2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)最新文献

{"title":"Novel Contradiction Resolution in Fixed Point Transformation-based Adaptive Control","authors":"H. Khan, J. Tar","doi":"10.1109/CINTI.2018.8928235","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928235","url":null,"abstract":"In the control practice the problem of “underactu-ation” often arises: for controlling the state of a multivariable system the number of the independently applicable control signals is smaller than that of the components of the state variables. Then either certain state components can propagate in time without direct control while the others are precisely controlled, or some compromise has to be elaborated on the basis of which the control forces are “distributed” to keep each variable under partial and imprecise control. Normally, only imprecise and/or incomplete system models are available. Traditionally a compromise is achieved by the use of optimal controllers in which the often contradictory requirements are represented as nonnegative contributions to a cost function that is minimized under the constraints representing the available approximate dynamic model. The heuristic “Receding Horizon Controller” (RHC) uses “Nonlinear Programming” (NP): the optimum is found over a discrete grid by the use of Lagrange's Reduced Gradient Method. For dealing with imprecise modeling and unknown external disturbances the control forces are calculated for and are exerted only over a “short” horizon, then, after observing the actual state by measurements, a new horizon is designed, etc. The adaptive controllers, that normally are designed on the basis of Lyapunov's 2nd method, do not allow simple integration with the optimal controllers. The design of optimal and adaptive controllers is a challenge. To take up this challenge in Adaptive Control Lyapunov's 2nd method was replaced by a “Fixed Point Transformation” (FPT)-based approach. At first the control problem is transformed into finding the fixed point of a contractive map over a Banach Space, then it is solved via iteration. With this approach the contradiction resolution was tackled by time-sharing instead of minimizing a cost function. Alternatively, the minimization of a cost function was tackled by FPT simply by driving the gradient of the Auxiliary Function directly to zero. In the present paper, to our best knowledge in the first time, a novel cost function-free adaptive solution is suggested for underactuated systems in which the compromise between the various requirements is “built in” into the FPT by interpretation. This approach is as heuristic as the RHC, and in general no good convergence can be guaranteed. As an application example the control of a 2 degree of freedom system, the FiztHugh Neuron Model is considered via computer simulations. The possibilities and the limitations of the suggested method are discussed.","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":"129316282","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":"Establishing sleep stages using Delta, Theta and Gamma oscillations from long term Local Field Potential (LFP) recordings in mice","authors":"László Molnár, J. Domokos, Isabella Ferando, I. Módy","doi":"10.1109/CINTI.2018.8928237","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928237","url":null,"abstract":"Most current methods determine sleep and awake stages in rodents by using subjective thresholding methods. In contrast, we implemented objective thresholding algorithms based on intrinsic characteristics of local field potential (LFP) signals. We recorded brain LFP and infrared video of freely moving adult mice. Continuous long-lasting (several weeks) recordings were performed during 12/12 hours of dark and light cycles. The movement information from video recordings was recorded and processed using iSpy Open Source Video Surveillance Software, by subtracting each video frame from the previous, thus obtaining an activity measure (A). We used Igor Pro technical graphing and data analysis software to process the LFP recording by band-pass FIR filtering: 1–4 Hz for Delta oscillations, 5–12 Hz for Theta and 30–120 Hz for Gamma. Using an 8 s sliding window (in steps of 1 or 0.5 s) over 12 hour periods we calculated the Root Mean Square (RMS) values of each filtered wave, obtaining the DeltaRMS, ThetaRMS and GammaRMS. The histograms of these RMS values showed bimodal normal (Gaussian) distributions. Similarly, the distributions of GammaRMS/DeltaRMS (G/D) and ThetaRMS/DeltaRMS (T/D) were also bimodal. Using a Gaussian probability-weighting mechanism, we defined the NREM (non-REM) sleep segments. This first findings were adjusted by the GammaRMS intensity for each period. The remaining periods were classified to REM or A(wake) depending on the bimodal distribution of ThetaRMS/DeltaRMS function together with a post-hoc classification based on the motor activity record.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"18 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":"129950378","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":"Deep sleep algorithms in battery powered TDMA wireless mesh sensor network","authors":"J. Kopják, Gergely Sebestyen","doi":"10.1109/CINTI.2018.8928209","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928209","url":null,"abstract":"In wireless sensor networks the sensor nodes in most cases have a battery supply. The lifetime of the battery in the sensor nodes can be increased by reducing the power consumption of the radio communication cycles. This paper focuses on the possible communication algorithms to reduce the power consumption of the receiver mode in the sensor nodes in a multi-hop TDMA wireless mesh network with flooding routing. One possible aspect of reducing power consumption is the synchronized sleep mode of the sensor nodes. In this case the sensor nodes can be sent to sleep mode by disabling the radio communication until the next data collecting period. Another aspect discussed in this paper is to optimize the different communication modes during the radio communication in the network. The analyzed communication algorithms based on the FRC (Fast Respond Command) central data collecting method.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"9 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":"127736161","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":"Pre-processing for the RBF-NNs with flexible parameters for multi-dimensional data","authors":"Mariia Martynova, Ondrej Kaas","doi":"10.1109/CINTI.2018.8928225","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928225","url":null,"abstract":"This paper describes a solution to the optimization task of approximation by radial-basis-function (RBF) neural network. The proposed method is created for the teacher NNs for complex system and is addressed to the problem of variable shape parameters for data using the RBF. It involves the k-means algorithm, the RBF neural network, the ideas of the algorithm for placing new centers of neurons and the structure of the future deep learning complex neural network (NN).","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"22 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":"115921683","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":"Gear efficiency modeling in a simulation model of a DC gearmotor","authors":"I. Kecskés, E. Burkus, P. Odry","doi":"10.1109/CINTI.2018.8928193","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928193","url":null,"abstract":"This paper presents how to build a simple simulation model of a DC gearmotor based on available datasheet parameters. The energy loss caused by the gearhead is broken down to inertia, viscous friction and coulomb friction. The gearhead inertia is transferred to the motor inertia, while the losses caused by the two frictions are calculated and added to the motor load torque. The coulomb friction is simulated as a constant, speed-independent efficiency - based on the datasheet's efficiency. The viscous friction is implemented as a speed dependent loss, for which the damping coefficient is estimated from other available parameters. The constructed model is tested and validated through constant voltage and constant speed tests. The plotted torque graphs illustrate the motor, gear and gearmotor efficiency.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"17 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":"114243694","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":"Dangers in autonomous vehicles","authors":"Csilla Eva Berecz, G. Kiss","doi":"10.1109/CINTI.2018.8928189","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928189","url":null,"abstract":"Nowadays, one of the biggest expectation of people of this era is the moment when self-driving cars finally become quotidian on the roads, just like in sci-fi movies. Car factories and software developers have been working tirelessly for years to achieve this goal, and these vehicles are passing their tests successfully, in some cases even preventing accidents that would have been the driver's fault. However, there are also reports of failed tests as the technology is still being tweaked. The aim of this article is to shed light on some of the factors that negatively affect different stages of development and to examine the functionality of these vehicles, paying close attention to software related issues that include information protection, security breaches, certain sensory malfunctions that may occur due to faulty road conditions, and even deliberate attempts to damage the vehicle.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"82 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":"127198879","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":"Modelling and Control of Complex Flexible Manufacturing Systems by Means of Petri Nets","authors":"F. Capkovic","doi":"10.1109/CINTI.2018.8928197","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928197","url":null,"abstract":"The paper presents an approach to modelling and control of complex flexible manufacturing systems (FMS) based on Petri nets (PN). Two kinds of PN are used here, namely place/transition PN (P/T PN) and timed PN (TPN). The supervisor is synthesized by means of P-invariants of P/T PN, taking into account prescribed conditions eliminating critical situations by means of the mutual exclusion method. The performance evaluation of the supervised systems is accomplished in Matlab by means of the TPN model, related to the P/T PN model, in the process of simulation. The simulation results are presented in the graphical form.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"61 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":"122165641","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":"Walking Pad and Gyroscope-Based Object Manipulation for Virtual Reality CAVE","authors":"M. Hudák, Š. Korečko, B. Sobota, Tomáš Balluch, Jakub Grib","doi":"10.1109/CINTI.2018.8928223","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928223","url":null,"abstract":"Thanks to the recent advancement in computer hardware and software, the virtual reality is becoming a hot topic, again. It can be utilized in various settings - from entertainment through education and workforce training to a training and assessment of visuospatial cognitive functions. A fully immersive virtual reality experience requires not only high quality stereoscopic graphical output but also input devices that feel natural to use. In this paper we present two cost-effective solutions that try to fulfil this requirement: a low-cost modular walking pad and an application for an Android device, which utilizes the gyroscope of the device to manipulate with objects in a virtual environment. While both solutions have been primarily developed to be used with cave automatic virtual environments, they are also suitable for installations utilizing see-through head-mounted displays or ordinary computer screens.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"6 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":"123768034","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":"Improve the Accuracy of Neural Networks using Capsule Layers","authors":"János Hollósi, C. Pozna","doi":"10.1109/CINTI.2018.8928194","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928194","url":null,"abstract":"Neural networks are a powerful and widely used tools for various classification and segmentation tasks. Nowadays, in the field of computer vision the convolutional neural networks (CNNs) are the most popular solution for many problems. The CNNs performance is looks like exceptionally great when the test images are very close to the training dataset. However if the input images are transformed, such as rotating or tilting, the efficiency of the neural network may be greatly reduced. A new kind of neural network, is called capsule network, is trying to solve this problem. In this paper we examines the efficiency of the capsule network, by trying to increase the accuracy of different networks with capsule layers.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"48 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":"132815272","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":"Preliminary Investigation on the Possible Adaptive Control of an Inverted Pendulum-type Electric Cart","authors":"H. Khan, T. Faitli, Tamás Szili, J. Tar","doi":"10.1109/CINTI.2018.8928229","DOIUrl":"https://doi.org/10.1109/CINTI.2018.8928229","url":null,"abstract":"The model-based control of Classical Mechanical systems often has to cope with the problem of the lack of precise dynamic models. In the case of underactuated systems this problem is further burdened by the existence of strong nonlinearities, even in the form of dynamic singularities. The simultaneous existence of these problems does not promise successful application of the traditional robust control approaches that are based on a Linear Time-invariant (LTI) approximation of the model in the vicinity of some “working point” and the intensive use of the frequency domain. The relatively simple, strongly nonlinear Robust Variable Structure/Sliding Mode (VS/SM) controllers may produce undesirable chattering while the more sophisticated, Lyapunov function-based adaptive techniques may require complicated computations because the dynamic model of a relatively simple mechanical structure computationally may be quite complicated, especially when the system is driven by a Pulse Width Modulated (PWM), brushless electric DC motor that together with the mechanical components determines a relative order 3 control task yielding terms of order 0, 1, 2, and 3 time-derivatives of the state variables. The aim of the present paper is to investigate whether to what extent the calculation of these terms can be eliminated by the use of a simple, Fixed Point-iteration (FPI)-based adaptive controller that could be implemented by the use of an embedded micro-controller. The simulation results that belong to a certain solution are promising.","PeriodicalId":409514,"journal":{"name":"2018 IEEE 18th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"356 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":"132863189","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}