The method of structural identification nonlinear dynamic systems is offered in the conditions of uncertainty. The method of construction the set containing the data about a nonlinear part of system is developed. The concept of identifiability system for a solution of a problem structural identification is introduced. The special class of structures S for a solution of problem identification is introduced. We will show that the system is identified, if the structure S is closed. The method of estimation the class of nonlinear functions on the basis of the analysis sector sets for the offered structure S is described. We showed, as on S a preliminary conclusion about a form of nonlinear function to make. We offer algorithms of structural identification of single-valued and many-valued nonlinearities. Examples of structural identification of nonlinear systems are considered.

Limited applicability of classical optimization methods influence the popularization of stochastic optimization techniques such as evolutionary algorithms (EAs). EAs are a class of probabilistic optimization techniques inspired by natural evolution process, witch belong to methods of Computational Intelligence (CI). EAs are based on concepts of natural selection and natural genetics. The basic principle of EA is searching optimal solution by processing population of individuals. This paper presents the results of simulation analysis of global optimization of benchmark function by Individually Directional Evolutionary Algorithm (IDEA) and other EAs such as Real Coded Genetic Algorithm (RCGA), elite RCGA with the one elite individual, elite RCGA with the number of elite individuals equal to population size. IDEA is a newly developed algorithm for global optimization. Main principle of IDEA is to monitor and direct the evolution of selected individuals of population to explore promising areas in the search space. The idea of IDEA is an independent evolution of individuals in current population. This process is focused on indicating correct direction of changes in the elements of solution vector. This paper presents a flowchart, selection method and genetic operators used in IDEA. Moreover, similar mechanisms and genetic operators are also discussed.

Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students’ course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students’ performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students’ performance database has been used; feedforward and radial basis function networks were trained for this task. The performances obtained from these networks were evaluated in consideration of achieved recognition rates and training time.

Accurate control of servomotor in proper positioning of objects is of utmost importance in industrial applications. This paper presents the position control of dc servomotor using pole placement technique via Ackerman’s formula. The mathematical model governing the dynamics of brush dc Pittman servomotor is developed and is then used to analyze which among the full state-feedback controller, feedback controller with feed-forward gain and integral controller with state feedback (SFB) will yield the best control performance. The steady state error, settling time and degree of overshoot are parameters on which the performance level is based. The whole simulation is validated using MATLAB/SIMULINK.

Due to the emergence of more data centric applications, the replication of data has become a more common phenomenon. In the similar context, recently, (PDDRA) a Pre-fetching based dynamic data replication algorithm is developed. The main idea is to pre-fetch some data using the heuristic algorithm before actual replication start to reduce latency In the algorithm further modifications (M-PDDRA) are suggested to minimize the delay in data replication. In this paper, M-PDDRA algorithm is tested under shared and output buffering scheme. Simulation results are presented to estimate the packet loss rate and average delay for both shared and output buffered schemes. The simulation results clearly reveal that the shared buffering with load balancing scheme is as good as output buffered scheme with much less buffering resources.

A new Genetic Algorithm based approach to the design of combinational logic circuits which uses only 2-1 multiplexers as the basic design unit has been proposed. To realize a function of n variables, conventional design needs 2n-1 units and n levels. Property of a multiplexer tree is that all the units in a level share the same control signal. In this paper, flexibility has been made in selecting the control signals so that units in the same level need not use the same select signal. Control signals can be any of the variables or functions derived from the immediate preceding level. Once a 100 % fit circuit is evolved, check for redundancy of units is made and redundant units are eliminated so that the circuit generated is optimal. It has been observed that the circuits evolved by this approach are superior to the circuits by conventional design in terms of area, power and delay. As power dissipation is an important metric in VLSI design, power loss can be minimized by eliminating unnecessary transitions/switching of idle multiplexers using a specific controller to select appropriate control signals. But in the proposed design power loss can be reduced without any additional device and hence these circuits can be recommended for low power devices.

In this study, linear and nonlinear methods were used to model forecasting performances on the daily crude oil production data of the Nigerian National Petroleum Corporation (NNPC). The linear model considered here is the random walk with drift, while the nonlinear model is the feed forward neural network model. The results indicate that nonlinear methods have better forecasting performance greater than linear methods based on the mean error square sense. The root mean square error (RMSE) and the mean absolute error (MAE) were applied to ascertain the assertion that nonlinear methods have better forecasting performance greater than linear methods. Autocorrelation functions emerging from the increment series, that is, log difference series and difference series of the daily crude oil production data of the NNPC indicates significant autocorrelations. As a result of the foregoing assertion we deduced that the daily crude oil production series of the NNPC is not firmly a random walk process. However, the original daily crude oil production series of the NNPC was considered to be a random walk with drift when we are not trying to forecast immediate values. The analysis for this study was simulated using MATLAB software, version 8.03.

Face veins based personal identification is a challenging task in the field of identity verification of a person. It is because many other techniques are not identifying the uniqueness of a person in the universe. This research paper finds the uniqueness of a person on the basis of face veins based technique. In this paper five different persons face veins images have been used with different rotation angles (left/right 900 to 2700 and 3150). For each person, eight different images at different rotations were used and for each of these images the same minimum cost minutiae tree (MCMT) is obtained. Here, Prim’s or Kruskal’s algorithm is used for finding the MCMT from a minutiae graph.
The MCMT is traversed in pre-order to generate the unique string of vertices and edge lengths. We deviated the edge lengths of each MCMT by five pixels in positive and negative directions for robustness testing.
It is observed in our experiments that the traversed string which consists of vertices and edge lengths of MCMT is unique for each person and this unique sequence is correctly identifying a person with an accuracy of above 95%. Further, we have compared the performance of our proposed technique with other standard techniques and it is observed that the proposed technique is giving the promising result.