Amar Partap Singh

Fuzzy classifier for fault diagnosis in analog electronic circuits.

Many studies have presented different approaches for the fault diagnosis with fault models having ± 50% variation in the component values in analog electronic circuits. There is still a need of the approaches which provide the fault diagnosis with the variation in the component value below ± 50%. A new single and multiple fault diagnosis technique for soft faults in analog electronic circuit using fuzzy classifier has been proposed in this paper. This technique uses the simulation before test (SBT) approach by analyzing the frequency response of the analog circuit under faulty and fault free conditions. Three signature parameters peak gain, frequency and phase associated with peak gain, of the frequency response of the analog circuit are observed and extracted such that they give unique values for faulty and fault free configuration of the circuit. The single and double fault models with the component variations from ± 10% to ± 50% are considered. The fuzzy classifier along the classification of faults gives the estimated component value under faulty and faultfree conditions. The proposed method is validated using simulated data and the real time data for a benchmark analog circuit. The comparative analysis is also presented for both the validations.

Development of ANN-based virtual fault detector for Wheatstone bridge-oriented transducers

This paper reports on the development of a new artificial neural network-based virtual fault detector (VFD) for detection and identification of faults in DAS-connected Wheatstone bridge-oriented transducers of a computer-based measurement system. Experimental results show that the implemented VFD is convenient for fusing intelligence into such systems in a user-interactive manner. The performance of the proposed VFD is examined experimentally to detect seven frequently occurring faults automatically in such transducers. The presented technique used an artificial neural network-based two-class pattern classification network with hard-limit perceptrons to fulfill the function of an efficient residual generator component of the proposed VFD. The proposed soft residual generator detects and identifies various transducer faults in collaboration with a virtual instrument software-based inbuilt algorithm. An example application is also presented to demonstrate the use of implemented VFD practically for detecting and diagnosing faults in a pressure transducer having semiconductor strain gauges connected in a Wheatstone bridge configuration. The results obtained in the example application with this strategy are promising.

On the design and optimisation of new fractal antenna using PSO

An optimisation technique for newly shaped fractal structure using particle swarm optimisation with curve fitting is presented in this article. The aim of particle swarm optimisation is to find the geometry of the antenna for the required user-defined frequency. To assess the effectiveness of the presented method, a set of representative numerical simulations have been done and the results are compared with the measurements from experimental prototypes built according to the design specifications coming from the optimisation procedure. The proposed fractal antenna resonates at the 5.8 GHz industrial, scientific and medical band which is suitable for wireless telemedicine applications. The antenna characteristics have been studied using extensive numerical simulations and are experimentally verified. The antenna exhibits well-defined radiation patterns over the band.

Design of Sierpinski Carpet Fractal Antenna using Artificial Neural Networks

This paper deals with utilization of artificial neural networks for the design of Sierpinski carpet fractal antenna. The difficulty in designing of fractal microstrip patch antennas is due to the involvement of large number of physical parameters and hence their associated optimal values. It is indeed very difficult to formulate an exact numerical solution through empirical studies based on practical observations. In order to circumvent this problem, an alternative solution is achieved using artificial neural networks. The proposed technique used feed-forward back-propagation artificial neural network (FFBP-ANN) with one hidden layer to approximate neural model of this antenna. Sierpinski carpet fractal antenna is simulated using IE3D software. The investigation is done between the ranges of frequencies from 1 to 20Ghzs. The results obtained by using artificial neural networks are in agreement with simulated results. KeywordsCarpet, Artificial Neural Networks, Sierpinski, Antenna.

Modified Koch fractal antenna with asymmetrical ground plane for multi and UWB applications

In this paper the proposed structure is based on a modified planar Koch curve antenna, whose geometrical parameters are determined by iterative function system algorithm for fractal curve generation. Compared with conventional antenna with same dimensions, modified Koch curve antenna provides additional frequency resonances. The asymmetrical ground plane has been optimized by means of bacterial foraging optimization (BFO) to make the proposed antenna feasible for wide band operation. In addition to miniaturization of about 40%, the optimized reference ground plane provides multi and ultra-wide band with high impedance matching throughout the frequency bands covering various wireless telemedicine applications. In order to assess the reliability of the antenna, measurements have been performed on the fabricated prototype and the obtained results shows good agreement with simulated results.

Texture Features Extraction in Mammograms Using Non-Shannon Entropies

This paper deals with the problem of texture-features-extraction in digital mammograms using non-Shannon measures of entropy. Texture-features-extraction is normally achieved using statistical texture-analysis method based on gray-level histogram moments. Entropy is important texture feature to measure the randomness of intensity distribution in a digital image. Generally, Shannon’s measure of entropy is employed in various feature-descriptors implemented so far. These feature-descriptors are used for the purpose of making a distinction between normal and abnormal regions in mammograms. As non-Shannon entropies have a higher dynamic range than Shannon’s entropy covering much wider range of scattering conditions, they are more useful in estimating scatter density and regularity. Based on these considerations, an attempt is made to develop a new type of feature-descriptor using non-Shannon’s measures of entropy for classifying normal and abnormal mammograms. Experiments are conducted on images of mini-MIAS (Mammogram Image Analysis Society) database to examine its effectiveness. The results of this study are quite promising for extending the work towards the development of a complete Computer Aided Diagnosis (CAD) system for early detection of breast cancer.

Intelligent Estimator for Assessing Apple Fruit Quality

proposed intelligent estimator is implemented using nearest neighbor classifier for automatic grading of red delicious apple fruit from its surface color using machine vision. Though different variants of nearest neighbor classifier are reported in the literature for color classification yet no systematic study is reported till-date for its application in fruit quality assessment using surface color information. The present work reports on comparative evaluation of different variants of nearest neighbor classifier for assessing the quality of apple fruit. It has been found experimentally that amongst different variants, Euclidean Distance Metric based k-Nearest Neighbor Classifier is best suited for this particular application. The performance of this classifier is evaluated at different illuminations of the fruit surface. It is found that efficiency is the highest at a particular intensity of surface illumination. In fact, efficiency achieved using proposed estimator is nearly 95.12% if manual grading is assumed to be 100% accurate taken as reference. However, 4.88 % variation is due to subjective judgment of human-beings in perceiving the apple fruit visually, which of course is obvious. Moreover, the repeatability of the proposed system is found to be 100% as observed after rigorous experimental validation.

Fuzzy Model Identification: A Firefly Optimization Approach

Nature-inspired methodologies are currently among the most powerful algorithms for optimization problems. This paper presents a recent nature-inspired algorithm named Firefly algorithm (FA) for automatically evolving a fuzzy model from numerical data. FA is a meta-heuristic inspired by the flashing behavior of fireflies. The rate and the rhythmic flash, and the amount of time form part of the signal system to attract other fireflies. The paper discusses fuzzy modeling for zero-order Takagi-Sugeno-Kang (TSK) type fuzzy systems. Simulations on two well known problems, one battery charger that is a fuzzy control problem and another Iris data classification problem are conducted to verify the performance of above approach. The results indicate that the FA is a very promising optimizing algorithm for evolving fuzzy logic based Systems as compared to some of the existing approaches. General Terms Soft Computing, Fuzzy Model Identification.

A novel design of hybrid fractal antenna using BFO

This paper presents a novel design of printed hybrid fractal tree (PHFT) antenna using bacterial forging optimization (BFO) in conjunction with curve fitting technique. The antenna geometry is based on the hybrid structure obtained by integrating meander line geometry with fractal tree, whose geometrical descriptors are determined by means of BFO. The fractal shape allows the new hybrid antenna to be effectively reduced in size without significantly impairing performance. Representative results of optimized antenna are reported in order to access the effectiveness of the developed approach for reliable implementation in wireless telemedicine applications. Moreover, useful guidelines on the effects of finite ground plane size on antenna characteristics have been adequately analyzed.

Neurocomputational Approach for Feed-Position Estimation in Circular Micro-strip Antenna

This paper presents a neurocomputational model for estimation of feed-position in circular microstrip antenna. The difficulty in computing the feed position in circular micro- strip antenna lies due to the involvement of a large number of physical parameters including their associated optimal values. It is indeed very difficult to formulate an exact numerical solution merely on practical observations based empirical studies. In order to circumvent this problem, an alternative solution is achieved using neurocomputational model. The proposed technique used feed-forward back-propagation artificial neural network (FFBP-ANN) trained with Levenberg-Marquardt algorithm. The results of neural estimation are quite promising.