检索结果-内蒙古大学图书馆

22nd International Conference on Emerging eLearning Technologies and Applications, ICETA 2024

作者： Čatloch, Dušan Chovancová, Eva Mat'ašová, Sylvia Technical University of Košice Faculty of Electrical Engineering and Informatics Department of Computers and Informatics Košice Slovakia

ISBN: (纸本)9798331527716

This paper discusses the development and application of linear regression (LR) to predict stock prices in the stock market. The main objective is to analyse the efficiency and accuracy of linear regression in relation to financial markets, and specifically to predict stock prices one day ahead. The paper begins with a detailed review of the related theoretical foundations and existing methods in the field of stock market forecasting. Next, it discusses the formulation of the stock price forecasting problem and the choice of linear regression as a tool to solve it. Particular emphasis is placed on understanding the properties of linear regression and its potential contribution to predictive models. The second part of the paper describes the implementation and testing of the LR algorithm, including the design and execution of experiments to evaluate its performance. The results are analysed using graphs and individual numerical predictions that were collected on a sample of multiple firm stocks. These results are described and discussed in detail, assessing their sensitivity to short-term volatility and deviation from fair value. The paper provides a new perspective on the use of linear regression in forecasting stock markets and contributes to a better understanding of its effectiveness and limitations. © 2024 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Architecture, Enhancements and Perspective of the L-NeRVEn Virtual Environment for Neurorehabilitation 17

Architecture, Enhancements and Perspective of the L-NeRVEn V...

引用

17th IEEE International Scientific Conference on informatics, informatics 2024

作者： Korecko, Stefan Sobota, Branislav Nehila, Peter Chmura, Damian Technical University of Košice Faculty of Electrical Engineering and Informatics Department of Computers and Informatics Košice Slovakia

ISBN: (纸本)9798350387674

Virtual reality is gaining more and more importance in the neurorehabilitation of patients suffering from the consequences of a stroke, a spinal cord injury, or other conditions. This paper deals with L-NeRVEn, a software solution for after-stroke upper limb neurorehabilitation. L-NeRVEn offers a shared virtual environment, experienced via a VR headset, where animated full-body avatars represent both the therapist and the patient. The patient's task is to imagine a particular movement with his or her disabled limb and the success of this imagination is determined by the processing and classification of the patient's electroencephalography (EEG) signal. The EEG processing component is loosely coupled with the rest of the solution and can be easily replaced. The paper presents the architecture of L-NeRVEn, explains the interaction of its components during a basic therapy procedure, lists certain enhancements of the system implemented on the basis of experts' feedback, and offers perspectives for the future development of the solution. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Another Empirical Proof of Transparent Intensional Logic's Expressive Power in the Field of Temporal Logical Systems 17

Another Empirical Proof of Transparent Intensional Logic's E...

引用

17th IEEE International Scientific Conference on informatics, informatics 2024

作者： Novotny, Samuel Steingartner, William Perhac, Jan Technical University of Košice Faculty of Electrical Engineering and Informatics Department of Computers and Informatics Košice Slovakia

ISBN: (纸本)9798350387674

This paper is focused on translating the modalities of fundamental temporal logical systems into the language of Transparent Intensional Logic, which represents a very expressive methodology for the logical analysis of natural language. Since the analyzed modalities play an important role in the area of model checking, their translation, carried out based on the explicit intensional and temporal character of Transparent Intensional Logic, also initiates further research aimed at connecting these areas. This brings an added value to our paper, whose main result is the presentation of another empirical proof of Transparent Intensional Logic expressiveness. © 2024 IEEE.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Assessing Comprehension of Petri Nets Across Diverse Backgrounds: An Experimental Insight 17

Assessing Comprehension of Petri Nets Across Diverse Backgro...

引用

17th IEEE International Scientific Conference on informatics, informatics 2024

作者： Korecko, Stefan Sobota, Branislav Rudy, Juraj Technical University of Košice Faculty of Electrical Engineering and Informatics Department of Computers and Informatics Košice Slovakia

ISBN: (纸本)9798350387674

Petri nets are a well-known technique for process modeling with an easy-to-understand graphical notation. But are Petri nets as easy to comprehend as assumed? How well can people from diverse backgrounds understand and use them? The study presented in this paper aims to provide limited insight into these questions, with the primary limitation being the number of participants (n=20). A particular type of Petri nets, the Elementary system nets, was presented to the study participants and then they have been given a task to complete a Petri net with arcs. There were 10 participants from the IT field and 10 outside of the IT field. 12 participants completed the task successfully, 7 from the IT group and 5 from the non-IT group. While the study has been conducted in the context of Petri Nets utilization for scenarios in virtual educational environments, the results are not limited to that context. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Decomposition of Railway Objects for Distributed Interlocking System

Periodica Polytechnica Electrical Engineering and Computer S...

引用

Periodica Polytechnica electrical engineering and Computer Science 2024年第4期68卷 319-326页

作者： Arató, Péter Markovits, Tibor Gergely Rácz, György Department of Control Engineering and Information Technology Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Magyar tudósok krt. 2. BudapestH-1117 Hungary

Railway interlocking systems can be implemented as distributed systems, where each part of a station is handled by a separate logical unit. The logical units of such systems form a network and communicate by interchanging messages. Such distributed architectures are well known in large industrial control systems. There are several design practices and also algorithmic task partitioning methods that are applicable in distributed control systems. Some of such methods can also be adapted in designing of railway interlocking systems as well. In the case of such systems, the communication time between components must be kept low. Namely each separate controller in a given route must be able to exchange their internal state within a limited time in order to permit the train movement authorization. This limitation could cause high traffic load, if every logical unit would be interconnected with each other. Therefore, the main goal of the minimization is to reduce the number of connections between logical units. This can achieved by distributing and assigning the topological railway objects to certain logical units. © 2024 Budapest University of Technology and Economics. All rights reserved.

关键词： Distributed parameter control systems

来源：评论

学校读者我要写书评

暂无评论

Robust Trajectory Tracking Control of a Differentially Flat Overhead Crane Using Sliding Mode

Periodica polytechnica Electrical engineering and computer s...

引用

Periodica polytechnica electrical engineering and computer science 2024年第2期68卷 213-221页

作者： Finta, Barnabás Kiss, Bálint Department of Control Engineering and Information Technology Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics University Műegyetem rkp. 3. BudapestH-1111 Hungary

The control of overhead cranes is a benchmark problem, since it is an underactuated mechanism and its mathematical model is nonlinear. During operation the mass of the load is unknown, representing an uncertainty in the inertial parameters, which requires robustness of the controlled system. Our paper proposes a novel robust control method, that combines the differentially flat property of the dynamics with the robustness of the sliding mode control. The sliding surface is constructed to ensure the tracking of the configuration variables whose accelerations is calculated using the flatness property of the dynamic model. This formulation also allows achieving the matching conditions of the parameter uncertainties. Considering a simplified overhead crane model where the load motion is restricted in a vertical plane, two sliding surfaces are defined for the rope angle and rope length, since the cart position can be calculated from the previous two. The suggested control method is successfully validated in simulations as well as using a reduced-size overhead crane. For the real crane, the rope angle was estimated by utilizing the dynamical model, which uses the estimated cart acceleration. © 2024 Budapest University of Technology and Economics. All rights reserved.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Comparison of Cellular Network Coverage Prediction Using Machine Learning Algorithms and Conventional Models 18

Comparison of Cellular Network Coverage Prediction Using Mac...

引用

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

作者： Edbert Saragih, Geo Perdana Iskandar Yuliana, Hajiar School of Electrical Engineering and Informatics Bandung Institue of Technology Telecommunicaation Engineering Bandung Indonesia School of Electrical Engineering and Informatics Bandung Institue of Technology Bandung Indonesia Universitas Jenderal Achmad Yani Faculty of Engineering Department of Electrical Engineering Cimahi Indonesia

ISBN: (纸本)9798331527686

Machine learning has emerged as a powerful tool for predicting signal range in wireless communication networks, offering significant improvements over conventional models. Traditional methods, such as empirical path loss models, rely on predetermined formulas and parameters that may not fully capture the complex variability of real-world environments. In contrast, machine learning algorithms leverage large datasets to learn intricate patterns and dependencies within the data, resulting in more accurate and robust predictions. Moreover, machine learning demonstrates better adaptability compared to traditional methods because it does not depend on fixed formulas, allowing it to adjust more effectively to diverse and changing conditions, especially in complex urban environments where signal propagation is affected by numerous variables. This advancement not only improves network planning and optimization but also ensures higher service quality for end-users. Therefore, incorporating machine learning into signal coverage prediction marks substantial progress in creating more efficient and dependable wireless communication networks. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

引用

Computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

Potential for De-dieselization : A Case Study on Kodingareng Island, Indonesia 6

Potential for De-dieselization : A Case Study on Kodingareng...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Winanti, Naftalin Rachmilda, Tri Desmana Purwadi, Agus Heryana, Nana Iskandar, Handoko Rusiana Universitas Jenderal Achmad Yani Faculty of Engineering Electrical Engineering Department Cimahi Indonesia Bandung Institut of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798331504694

One form of energy security, as stated in Government Regulation No. 79/2014 is a condition where there is energy availability, and the energy can be reached by all levels of society. The use of Diesel Power Plants (PLTD), which are still widely used in the Indonesian archipelago, is not in accordance with the energy security program because the availability of fuel on the island takes time. It is necessary to utilize the energy available in locations such as solar energy which is a potential renewable energy in Indonesia. In addition to the implementation of energy security, the use of solar energy can also be the realization of Indonesia's commitment to reducing emissions. One of the islands that utilize PLTD is Kodigareng island, where on the island, the existing solar energy potential is quite large at 5.87 kWh/m2/day. In this study, a dedieselization system is made with a solar power plant (PLTS) by ensuring that the PLTS capacity can supply electrical energy needs on Kodingareng Island with 0% shortage. To fulfill this, the appropriate capacity of the PLTS is l,127kWp, while still utilizing the PLTS as a backup. With this combination of PLTS and PLTD, the fuel cost reduction obtained is IDR 5,735,958,676 with a Co2 reduction of 93%. This PLTS system also has the smallest COE value of IDR 3,982. © 2024 IEEE.

关键词： Diesel power plants

来源：评论

学校读者我要写书评

暂无评论

Techno-economics Utilization Case Study of Renewable Energy PV Source for Battery Swapping Charging Stations 6

Techno-economics Utilization Case Study of Renewable Energy ...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Iskandar, Handoko Rusiana Heryana, Nana Purwadi, Agus Furqani, Jihad Universitas Jenderal Achmad Yani Faculty of Engineering Electrical Engineering Department Cimahi Indonesia Bandung Institut of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798331504694

This paper discusses the techno-economic assessment of the exploitation of new renewable energy (RE) that may be used as a source of energy from the Public Electric Battery Swapping Charging Station (PEBSCS). This paper analyzes RE systems and technologies, including identifying the potential use of various types of RE that can be applied in PEVBCS, analyzing their benefits and drawbacks, measuring the load profile of Gas Stations that already have BSCS, and calculating the RE contributions that can be made from electricity use at Hayam Wuruk Gas Station in Bali, Indonesia. When simulating techno-economy studies, cost inputs include capital costs, replacement costs, operational and maintenance costs that have been changed and selected based on current conditions, and inflation values updated in recent years in accordance with the Minister of Finance's regulation letter. The findings of the use of PV-based RE may be extended to all existing PEVBCS, since according to the studies conducted, the use of PV at the Hayam Wuruk Gas Station - Bali site results in a substantially cheaper Levelized Cost of Energy (LCOE) value than the use of PLN electrical energy tariff special services. The comparison of the findings and the resultant value is a description of the hybrid scheme (PV, battery, and grid) based on many models and simulations performed on the PEBSCS object utilizing both external and existing batteries. © 2024 IEEE.

关键词： Charging stations

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：