检索结果-内蒙古大学图书馆

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Mochammad Haldi Widianto Alexander Agung Santoso Gunawan Yaya Heryadi Widodo Budiharto Computer Science Department BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Electrical energy consumption is always increasing, and this causes the supply of electrical energy to be increased to compensate. One solution is to predict electricity energy consumption using Artificial Intelligence (AI) technology in Smart Homes. Several studies' solutions for predicting electrical energy consumption usually focused only on performance but rarely evaluated Machine Learning (ML) by correlation for feature selection and utilized interpretability model. This study uses an ML model for predicting utilization (Linear Regression, Decision Tree, Random Forest, and XGBoost). Then, Feature Selection utilizes correlation to choose the best feature. After that, the interpretability model utilizes Local Interpretable Model-agnostic Explanations (LIME). The results show that XGBoost has the best Root Mean Squared Error (RMSE) value (0.318) with a percentage of the number of train and test data (90/10). After that, by eliminating features that correlate with 0.01, XGBoost improves with an increase of (0.018) to become (0.3). Then from LIME. This work also gets positive feature from XGBoost such as: "Furnance, Well dan Living Room".

关键词： Energy consumption Correlation Linear regression Smart homes Predictive models Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Location Prediction Using Named Entity Recognition for Indonesia Natural Disasters in Data Twitter

SSRN

引用

SSRN 2022年

作者： Girsang, Abba Suganda Noveta, Bima Krisna Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Indonesia is in an area prone to natural disasters, there were 4,650 natural disasters that occurred in 2020. However, the community does not have spatial data regarding the location of the disasters that occurred. The purpose of this study is to provide the location of natural disasters that are poured into maps to the public by utilizing Twitter data which has a fast distribution with the fifth most users in the world. This study proposes a system for geolocation of types of natural disasters obtained from Twitter, which are classified into eight classes of natural disasters using the Support Vector Machine (SVM) method. Then the Twitter text is extracted to find the location in the Twitter text using Named Entity Recognition (NER). NER uses six special classes based on the regional level in Indonesia with an accuracy rate of 85.65%. The result of geolocation using ArcGIS maps is 87,5%. It is hoped that with this research, people will get spatial data to see the points of natural disasters that occur using maps. So, the public can anticipate future disasters, and the authorities can send aid to the location. © 2022, The Authors. All rights reserved.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Clustering Analysis of a Spatiotemporal Dataset with a Novel Kernel Density Estimator

Clustering Analysis of a Spatiotemporal Dataset with a Novel...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Yu, Jen-Chien Yang, Chun-Chieh Gilbert, John Reuben Liu, Rou-Jun Oyang, Yen-Jen Yang, Meng-Han National Kaohsiung University of Science and Technology Department of Computer Science and Information Engineering Kaohsiung City807618 Taiwan National Taiwan University Master Program in Statistics Taipei106216 Taiwan National Taiwan University Department of Computer Science & Information Engineering Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taiwan

ISBN: (纸本)9798350303780

A vast number of spatiotemporal datasets collected from a wide range of sources has motivated scientists to develop effective approaches to identify interesting patterns hidden in these datasets. In this respect, kernel density estimators, which belong to a class of non-parametric estimators in statistics, have been widely exploited in recent years. With this background, we have developed a novel kernel density estimator aiming to provide accurate analysis results. According to the evaluation with a real spatiotemporal dataset, which collected emergency medical service records in a county in the United States, the proposed kernel density estimator can approximate the probability density function significantly more accurately than a conventional kernel density estimator. Furthermore, we have exploited the proposed kernel density estimator to identify interesting patterns hidden in the real spatiotemporal dataset. © 2023 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Energy Sector Stock Price Prediction Using The CNN, GRU & LSTM Hybrid Algorithm

Energy Sector Stock Price Prediction Using The CNN, GRU & LS...

引用

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Bambang Sulistio Harco Leslie Hendric Spits Warnars Ford Lumban Gaol Benfano Soewito Computer Science Department Binus Graduate Program – Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Nowadays, many people are starting to care about early investment. One of the most popular investments lately, especially for millennials, is a stock investment. In investing, there are advantages and risks of loss. One way to reduce the risk of loss is by using price predictions before investing in stocks. This paper proposes the use of deep learning in making stock predictions. We conducted research by calculating the performance of six deep-learning algorithms to predict stock closing prices. The application of the CNN-LSTM-GRU hybrid algorithm combination produces the best performance compared to other methods, based on the value: Root Mean Squared Error (RMSE) decreased by 1.100 by 14%, Mean Absolute Error (MAE) was successfully reduced by 0.798 by 13.4%, and R Square increased by 0.957 by 3.9%. In predicting stock prices on the Indonesian Stock Exchange, especially in the energy sector, CNN-LSTM-GRU is more appropriate for investors than using a single algorithm to make decisions in investing in stocks..

关键词： Deep learning computer science Recurrent neural networks Sociology Prediction methods Prediction algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analyzing Company’s Share Purchase Value Based on Financial Reports Using Artificial Neural Network (ANN)

Analyzing Company’s Share Purchase Value Based on Financial...

引用

International Conference on Computing, Engineering, and Design (ICCED)

作者： Jeremy Shawn Jonathan Gunawan Chen Zi Hao Maria Susan Anggreainy Afdhal Kurniawan Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

Because financial time series forecasting is sensitive to political, economic, and social factors, it is not a simple task. As a result, those who make investments in currency exchange and financial markets typically search for reliable models that can guarantee they will maximize their profile and minimize their losses. Fortunately, many studies have used a method from Artificial Neural Networks (ANNs) called Backpropagation, could improve the predictive accuracy of the behavior of the financial data over time. This paper aims to forecast stock share prediction from closing value of PT. Bank Central Asia Tbk, and PT. Bank Maybank Indonesia Tbk. The results show that the using Backpropagation gives the closest result. And for the rating of judgement for cast accuracy, it exceeded 10% accuracy, which means high accurate from the prediction. For further checking, comparing the results of research from Victor’s results, it almost hits the same accuracy percentage. Which means, these prediction are accurate enough to do time series forecasting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Threats, Risks, and Mitigations in Cloud Computing Environment

Threats, Risks, and Mitigations in Cloud Computing Environme...

引用

International Conference on Informatics and Computing (ICIC)

作者： Nur Chalik Azhar Muhammad Zarlis Yulyani Arifin Benfano Soewito Computer Science Department BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia Information System Management Department Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Cloud computing has many benefits in various sectors. However, there are threats such as malware, data loss, and misuse of access rights, as well as risks, that occur in the cloud computing environment. This study aims to identify and further explore the types of threats, risks, and mitigation strategies in the cloud computing environment, as well as what risk mitigation components are needed to mitigate risks in the cloud computing environment. This research method uses Kitchenham because it is commonly used to conduct systematic literature reviews (SLR). Sources only refer to journals and proceedings indexed in the IEEE Explorer, scienceDirect, Springer, ACM Digital Library, Wiley Online Library, and Emerald Insight database. The results of this study identified 173 papers based on keywords, 68 papers based on titles, and abstracts, and produced 59 selected papers based on inclusion and exclusion criteria, where the type of threat produced 20 findings, the type of risk 11 findings, and risk mitigation strategies 13 findings, and produced 4 findings for risk mitigation components. Based on the findings, it can be used to mitigate risks in the cloud computing environment.

关键词： Cloud computing Databases Prevention and mitigation Permission Libraries Malware Informatics Risk mitigation Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Development of Key Performance Indicators in e-Learning Implementation in Higher Education Institutions 8

Development of Key Performance Indicators in e-Learning Impl...

引用

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

作者： Sardjono, Wahyu Kristin, Desi Maya Putra, Gustian Rama Binus Graduate Program - Master of Information Systems Management Bina Nusantara University Information Systems Management Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Pakuan University Computer Science Study Program Faculty of Mathematics & Natural Sciences Bogor Indonesia

ISBN: (纸本)9798350326093

Companies or organizations usually use key performance indicators (KPI) as indicators to determine their performance. The company's performance achievements are reflected in the set indicators that will describe the overall performance, as well as higher education institutions can also set key performance indicators, to see their performance achievements. The use of e-learning as a tool to support teaching and learning processes to be more effective and efficient is an example of which performance needs to be measured. This article discusses how the process of developing key performance indicators is carried out through the stages of designing questionnaires and distributing questionnaires to students, data is processed using the method of factor analysis to obtain the main indicators determining performance and the method of regression analysis is also used to build performance models. obtain KPI determinants, and then develop KPI models. The results show that there are indicators of sharing knowledge, managing knowledge, understanding knowledge, and utilization knowledge as performance measurement indicators. © 2023 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

The Information Systems and Model for Succession Planning in Higher Education Institutions

The Information Systems and Model for Succession Planning in...

引用

computer Applications (ICCA), IEEE Conference on

作者： Devyano Luhukay Ford Lumban Gaol Meyliana Harjanto Prabowo Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331534592

ISBN: (纸本)9798331534608

Succession planning is important in organization management. It is a strategic level management that involves not only finding the best successor but also including the development program for the successor so that they will be ready for the new prospective position. The integration and collaboration between all related stakeholders are important. Specifically, in succession planning at higher education, key positions play an important role so that institutional operations can run well. In this research, a succession planning model in higher education was built using the Systematic Literature Review(SLR), and the Software Development Lifecycle(SDLC) method was used for the application development, also, to be able to evaluate the implementation of one of the steps of the model, the simulation technique used machine learning (ML) to find the best algorithm for predicting the readiness of potential successors at higher education. Six algorithms were used: Logistic Regression, Decision Tree, K-Nearest Neighbor, Linear Discriminant Analysis, Gaussian Naïve Bayes, and Support Vector Machine. The data prepared for the simulation is based on the factors for the best successor candidate. The results obtained in this research are the succession planning model and the application design, as well as the Support Vector Machine (SVM) algorithm as the best algorithm for predicting the readiness status of successor candidates based on SVM’s accuracy score that is compared to the other algorithm in some variance amounts of data. The Succession Planning Model that is actualized in the application design provides a reference for the higher education institution to implement the Succession Model in their institution.

关键词： Support vector machines Machine learning algorithms Systematics Education Software algorithms Machine learning Predictive models Prediction algorithms Planning Information systems

来源：评论

学校读者我要写书评

暂无评论

YOLOS-MCI: Automating Microservices Coupling Index Calculation using Vision Transformers

引用

Procedia computer science 2024年 245卷 924-933页

作者： Gintoro Yaya Heryadi Lukas Lili Ayu Wulandhari Ilvico Sonata Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Cognitive Engineering Research Group (CERG) Universitas Katolik Indonesia Atma Jaya Jakarta 12930 Indonesia

Microservice Architectures (MSA) provide flexibility and scalability in software development. However, accurately measuring the level of interdependence among Microservices continues to be a difficult task. Precisely evaluating this connection is essential for efficient MSA design, maintenance, and future development. Conventional techniques for assessing Microservice coupling are frequently done by hand, require a significant amount of time, and are susceptible to mistakes. This impedes the capacity to make well-informed judgments regarding the integration and adjustment of services. This study introduces a new method for automating the computation of the Microservice Coupling Index (MCI) by utilizing the You Only Look at One Sequence (YOLOS) object identification technique in combination with Vision Transformer (ViTs) technology. YOLOS is utilized for identifying constituents within Unified Modeling Language (UML) Component Diagrams, facilitating precise classification and effective assessment of coupling. The model exhibits varying performance over multiple Intersection over Union (IoU) thresholds and object sizes, with an average precision (AP) of 0.406 over IoU values ranging from 0.50 to 0.95. The maximum precision is achieved at an IoU of 0.50, with an AP of 0.709. The model demonstrates good performance in identifying smaller components, especially when evaluated at a 0.75 IoU threshold. However, it faces challenges in detecting small items, suggesting potential areas for improvement in future iterations. Initial results indicate that this automation greatly decreases the need for manual, labor-intensive tasks and enhances the precision of measuring coupling in MSA, hence facilitating effective decision-making in service integration and modification. Automating the computation of the coupling index has the potential to significantly influence the design and management of durable and readily controllable microservice architectures.

关键词： Coupling Microservices Microservices Coupling Index UML Component Diagrams Vision Transformer YOLO

来源：评论

学校读者我要写书评

暂无评论

The Utilization of Fuzzy Logic and Bollinger Bands to Enhance Trading Decision-Making During the Bitcoin Halving Phase

引用

Procedia computer science 2024年 245卷 272-281页

作者： Oscar Adam Darmawan Yaya Heryadi Lukas Lili Ayu Wulandhari Ilvico Sonata Computer Science Department Binus Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Cognitive Engineering Research Group (CERG) Universitas Katolik Indonesia Atma Jaya Jakarta 12930 Indonesia

The volatile behavior of Bitcoin's price, especially during its halving periods, poses considerable obstacles for forecasting and decision-making in cryptocurrency trading. This paper presents a novel method that combines application fuzzy logic with Bollinger Bands to improve trading decision-making in times of high market volatility. This study conducted an experiment utilizing three fuzzy logic controllers and Bollinger Bands (BB) to determine the strength of buy, hold, and sell signals. This dataset includes the initial and final prices that are used to calculate the BB. The raw and computed values serve as the precise input parameters for the Fuzzy Inference System (FIS). The membership functions were categorized into four levels: very low, low, high, and very high, based on the input default settings utilized by traders. Rulesets were created using fuzzy logic to produce signals that indicate the level of strength of a trading advice. This study evaluate the effectiveness of this hybrid method in comparison to the traditional utilization of the Bollinger Band only indicator and Moving Average Convergence Divergence (MACD) indicator, which is widely favored by traders to identify possible market fluctuations. This methodology involves creating a trading simulation that is based on past Bitcoin halving events. The objective is to assess the efficacy of these strategies in managing heightened volatility. The application of fuzzy logic with the Bollinger Bands model yielded a success rate of 92.47% while analyzing 93 daily data points from the previous Bitcoin halving event on May 11, 2020.

关键词： fuzzy logic crypto price prediction bitcoin bollinger bands macd cryptocurrency

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：