzy inference process is finally used to classify the output. The aforementioned methodology is applied to the Pima Indian Diabetes (PID) dataset. The results show a promising accuracy of 89.02% in predicting patients with DM. Additionally, the approach taken provides an optimized count of Fuzzy rules while still maintaining sufficient accuracy.

关键词： Diabetes Mellitus Feature Selection Fuzzy Logic Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Applied artificial intelligence in healthcare research with bibliometric approach

引用

AIP Conference Proceedings 2023年第1期2865卷

作者： Fairuz Iqbal Maulana Dian Lestari Agung Purnomo Donna Carollina Computer Science Department School of Computer Science Bina Nusantara University 11480 Jakarta Indonesia School of Midwifery Faculty of Medicine Universitas Airlangga Surabaya Indonesia Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University 11480 Jakarta Indonesia Visual Communication Design Department School of Design Bina Nusantara University 11480 Jakarta Indonesia

Artificial intelligence (AI) in healthcare is becoming increasingly important, given its potential to optimize healthcare resources, such as generating and analyzing healthcare data, facilitating better patient experiences, increasing healthcare professional satisfaction, reducing per capita costs, and increasing population health. Most research focuses on the potential benefits and barriers of implementing AI in healthcare. At the same time, only a few describe rational research opportunities and trends for developing Applied Artificial Intelligence in Healthcare research. In this study, a graphical mapping of scientific publications and research trends in the Applied Artificial Intelligence in the Healthcare sector worldwide was conducted using biometric analysis. The Scopus database was used to collect information and conduct online analysis using the Scopus website. A demonstration of bibliometric network mapping was conducted using VOSViewer. The selection of articles starts by searching based on the desired keywords and year restrictions. Then the database was exported as RIS and CSV format files. Based on the search results from the Scopus database for the last five years, researchers obtained 492 scientific publications published between 2012 and 2021. We also use VOSViewer to map the network. According to the database, researchers in United States had the most published papers indexed by Scopus among the most prolific authors (N=98), with the India coming second (N=72) and the China third (N=48). This study recommends combining the research subjects of Applied Artificial Intelligence in Healthcare: Internet, Covid, Artificial Intelligence, Dataset, abbreviated with the ICAD research theme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Recent Advancements in Appearance-based Object Recognition

引用

Procedia computer science 2019年 157卷 613-620页

作者： Gede Putra Kusuma Evan Kristia Wigati Edward Chandra Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Appearance-based object recognition can be used in various applications such as human-computer interface and information retrieval. Therefore, many researchers compete with others to present their best in object recognition. Since object recognition has been studied for a long time and encompassed diverse approaches, therefore a review of the latest works is needed. This paper aims to deliver the trends in object recognition researches focusing on instance recognition and foreground detection such as salient object detection and object detection as supporting methods. Covering 34 publications, we survey the approaches, methods, datasets, performance measure, and experimental results. We also present research challenges in object recognition which can be used as suggestions for future works. We hope that our work can provide an overview of the current trends for object recognition and foreground detection methods.

关键词： Instance recognition Fine-grained recognition Foreground detection Salient object detection Object detection

来源：评论

学校读者我要写书评

暂无评论

Convolve4D: A Novelty Approach to Improve Convolutional Process

引用

IOP Conference Series: Earth and Environmental science 2021年第1期794卷

作者： Suryadiputra Liawatimena Edi Abdurahman Agung Trisetyarso Antoni Wibowo Wiedjaja Atmadja Fandy Effendi Ivan Sebastian Edbert Computer Science Department BINUS Graduate Program - Doctor ofComputer Science Bina Nusantara University Jakarta Indonesia 11480 ComputerEngineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia 11480 ComputerScience Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Convolutional neural networks (ConvNet or CNN) are deep learning algorithms that can process input images, assign meaning to various aspects or objects in the image (biases and learnable weight) and recognize one image from another. The bigger kernel size will take more time to process the *** present a novelty way to use a 4D rank tensor to improve a convolutional process. At the early stage of the Convolve4D development, the edge detection with 3×3 kernel and The Laplacian of Gaussian (LoG) with 5×5 kernel size was used to demonstrate the convolutional process improvement. The Convolve4D needs more elaboration to be used into a CNN algorithm. The advantage of convolve4D is only need 9 loops to calculate 81 outputs, whereas convolve2D need 9 × 9 × 3 × 1 × 7 × 7 = 11.907 loops. The result is 18.5% shorter when using a 5×5 kernel; it reduces from 0.54 seconds to 0.44 seconds for the edge detection convolution process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The sustainability of Batik tulis lasem through participatory rural appraisal (PRA) in the new motif design

引用

AIP Conference Proceedings 2023年第1期2594卷

作者： V. J. Basiroen I. B. K. Manuaba Graphic Design & New Media Program Visual Communication Design Department BINUS Northumbria School of Design Bina Nusantara University Jakarta Indonesia 11480 Computer Science Program Faculty of Computing and Media Bina Nusantara University Jakarta Indonesia 11480

Research activities carried out by researchers took place in Jeruk and Karas Kepoh Village, Pancur District, Rembang. Batik Tulis Lasem is the embodiment of the Javanese-Chinese cultural acculturation, which supports the socio-economic life of the Lasem community. Batik Lasem, which is part of the nation's cultural heritage, is currently experiencing a crisis period because there are no new designs that can attract young generation interest in this batik art. The decline in the interest of the younger generation to Batik Lasem raises two critical problems: the difficulty of regenerating Lasem entrepreneurs and the human resources of batik artisans who can produce batik motifs, and there is a threat of extinction Batik Lasem in the future. For this reason, genuine efforts are needed to design a sustainable design for Batik Lasem through the creation of new motifs. In the implementation of this research, the Participatory Rural Appraisal (PRA) method was used to act as facilitators to increase the competence of the artisans in the design motifs training, to produce new Batik Lasem motifs as a sustainable design and favored by the younger generation. At the end of this training, artisans in the two villages have successfully created sixteen batik cloth with new motifs based on local culture without losing the originality and characteristics of Batik Lasem. It is hoped that the new motif can become a new attraction and energy and a sustainable design in the life of the Batik Tulis Lasem industry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Weed Identification Using Machine Learning and Image Processing in Oil Palm Plantations

引用

IOP Conference Series: Earth and Environmental science 2022年第1期998卷

作者： Erick Firmansyah Teddy Suparyanto Alam Ahmad Hidayat Bens Pardamean Agricultural Engineering Department Institute of Agricultural STIPER Yogyakarta 55282 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

The effectiveness and efficiency of the operation of oil palm plantations are considered to be the most crucial factor to develop the productivity and profitability of the palm oil business. One of the major obstacles for the plants to optimally produce crops based on their capacity is caused by the presence of noxious weeds in the plantation area. However, weed control via chemical processes may potentially harm the surrounding environment if it is not properly managed. Therefore, an automatic system to assist the farmers to identify and control the weeds is required to minimize harmful impacts on the environment. Machine Learning (ML) and Artificial Intelligence (AI)-based systems provide powerful tools to perform such tasks. In this work, we aim for an ML-based system design to perform an automatic weed recognition task. The methodology can provide an effort for environmental sustainability in oil palm plantations. The weed identification involves the description, the local names, and tolerance class of the weeds as well as suggestions to control them. The flow of this work consists of weed and herbicide data acquisition, data labeling, model configurations, and data training. Further, the proposed system can be adopted as an android-based application in mobile devices that can deploy the trained model to predict weed category in both real-time and non-real-time tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart IoT CPO Storage Tank

引用

IOP Conference Series: Earth and Environmental science 2022年第1期998卷

作者： Rengga Arnalis Renjani Hermantoro Prima Okta Adi Nugraha Kartika Purwandari Teddy Suparyanto Bens Pardamean Department of Agricultural Engineering Institute of Agriculture STIPER Yogyakarta Indonesia 55281 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

Indonesia's crude palm oil (CPO) production from year to year continues to increase, at the end of 2020 it reached 17.35 million tons, up 3.6% from the previous year. Increasing production will result in more CPO stock and require good storage. The storage process that occurs is to maintain the temperature of the CPO so that the quality is not damaged. This temperature regulation is still done manually and raises the risk of work accidents. The purpose of this research is to create a temperature control system and automatic volume measurement that can be monitored from a smartphone. The manufacture of a control system used ESP8266 NodeMCu microcontroller, temperature sensor, proximity sensor, and 1000-Watt heater. programming used the Arduino IDE and C++. The result of this study was an IoT CPO Storage Tank design equipped with sensors and microcontrollers. The temperature was measured with the DS18B20 sensor had a data accuracy of 99.19% while the volume measured with the HC-SR04 sensor had an accuracy of 99.78%. Data obtained from the sensor could be seen through the Thingspeak application from a computer or smartphone.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiple-Clustering Comparison in Spatial Data for Additional Accuracy Measurement in Land-use Classification

Multiple-Clustering Comparison in Spatial Data for Additiona...

引用

International Conference on Informatics and Computing (ICIC)

作者： Herlawati Yaya Heryadi Harco Leslie Hendric Spits Warnars Ford Lumban Gaol Edi Abdurachman Benfano Soewito BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

Satellite imageries have been widely used to analyze a region by planners. Data from the satellite usually have lower accuracy than other expensive methods e.g. drone, aerial view, etc. However, the data from satellite have wide range area and sufficient enough for modeling a land use. The accuracy assessment, therefore, becomes a vital task to ensure the model from the satellite imagery meets the minimum requirement. Validating the classification result by comparing to the real location or by other higher resolution images is needed. The paper proposed additional validation by comparing the classification result by another result in different date through the cross-tabulation method. Two satellite imageries in the same year were processed before classification to get the land-use and land-cover classification. Comparing two land-use classified images gave the accuracy statistics using cross-tabulation. The kappa statistic and accuracy showed the classification performance of 0.7592 that similar to the sampling-based accuracy assessment (0.75390). Therefore, the proposed method was appropriate as the accuracy assessment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scoring Urban Sustainability as a Guidance and Self-Learning for City Planners

Scoring Urban Sustainability as a Guidance and Self-Learning...

引用

International Congress on Applied Information Technology

作者： Herlawati Yaya Heryadi Agung Trisetyarso Wayan Suparta Chul Ho Kang Bahtiar Saleh Abbas BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728158624

ISBN: (纸本)9781728158631

City planners worldwide have tried to develop their cities following the concept of sustainable development. To allocate land use properly, the zoning method has been widely used, especially in densely populated cities, namely a kind of sustainable urban form with considers the mix of use/diversity of land use to minimize travel distance. This study proposes a method for calculating how much a city meets the sustainable urban forms based on compact city criteria, i.e. compatibility, dependency, and compactness. After the survey filling in compatibility and dependency scores for each land use, and compactness was calculated for each sub-district. Fuzzy C-Means clustering was used to cluster the result to classify other areas. In addition, this method can be used by planners to check whether their plans meet the concept of sustainable development or not.

关键词： Urban areas Sustainable development computer science Education Matrix converters Hospitals

来源：评论

学校读者我要写书评

暂无评论

Prediction Diabetes Mellitus Using Decision Tree Models

Prediction Diabetes Mellitus Using Decision Tree Models

引用

International Congress on Applied Information Technology

作者： Aswan Supriyadi Sunge Harco Leslie Hendric S. Warnar Yaya Heryadi Edi Abdurachman Benfano Soewito Ford Lumban Gaol BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728158624

ISBN: (纸本)9781728158631

Health is an essential thing in human life, but Indonesian people are still far from the word healthy lifestyle. One disease that can be caused by an unhealthy lifestyle is diabetes mellitus that can cause many deaths. So far, there are many data in the hospital, but the data can not be maximized well even if it can be used to predict diabetes. The need for accuracy to produce better results. In conducting this test, the results obtained using C 4.5 only algorithm is 72.08%.

关键词： Diabetes Data mining computer science Classification algorithms Diseases Decision trees Testing

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：