检索结果-内蒙古大学图书馆

24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023

作者： Miranda, Eka Madyatmadja, Evaristus Didik Sano, Albert Verasius Dian Alvand, Khalfani Wijaya, Marcel Pretycia, Valen Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350313956

According to WHO, cardiovascular illnesses are the main cause of death globally, killing 17.9 million people every year. Machine learning analysis of patients' Electronic Medical Records (EMR) data was helpful for disease risk prediction. Goal of our research was for constructing machine learning-based prediction model for atherosclerotic heart disease prediction. This research investigated machine learning algorithms, namely AdaBoost, Random Forest and Naive Bayes. The study began with data collection based on the electronic medical records from Harapan Kita National Heart Center patients from the period of 2016-2021. Data pre-processing produced 4691 records for dataset. Discussion with a medical professional was used to select the features predictions, which were thrombocyte, khermchc, erythrocyte, hematocrit, hermch, hemoglobin, age, leukocyte, and gender. The outcomes revealed AdaBoost reached the utmost ROC AUC score (68%), followed by Naive Bayes (66%) and Random Forest (56%). Subsequently we used Shapley Additive Explanations (SHAP) and beeswarm plot to reveal information-dense summary, to interpret the prediction result and to describe how each attribute affected the prediction model. We revealed that thrombocyte was the most important feature for the prediction model. This research contributed by paving the way a framework for predicting and improved the information-dense summary of arteriosclerosis heart disease prediction model. © 2023 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Waste Classification with YOLOv8 Models for Efficient and Accurate Sorting

引用

Procedia computer science 2024年 245卷 889-895页

作者： Deverel Vieri Rendy Susanto Eko Setyo Purwanto Muhamad Keenan Ario Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Mobile Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

As of 2023, Indonesia ranks as the second largest waste-producing country globally. The waste produced is not segregated properly, leading to the vast amount of waste piling up in local landfills. Traditional methods, such as manual sorting, have been widely used to segregate waste but suffer from inefficiencies and inaccuracies. In contrast, deep learning models offer an alternative solution for waste classification, overcoming the limitations of traditional methods. A deep learning approach using YOLOv8 was proposed to classify waste into six distinct categories. Three different YOLOv8 variants: nano, small, and medium, are trained after the dataset has been augmented into 3,500 labeled images. The results indicate that these models were able to achieve high accuracy in classifying images, with the nano variant having the least training time and an accuracy of approximately 89%.

关键词： Waste Classification Waste Management Artificial Intelligence Machine Learning Deep Learning Convolution Neural Network YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Usefulness of Honeypots Towards Data Security: A Systematic Literature Review

Usefulness of Honeypots Towards Data Security: A Systematic ...

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Silaen, Kalpin Erlangga Meyliana, Meyliana Warnars, Harco Leslie Hendric Spits Prabowo, Harjanto Hidayanto, Achmad Nizar Anggreainy, Maria Susan Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta Indonesia Universitas Indonesia Faculty of Computer Science Department of Information System Depok Indonesia

ISBN: (纸本)9798350382914

The increasing data volume given by the exponential growth of digital devices, cloud platforms, and the Internet of Things (IOT) had become an attractive target for attackers. This makes the search for innovative defense mechanisms intensified leading to a renewed focus on the utilization of honeypots to improve data security. This Systematic Literature Review (SLR) examines the usage and contributions of honeypots in data security field across diverse sectors and environments. Analyzing 38 selected articles from 2018 to 2023, the study highlights the growing adoption of honeypots as tools for detecting and preventing data breaches, exfiltration, and other security incidents. Our finding found that honeypots, with their deceptive capabilities, have proven could be deployed in sectors like healthcare, cloud computing, and industrial control systems and effective in detection and prevention data breaches, exfiltration, and other data breaches, making them as a crucial tool in the data security protection. The future of honeypots lies in their integration with machine learning and AI, to predict and counteract sophisticated. Moreover, evolving honeypots into tools for deterrence and corrective action opens new avenues for cybersecurity strategies. Their ability to act as deterrents by increasing perceived risks for attackers, coupled with their role in aiding recovery from data breaches through detailed forensic analysis, positions honeypots as a cornerstone in the development of resilient data security frameworks. This study paves the way for a more adaptive, proactive, and comprehensive approach to data security, highlighting the indispensable role of honeypots in the ever-evolving landscape of cybersecurity. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Usability Evaluation of Open Data of Government Website: A Case Study Approach 9

Usability Evaluation of Open Data of Government Website: A C...

引用

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Kurniawan, Yohannes Luhukay, Devyano Prasetya, Erdi Meiryani Philip, Samuel Anwar, Norizan School of Information Systems Bina Nusantara University Information Systems Department Jakarta Indonesia Bina Nusantara University Accounting Department School of Accounting Jakarta Indonesia Bina Nusantara University Computer Science Department School of Computer Science Jakarta Indonesia School of Information Science College of Computing Informatics and Media Universiti Teknologi Mara Shah Alam Malaysia

ISBN: (纸本)9798350383010

Open data is closely related to government, supporting transparency and accountability. The paper focus on DKI Jakarta government's open data website, which this website provides an accurate, open, centralized, and integrated database for e-government. This research will use three tools to help collect information for evaluation purpose. First is the Web Accessibility Evaluation tool (WAVE) which will help identify accessibility errors and the web content accessibility guideline. Then the second is the Webpage Test to analyze the website network and speed of loading when accessing the website. And the third use VisualEyes to see how attractive and clear the website is. The aim of this research is to identify the errors and malfunctions that occur and do not affect user comfort when accessing and improving the quality of the site in future. From the results of this research using WAVE, there is still a color contrast between the background and text, and some small errors were found. For now, the website's loading is quite fast, only 8.40 seconds, and the results from VisualEyes are quite high that is 77%, where the website is sufficient to be clear and aesthetically appealing. © 2024 IEEE.

关键词： accessibility aesthetics open data quality assurance usability user experience website

来源：评论

学校读者我要写书评

暂无评论

Designing a Blockchain-based System for Wholesale Central Bank Digital Currency 7

Designing a Blockchain-based System for Wholesale Central Ba...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Taufik, Derryl Kusuma, Marchel Budi Gunawan, Alexander Agung Santoso Richard School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia

ISBN: (纸本)9798350307504

Driven by advancements in financial technology, Central Bank Digital Currency (CBDC) has garnered significant interest, with over eighty percent of central banks worldwide exploring its potential in 2021. This paper aims to design and implement a wholesale Central Bank Digital Currency (w-CBDC) prototype using the Hyperledger Besu, an Ethereum Virtual Machine-based blockchain platform. To extend the contribution of this paper, an experiment is conducted by creating smart contracts as the basis of digital currency. The smart contract will handle w-CBDC functionalities, such as issuance, redemption, transfer, and Delivery versus Payment (DvP). The results show that implementing w-CBDC functionalities in Hyperledger Besu private blockchain can address the required functionalities. However, privacy remains a notable concern, as anyone running the node can see all the transaction activities on the blockchain. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

R Package Development to Support Discrete Events Simulation Learning 8

R Package Development to Support Discrete Events Simulation ...

引用

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

作者： Yudistira, I. Gusti Agung Anom Nariswari, Rinda Sevien Statistics Department School of Computer Science Bina Nusantara University Jakarta Indonesia

This study aims to describe the various capabilities of the simmer package for R, particularly when running a discrete event simulation model. It then develops a technique for building effective DES simulation models that accurately represent real systems and examines the simulation output on this simmer, both in statistical summary form and parameter estimation. The literature review method with descriptive and exploratory methodologies was employed in this study. When starting with simple models and progressing to more complicated forms step by step while explaining the system with a flow chart, model development is more successful. It is simple to replicate simulations in order to obtain standard error values for model parameter estimators. Creating a discrete event simulation in stages. © 2023 The Authors. Published by Elsevier B.V.

关键词： discrete event R-package simulation

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

Implementation of Upselling Model in Customer Relationship Management for Revenue Maximization in Telecommunications Industry 18

Implementation of Upselling Model in Customer Relationship M...

引用

18th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2024

作者： Kusnadi, Clarissa Audrey Fabiola Jeffrey Munthe, Priscilla Abigail Qomariyah, Nunung Nurul Bahana, Raymond School of Computing and Creative Arts Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331527686

In this rapid era of business and commerce, it is crucial to build long-term customer relationships to maximize a company's revenue. To increase the growth and profitability of the telecommunications industry, up-selling strategies can be employed. In our research, we explore the use of predictive modeling and recommendation systems in Customer Relationship Management (CRM), with a specific focus on up-selling techniques. Utilizing a wide-ranging data set that includes various customer attributes, we employed six supervised machine learning techniques to create predictive models for the telecommunications industry around the world, namely XGBoost, HistGradientBoost, random forest, naive bayes, k-nearest neighbor and decision tree. We evaluated the performance of each model to reveal which algorithm performs best. We found that XGBoost turns out to be the most applicable and reliable model for upsell applications, with an accuracy of 0.96. © 2024 IEEE.

关键词： Telecommunication industry

来源：评论

学校读者我要写书评

暂无评论

Orthogonal Persistence a Breakthrough for Scaling and Seveloping an Application in Blockchain Scenario 8

Orthogonal Persistence a Breakthrough for Scaling and Sevelo...

引用

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

作者： Otnieliem, Kevin Herman Kerthyayana Manuaba, Ida Bagus School of Computer and Creative Arts Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350326093

Blockchain technology has changed our perception of decentralized, secure data storage and administration. However, the scalability and development issues that blockchain-based applications confront remain substantial barriers to the broad use of blockchain technology. A novel concept called orthogonal persistence has emerged as a feasible alternative for improving the scalability and development of blockchain-based apps. This research looks towards orthogonal persistence as a possible breakthrough for scaling and growing blockchain systems. Data persistence in a blockchain environment is simplified by orthogonal persistence, making it easier for developers to maintain and grow the system. Orthogonal persistence has the potential to improve blockchain application efficiency and scalability while lowering design and maintenance costs. The study concludes that orthogonal persistence is a realistic technique for developing blockchain applications that may support innovation and success in this rapidly evolving technology industry. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Quality Control of Automatic Weather Station Data: Study Case in DKI Jakarta 10

Quality Control of Automatic Weather Station Data: Study Cas...

引用

10th IEEE International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2024

作者： Purwandari, Kartika Siga, Florence A. Karnisih Sigalingging, Join W.C. Bina Nusantara University School of Computer Science Department of Computer Science Jakarta11530 Indonesia Centre for Database The Agency for Meteorology Climatology and Geophysics Jakarta10720 Indonesia

ISBN: (纸本)9798350365283

Automatic Weather Station (AWS) is an automatic weather station designed to measure and record meteorological parameters and transmit them automatically. To determine the validity of data from AWS equipment, quality control (QC) of the data is required. To determine the validity of AWS data, QC for the period January 2021 - July 2022 in DKI Jakarta was performed using range checks, consistency checks, and step checks. While range checks showed over 86.6% compliance, step checks indicated a lower success rate due to significant deviations. This paper proposes using local historical data for more accurate range checks and explores alternative step check methods based on weather conditions. The data is then carried out QC consistency check and step check. Consistency checks on the elements of solar radiation, wind and air temperature gave the result that more than 89.09% of the data were consistent. Step check was applied to air pressure, air humidity and average air temperature. The difference between the data and the previous data was compared with the standard deviation. This test gives a small average percentage that passes the test, namely 2.1% for air humidity and 47.4% for air pressure and average air temperature. This is due to the difference in data difference which is much greater than the standard deviation. © 2024 IEEE.

关键词： Data consistency

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：