检索结果-内蒙古大学图书馆

16th International Baltic Conference on digital Business and Intelligent Systems, Baltic DB and IS 2024

作者： Žvirblis, Tadas Pučinskas, Donatas Institute of Data Science and Digital Technologies Vilnius University Vilnius Lithuania Institute of Computer Science Vilnius University Vilnius Lithuania

ISBN: (纸本)9783031635427

This work evaluates the applicability of GANs in generating synthetic time series data. Hypoid gear vibration data was used as experimental data to test models. GANs for time series can be divided into two different types: discrete type (discrete time series) and continuous type (continuous time series). In time series, there are complex time-dependent features and their attributes, for example, when using biometric data, ECG characteristics will depend on the age and health of the individual. TimeGAN is a generative time series model that combines unsupervised learning using GAN with supervised autoregressive learning. TimeGAN model performace was evaluated using predictive score and visualization using PCA and tSNE analysis for original and synthetic data. The best predictive score was 0.062, however visual evaluation using tSNE and PCA analysis revealed that generated data was not sufficiently similar to the real. It can be concluded that the application of GANs to time series presents difficulties that are not present in image generation models. Continuing this work could lead to testing other time series GANs in the future, e.g. DoppelGANger whose synthetic data structure does not require complex reconstruction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Examining Transactional Decentralization on the Ethereum Blockchain 6

Examining Transactional Decentralization on the Ethereum Blo...

引用

6th International Conference on Blockchain Computing and Applications, BCCA 2024

作者： Juodis, Mindaugas Filatovas, Ernestas Goštautas, Donatas Paulavičius, Remigijus Institute of Data Science and Digital Technologies Vilnius University Vilnius Lithuania Gjensidige Lithuania Vilnius Lithuania

ISBN: (纸本)9798350351538

The decentralized nature of blockchain ecosystems involves a complex interplay of various sources, entities, and decision-makers that act collectively, yet independently, avoiding unnecessary concentration or dominance. Decentralization can be assessed through various dimensions, such as consensus, network, governance, transaction, and wealth. This work presents an overview of the current landscape of transactional decentralization. Assessing decentralization requires robust metrics capable of distinguishing and incorporating factors such as the distribution of participants between addresses, blocks, and transactions. Therefore, in this work, we actively utilize and examine well-known statistical metrics, including the decentralization index, Gini coefficient, Nakamoto coefficient, Herfindahl-Hirschman index, and Shannon entropy, using Ethereum blockchain data over a period of seven years. Our analysis delves into the intricate dynamics of decentralized transactions, uncovering the evolving trends and challenges that define decentralization. This research contributes to the ongoing discourse surrounding blockchain decentralization, providing information on the measurement and evaluation of the status of decentralization using raw and grouped data from the Ethereum blockchain. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent System for Facility Location Problem 16

Multi-Agent System for Facility Location Problem

引用

Joint of 16th International Baltic Conference on digital Business and Intelligent Systems Conference Forum and Doctoral Consortium, Baltic-DB and IS-Forum-DC 2024

作者： Sellapperuma, Sathuta Institute of Data Science and Digital Technologies Vilnius University Akademijos St. 4 Vilnius Lithuania

Effective facility location decisions are pivotal for enhancing a firm’s performance and competitive edge. Traditional methods often struggle to adapt to dynamic market conditions, leading to suboptimal outcomes. This research proposes a novel Multi-Agent System (MAS) application to address the Facility Location Problem (FLP). By leveraging distributed decision-making agents, the MAS platform aims to optimize facility locations in real time, integrating dynamic factors such as evolving consumer preferences and market trends. This study will design, implement, and evaluate an MAS platform where agents representing stakeholders—customers, suppliers, and facilities—interact to find optimal locations, considering cost minimization, customer satisfaction, and competitive advantage. The MAS framework also incorporates advanced decision-making algorithms and optimization techniques to enhance the efficiency and robustness of the solution. The system’s adaptability to market changes and real-time data integration capabilities will be thoroughly assessed through comprehensive evaluation metrics. The anticipated outcomes include improved decision-making efficiency, enhanced adaptability to market changes, and a robust solution capable of mitigating market cannibalization effects. Ultimately, this research aims to provide a practical and scalable approach to facility location optimization, fostering long-term organizational success in a competitive global environment. © 2024 Copyright for this paper by its authors.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

An Experimental Selection of Deep Neural Network Hyperparameters for Engine Emission Prognosis 11

An Experimental Selection of Deep Neural Network Hyperparame...

引用

11th IEEE Open Conference of Electrical, Electronic and Information sciences, eStream 2024

作者： Žvirblis, Tadas Matijošius, Jonas Kilikevičius, Arturas Institute of Data Science and Digital Technologies Vilnius University Vilnius Lithuania Institute of Mechanical Science Vilnius Gediminas Technical University Vilnius Lithuania

ISBN: (纸本)9798350352412

This research presents results and discussion on prognostic deep learning models developed for the prediction of emission parameters of internal combustion engines. The resulting models were trained to predict various engine emission parameters from engine vibrations and the type of fuel used. To train and test the models, a dataset was created, where the input data was obtained from the measured engine vibrations at certain moments of time and the type of fuel used. Using obtained input data, the output data were calculated using a prognostic model. 162 models of multilayer perceptron network architecture were created and trained using different combinations of training parameters. The accuracy of each model was measured using the mean absolute percentage error and mean squared error metrics. The paper analyzes the influence of each selected parameter on the accuracy of the model. The best accuracy was achieved by a multilayer perceptron neural network model with 1 hidden layer and 50 neurons, which was trained for 20 epochs with a batch size of 16. The accuracy of the model on the testing dataset was 0.02161 and 0.00014, respectively, based on the mean absolute percentage error and mean squared error metrics. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Hot Off the Press: Benchmarking Derivative-Free Global Optimization Algorithms under Limited Dimensions and Large Evaluation Budgets

Hot Off the Press: Benchmarking Derivative-Free Global Optim...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Stripinis, Linas Kůdela, Jakub Paulaviçius, Remigijus Institute of Data Science and Digital Technologies Vilnius University Vilnius Lithuania Institute of Automation and Computer Science Brno University of Technology Brno Czech Republic

ISBN: (纸本)9798400704956

This Hot Off the Press paper provides a brief summary of our recent work "Benchmarking Derivative-Free Global Optimization Algorithms under Limited Dimensions and Large Evaluation Budgets"published in IEEE Transactions on Evolutionary Computation [5]. In the paper, we performed a comprehensive computational comparison between stochastic and deterministic global optimization algorithms with twenty-five representative state-of-the-art methods selected from both classes. The experiments were set up with up to twenty dimensions and relatively large evaluation budgets (105 X n). Benchmarking was carried out in a significantly expanded version of the DIRECTGOLib v2.0 library, which included ten distinct collections of primarily continuous test functions. The evaluation of the methods focused on various aspects, such as solution quality, time complexity, and function evaluation usage. The rankings were determined using statistical tests and performance profiles. Our findings suggest that while state-of-the-art deterministic methods could find reasonable solutions with comparatively fewer function evaluations, most stochastic algorithms require more extensive evaluation budgets to deliver comparable results. However, the performance of stochastic algorithms excelled in more complex and higher-dimensional problems. These research findings offer valuable insights for practitioners and researchers, enabling them to tackle diverse optimization problems effectively. © 2024 Copyright held by the owner/author(s).

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Attention-Based and Time Series Models for Short-Term Forecasting of COVID-19 Spread

引用

Computers, Materials & Continua 2022年第1期70卷 695-714页

作者： Jurgita Markeviciute Jolita Bernataviciene Ruta Levuliene Viktor Medvedev Povilas Treigys Julius Venskus Institute of Applied Mathematics Vilnius UniversityVilnius03225Lithuania Institute of Data Science and Digital Technologies Vilnius UniversityVilnius08412Lithuania

The growing number of COVID-19 cases puts pressure on healthcare services and public institutions *** pandemic has brought much uncertainty to the global economy and the situation in *** methods and modeling techniques are important tools for governments to manage critical situations caused by pandemics,which have negative impact on public *** main purpose of this study is to obtain short-term forecasts of disease epidemiology that could be useful for policymakers and public institutions to make necessary short-term *** evaluate the effectiveness of the proposed attention-based method combining certain data mining algorithms and the classical ARIMA model for short-term forecasts,data on the spread of the COVID-19 virus in Lithuania is used,the forecasts of epidemic dynamics were examined,and the results were presented in the ***,the approach presented might be applied to any country and other pandemic *** COVID-19 outbreak started at different times in different countries,hence some countries have a longer history of the disease with more historical data than *** paper proposes a novel approach to data registration and machine learning-based analysis using data from attention-based countries for forecast validation to predict trends of the spread of COVID-19 and assess risks.

关键词： COVID-19 spread modeling attention-based forecasting machine learning data registration data analysis ARIMA

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks Application for Cup-to-Disc Ratio Estimation in Eye Fundus Images 18

Deep Neural Networks Application for Cup-to-Disc Ratio Estim...

引用

18th Conference on Computer science and Intelligence Systems, FedCSIS 2023

作者： Virbukaite, Sandra Bernataviciene, Jolita Institute of Data Science and Digital Technologies Vilnius University Akademijos Str. 4 Vilnius Lithuania

ISBN: (纸本)9788396744784

Glaucoma is the second eye disease causing blindness worldwide. Optic Cup-to-Disc ratio (CDR) is a commonly applied method in glaucoma detection. The CDR is calculated based on Optic Disc (OD) and Optic Cup (OC) in eye fundus image screening. Therefore, the accurate segmentation of these two parameters is very important. Lately, Deep Neural Networks have demonstrated great effort in automated Optic Disc and Optic Cup segmentation but the overlapping between regions of OC and OD cause the challenge to obtain CDR automatically with high accuracy. In this paper, we assess the performance of CDR evaluation on three modifications of the Convolutional Neural Network (CNN) U-Net, namely Attention U-Net, Residual Attention U-Net (RAUNet), and U-Net++ applied on publicly available datasets RIM-ONE, DRISHTI, and REFUGE. We calculated the ground truth CDR value of testing eye fundus images of these datasets and compared it with the CDR value obtained by trained CNNs. Our results show that Attention U-net obtains the closest CDR to the ground truth CDR value but the identification of early-stage glaucoma needs an improvement. © 2023 Polish Information Processing Society.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Behavioral Biometrics Authentication in Critical Infrastructure Using Siamese Neural Networks 5th

Behavioral Biometrics Authentication in Critical Infrastruc...

引用

5th International Conference on HCI for Cybersecurity, Privacy and Trust, HCI-CPT 2023, held as part of the 25th International Conference on Human-Computer Interaction, HCII 2023

作者： Budžys, Arnoldas Kurasova, Olga Medvedev, Viktor Institute of Data Science and Digital Technologies Vilnius University Akademijos str. 4 Vilnius08412 Lithuania

ISBN: (纸本)9783031358210

Cybersecurity is a crucial issue in today’s critical infrastructure to ensure a secure connection between the administrator and the session. Detecting insiders is a difficult task for cybersecurity professionals, as insiders are hard to detect and identify and thus require advanced techniques to prevent their activities. These users may be current or former employees with access to the organization’s data. A methodology for authenticating users of critical infrastructure systems using deep learning networks is proposed in this paper. Behavioral biometric data or user behavioral characteristics are converted into an image and used in the proposed methodology for authentication. The keystroke data obtained from the login password is transformed into a more acceptable format for deep neural networks. Siamese neural networks can be used for image similarity detection to distinguish a real user from an insider. In the current investigation, numerical keystroke data has been transformed into graphical representations. The transformed data are then subjected to comparative analysis, leading to the determination of similarities between the biometric keystroke profiles. The experiments have shown there is a tendency for the accuracy of a Siamese neural network with a triplet loss function to decrease with increasing margin size. The results obtained are promising, showing that using a deep learning-based approach to analyze images derived from user keystroke data can improve intrusion detection accuracy and perform user authentication more efficiently. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Self-Checkout Product Class Verification using Center Loss approach

Self-Checkout Product Class Verification using Center Loss a...

引用

作者： Ciapas, Bernardas Treigys, Povilas Institute of Data Science and Digital Technologies Vilnius University Akademijos str. 4 VilniusLT-08663 Lithuania

The traditional image classifiers are not capable to verify if samples belong to specified classes due to several reasons: classifiers do not provide boundaries between in-class and out-of-class samples;although classifiers provide separation boundaries between known classes, classifiers' latent features tend to have high intra-class variance;classifiers often predict high probabilities for out-of-distribution samples;training classifiers on unbalanced data results in bias towards over-represented classes. The nature of the class verification problem requires a different loss function than the ubiquitous cross entropy loss in traditional classifiers: input to a class verification function includes a suggested class in addition to an image. As opposed to outlier detection, space is transformed to be not only separable, but discriminative between in-class and out-of-class inputs. In this paper, class verification based on a euclidean distance from the class centre is proposed and implemented. Class centres are learnt by training on a centre loss function. The method's effectiveness is shown on a self-checkout image dataset of 194 food retail products. The results show that a two-fold loss function is not only useful to verify class, but does not degrade classification performance - thus, the same neural network is usable both for classification and verification. © 2023 The Author(s).

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Deep Autoencoder Model for Hypoid Gear Fault Diagnosis With Dynamic Torque and Rotation Speed 11

Deep Autoencoder Model for Hypoid Gear Fault Diagnosis With ...

引用

11th IEEE Workshop on Advances in Information, Electronic and Electrical Engineering, AIEEE 2024

作者： Zvirblis, Tadas Skrickij, Viktor Kilikevicius, Arturas Vilnius University Institute of Data Science and Digital Technologies Vilnius Lithuania Vilnius Gediminas Technical University Transport & Logistics Competence Centre Vilnius Lithuania Vilnius Gediminas Technical University Institute of Mechanical science Vilnius Lithuania

ISBN: (纸本)9798331527761

In this study the applicability of autoencoder-based deep neural networks to solve fault classification problems using vibration signals. This work will aim to construct CNN and LSTM type autoencoder-based neural networks, which would be suitable for solving fault classification tasks, and compare them with traditional neural networks. This study explores the applicability of autoencoder-based deep neural networks to solve fault classification problems using vibration signals. The study examines 7 different types of gear failures of hypoid gear. CNN-2D, CNN-2D with autoencoder, LSTM, and LSTM with autoencoder were developed and compared. CNN-2D model reached 0.72 of overall accuracy while CNN-2D with autoencoder reached only 0.65. LSTM models (with and without autoencoder) showed worse overall accuracy that CNN-2D. The general conclusion of the research is that in order to achieve better results of autoencoders use for the classification of vibration signal data, it is necessary to perform more tests: to test different data augmentations, architectures of the models. © 2024 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

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：