Informatics Publishing Limited

R. Kaleeswari ¹, M. Rajalakshmi ¹

Affiliations
1 Sankara College of Science and Commerce, Coimbatore, IN

Abstract

Biological studies progress through the expansion of the expertise technologies. A DNA microarray is a high throughput technology used in molecular biology and in medicine. DNA micro arrays can be used to measure changes in expression levels or to detect single nucleotide polymorphisms. One can analyze the expression of many genes in a single reaction quickly and in an efficient manner. The main application of microarray technology is disease diagnosis. Patterned DNA microarrays are promising as a potent and cost-effective tool for large scale analysis of gene expression. Microarrays can be used to measure the relative quantities of specific mRNAs in two or more tissue samples for thousands of genes simultaneously. As the power of this technology has been recognized, many open queries remain about appropriate analysis of microarray data. One such is about the valid estimates of the relative expression for genes that are not biased by ancillary sources of variation. Be acquainted with that there is inherent noise in microarray data will the recognition system estimates the error variation associated with an estimated change in expression and construct the error bars. For the above impenetrability and to get better consequences of the system with accuracy a new learning algorithm called Extreme Learning Machine (ELM) is used. ELM avoids problems like local minima improper learning rate and overfitting commonly faced by iterative learning methods and completes the training very fast. ELM uses the error free ANOVA methods in the preprocessing phase itself. Here it demonstrates that ANOVA methods can be used to normalize microarray data and provide estimates of changes in gene expression that are corrected for potential perplexing effects. The multicategory classification performance of ELM is evaluated on Lymphoma data set. The results indicate that ELM with ANOVA test produces comparable or better classification accuracies with reduced training time and implementation complexity compared to Support Vector Machine (SVM) with ANOVA.

Full Text

     

C. Karthik ¹, K. Valarmathi ¹, M. Rajalakshmi ¹

Affiliations
1 Kalasalingam University, Tamilnadu, IN

Abstract

This paper is focuses modeling of the last part of the paper machine – the drying section. Paper is dried by letting it pass through a series of steam heated group of cylinders and the evaporation is thus performed by the latent heat of vaporization of the steam. By adjusting the set point of the steam pressure controllers to the cylinders we can control the moisture in the paper. There exist several incentives to focus on the performance of the moisture control. The time to perform a grade change is often limited by the moisture then time is directly correlated to economic profit. The process model is identified regularly and the changes in its characteristics are observed periodically. This method of identification gives a great advantage over the conventional controller tuning methods, which uses the process model at the nominal operating conditions. A number of structures are available for modeling a process system. Model for the drying process of Paper industry is established based on gathering 1000 groups of 2500 real-time sample data. Based on the collection of data, that was adapted to both the conventional and intelligent modelling process. Finally the suitable model is tuned with the suitable controller for optimal control of the drying process.

Keywords

Drying Process of Paper Machine, System Identification, Artificial Neural Network, T-S Fuzzy Modelling, Hammerstein-Weiner Model.

Full Text

     

M. Rajalakshmi ¹, C. Karthik ²

Affiliations
1 Department of EIE, Kamaraj College of Engineering and Technology, Virudhunagar, Tamilnadu, IN
2 Department of EIE, Kalasalingam University, Krishnankoil, Tamilnadu, IN

Abstract

This paper discusses the application of Neural Network Auto-Regressive model with eXogenous inputs (NNARX) in the area of identification of nonlinear dynamical systems. The main contribution of this paper is to identify suitable model and model structure of nonlinear dynamic system. In this paper Neural Network Auto-Regressive model with eXogenous inputs (NNARX) and ANFIS models are applied to identify highly nonlinear dynamic process and comparison was made between NNARX and ANFIS. The simulation results show that ANFIS is very effective to identify the nonlinear system.

Keywords

pH Process, NNARX, ANFIS.

Full Text

     

Mankernika N. Guttikar ¹, Myna Panemangalore ¹, M. Rajalakshmi ¹, D. Rajalakshmi ¹, R. Rajagopalan ¹, M. Swaminathan ¹

Affiliations
1 Central Food Technological Research Institute, Mysore, IN

Abstract

In the preceding paper, the results of studies on the preparation, chemical composition and shelf-life of protein foods based on blends of groundnut, Bengal gram, soya and sesame flours and fortified with limiting amino acids, calcium salts and essential vitamins have been reported'. The present paper deals with studies on the amino acid composition and nutritive value of the protein present in the protein foods.

Full Text

   

M. Rajalakshmi , S. Boopathi

Abstract

Karyotyping is a common method in cytogenetic. Automatic classification of the chromosomes within the microscopic images is the first step in designing an automatic karyotyping system. This is a difficult task especially if the chromosome is highly curved within the image. The main aim of this paper was to define a new group of features for better representation and classification of chromosomes.  this paper proposes classification & analysis of human chromosomes which includes the following steps i)we use image processing utilities and filter to remove noise .ii)the filtered image is then entered into segmentation algorithm to segment the image .iii)then the segments enter into two tracks for classifying chromosomes. the first one depends on image processing for measuring the length of chromosomes  where the second one deals with  initiating the feed forward neural network which is trained by means of back propagation algorithm. By using feed forward neural network and back propagation algorithm, width, position and the average intensity of chromosome was determined. back propagation algorithm achieves high accuracy with minimum training time, which makes it suitable for real-time chromosome classification in the laboratory.in our paper ,segmentation is done by using image processing and classification is done by using feed forward neural network and back propagation algorithm.

Full Text

   

S. Kowsalya ¹, M. Rajalakshmi ¹, P. Selvaraj ¹, S. Soundarrajan ¹, D. Shanmugavel ¹

Affiliations
1 Department of EEE, Pollachi Institute of Engineering and Technology, Pollachi, IN

Abstract

This paper suggests a new converter called Solar Reconfigurable Converter (SRC) for BLDC drive with PV-battery application using fuzzy control algorithm. The main concept of the SRC is reducing different power conversion stages to a single power conversion stage.  For BLDC drive fuzzy logic controller is used to control the motor drive in closed loop. The main advantage of the fuzzy logic control is to eliminate steady state error and harmonic content and improve the system performance. By gaining that system response effectively. We get reliability of power supply with less time and on low cost. Both DC-AC and DC-DC operations can be performed in a single stage of conversion with MPPT algorithm. A MPPT technique is also used to extract the maximum power from the PV panel to the battery. And the SRC integrates the different energy storages levels. This converter solution is using for PV-battery application, since it reduce number of conversion stages, thereby improving the efficiency. Ultimately the efficiency of the project gives more than that of the normal solar converter efficiency. A development of the model and analysing the simulation is done using MATLAB/simulation software.

Full Text