检索结果-内蒙古大学图书馆

Generating Lymphoma Variability Through Adversarial Generation Models: A Limited Resource Approach for Synthetic Histopathology Image Generation and Classification

SSRN

引用

SSRN 2024年

作者： Tiwari, Ashutosh Saudarshan, Harsh Krisnawati, Dyah Ika Khafid, Muhamad Wardani, Erika Martining Mutalik, Chinmaya Chen, Chi-Long Kuo, Tsung-Rong International Ph.D. Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Department of Computer Science and Engineering Guru Ghasidas Vishwavidyalaya Chhattisgarh Bilaspur495509 India Department of Nursing Faculty of Nursing and Midwifery Universitas Nahdlatul Ulama Surabaya East Java Surabaya60237 Indonesia Graduate Institute of Nanomedicine and Medical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Department of Pathology School of Medicine College of Medicine and Taipei Medical University Hospital Taipei Medical University Taipei11031 Taiwan International Master/Ph.D. Program in Medicine College of Medicine Taipei Medical University Taipei11031 Taiwan Precision Medicine and Translational Cancer Research Center Taipei Medical University Hospital Taipei11031 Taiwan Tulane University United States Graduate Institute of Clinical Medicine Taiwan

Lymphomas, a diverse group of blood cancers originating from the lymphatic system, present significant challenges for diagnosis and treatment due to their morphological and genetic differences. These variability obscures the development of personalized therapies and impacts disease outcomes. The scarcity of high-quality, diverse images of lymphoma cells is further hindered by patient privacy concerns, the rarity of certain types, and logistical challenges of collecting and processing biomedical images. Additionally, the costs and technical difficulties of microscopic imaging limit the scope of research. This paper addresses these challenges by utilizing generative adversarial networks (GANs) to generate synthetic yet realistic images of lymphoma histopathology and classify them in a low resource setting. Focusing specifically on chronic lymphocytic leukemia (CLL), follicular lymphoma (FL), and mantle cell lymphoma (MCL), we employed GANs to enhance the understanding of lymphoma variability and support advancements in digital cancer biology and pathology. This dual approach of image generation and classification aims to improve disease diagnosis and prognosis, ultimately contributing to better patient outcomes. © 2024, The Authors. All rights reserved.

关键词： Lung cancer

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

Model Decision Support System For Diagnosis COVID-19 Using Forward Chaining: A Case in Indonesia

Model Decision Support System For Diagnosis COVID-19 Using F...

引用

International Conference on Cyber and IT Service Management (CITSM)

作者： Henderi Miftah Maulana Harco Leslie Hendrie S. Warnars Didik Setiyadi Taufik Qurrohman University of Raharja Tangerang Indonesia BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Bina Insani University Bekasi Indonesia

ISBN: (数字)9781728177014

ISBN: (纸本)9781728177021

The government in Indonesia and its staff work together to make tactical steps to prevent the spread of COVID-19 in the community. From the ministerial level to the heads of the provinces, regencies, and even the government. Therefore, this study aims to make a model decision support system to diagnose patients exposed to Covid-19, such as people in control, patients in oversight, and those who are positive for the Covid-19 Virus. Model decision support system development aims to provide information about the development of COVID- 19 and help the community in diagnosing themselves related to COVID-19 infection. In this study, the authors use the forward chaining method in application to get conclusions from the symptoms of the Covid-19. This research resulted in an application that patients exposed to the Covid-19, and it's also provided a solution for healing from patients. And this could be a reference for patients before consulting further with the doctor.

关键词： COVID-19 History Expert systems Viruses (medical) Decision support systems Lung Informatics

来源：评论

学校读者我要写书评

暂无评论

*** as digital platform for vegetation analysis and estimation of carbon stock in KEHATI aqua park

引用

AIP Conference Proceedings 2024年第1期3026卷

作者： Nanda Satya Nugraha Dian Pratama Putra Mohammad Prasanto Bimantio Amallia Ferhat Rama Zakaria Rudi Nirwantono Teddy Suparyanto Bens Pardamean Faculty of Forestry Institute of Agriculture STIPER Yogyakarta Indonesia 55282 Faculty of Agriculture Institute of Agriculture STIPER Yogyakarta Indonesia 55282 Faculty of Agricultural Technology Institute of Agriculture STIPER Yogyakarta Indonesia 55282 PT. Tirta Investama Pabrik Klaten Klaten Central Java Indonesia 57474 Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia 1148 Biotechnology Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

KEHATI AQUA Park is one of the green areas managed by PT. Tirta Investama Klaten (Klaten Factory). This area is located in Wangen and Ponggok Villages, Polanharjo District, Klaten Regency, Central Java, and is an integral part of the company’s seriousness in carbon reduction movement. When maintenance of the area is important for the sustainability of the park, there is however no data on the trees inventory in the area. Therefore, this study aims to invent the trees at KEHATI AQUA Park and evaluate the potential of the area to become a carbon sink using *** application. This study was conducted at the KEHATI AQUA Park. The census method was performed to collect tree data, and the result was recorded in *** application. The carbon stock calculation was estimated using the application according to the tree data submitted in the application. The study included a total of 1048 plantation spots in 51 tree species. From those numbers, about 738 trees existed, and the remaining spots were blank spaces. Based on the condition of the trees, those were 660 good trees, 17 dry trees, and 61 under pest infection. The carbon stock estimation at KEHATI AQUA Park Klaten in the next five years (2026) is around 40 tons of carbon. Therefore, it can be concluded that the park is valuable as an area to preserve biodiversity and as a carbon sink.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measure The Level Of Success In Using Google Drive with the Kuder Richardson (KR) Reliability Method

Measure The Level Of Success In Using Google Drive with the ...

引用

International Congress on Applied Information Technology

作者： Andi Nugroho Harco Leslie Hendric Spits Warnars Yaya Heriyadi Lukas Tanutama Mercu Buana University and Binus Graduate Program - Doctor of Computer Science Jakarta Indonesia Binus Graduate Program - Doctor of Computer Science Jakarta Indonesia

ISBN: (数字)9781728158624

ISBN: (纸本)9781728158631

The Google Sheets is a cloud technology part of Google Drive. Google Drive is a cloud operating system owned by Google's search engine. National Elementary School (SDN) to make a report book or Basic Education Databook (Dapodik) still use Microsoft Excel, which has the effect of delaying the delivery of report results to parents. This happens because to fill in the DAPODIK score must be filled by teachers who teach subjects in class. This study aims to provide knowledge to teachers in collaborating to fill DAPODIK and measure how reliable the delivery of material received by each teacher. Using the method of reliability Kuder Richardson KR-20 and KR-21 produces a value before the training on reliability values KR-20 = 0.6328, and KR-21 = 0.6000, after the training, the reliability values KR-20 = 0.5788 and KR-21 = 0.6231. From these results, it is known that the value after training for KR-21 has increased and according to the conventional correlation coefficient. In future research can be re-developed by making application system recommendations in determining teachers in schools to become instructors in accordance with the capabilities possessed based on the reliability testing results of the KR-20 and KR-21.

关键词： Reliability Training Google Testing Collaboration computer science Correlation

来源：评论

学校读者我要写书评

暂无评论

An Agile Implementation Model for ERP 4

An Agile Implementation Model for ERP

引用

4th International Conference on Information Management and Technology, ICIMTech 2019

作者： Wijaya, Santo Fernandi Prabowo, Harjanto Kosala, Raymondus Raymond Meyliana Information Systems Department Computer Science Department Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Doctor of Computer Science Management Department Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

The growing impact of industrial dynamics will be a challenge to increase productivity. Productivity is a demand for improving organizational performance. ERP systems are a way to increase productivity. Therefore, ERP implementation is important to ensure that ERP runs well. Critical factors in ERP implementation must get serious attention to project management. Even so, the reality of ERP implementation is slowly, even tends to experience failure, resulting in highly expensive. The previous research that carried out ERP implementation showed that the failure reached 40%, and the achievement of the benefits of ERP implementation in Indonesia is still not optimal. It can be said that ERP implementation is a complexity project. For this reason, it is necessary to consider other implementation methods that can overcome the problem in implementing ERP. An agile method is a proactive and reactive alternative to handle the problem in implementing of ERP. The development of an agile ERP model is one way to achieve success in ERP implementation. This research methodology is a survey approach to the study of literature. This research will propose an agile ERP model which will be used as an effective guide for achieving the success of ERP implementation. © 2019 IEEE.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

Optimum Nutrition Intake from Daily Dietary Recommendation for Indonesian Children using Binary Particle Swarm Optimization Algorithm

引用

Procedia computer science 2019年 157卷 16-24页

作者： Fanny Lili Ayu Wulandhari Sani Muhamad Isa Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Optimum nutrition intake in daily dietary habit has a significant role for children growth. Nevertheless, the mistakenness in the fulfillment of nutrition still concerned. It happens because an individual does not have much knowledge about the energy content of food and food combination to meet the nutrition requirement. The objectives of this research are to facilitate an individual to obtain the optimum nutrition intake from their daily dietary habit. This paper proposes a Binary Particle Swarm Optimization (BPSO) algorithm to find the optimum combination of food portion and food option for an individual daily dietary habit. The food data is obtained from ’Tabel Komposisi Pangan Indonesia ’ book which contains more than 1600 kind of Indonesian food. The results show that BPSO provides an optimum nutrition intake accuracy of 99.14%. Moreover, the nutritionist is already validated that this experiment is succeed in recommending a variation of daily dietary habit that meet an optimum nutrition intake for an individual. Based on this result it can be conducted that BPSO can provide the better accuracy of optimum nutrition intake than Genetic Algorithm (GA), while GA can only provide an optimum nutrition intake accuracy of 97.87%.

关键词： Optimum nutrition Energy requirement Energy intake Dietary habit recommendation Binary Particle Swarm Optimization

来源：评论

学校读者我要写书评

暂无评论

Detection Traffic Congestion Based on Twitter Data using Machine Learning

引用

Procedia computer science 2019年 157卷 118-124页

作者： Muhammad Taufiq Zulfikar Suharjito Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Twitter is one of the social media with text and image information that can be used as a source of information to detect traffic congestion in real-time. This study developed a system to detect traffic congestion in Indonesia, especially DKI Jakarta. The system displays the direction of the street according to the name of the street being passed and from each of the names of the streets, resulting in a tweet from the classification. The proposed method uses the Support Vector Machine (SVM) classification with the sigmoid kernel. This study shows that the SVM classification with the sigmoid kernel (libSVM) has an accuracy rate of 96.24% and that was increased by 2.68% when compared to SVM dot (mySVM). Based on the evaluation result of the proposed system compare to google maps application on detecting traffic congestion, the system could find a similar condition as many as 17 times from 25 of testing.

关键词： Traffic Congestion Text Classification Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Prediction Methods for Credit Default on Peer to Peer Lending using Machine Learning

引用

Procedia computer science 2019年 157卷 38-45页

作者： Netty Setiawan Suharjito Diana Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Social lending or peer to peer lending (p2p lending) has emerged as a viable digital platform where lenders and borrowers can do business without the involvement of financial institutions. P2p lending has gained significant momentum recently, with some platform has reached billion-dollar loan circulation. However, p2p lending platforms are not free from any form of risks. A higher return on investment for investor comes with a risk of the loan and interest not being repaid. For this purpose, this research proposes a tree-based classification method for predicting whether a loan will go bad or default before the loan is approved. The high dimensionality of the dataset needs to be processed and chosen carefully. This paper proposes a Binary PSO with SVM to perform feature selection for the dataset and Extremely Randomized Tree (ERT) and Random Forest (RF) as the classifiers. In this research, BPSOSVM-ERT and BPSOSVM-RF are compared with several performance metrics. The experimental results show BPSOSVM can produce subset of features without decreasing the performance from the original features and ERT can outperform RF in several performance metrics.

关键词： P2P lending Random forest Extremely randomized tree PSO BPSO

来源：评论

学校读者我要写书评

暂无评论

The Implementation of Isolated Geothermal Grid on the Community Cuisine Learning in Rural Area in North Sumatera

The Implementation of Isolated Geothermal Grid on the Commun...

引用

International Conference on ICT For Smart Society (ICISS)

作者： Ford Lumban Gaol Meyliana Winanti Harjanto Prabowo Fonny Hutagalung BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Jalan Universiti Kuala Lumpur Wilayah Persekutuan Malaya University Kuala Lumpur Malaysia

ISBN: (数字)9781665404228

ISBN: (纸本)9781665404235

Hutajulu is a village of 450 households with a minigrid supplied solely by a 45kW geothermal system. The problems that happened is the very low performance of the grid interactions between energy use and grid operating practices when the areas are in the dry season. We also found that the weak. We use the approached with the Design Research that will adopt for modelling approached of the experiment on the Grid performance. The experiment results are shown that to reduce the consumption of the firewood for eight households, we adopt four types of electric cookstove that use the geothermal. We also investigate the interaction between the electric cookstove and the power system. We also found that The effects of the power system and the electric stoves on the cooking preferences is also revealed.

关键词： computer science Generators Maintenance engineering Turbines Resistance heating Medical services Energy consumption

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：