Ali Ekber Özdemir

Reviewing and designing pre-processing units for RBF networks: initial structure identification and coarse-tuning of free parameters

This paper reviews some frequently used methods to initialize an radial basis function (RBF) network and presents systematic design procedures for pre-processing unit(s) to initialize RBF network from available input–output data sets. The pre-processing units are computationally hybrid two-step training algorithms that can be named as (1) construction of initial structure and (2) coarse-tuning of free parameters. The first step, the number, and the locations of the initial centers of RBF network can be determined. Thus, an orthogonal least squares algorithm and a modified counter propagation network can be employed for this purpose. In the second step, a coarse-tuning of free parameters is achieved by using clustering procedures. Thus, the Gustafson–Kessel and the fuzzy C-means clustering methods are evaluated for the coarse-tuning. The first two-step behaves like a pre-processing unit for the last stage (or fine-tuning stage—a gradient descent algorithm). The initialization ability of the proposed four pre-processing units (modular combination of the existing methods) is compared with three non-linear benchmarks in terms of root mean square errors. Finally, the proposed hybrid pre-processing units may initialize a fairly accurate, IF–THEN-wise readable initial model automatically and efficiently with a minimum user inference.

Usage of piezoelectric material and generating electricity

Today, another alternative usage area of the piezoelectric materials having a wide usage area from the automotive sector to the military industry is the production of electricity energy. In this study; information has been given regarding the piezoelectric impact and the usage areas of the materials showing this impact. The number of the studies conducted in the area of renewable energy production systems increase day by day as a result of the consumption of the traditional energy resources in time due to the increase in the demand for energy. For this reason; piezoelectric materials have the property of being an alternative renewable energy production material because they could transform the wind and wave energy into electricity energy in which permanent pressure changes could be provided due to the operational principles of the piezoelectric materials. In this study; the studies in the literature regarding the production of electricity energy in which piezoelectric materials have been used in majority have been explained.

Alternative renewable energy producing systems by utilizing piezoelectric transducers

Main purpose of this manuscript is to show and discuss some alternative renewable energy producing systems by utilizing piezoelectric crystal materials. It is known that piezoelectric materials have the ability to produce electricity from mechanical strain. This type of materials can be used for renewable energy production. In this study, 5 different designs are introduced as alternative energy producing systems by using piezoelectric materials. These kinds of systems utilizing piezoelectric materials need mechanical vibration for electricity producing. This mechanical vibration can be obtained from various sources such as wind or wave. These 4 designs are conceptual and it open to further improvements and critics. A major advantage of piezoelectric crystals over conventional materials such as the solar panels or thermoelectric generators used in renewable energy production is the significant cost efficiency and lower depreciation time.

Conceptual design of solar and sea based renewable energy production with thermoelectric generator

Main purposes of this paper are to show and discuss an alternative renewable energy producing system via thermoelectric generator (TEG). A TEG module produces electricity from temperature differences. This temperature differences is applied to two sides of TEG module that they are called hot and cold sides. In many applications TEG modules are used for energy producing from waste heat. But our paper is based on renewable energy producing. For this reason, needed temperature difference is ensured from solar energy that uses for heating process and sea that uses for cooling process. Solar collector tubes are used for concentrating solar radiation. Presented system is a conceptual design and a suitable system for any improvement.

A two-pass hybrid training algorithm for RBF networks

This paper presents a systematic construction of linearly weighted Gaussian radial basis function (RBF) neural network. The proposed method is computationally a two-stage hybrid training algorithm. The first stage of the hybrid algorithm is a pre-processing unit which generates a coarsely-tuned RBF network. The second stage is a fine-tuning phase. The coarsely-tuned RBF network is then optimized by using a two-pass training algorithm. In forward-pass, the output weights of RBF are calculated by the Levenberg - Marquardt (LM) algorithm while the rest of the parameters is remained fixed. Similarly, in backward-pass, the free parameters of basis function (center and width of each node) are adjusted by gradient descent (GD) algorithm while the output weights of RBF are remained fixed. Hence, the effectiveness of the proposed method for an RBF network is demonstrated with simulations.