-
[show abstract]
[hide abstract]
ABSTRACT: We introduce a dynamic programming algorithm to perform linear segmentation of concatenated texts by global minimization of a segmentation cost function which consists of: (a) within-segment word similarity (expressed in terms of the generalized density of the text dotplot) and (b) prior information regarding segment length. Our algorithm is evaluated on two Greek text collections and proves that it outperforms several other algorithms because it performs global optimization of a global cost function.
Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on; 11/2007
-
[show abstract]
[hide abstract]
ABSTRACT: The procedure of harmonic insertion is generalized in this paper. Analytical expressions of the voltage spectra are derived. The insertion of the 3rd harmonic to the modulating signal, which is of particular interest, is considered as a special case. It is demonstrated in this case that the fundamental harmonic component of the phase and the line-to-line voltage is not affected by the insertion of the 3rd harmonic for sufficiently high values of the chopping ratio. However it has been shown that the higher harmonic spectrum is significantly improved as compared to the case of pure sinusoidal modulation. For different values of the fundamental component the optimal values of the amplitude of the third harmonic to be inserted have been calculated so that the distortion factor of the higher harmonic spectrum is minimized. Other cases of harmonic insertion are also considered which provide spectrum efficiency improvement. Experimental results are given which have been obtained by means of a microcomputer controlled PWM generator constructed for this purpose.
European Transactions on Electrical Power 09/2007; 2(3):143 - 151. · 0.58 Impact Factor
-
Stochastic Environmental Research and Risk Assessment 03/2007; 21(4):451-455. · 1.52 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We introduce a multi-model parameter estimation method for nonlinear dynamic systems. The method employs a genetic search
with a recursive probability selection mechanism for parameter estimation. The method is applied to nonlinear systems with
known structure and unknown parameters. A new technique is used to determine the selection probabilities. First, a population
of models with random parameter vectors is produced. Second, a probability is recursively assigned to each member of a generation
of models. The probabilities reflect the closeness of each model output to the true system output. The probabilities have
to satisfy an entropy criterion so as to enable the genetic algorithm to avoid poor solutions. This is a new feature that
enhances the performance of the GA on the parameter estimation problem. Finally, the probabilities are used to create a new
generation of models by the genetic algorithm. Numerical simulations are given concerning the parameter estimation of a planar
robotic manipulator.
07/2006: pages 1008-1017;
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we present a promising technique that enhances the efficiency of GAs, when they are applied to constrained optimisation
problems. According to this technique, the problem constraints are included in the fitness function as penalty terms, that
vary during the GA evolution, facilitating thus the location of the global optimum and the avoidance of local optima. Moreover
we proceed to test the effect that the rate of change in the fitness function has on GA performance. The tests are performed
on two well-known real-world optimisation problems: the Cutting Stock problem and the Unit Commitment problem. Comparative
results are reported.
07/2006: pages 211-220;
-
[show abstract]
[hide abstract]
ABSTRACT: Different optimisation methods developed for the solution of the nonlinear OPF problem with both continuous and discrete variables are compared. Two mathematical programming methods are compared with two metaheuristics, an enhanced genetic algorithm and a particle swarm optimisation implementation. Test results from the application of the methods to several IEEE systems are presented and compared. Useful conclusions are drawn concerning the execution times and the 'optimum' costs provided by all four tested methods.
IEE Proceedings - Generation Transmission and Distribution 02/2006; · 0.48 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We present a procedure for the segmentation of hydrological and environmental time series. The procedure is based on the minimization
of Hubert’s segmentation cost or various generalizations of this cost. This is achieved through a dynamic programming algorithm,
which is guaranteed to find the globally optimal segmentations with K=1, 2, ..., K
max segments. Various enhancements can be used to speed up the basic dynamic programming algorithm, for example recursive computation
of segment errors and “block segmentation”. The “true” value of K is selected through the use of the Bayesian information criterion. We evaluate the segmentation procedure with experiments
which involve artificial as well as temperature and river discharge time series.
Stochastic Environmental Research and Risk Assessment 12/2005; 20(1):77-94. · 1.52 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents a comparison of different optimization methods developed for the solution of the nonlinear OPF problem with both continuous and discrete variables. Two mathematical programming methods are compared with two metaheuristics, a particle swarm optimization implementation and an enhanced genetic algorithm. Test results from the application of the methods to several IEEE systems are presented and compared. Useful conclusions are drawn concerning the execution times and the "optimum" costs provided by all four tested methods.
Intelligent Systems Application to Power Systems, 2005. Proceedings of the 13th International Conference on; 12/2005
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, a genetic algorithm solution to the hydrothermal coordination problem is presented. The generation scheduling of the hydro production system is formulated as a mixed-integer, nonlinear optimization problem and solved with an enhanced genetic algorithm featuring a set of problem-specific genetic operators. The thermal subproblem is solved by means of a priority list method, incorporating the majority of thermal unit constraints. The results of the application of the proposed solution approach to the operation scheduling of the Greek Power System, comprising 13 hydroplants and 28 thermal units, demonstrate the effectiveness of the proposed algorithm.
IEEE Transactions on Power Systems 09/2004; · 2.68 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The authors reply to the comments made and the questions asked by Yog Raj Sood et al. (see ibid., vo.18, no.3, p.1219, 2003) relative to the original paper (see ibid., vol 17, p.229-36, 2002).
Power Systems, IEEE Transactions on 09/2003; 18(3):1219-.
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents the Bayesian Combined Predictor (BCP), a probabilistically motivated predictor for Short Term Load Forecasting (STLF) based on the combination of an artificial neural network (ANN) predictor and two linear regression (LR) predictors. The method is applied to STLF for the Greek Public Power Corporation dispatching center of the island of Crete, using 1994 data, and daily load profiles are obtained. Statistical analysis of prediction errors reveals that during given time periods the ANN predictor consistently forecasts better for certain hours of the day, while the LR predictors forecast better during for the rest. This relative prediction advantage may change over different time intervals. The combined prediction is a weighted sum of the ANN and LR predictions, where the weights are computed using an adaptive update of the Bayesian posterior probability of each predictor, based on their past predictive performance. The proposed method outperforms both ANN and LR predictions.
05/2003;
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we introduce a dynamic programming algorithm which performs linear text segmentation by global minimization of a segmentation cost function which incorporates two factors: (a) within-segment word similarity and (b) prior information about segment length. We evaluate segmentation accuracy of the algorithm by precision, recall and Beeferman's segmentation metric.
05/2003;
-
[show abstract]
[hide abstract]
ABSTRACT: Most of the text categorization algorithms in the literature represent documents as collections of words. An alternative which has not been sufficiently explored is the use of word mcanin#s, also known as senses. In this paper, using several algorithms, we compare the categorization accuracy of classifiers based on words to that of classifiers based on senses. The document collection on which this comparison takes place is a subset of the annotated Brown Corpus semantic concordance. A series of experiments indicates that the use of senses does not result in any significant categorization improvement.
05/2003;
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we examine a problem which arises in connection with the application of the Lainiotis Partition Algorithm to tasks of signal classification, prediction and parameter estimation. We are particularly interested in tasks which involve composite systems, comprising of a finite number of switched sub-systems. The problem we consider arises in situations of unsupervised, online classification and modeling and can be characterized as a problem of data allocation, i.e. how to partition observed data into separate training sets and use the members of each set for training the model of a particular sub-system. We propose an algorithm that effects unsupervised, online data allocation and prove that under mild separability conditions the algorithm converges to the "correct" solution. The proposed algorithm is also tested by numerical experiments.
05/2003;
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents an interactive-, menu-driven prototype software platform, namely automatic control educational software (ACES), for self-instruction and self-evaluation in automatic control systems. ACES is used for enriching instruction in automatic control at Aristotle University of Thessaloniki, Greece, in the Department of Electrical and Computer Engineering. The ACES platform includes theory with hyperlinks, a concept-graph, and a database with exercises. Students' answers to exercises are evaluated automatically "on-line." Furthermore, exercises can be proposed automatically by ACES. An instructor/supervisor can support in person the learning effort of a student, monitor the progress of a student, and, also, tailor a course's contents on the modular ACES platform. Two statistical hypothesis tests on both attitude questionnaires and student marks in the final (written) exam confirmed that the employment of ACES in the educational process can improve the performance of students in an automatic control course although the attitude of students toward the course does not change significantly with the use of ACES.
IEEE Transactions on Education 03/2003; · 1.02 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we present a promising technique that enhances the efficiency of GAs, when they are applied to constrained optimisation problems.
04/2002;
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents an enhanced genetic algorithm for the solution of the optimal power flow with both continuous and discrete control variables. The continuous control variables modeled are unit active power outputs and generator-bus voltage magnitudes, while the discrete ones are transformer-tap settings and switchable shunt devices. A number of functional operating constraints, such as branch flow limits, load bus voltage magnitude limits, and generator reactive capabilities are included as penalties in the genetic algorithm fitness function. Advanced and problem-specific operators are introduced in order to enhance the algorithm's efficiency and accuracy. Numerical results on two test systems are presented and compared with results of other approaches.
IEEE Power Engineering Review 03/2002; 22(2):60-60.
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we explore some aspects of the problem of online unsupervised learning of a switching time series, i.e., a time series which is generated by a combination of several alternately activated sources. This learning problem can be solved by a two-stage approach: 1) separating and assigning each incoming datum to a specific dataset (one dataset corresponding to each source) and 2) developing one model per dataset (i.e., one model per source). We introduce a general data allocation (DA) methodology, which combines the two steps into an iterative scheme: existing models compete for the incoming data; data assigned to each model are used to refine the model. We distinguish between two modes of DA: in parallel DA, every incoming datablock is allocated to the model with lowest prediction error; in serial DA, the incoming datablock is allocated to the first model with prediction error below a prespecified threshold. We present sufficient conditions for asymptotically correct allocation of the data. We also present numerical experiments to support our theoretical analysis.
IEEE Transactions on Neural Networks 02/2002; 13(6):1432-49. · 2.95 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we examine a problem which arises in connection with the application of the Lainiotis Partition Algorithm to tasks of signal classification, prediction and parameter estimation. We are particularly interested in tasks which involve composite systems, comprising of a finite number of switched sub-systems. The problem we consider arises in situations of unsupervised, online classification and modeling and can be characterized as a problem of data allocation, i.e. how to partition observed data into separate training sets and use the members of each set for training the model of a particular sub-system. We propose an algorithm that effects unsupervised, online data allocation and prove that under mild separability conditions the algorithm converges to the correct solution. The proposed algorithm is also tested by numerical experiments. Keywords: Partition Algorithms, Classification, Prediction, Parameter Estimation, Multiple Models. 1.
11/2001;
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we explore some aspects of the problem of on-line, unsupervised learning of a switching time series, i.e. a time series which is generated by a combination of several, alternately activated sources. This learning problem can be solved by a two-stage approach: (a) separating of the incoming data to several datasets (one dataset corresponding to each source); (b) developing one model per dataset (i.e. one model per source). We introduce a general data allocation methodology which combines the two steps into an iterative scheme: existing models compete for the incoming data; data assigned to each model are used to refine the model. We distinguish between two modes of data allocation: in parallel data allocation every incoming datablock is allocated to the model with lowest prediction error; in serial data allocation the incoming datablock is allocated to the first model with prediction error below a prespecified threshold. We present su#cient conditions for asymptotically correct allocation of the data. We also present numerical experiments to support our theoretical analysis. 1
11/2001;
