11th Symposium on Neural Network Applications in Electrical Engineering最新文献

{"title":"Functional organization and hierarchy of control levels in Homo sapiens CNS","authors":"K. Nikolic, I. Šćepanović","doi":"10.1109/NEUREL.2012.6420010","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6420010","url":null,"abstract":"The paper tries to propose objectively existing hierarchy of control levels in Central Nervous System(CNS), based on already accomplished medical research results on Homo sapiens, i. e. Homo sapiens - sapiens CNS as well as the theory of control and the science of neural networks. Human CNS has been vague until 60 years ago. Although, there were intensive researches in the last 30 years worldwide, various enigmas remain. Numerous results that have been achieved cannot be considered final. This also refers to the ideas presented in this work, so they can be corrected or completed in the near or distant future. This work refers to CNS as very complex bio cybernetic adaptable system. In the Five Levels Control Hierarchy Scheme realization, we had in mind an integrative role of certain regions of cortex. The validity of the proposed scheme has been provided by checking of external and internal stimulus transmission. In the same manner, when analyzing higher psychological functions, we have taken into consideration the contribution of lower neural formations. The importance of development of all three types of intelligence: rational, emotional and social has been emphasized. The suggested scheme can be interesting to psychologists, psychiatrists, neurologists, as well as researchers whose field of research is neural networks and social intelligence.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127924934","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":"Neural networks in feedforward control of a robot arm driven by antagonistically coupled drives","authors":"P. Milosavljevic, N. Bascarevic, K. Jovanovic, G. Kvascev","doi":"10.1109/NEUREL.2012.6419967","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6419967","url":null,"abstract":"The paper deals with a rapidly growing trend in robotics - anthropomimetics. Following a human paragon, bio-inspired control of the robot arm is presented using artificial neural networks. This work demonstrates results achieved by feedforward control comparing feedforward backpropagation networks and radial bases networks. Use of radial bases network prevails as an efficient tool to evade the exact mathematical modeling and conventional control of the complex mechanical system that is highly nonlinear and includes passive compliance.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128389453","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":"Sampling, sparsity, and inverse problems","authors":"M. Vetterli","doi":"10.1109/NEUREL.2012.6420021","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6420021","url":null,"abstract":"Sampling is a central topic in signal processing, communications, and in all fields where the world is analog and computation is digital. The question is simple: When does a countable set of measurements allow a perfect and stable representation of a class of signals? This allows the reconstruction of the analog world, or interpolation. A related problem is when these measurements allow to solve inverse problems accurately, like source localization. Classic results concern bandlimited functions and shift-invariant subspaces, and use linear approximation. Recently, nonlinear methods have appeared, based on parametric methods and/or convex relaxation, which allow a broader class of sampling results. We review sampling of finite rate of innovation (FRI) signals, which are non-bandlimited continuous-time signals with a finite parametric representation. This leads to sharp results on sampling and reconstruction of such sparse continuous-time signals. We then explore performance bounds on retrieving sparse continuous-time signals buried in noise. While this is a classic estimation problem, we show sharper lower bounds for simple cases, indicating (i) there is a phase transition and (ii) current algorithms are close to the bounds. This leads to notions of resolution or resolvability. We then turn our attention to sampling problems where physics plays a central role. After all, many sensed signals are the solution of some PDE. In these cases, continuous-time or continuous-space modeling can be advantageous, be it to reduce the number of sensors and/or the sampling rate. First, we consider the wave equation, and review the fact that wave fields are essentially bandlimited in space-time domain. This can be used for critical sampling of acquisition or rendering of wave fields. We also show an acoustic source localization problem, where wideband frequency probing and finite element modeling show interesting localization power. Then, in a diffusion equation scenario, source localization using a sensor network can be addressed with a parametric approach, indicating trade-offs between spatial and temporal sampling densities. This can be used in air pollution monitoring and temperature sensing. In all these problems, the computational tools like FRI or CS come in handy when the modeling and the conditioning is adequate. Last but not least, the proof of the pudding is in experiments and/or real data sets.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"47 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126122319","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":"State estimation for power systems with multilayer perceptron neural networks","authors":"O. Ivanov, M. Garvrilas","doi":"10.1109/NEUREL.2012.6420026","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6420026","url":null,"abstract":"The Static state estimation is widely used in power systems for real time monitoring and analysis. Standard methods, such as the weighted least squares (WLS) algorithm, require the computation of bus admittance and Jacobian matrices and the solution is found in an iterative process. This paper presents an alternative for the classic state estimation (SE) algorithms, which uses a multilayer perceptron for the state estimator. Results are presented for the IEEE 14 bus system.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121481531","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":"Ensemble fusion methods for medical data classification","authors":"B. Krawczyk, G. Schaefer","doi":"10.1109/NEUREL.2012.6419993","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6419993","url":null,"abstract":"Medical data classification is acknowledged as an area of increasing importance, yet also poses many difficulties. One of these is that medical datasets are often imbalanced; that is that there are (potentially many) more samples of some classes compared to others. In this paper, a dedicated algorithm - Undersampling Balanced Ensemble (USBE) - is used to deal with this problem. We then conduct an experimental study to investigate the quality of different fusion methods for combining classifiers in an ensemble. Several fusion techniques based on discrete and continuous responses from (neural network) base classifiers are evaluated and it is shown that a careful choice of fusion method can boost the recognition rate of the minority class. In particular, a neural network trained fuser is shown to provide the best classification performance on two separate breast cancer datasets.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127722756","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":"GA-based optimisation of fuzzy rule bases for pattern classification","authors":"G. Schaefer","doi":"10.1109/NEUREL.2012.6419989","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6419989","url":null,"abstract":"Many decision making problems can be formulated as pattern classification problems. Therefore, high performing classification algorithms are highly sought after. Rule based pattern classification algorithms have an advantage that they do not appear to the user just as a “black box” but may provide additional insight based on the generated rules. In this paper, we focus on fuzzy rule based approaches which employ concepts from fuzzy logic theory to encode input patterns in a non-binary way. Starting with a basic fuzzy classifier we show that, through a simple modification, it can be turned into a cost sensitive classification method, and that classification performance can be improved through an error correction learning approach. Importantly, since rule-based classifiers are prone to rule explosion, we then show that a compact yet powerful rule base can be generated through an optimisation approach based on genetic algorithms.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132270905","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":"Detection of the first heart sound using fibre-optic interferometric measurements and neural networks","authors":"D. Zazula, S. Sprager","doi":"10.1109/NEUREL.2012.6420001","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6420001","url":null,"abstract":"Fiber-optic interferometry is used to measure subtle changes of the optical fibre length. It has been shown that in this way also the heart activity can be detected if the fibre is in direct or indirect contact with human body. The measured interferometric signal must be first demodulated and band-pass filtered to separate superimposed contributions of signal components. Only then their detection and classification is feasible. In this paper, we deploy feedforward neural network for detecting the first heart sound (S1) from fibre-optic interferometric signals. A reliable and robust classification of S1 and finding its location in time importantly support diagnosing of cardiac arrhythmias and valve abnormalities. Our experimental results on a group of ten healthy subjects that underwent submaximal stress testing before fibre-optic measurements yield 98.2±1.5% and 98.4±0.9% for sensitivity and precision of S1 detection, respectively.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133598015","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":"Coherent oscillations in minimal neural network of excitable systems induced by noise and influenced by time delay","authors":"N. Vasovic, N. Buric, I. Grozdanović, K. Todorović, A. Samčović","doi":"10.1109/NEUREL.2012.6419957","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6419957","url":null,"abstract":"Influence of small time-delays in coupling between noisy excitable systems on the coherence resonance and self-induced stochastic resonance is studied. Parameters of delayed coupled deterministic excitable units are chosen such that the system has only one attractor, namely the stationary state, for any value of the coupling and the time-lag. Addition of white noise induces qualitatively different types of coherent oscillations, and we analyzed the influence of coupling time-delay on the properties of these coherent oscillations. The main conclusion is that time-lag τ ≥ 1, but still smaller than the refractory period, and sufficiently strong coupling drastically change signal-to-noise ratio in the quantitative and qualitative way. An interval of noise values implies quite large signal to noise ratio and different types of noise induced coherence are greatly enhanced. We also observed coincident spiking for small noise intensity and time-lag proportional to the inter-spike interval of the coherent spike trains. On the other hand, time-lags τ <; 1 and/or weak coupling induce negligible changes in the properties of the stochastic coherence.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116578979","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":"Kinect in neurorehabilitation: Computer vision system for real time hand and object detection and distance estimation","authors":"Matija Štrbac, Marko Marković, D. Popović","doi":"10.1109/NEUREL.2012.6419983","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6419983","url":null,"abstract":"This paper presents image processing and scene analysis methods that can provide artificial vision that is of interest for automatic selection of hand trajectory and prehension. The new algorithm, which uses data from the Kinect sensor, allows real-time detection of the hand of the person grasping an object at working table in front of that person. The outputs are real world coordinates of the hand and the object. The image processing is done in Matlab over the depth image stream taken from the Microsoft Kinect as a sensory input. Results show that in the presented system setup our program is capable of tracking hand movements in the transverse plane and estimating hand and object position in real-time with tolerable estimation error for the selection of stimulation paradigm that could control hand trajectory.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133860303","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":"Neural network ensemble for power transformers fault detection","authors":"D. Furundžić, Z. Djurovic, V. Celebic, I. Salom","doi":"10.1109/NEUREL.2012.6420027","DOIUrl":"https://doi.org/10.1109/NEUREL.2012.6420027","url":null,"abstract":"Electrical transformers are the most important elements in the process of transmission and distribution of electricity. Depending on the size and position of the transformer, the sudden device failure can cause tremendous damage. Neural networks are widespread technique for transformer health monitoring. Neural Network Ensembles are an advanced neural technique that improves the accuracy and reliability in the transformers health diagnosis and failure prognosis. This paper describes a technique how to identify causal relation of dissolved gases in transformers oil and the current state of the transformers health. The described algorithm improves the interpretation of results obtained by dissolved gas analysis (DGA) technique. The most important result of this algorithm is a timely and reliable prediction of transformers failure based on incipient faults detection.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125677148","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}