{"title":"Nonlinear moving horizon predictive control of ground vehicles","authors":"G. Max, B. Lantos","doi":"10.1109/CINTI.2014.7028712","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028712","url":null,"abstract":"The paper deals with the approximately time-optimal control of automatically driven cars modeled with gear shift as discrete control input beside the continuous ones in a path between two path boundaries. The path boundaries are defined by their corner points that may be the result of image processing in real time or prescribed in advance. The path is divided into sections for which separate optimum control problems are solved in a nonlinear moving horizon predictive control (NMHPC) fashion increasing the semi-online character of the approach. In each section the problem can be formulated as a mixed-integer optimal control problem (MIOCP). The resulting MIOCP is solved by reformulating it to static mixed-integer nonlinear program (MINLP) using time discretization and direct multiple shooting method. Non-commercial open software packages are applied that substantially use the gradients of the objective function and the Jacobians of the constraints exploiting sparsity. The elaborated method can be applied both for combustion engine and electric driven cars. It can also form the basis to generate an offline database of a central general collision avoidance system (CAS) for varying path parameters on a grid which can further support real time applications.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125947825","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":"Experimental identification of the small turbojet engine MPM-20","authors":"Ladislav Nyulászi, L. Madarász","doi":"10.1109/CINTI.2014.7028726","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028726","url":null,"abstract":"This article deals with modelling of a small turbojet engine MPM-20 through programming environment Matlab and Simulink extension. The article describes methods of experimental identification (the method of successive integration, the area method, artificial neural network) along with their application to the measured engine parameter data obtained by testing in the Laboratory of Intelligent Control Systems of Jet Engines.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129742907","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":"Designing a digitally controlled fuel system for an experimental small turbojet engine","authors":"J. Hrabovský, R. Andoga, L. Főző","doi":"10.1109/CINTI.2014.7028725","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028725","url":null,"abstract":"This contribution presents a proposal and practical implementation of a digitally controlled fuel system for control of fuel supply into a small turbojet engine, iSTJ-21V. In the past, for the purposes of fuel metering to the engine MPM-20, which was a previous version of the iSTJ-21V, the servo valve LUN 6743 was used. However, this solution has several disadvantages such as increased strain on the fuel pump and non-linear characteristics. The new fuel control system was tested on a measuring stand and implemented into microcontroller platform and tuned during full operation of the engine. As microcontroller platform the 32 bit NXP LPC1768 microcontroller was chosen. The contribution consists of the principle of control of a small turbojet iSTJ-21V engine and a summary of the results in a graphical form. The main contribution of this work is to create a digitally controlled fuel system with sufficient accuracy control of fuel supply to the engine the need to increase its effectiveness and application of modern control algorithms at a higher level.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131244966","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":"Optimization of static and dynamic anti-windup compensator using new improved particle swarm optimization algorithm","authors":"Z. Shareef, Zubair Usman, M. A. Rana","doi":"10.1109/CINTI.2014.7028675","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028675","url":null,"abstract":"In this paper, the optimal static and the dynamic anti-windup compensators (AWC) are designed using a new improved particle swarm optimization (PSO) algorithm. The existing optimization techniques for AWC make use of LMI (Linear Matrix Inequality) and various concepts of nonlinear control concepts that require complex mathematics. For this optimization, we have developed and utilized an improved version of PSO. In this new improved PSO algorithm, first the problem-space is explored with constant non-zero inertia factor until the fitness function saturates to a local or global minima. The solution obtained thus far is then further refined by rerunning the algorithm but with inertia factor set to zero. This slight improvement enables a better search for a solution within the already explored problem-space. The optimized static and dynamic AWC is compared with the existing LMI-based AWC for the performance index, and it is observed that the improved PSO-based AWC gave better results and optimized value of the performance index.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"37 35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131270222","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":"Study of light electric vehicles propulsion solutions by means of finite element method based co-simulations","authors":"M. Ruba, L. Szabó","doi":"10.1109/CINTI.2014.7028710","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028710","url":null,"abstract":"The paper deals with the analysis of two solutions for light electric vehicles propulsion units. The propulsion machines taken into study are the switched reluctance and variable reluctance synchronous machines. Variable reluctance machines were chosen because there are cheep and reliable machines, these being key points for such applications. The analysis is performed by means of finite element method program coupled with MATLAB-Simulink in order to simulate the machine controlled by its electronic converter. The co-simulation is chosen in order to create realistic simulation conditions for both machines. The propulsion unit in study can be used for light electric vehicles, in particular for an electric vehicle used for people with disabilities. In the paper the two possible propulsion solutions are analyzed and compared, emphasizing benefits and drawbacks for each of them. This study will help designers in future decisions to be taken when the proper solution for such applications has to be selected. The study is focused on the torque development and machines performances point of view.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130046236","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":"Methods of reducing bio-cryptographic algorithms computational complexity","authors":"M. Velciu, V. Patriciu","doi":"10.1109/CINTI.2014.7028667","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028667","url":null,"abstract":"Traditional biometric systems have always been regarded with skepticism, due to the uniqueness and universality features of human biometrics - once stolen or compromised, they cannot be safely replaced. For this reason, common efforts of Cryptography and biometric systems researchers gave birth to Bio-cryptography, a domain which proposes to overcome the main security issues associated with biometrics usage, by generating or securing existing cryptographic keys, using biometric data. The main advantages brought by Bio-cryptography are represented by eliminating the need for storing biometric templates and the flexibility of resulted bio-cryptograms. On the other hand, one major drawback concerning bio-cryptographic algorithms is their high consumption of computational resources, caused by the various mathematical processing and large amounts of data used. This paper proposes two methods of reducing bio-cryptographic algorithms computational complexity: the usage of error-correcting codes in the secret key recovery stage and the shared biocryptograms approach for the entire biometric encryption process.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129588684","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":"Increasing memory security through data scrambling and information entropy models","authors":"M. Neagu, G. Sebestyen","doi":"10.1109/CINTI.2014.7028727","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028727","url":null,"abstract":"The memory of any digital system stores sensitive information that needs to be protected from any type of attacks. In the last decade, device specific attacks have been reported and analyzed, attacks that successfully extract private encryption keys from AES algorithms. In this work, a novel technique is proposed which targets the increase of security in memory systems through the use of data scrambling and information entropy models. In order to make the proposed solution viable, dissemination rules are employed and explained. Also, the method is evaluated from several points of view.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114500125","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":"Is AdaBoost competitive for phoneme classification?","authors":"G. Gosztolya","doi":"10.1109/CINTI.2014.7028650","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028650","url":null,"abstract":"In the phoneme classification task of speech recognition, usually Gaussian Mixture Models and Artificial Neural Networks are used. For other machine learning tasks, however, several other classification algorithms are also applied. One of them is AdaBoost.MH, reported to have high accuracy, which we tested for phoneme recognition on the well-known TIMIT dataset. We found that it can achieve an accuracy comparable to standard ANNs in this task, but lags behind recently-proposed Deep Neural Networks. Based on our experimental results, we list a number of possible reasons why this might be so.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132328370","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}
Thomas Kopinski, Darius Malysiak, A. Gepperth, U. Handmann
{"title":"Time-of-flight based multi-sensor fusion strategies for hand gesture recognition","authors":"Thomas Kopinski, Darius Malysiak, A. Gepperth, U. Handmann","doi":"10.1109/CINTI.2014.7028683","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028683","url":null,"abstract":"Building upon prior results, we present an alternative approach to efficiently classifying a complex set of 3D hand poses obtained from modern Time-Of-Flight-Sensors (TOF). We demonstrate it is possible to achieve satisfactory results in spite of low resolution and high noise (inflicted by the sensors) and a demanding outdoor environment. We set up a large database of pointclouds in order to train multilayer perceptrons as well as support vector machines to classify the various hand poses. Our goal is to fuse data from multiple TOF sensors, which observe the poses from multiple angles. The presented contribution illustrates that real-time capability can be maintained with such a setup as the used 3D descriptors, the fusion strategy as well as the online confidence measures are computationally efficient.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114188209","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 of incoming calls by a windows phone based brain computer interface","authors":"J. Katona, D. Peter, T. Ujbanyi, A. Kovari","doi":"10.1109/CINTI.2014.7028661","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028661","url":null,"abstract":"The research area of “brain control” includes different innovative systems based on brain computer interface (BCI) technology and it is implemented, integrated, studied and tested at universities and research institutes. Using this technology, in this research a complex system has been developed that is suitable to observe EEG signals based on the observation of brain activity, the electric and magnetic signals of neural activity. Furthermore, based on the processing of the measured EEG signals, it is also suitable to implement EEG-based control and testing. Calculating the brain waves of brain activity by using quantitative EEG analysis, the developed test system can control answering and rejecting mobile phone calls. The results of this research can give the basis of helping disabled people or complete limb amputees to establish contacts with others.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114342845","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}