2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)最新文献_第5页

Comparison of Full Factorial DoE and SSTE® 全因子DoE与SSTE®的比较

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465612

Endre Laguel, T. Szakács

{"title":"Comparison of Full Factorial DoE and SSTE®","authors":"Endre Laguel, T. Szakács","doi":"10.1109/SACI51354.2021.9465612","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465612","url":null,"abstract":"Understanding the behavior of industrial operations require complex resource needs, such as budget, operation downtime to perform experiments, and so on. Engineers and scientists mainly use Design of Experiment to understand the effects of the observed factors. In specific cases, these experiments require increased calculation power, due to the rise of the measured records and factors. The results are often questioned, because interpreting them requires an expert in any topic. This study aims to determine, if there is a faster, more cost effective alternative method, with lower need of calculation power, within the same complexity of a model. In this context, the Full Factorial Design of Experiment method was compared with the Secondary Substitution Transfer Equation practice. The results showed many differences between the two methods, reflecting the accuracy of the prediction, the calculation power need, the file size, ease of use, and last, but not least, the file sizes. These results suggest that, the Secondary Substitution Transfer Equation method is a comparative alternative, especially in complex cases, where the observed factors do not behave linearly. It also requests less resource, which can make this practice an easy to use and cost effective way in the experiments.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131936935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Developing Novel Activation Functions in Time Series Anomaly Detection with LSTM Autoencoder 基于LSTM自编码器的时间序列异常检测新激活函数

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465604

Marina Adriana Mercioni, S. Holban

{"title":"Developing Novel Activation Functions in Time Series Anomaly Detection with LSTM Autoencoder","authors":"Marina Adriana Mercioni, S. Holban","doi":"10.1109/SACI51354.2021.9465604","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465604","url":null,"abstract":"Our proposal consists of developing two novel activation functions in time series anomaly detection, they have the capability to reduce the validation loss. The approach is based on a current activation function in Deep Learning, a very intensive field studied over time, in order to find the most suitable activation in a neural network. In order to achieve this purpose, we used an LSTM (Long Short-Term Memory) Autoencoder architecture, using these two novel functions to see the network’s behavior through introducing them. The key point in our proposal is given by the learnable parameter, assuring more flexibility within the network in weights’ updates, in fact, this property being more powerful than a predefined parameter that will bring a constraint due to its limit. We tested our proposal in comparison to other popular functions such as ReLU (Linear Rectifier Unit), hyperbolic tangent (tanh), Talu activation function. Also, the novelty of this paper consists of taking into consideration of piecewise behavior of an activation function in order to increase the performance of a neural network in Deep Learning.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126790039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Generic Control Loop Model for Fluctuation Analysis in Production Systems 生产系统波动分析的通用控制环模型

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465603

Rocky Telatko, S. Ihlenfeldt, Dirk Reichelt

引用次数: 0

Distorsion Prediction of Additive Manufacturing Process using Machine Learning Methods 基于机器学习方法的增材制造过程畸变预测

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465625

Zoltán Biczó, I. Felde, S. Szénási

引用次数: 0

SapiMouse: Mouse Dynamics-based User Authentication Using Deep Feature Learning 使用深度特征学习的基于鼠标动态的用户认证

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465583

M. Antal, Norbert Fejér, Krisztián Búza

引用次数: 10

A Study on Distributed Fault-Tolerant Service Architectures for Critical Software Systems 关键软件系统分布式容错服务体系结构研究

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465574

Ioan Cristian Schuszter, M. Cioca

引用次数: 0

Adaptive Fireworks Algorithm to solve 2D Inverse Heat Conduction Problem 求解二维逆热传导问题的自适应烟花算法

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465543

Á. Szabó-Gali, I. Felde, S. Szénási

引用次数: 1

Study on fingerprint authentication systems using convolutional neural networks 基于卷积神经网络的指纹认证系统研究

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465628

Delia Moga, I. Filip

引用次数: 2

Development of Bioimpedance-based Measuring Systems for Diagnosis of Non-alcoholic Fatty Liver Disease 基于生物阻抗的非酒精性脂肪肝诊断测量系统的研制

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465584

Nina Gyorfi, Á. Odry, Z. Karádi, P. Odry, T. Szakáll, B. Kuljic, Attila Tóth, Zoltán Vízvári

{"title":"Development of Bioimpedance-based Measuring Systems for Diagnosis of Non-alcoholic Fatty Liver Disease","authors":"Nina Gyorfi, Á. Odry, Z. Karádi, P. Odry, T. Szakáll, B. Kuljic, Attila Tóth, Zoltán Vízvári","doi":"10.1109/SACI51354.2021.9465584","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465584","url":null,"abstract":"Non-alcoholic fatty liver disease (NAFLD) is a leading cause of chronic liver disease worldwide, it is the primary cause of liver-related morbidity and mortality. The prevalence of the disease is estimated as high as 25% of the general population up to 90% of obese and diabetic patients. Most patients are asymptomatic or does not experience specific complaints making them difficult to diagnose and treat. However, due to the limitations of available diagnostic procedures and the current gold standard for diagnosis, the liver biopsy, there is a worldwide demand to develop a non-invasive diagnostic tool and procedure that can detect the disease with high accuracy at an early reversible stage, furthermore is cost-effective, user-friendly, and provides repeatable measurement. Based on the metrological experience of our research team, we started developing an electrical impedance-based diagnostic procedure a few years ago that meets these requirements and is suitable for early detection of NAFLD with the help of a world-new measurement and data collection solution. In this article, we present the most important milestones in the development of instruments related to research.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126398628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Implementing a System for Diagnosing Pulmonary Fibrosis using Hough Algorithm 基于Hough算法的肺纤维化诊断系统的实现

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465554

C. Stancioi, I. Clitan, Abrudean Mihai, V. Muresan, M. Ungureșan

引用次数: 0