Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782751
Miroslav Jaščur, Norbert Ferenčík, M. Bundzel, I. Zolotová
We have build a device named RepaiR for strength measurements and isokinetic rehabilitation of the wrist joint. We have performed series of measurements on 25 healthy individuals and 10 patients with neuromuscular and traumatic impairments. Our initial goal was to verify that the measured data contain sufficient information to distinguish between healthy and not healthy subjects as a proof of concept. We have implemented Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) that processes the time structured measurements. LSTM effectively models the varying length of the input vector and the long term dependencies. We compare performances of our models on the data sets with varying minimal input vector lengths. We have proven that the measurements can be used to detect neuromuscular impairments and our best performing model worked with 77,6 % accuracy.
{"title":"Using LSTM for Detection of Wrist Related Disorders","authors":"Miroslav Jaščur, Norbert Ferenčík, M. Bundzel, I. Zolotová","doi":"10.1109/SAMI.2019.8782751","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782751","url":null,"abstract":"We have build a device named RepaiR for strength measurements and isokinetic rehabilitation of the wrist joint. We have performed series of measurements on 25 healthy individuals and 10 patients with neuromuscular and traumatic impairments. Our initial goal was to verify that the measured data contain sufficient information to distinguish between healthy and not healthy subjects as a proof of concept. We have implemented Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) that processes the time structured measurements. LSTM effectively models the varying length of the input vector and the long term dependencies. We compare performances of our models on the data sets with varying minimal input vector lengths. We have proven that the measurements can be used to detect neuromuscular impairments and our best performing model worked with 77,6 % accuracy.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115146630","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782785
J. Kubícek, M. Penhaker, David Oczka, M. Bužga, M. Augustynek, M. Cerný, Jaroslav Vondrák, Alice Krestanova
Electrogastrography (EGG) has a substantial importance for the clinical practice for examination of gastric disorders and the stomach function. From a view of the EGG signal processing, there is not a unified scheme for the EGG evaluation due to complex variable EGG representation. The most important issue of the EGG is an interference with other electrophysiological signals, particular attention is paid to the ECG (electrocardiography) signal. In this context, the Wavelet transformation gives satisfactory results. The main issue we have to deal with is an optimal setting of the Wavelet transformation for the EGG filtration. In this paper, we have proposed a novel scheme utilizing the modified Artificial Bee Colony algorithm with the goal of an optimal selection of the Wavelet filter design. Based on the ABC evolutionary process, we specify an optimal mother’s wavelet and the decomposition level for the ECG reduction. The optimization procedure has been objectively verified by using selected evaluation parameters.
{"title":"A Proposal of Optimal Wavelet Filter Design for EGG Signal Decomposition based on Modified ABC Evolutionary Optimization","authors":"J. Kubícek, M. Penhaker, David Oczka, M. Bužga, M. Augustynek, M. Cerný, Jaroslav Vondrák, Alice Krestanova","doi":"10.1109/SAMI.2019.8782785","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782785","url":null,"abstract":"Electrogastrography (EGG) has a substantial importance for the clinical practice for examination of gastric disorders and the stomach function. From a view of the EGG signal processing, there is not a unified scheme for the EGG evaluation due to complex variable EGG representation. The most important issue of the EGG is an interference with other electrophysiological signals, particular attention is paid to the ECG (electrocardiography) signal. In this context, the Wavelet transformation gives satisfactory results. The main issue we have to deal with is an optimal setting of the Wavelet transformation for the EGG filtration. In this paper, we have proposed a novel scheme utilizing the modified Artificial Bee Colony algorithm with the goal of an optimal selection of the Wavelet filter design. Based on the ABC evolutionary process, we specify an optimal mother’s wavelet and the decomposition level for the ECG reduction. The optimization procedure has been objectively verified by using selected evaluation parameters.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116761992","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782722
Jaroslav Vondrák, J. Grepl, M. Penhaker, M. Hlavácková, Petr Kovar, J. Kubícek
This paper deals with the design and construction of the electrosurgery instrument for hysteroscopy, which would replace the current set of tools, shorten the time required to perform the procedure and make it easier, safer and more precise to use. In this paper, we have proposed a designing the mechanism of the new instrument and its own shape, dimensions, manufacturing the prototype, testing and measurement of the required parameters. The resulting device is primarily intended for the finite element method strength analysis of the proposed instrument.
{"title":"Design and FEM Analysis of Laparoscopical Tool for Electrocoagulation Surgery","authors":"Jaroslav Vondrák, J. Grepl, M. Penhaker, M. Hlavácková, Petr Kovar, J. Kubícek","doi":"10.1109/SAMI.2019.8782722","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782722","url":null,"abstract":"This paper deals with the design and construction of the electrosurgery instrument for hysteroscopy, which would replace the current set of tools, shorten the time required to perform the procedure and make it easier, safer and more precise to use. In this paper, we have proposed a designing the mechanism of the new instrument and its own shape, dimensions, manufacturing the prototype, testing and measurement of the required parameters. The resulting device is primarily intended for the finite element method strength analysis of the proposed instrument.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129729576","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782745
L. Horváth
This paper is about a program which a new attempt to introduce latest virtual engineering technology in research at the Doctoral School of Applied Informatics and Applied Mathematics (DSAIAM), Óbuda University. The program which includes elaboration of new topics and subjects from latest achievement in virtual engineering and establishing virtual laboratory environment to develop experimental models to verify student research results is motivated by increased role of applied informatics and applied mathematics in industrial engineering activities. By now, advanced industrial product is operated by smart systems. Engineering activities rely upon systems engineering, intelligent informatics, and applied mathematics, harmonizing theory and experience at engineer decisions, and integrating fundamental, engineering problem solving, and product related research with activities of product development in industry. As the only proven way to cope with the above changes engineer activities are served by the same complex model system during whole innovation and life cycle of generic industrial product. Engineering modeling systems are awaited to integrate modeling capabilities for the above purpose. DSAIAM decided to extend its research program serving the above new engineering in applied informatics and applied mathematics. Laboratory of Intelligent Engineering Systems is being upgraded for the new program.
{"title":"Laboratory in Cloud for Model Systems of System Based Engineering Structures","authors":"L. Horváth","doi":"10.1109/SAMI.2019.8782745","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782745","url":null,"abstract":"This paper is about a program which a new attempt to introduce latest virtual engineering technology in research at the Doctoral School of Applied Informatics and Applied Mathematics (DSAIAM), Óbuda University. The program which includes elaboration of new topics and subjects from latest achievement in virtual engineering and establishing virtual laboratory environment to develop experimental models to verify student research results is motivated by increased role of applied informatics and applied mathematics in industrial engineering activities. By now, advanced industrial product is operated by smart systems. Engineering activities rely upon systems engineering, intelligent informatics, and applied mathematics, harmonizing theory and experience at engineer decisions, and integrating fundamental, engineering problem solving, and product related research with activities of product development in industry. As the only proven way to cope with the above changes engineer activities are served by the same complex model system during whole innovation and life cycle of generic industrial product. Engineering modeling systems are awaited to integrate modeling capabilities for the above purpose. DSAIAM decided to extend its research program serving the above new engineering in applied informatics and applied mathematics. Laboratory of Intelligent Engineering Systems is being upgraded for the new program.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114726835","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782725
Bence Dankó, Gábor Kertész
The aim of this paper is to introduce a Recurrent Convolutional Neural Network based on depth data to recognize the signs of the Hungarian fingerspelling alphabet. The training dataset contains depth data of 27 static and 15 dynamic signs. A 88.6% classification accuracy was measured for during the test with the recommended model in this paper, which is a special type of recurrent network containing LSTM and convolutional layers.
{"title":"Recognition of the Hungarian fingerspelling alphabet using Recurrent Neural Network","authors":"Bence Dankó, Gábor Kertész","doi":"10.1109/SAMI.2019.8782725","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782725","url":null,"abstract":"The aim of this paper is to introduce a Recurrent Convolutional Neural Network based on depth data to recognize the signs of the Hungarian fingerspelling alphabet. The training dataset contains depth data of 27 static and 15 dynamic signs. A 88.6% classification accuracy was measured for during the test with the recommended model in this paper, which is a special type of recurrent network containing LSTM and convolutional layers.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117350534","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782729
Bence Dávid, Gergő Láncz, Gergely Hunyady
The development of autonomous vehicles is one of the most active research areas in the automotive industry. The objective of this study is to present a concept for analysing the situation the vehicle is currently in, providing the necessary information to high level decision making algorithms. Our work focuses on a neural network based approach for assessing risks for each of the dynamically available manoeuvres in real-time and recognizing certain traffic scenarios to prepare the decision making and affect the outcome of the behaviour planner function regarding road safety. This paper provides insight to our research we carried out in collaboration with the Commercial Vehicle Systems Division of Knorr-Bremse Fékrendszerek Kft. Given the profile of the group, the aim of our study concentrated on heavy duty commercial vehicles, although the discussed algorithms are not truck-specific.
自动驾驶汽车的发展是汽车工业中最活跃的研究领域之一。本研究的目的是提出一个概念来分析车辆当前所处的情况，为高级决策算法提供必要的信息。我们的工作重点是基于神经网络的方法，用于实时评估每个动态可用操作的风险，并识别某些交通场景，以准备决策并影响有关道路安全的行为规划函数的结果。本文为我们与Knorr-Bremse f krendszerek Kft商用车系统部门合作开展的研究提供了见解。鉴于该群体的概况，我们的研究目标集中在重型商用车上，尽管所讨论的算法并非针对卡车。
{"title":"Highway Situation Analysis with Scenario Classification and Neural Network based Risk Estimation for Autonomous Vehicles","authors":"Bence Dávid, Gergő Láncz, Gergely Hunyady","doi":"10.1109/SAMI.2019.8782729","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782729","url":null,"abstract":"The development of autonomous vehicles is one of the most active research areas in the automotive industry. The objective of this study is to present a concept for analysing the situation the vehicle is currently in, providing the necessary information to high level decision making algorithms. Our work focuses on a neural network based approach for assessing risks for each of the dynamically available manoeuvres in real-time and recognizing certain traffic scenarios to prepare the decision making and affect the outcome of the behaviour planner function regarding road safety. This paper provides insight to our research we carried out in collaboration with the Commercial Vehicle Systems Division of Knorr-Bremse Fékrendszerek Kft. Given the profile of the group, the aim of our study concentrated on heavy duty commercial vehicles, although the discussed algorithms are not truck-specific.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124831916","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782719
Ádám Domina, V. Tihanyi
The driver assistance systems becomes more common in today’s vehicles, and in the future highly automated vehicles and large number of autonomous vehicles will appear in roads. In the beginning these systems only support the human driver, but later they will able to control the vehicle driving. Hence vehicles have to plan the path, and follow it accurately and safely. Furthermore it has to provide convenience for the passengers. To find a better trajectory following controller first it is necessary to test it in simulation environment, then to test it in real environment in a vehicle.The subject of this article is an implementation of a lateral dynamic bicycle model, and an implementation of different controllers. Besides it will contain the testing of the controllers. If the controllers work with sufficient precision in the simulation, it will be tested in a real vehicle. The essence of the test is the speed limit, where the simulation and the real test starting to deviate. In the end of the article we compare the performance of the different controllers and evaluate which is the most appropriate. Besides the difference will also be evaluated between the simulated results and the results on the real vehicle. This comparison reveal which is the speed limit, as long as the values calculated on the lateral dynamic bicycle model approximate the actual results in a simulation environment with sufficient precision.
{"title":"Comparison of path following controllers for autonomous vehicles","authors":"Ádám Domina, V. Tihanyi","doi":"10.1109/SAMI.2019.8782719","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782719","url":null,"abstract":"The driver assistance systems becomes more common in today’s vehicles, and in the future highly automated vehicles and large number of autonomous vehicles will appear in roads. In the beginning these systems only support the human driver, but later they will able to control the vehicle driving. Hence vehicles have to plan the path, and follow it accurately and safely. Furthermore it has to provide convenience for the passengers. To find a better trajectory following controller first it is necessary to test it in simulation environment, then to test it in real environment in a vehicle.The subject of this article is an implementation of a lateral dynamic bicycle model, and an implementation of different controllers. Besides it will contain the testing of the controllers. If the controllers work with sufficient precision in the simulation, it will be tested in a real vehicle. The essence of the test is the speed limit, where the simulation and the real test starting to deviate. In the end of the article we compare the performance of the different controllers and evaluate which is the most appropriate. Besides the difference will also be evaluated between the simulated results and the results on the real vehicle. This comparison reveal which is the speed limit, as long as the values calculated on the lateral dynamic bicycle model approximate the actual results in a simulation environment with sufficient precision.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"523 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129829181","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782753
N. Iacobici, E. Cazacu, M. Frigura-Iliasa, F. Frigura-Iliasa
Many industrial or domestic applications contain non-linear loads (converters, UPSs, process computers, LED lamps) that generate higher harmonics and distortions in the waveform spectrum of the absorbed current. When operating far from the sinusoidal shape of the current passing through the transformer, its windings generate additional losses, complementary to those of the permanent sinusoidal mode, thus reducing the transformer charging capacity (which has been designed for purely sinusoidal regimes). Therefore, in order not to cause supplementary heating inside its constructive elements, it is necessary to assess its power in relation to the level of the deforming regime.
{"title":"Computer Based Analysis for the Parameters of a Distribution Transformer in a Non-Sinusoidal Regime","authors":"N. Iacobici, E. Cazacu, M. Frigura-Iliasa, F. Frigura-Iliasa","doi":"10.1109/SAMI.2019.8782753","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782753","url":null,"abstract":"Many industrial or domestic applications contain non-linear loads (converters, UPSs, process computers, LED lamps) that generate higher harmonics and distortions in the waveform spectrum of the absorbed current. When operating far from the sinusoidal shape of the current passing through the transformer, its windings generate additional losses, complementary to those of the permanent sinusoidal mode, thus reducing the transformer charging capacity (which has been designed for purely sinusoidal regimes). Therefore, in order not to cause supplementary heating inside its constructive elements, it is necessary to assess its power in relation to the level of the deforming regime.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121562773","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}
Pub Date : 2019-01-01DOI: 10.1109/SAMI.2019.8782748
M. Kenyeres, J. Kenyeres, I. Budinská
The fault tolerance is an important design issue of many real-life applications based on the wireless sensor networks. However, the implementation of protective mechanisms results in increased overall energy consumption, making its usage not optimal. This paper focuses on the fault tolerance of the average consensus algorithm with the generalized Metropolis-Hastings weight design with a modified mixing parameter and without any protection. The robustness of the algorithm is examined using an MSE-metric for four various initial configurations and the obtained results are compared with concurrent weight designs for various failure probabilities.
{"title":"Vulnerability of Average Consensus Algorithm: Impact of Stochastic Communication Breakdowns on Generalized Metropolis-Hastings Weight Design","authors":"M. Kenyeres, J. Kenyeres, I. Budinská","doi":"10.1109/SAMI.2019.8782748","DOIUrl":"https://doi.org/10.1109/SAMI.2019.8782748","url":null,"abstract":"The fault tolerance is an important design issue of many real-life applications based on the wireless sensor networks. However, the implementation of protective mechanisms results in increased overall energy consumption, making its usage not optimal. This paper focuses on the fault tolerance of the average consensus algorithm with the generalized Metropolis-Hastings weight design with a modified mixing parameter and without any protection. The robustness of the algorithm is examined using an MSE-metric for four various initial configurations and the obtained results are compared with concurrent weight designs for various failure probabilities.","PeriodicalId":240256,"journal":{"name":"2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122314686","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：