{"title":"Q-learning based Reinforcement Learning Approach for Lane Keeping","authors":"Árpád Fehér, S. Aradi, Tamás Bécsi","doi":"10.1109/CINTI.2018.8928230","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928230","url":null,"abstract":"The paper presents the application of a Q-Iearning reinforcement learning method in the area of vehicle control. The purpose of the research presented is to design an end-to-end behavior control of a kinematic vehicle model placed in a simulated race track environment, by using reinforcement learning approach. The varied trajectory of the track to provide different situations for the agent. The environment sensing model is based on high-level sensor information. Track curvature, lateral position, and relative yaw angle can be reached from the current automotive sensors, such as camera or IMU based systems. The objectives were reached through the definition of a rewarding system, with subrewards and penalties enforcing lane keeping. After the description of the theoretical basis the environment model with the reward function is detailed. Finally the experiments with the learning process are presented and the results of the evaluation are given from some aspects of control quality and safety.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116553506","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}
{"title":"Methodolody of Advanced Graph Model-based Vehicle Systems' Analysis","authors":"L. Pokorádi","doi":"10.1109/CINTI.2018.8928238","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928238","url":null,"abstract":"Vehicle systems, such as automotive sensor networks, have network structures. During analysis or synthesis of an automotive sensor network, it is a key issue to define interconnections between the subsystems and elements. In the case of system with complex interconnections, the identification of connections is difficult due to its complexity. Graph theory is a well-known part of mathematics to study interconnections between elements of network structure systems. This paper proposes a convenient algorithm to determine and characterize the interconnections between the network-components.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126110799","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}
{"title":"Control design of variable-geometry suspension systems using a reconfiguration strategy","authors":"Dániel Fényes, B. Németh, P. Gáspár","doi":"10.1109/CINTI.2018.8928204","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928204","url":null,"abstract":"The role of variable-geometry suspension systems is to improve the lateral dynamics of a vehicle, in which the tilting of the wheels and the torque-vectoring functionalities can be coordinated. This paper proposes a reconfiguration strategy which is based on the design of an LPV control. The results of a reachability set analysis of the variable-geometry suspension system are also built into the reconfiguration strategy. The efficiency of the proposed control design is illustrated through simulation examples, in which various fault scenarios are considered.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"10 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130425799","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}
{"title":"Packet Loss and Duplication Handling in Stream Processing Environment","authors":"István Finta, Gergely Èliás, J. Illes","doi":"10.1109/CINTI.2018.8928195","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928195","url":null,"abstract":"In the course of transmission through networks a particular packet, like a Storm tuple or a performance/fault management (PM/FM) report in XML format of an Operation Support SystemOSS) application, data loss/out of order arrival/duplication phenomena may cause the packet not to arrive at the destination, to arrive exactly once or to arrive in several copies. Vast literature explores typical distributions for packet loss/duplication. At each layer of the network the entities processing the packets need to cope with packet loss/duplication in a certain way. In some cases loss/duplication does not matter too much. In other cases losses/duplications need to be very strictly handled. At the application level such strict handling is a must in case of an OSS application: missing or duplicated PM data may cause a wrong perception about the real performance of the network. In such cases for every received packet the receiving end needs to check whether the packet has already been received or not and then to insert it exactly once. The efficiency of the checking depends on the data structure being used for storing the packets or their keys. In this contribution we construct a model about typical statistical distribution of packet loss and duplication in stream processing environment. Then through the parameters of the model we assess the performance of an interval-based, lightweight, high speed filtering tree against traditional binary search trees.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124513349","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}
D. Drexler, I. Nagy, V. Romanovski, J. Tóth, L. Kovács
{"title":"Qualitative analysis of a closed-loop model of tumor growth control","authors":"D. Drexler, I. Nagy, V. Romanovski, J. Tóth, L. Kovács","doi":"10.1109/CINTI.2018.8928208","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928208","url":null,"abstract":"Tumor volume modeling and control is a promising way to design more efficient, personalized tumor treatment. This requires a model of tumor growth dynamics, and a control law to design the therapy. Tumor growth models are usually nonlinear, while most control laws are linear, and the controllers are designed for approximate linear models thus stable operation is guaranteed only locally. We consider the application of a linear state feedback for a nonlinear tumor growth model, and carry out the qualitative analysis of the closed-loop model. We give conditions for the control law parameters to have a globally stable closed-loop system, and analyze the effect of the control law parameters on the steady-state tumor volume and the maximal drug injection.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123253576","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}
{"title":"The Fourth Industrial Revolution in Hungary","authors":"L. Juhász","doi":"10.1109/CINTI.2018.8928236","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928236","url":null,"abstract":"In response to the challenges facing the industrial sector in the 2010s, Germany has presented an industrial modernisation program, the Industry 4.0 or the Fourth Industrial Revolution, which has received a lot of attention lately. In this article, we are looking at what progress has been made in Industry 4.0 in Hungary since its publication. In the first chapter, the problems leading to the publication of Industry 4.0 in the region and the circumstances in which they are born are considered. In the second chapter, we try to find a brief description of Industry 4.0 for a company's impact. In the third chapter, we take the government, university and industry initiatives in Hungary.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123036450","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}
{"title":"Fault Analysis and System Modelling in Vehicle Engineering","authors":"I. Nagy, Szilárd Tuloki","doi":"10.1109/CINTI.2018.8928203","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928203","url":null,"abstract":"In this paper a real (Nissan Leaf Z0), fully electric vehicle's sensor and communication network system will be explored, then the AMR wheel speed sensor operation is analyzed, drawing attention to the sensor faults and fault error spreading in the network. Furthermore, the vehicle's dynamic system model will be created and shown, how the sensor faults are built-in into this model.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123544472","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}
{"title":"CoPeD: Comparable Pedestrian Driver Data Set for Traffic Scenarios","authors":"Judith Jakob, J. Tick","doi":"10.1109/CINTI.2018.8928211","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928211","url":null,"abstract":"We present the Comparable Pedestrian Driver (CoPeD) data set for traffic scenarios. It contains several comparable video sequences for the categories lanes, crossing, and obstacles. Additionally, the data set includes single images of traffic signs that are of importance for pedestrians, namely bus stops, pedestrian and bicycle paths, and crosswalk signs. The CoPeD data set will be used to develop a concept for transferring camera based driver assistance algorithms to the assistance of the visually impaired. It is licensed under the Creative Commons Attribution 4.0 International License and hosted publicly which makes it available for all researchers.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121586645","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}
{"title":"Quadcopter power consumption analyzation at different landing trajectories","authors":"I. Lovas, A. Molnár","doi":"10.1109/CINTI.2018.8928215","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928215","url":null,"abstract":"The power supply of quadcopters is provided for by a battery. Flight time depends on total weight and on battery capacity. The most widespread one is the lithium polymer (LiPo) battery. Its advantage is that it has a high electricity transmission ability and a very good mass-capacity ratio. In case of a critical capacity level it is important for the quadcopter to land as soon as possible. Landing speed however is limited. The so-called vortex wave state (vortex ring state) appears at landing. The vortex ring state was first observed at helicopters. The reason for the phenomenon is that at descent the air flow speed arriving from below at a vertical descent approximates the speed of the air currents generated by the rotors. In this moment, the air flowing through the rotors creates a closed vortex wave and a low-pressure spot is created. In this case, the perfomance of the rotors drops, the quadrocopter might become instable and uncontrollable. This phenomenon can be avoided by limiting descent speed. In the article, I tested how to increase descent speed to be able to land safely as fast as possible, using the least possible energy.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129796817","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}
{"title":"Comparison of the Defuzzification Methods in Risk Assessment Applications","authors":"S. Koçak, E. Tóth-Laufer, L. Pokorádi","doi":"10.1109/CINTI.2018.8928196","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928196","url":null,"abstract":"In risk assessment models the soft computing methods are very popular, because they can handle the uncertainty and imprecision in the data and in the evaluation process. Nevertheless, in practical applications, especially equipment and engineering plans for the project sizing and design studies are needed to precise numerical values. In this paper a fuzzy-based risk assessment model is introduced, where the fuzzy information, which is obtained as the result of the inference, should be defuzzifed in order to give the necessary answer. The main aim of this paper is about presenting the risk assessment calculation and achievement of well-known traditional defuzzification methods using MATLAB Fuzzy Logic Toolbox application.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127829166","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}