检索结果-内蒙古大学图书馆

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Trinugroho, Joko Pebrianto Hidayat, Alam Ahmad Isnan, Mahmud Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Department of Mathematics School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

Lactose intolerance is a type of digestive problem that may threaten the population because milk and dairy products compose of nutrients that are essential for human body. Genetic tests possess a great potential to detect lactose intolerance as it can be used in children and even infants. However, a new approach to analyze the genetic test results is needed to elucidate the Single Nucleotide Polymorphisms (SNPs) that are related to lactose intolerance. In this work, we utilized the machine learning based feature selection to select the SNPs associated with lactose tolerance trait from genotyping samples of direct-to-customer (DTCG genetic tests, obtained from the public database. Recursive Feature Elimination (RFE) with XGBoost model was used to perform feature selection. We also compared three different models, such as XGBoost, support vector machine (SVM), and random forest (RF) for training the selected features. Our findings revealed that 20 SNPs (out of 3501) were chosen, with rs4394668 as the most important variables (F-score 0.009). Furthermore, when compared to the RF and SVM models, the XGBoost model had the highest accuracy (0.87). Further studies should be undertaken to elucidate how the selected SNPs may lead to the lactose intolerance trait. © 2023 The Authors. Published by Elsevier B.V.

关键词： feature selection genetic test lactose intolerance SNP

来源：评论

学校读者我要写书评

暂无评论

Influence of Feature Extraction Methods using Neighborhood Component Analysis (NCA) to Improve Classification Performance for Hepatitis C Disease 9

Influence of Feature Extraction Methods using Neighborhood C...

引用

9th International Conference on Informatics and Computing, ICIC 2024

作者： Setiawan, Christiella Abinosy Anggreainy, Maria Susan Fitriawati, Nora Lucky, Raymasterio Vera Sabrina, Renatha Dewi Matthew, Steven Wijayanti, Vierdaria Bina Nusantara University School of Computer Science Computer Science Department Jakarta 11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta 11530 Indonesia Bina Nusantara University Binus Online Learning Information Systems Department Jakarta 11530 Indonesia

ISBN: (纸本)9798331517601

Research in the development of Hepatitis C disease prediction is increasingly developing, especially using machine learning models which is able to make predictions quickly and accurately. In this study, a comparison of several classification methods was carried out by also applying feature reduction, NCA. In this study, a comparison of performance was carried out if the data was entered into the NCA feature extraction method with KNearest Neighborhood (KNN) and Support Vector Machine (SVM) and a comparison of performance if the data did not use the NCA feature extraction method. The performance comparison metrics used in the study were accuracy, sensitivity, specification, Matthews Correlation Coefficient (MCC), and Kappa value. The highest accuracy (99.36%), sensitivity (91.94%), specification (99.67%), MCC (0.895) and the best Kappa value (0.889) were obtained in the KNN-NCA prediction method. © 2024 IEEE.

关键词： Hepatitis C Disease KNN NCA Prediction SVM

来源：评论

学校读者我要写书评

暂无评论

The Country's Implementation and Adoption of Standardized Health Terminologies to Promote Interoperability: A Systematic Literature Review 8

The Country's Implementation and Adoption of Standardized He...

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Sitompul, Taufiq Hendric Spits Warnars, Harco Leslie Meyliana Hidayanto, Achmad Nizar Prabowo, Harjanto Bina Nusantara University Binus Graduate Program - Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Universitas Indonesia Faculty of Computer Science Depok16424 Indonesia Binus Business School Undergraduate Program Bina Nusantara University Management Department Jakarta11480 Indonesia

ISBN: (纸本)9798350326093

Modern healthcare systems demand comprehensive information systems but face obstacles during adoption. Organizational and structural complexity, especially decentralized systems, challenges the integrated management and sharing of data across information systems. Interoperability is critical to address these issues effectively in heterogeneous and distributed environments. However, different medical terminology hinders interoperability within health information systems. To address this, a systematic literature review examined various medical terminology standards for national interoperability. From 790 articles, 12 were selected according to PRISMA guidelines with inclusion and exclusion criteria. Standard health terminology is critical to achieving interoperability, and many countries have adopted it, although some have required adaptation to accommodate local contexts. Data models, governance, and maintenance of standards are equally important in achieving national interoperability. In addition, standardized health terminology promotes consistency and uniformity in terminology, which is beneficial for decision-making by stakeholders in the health system. © 2023 IEEE.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Leveraging ChemBERTa Robustness in Drug-Drug Interaction Classification via Molecular Decomposition 7

Leveraging ChemBERTa Robustness in Drug-Drug Interaction Cla...

引用

7th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2024

作者： Kenneth, Christian Imani, Alyssa Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331519643

Understanding drug-drug interactions (DDIs) can benefit us by enhancing drug effectiveness and preventing side effects that arise from consuming multiple drugs administered together. However, as the number of novel drugs increases, predicting potential DDIs becomes more challenging. Previous studies have used the molecular language model ChemBERTa to predict potential DDIs, but the predictions were only tested on unseen drugs and not dissimilar drugs, while also performing poorly. In this study, we demonstrate that a simple molecular preprocessing method using BRICS decomposition can enhance ChemBERTa robustness in predicting potential DDIs for unseen-dissimilar drugs. Specifically, we employ fragmentation with a minimum fragment size of 5 (BRICS-5), which balances the number of fragments and decomposition speed. Using this method, we were able to improve ChemBERTa robustness, reflected by an approximate increase of 1.5% in recall and 2.2% in the f1-score compared to non-decomposed molecules. Our findings suggest that this preprocessing method could be useful in the development of future AI-based approaches for solving challenging molecular tasks across different settings and various model architectures. © 2024 IEEE.

关键词： BRICS ChemBERTa data preprocessing drug-drug interactions robust multiclass

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

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

Developer-Centric Task Allocation: An Intelligent Approach for Enhanced Software Productivity 15

Developer-Centric Task Allocation: An Intelligent Approach f...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Fensterseifer Filho, Evandro L. R. Assuncao, Joaquim V. C. Fontoura, Lisandra M. Federal University of Santa Maria - Ufsm Graduate Program in Computer Science RS Santa Maria Brazil Federal University of Santa Maria - Ufsm Applied Computing Department RS Santa Maria Brazil

ISBN: (纸本)9798350368833

Software projects are affected by technical knowledge as well as the personality of the team. Such factors can reduce or increase the software quality and development speed. For successful task allocation, it is essential to consider the skills and profile of each developer, thus maximizing their productivity. In projects with large teams, task allocation can be challenging, and the help of tools can facilitate its execution. In this work, we propose an intelligent approach for allocating software development tasks suitable to the profile of developers. From the literature, we define the appropriate skills and technical profiles for a development team, and the assessment is based on the developer completing a questionnaire. We developed a recommendation system to suggest tasks to be allocated to developers, employing text processing techniques. For validation, 495 tasks were used from an actual project developing simulator software for military training. The recommended allocations were evaluated by the project developers and used to improve the system. Validations showed that the developed approach makes consistent and coherent task recommendations to developers according to the developer profile, as participants agree with the recommendation for 76% of tasks. © 2024 IEEE.

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Detecting Bipolar Disorder based on Crowdsourced Symptoms using Machine Learning with Shapley Additive Explanations 9th

Detecting Bipolar Disorder based on Crowdsourced Symptoms us...

引用

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

作者： Martawidjaja, Marvel Lefrandt, Matthew Paramita, Ni Luh Putu Satyaning Pradnya Zhan, Rongfang Komalasari, Renata Kurniadi, Felix Indra Sihotang, Erna Fransisca Angela Anggreainy, Maria Susan Cahyono, Dwy Bagus Jati, Putu Hadi Purnama Computer Science Department School of Computer Science Bina Nusantara University Jakarta11530 Indonesia Department of Rehabilitation and Health Services University of North Texas Denton76203 United States College of Nursing Pennsylvania State University State College16802 United States Statistics Department School of Computer Science Bina Nusantara University Jakarta11530 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11530 Indonesia Meta Lab Jakarta10310 Indonesia

Bipolar disorder is a mental health condition characterized by extreme mental states ranging from manic highs to depressive lows. Early intervention is crucial to prevent progression and complications of bipolar disorder, which can lead to significant loss. This study proposes a framework to detect bipolar disorder based on crowdsourced symptoms in the form of free texts. We extract the features by transforming these free-text symptoms into binary features using a set of natural language processing techniques. We build support vector machine models with different kernel functions and penalized logistic regression models with different penalty functions, where the best models have a precision of 0.7, recall of 0.78, F1 score of 0.74, and accuracy of 0.88. Moreover, the models are explainable since we incorporate a model-agnostic explanation method called Shapley additive explanations to understand the symptoms that mostly contributed to the prediction of bipolar disorder. The models presented in this study can be implemented in the initial screening process of bipolar disorder for further examination. © 2024 The Authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Spectral Learning of Shared Dynamics Between Generalized-Linear Processes 38

Spectral Learning of Shared Dynamics Between Generalized-Lin...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Oganesian, Lucine L. Sani, Omid G. Shanechi, Maryam M. Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA United States Ming Hsieh Department of Electrical and Computer Engineering Thomas Lord Department of Computer Science Alfred E. Mann Department of Biomedical Engineering Neuroscience Graduate Program University of Southern California Los AngelesCA United States

Generalized-linear dynamical models (GLDMs) remain a widely-used framework within neuroscience for modeling time-series data, such as neural spiking activity or categorical decision outcomes. Whereas the standard usage of GLDMs is to model a single data source, certain applications require jointly modeling two generalized-linear time-series sources while also dissociating their shared and private dynamics. Most existing GLDM variants and their associated learning algorithms do not support this capability. Here we address this challenge by developing a multi-step analytical subspace identification algorithm for learning a GLDM that explicitly models shared vs. private dynamics within two generalized-linear time-series. In simulations, we demonstrate our algorithm's ability to dissociate and model the dynamics within two time-series sources while being agnostic to their respective observation distributions. In neural data, we consider two specific applications of our algorithm for modeling discrete population spiking activity with respect to a secondary time-series. In both synthetic and real data, GLDMs learned with our algorithm more accurately decoded one time-series from the other using lower-dimensional latent states, as compared to models identified using existing GLDM learning algorithms. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequence to Sequence Deep Learning Architecture for Forecasting Temperature and Humidity inside Closed Space 10

Sequence to Sequence Deep Learning Architecture for Forecast...

引用

10th International Conference on Cyber and IT Service Management, CITSM 2022

作者： Setiawan, Karli Eka Elwirehardja, Gregorius Natanael Pardamean, Bens Bina Nusantara University Binus Graduate Program Computer Science Program Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia

ISBN: (数字)9781665460743

ISBN: (纸本)9781665460743

Solar Dryer Dome (SDD), an agricultural facility for drying and preserving agricultural products, needs a smart ability to predict the future indoor climate accurately, including indoor temperature and indoor humidity, in order to optimize electricity usage. To overcome these challenges, deep learning has been a widely adopted method. This research aims to forecast the future indoor climate using time series data by implementing a sequence-to-sequence (seq2seq) architecture, which is mostly used in Natural Language Processing (NLP) tasks. The two proposed seq2seq models, Long Short-Term Memory (LSTM) seq2seq and Gated Recurrent Unit (GRU) seq2seq, have proven to be superior to the adapted LSTM and GRU. The results show that the seq2seq GRU model outperforms the adapted GRU baseline model by an average difference of 0.03013 in MAE and the seq2seq LSTM model outperforms the adapted LSTM baseline model by an average difference of 0.00941 in MAE. To the best of our knowledge, this is the first implementation of seq2seq models for indoor climate forecasting on the Room Climate dataset. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enhancing Interoperability of Digital Twin in the Maintenance phase of Lifecycle 6

Enhancing Interoperability of Digital Twin in the Maintenanc...

引用

6th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2022

作者： Ariansyah, Dedy Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Centre Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350399615

In today's digitalization era, asset management has evolved following the rapid adoption of information systems and digital technologies. In the maintenance phase of the asset, Digital Twin (DT) emerges as an effective approach to improve failure recognition and structural damage prediction through DT-driven Prognostic and Health Monitoring (PHM). As a result, DT allows asset manager to proactively plan maintenance strategy to improve the availability of the assets. However, to reduce asset downtime in a cost-effective and time efficient manner, DT for maintenance phase needs to be integrated with other software systems that manage the provision of maintenance service and spare part such as computerized maintenance management system (CMMS) or Enterprise Resource Planning (ERP). Nevertheless, many of the developed DT in PHM were not equipped with semantic data model and hence, lacks interoperability with other systems (e.g., other DT or non-DT system) and limits the effective use of the DT. To qualify as an effective DT, it needs a semantical-enabled interface to connect with data and models from various domain to enable DT-driven decision-making. This paper leverages a rule-based ontology reasoning model to enhance DT interoperability with other maintenance software systems. The results depicts that the developed model paves a way for an effective use of DT-driven system in asset maintenance management. © 2022 IEEE.

关键词： CMMS Digital Twin ERP Maintenance Ontology

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：