ANN for classification of cardiac arrhythmias

B. Anuradha and V. C. Veera Reddy

Electrocardiography deals with the electrical activity of the heart. The condition of cardiac health is given by ECG and heart rate. A study of the nonlinear dynamics of electrocardiogram (ECG) signals for arrhythmia characterization was considered. The statistical analysis of the calculated features indicate that they differ significantly between normal heart rhythm and the different arrhythmia types and hence, can be rather useful in ECG arrhythmia detection. The discrimination of ECG signals using non-linear dynamic parameters is of crucial importance in the cardiac disease therapy and chaos control for arrhythmia defibrillation in the cardiac system. The four non-linear parameters considered for cardiac arrhythmia classification of the ECG signals are Spectral entropy, Poincaré plot geometry, Largest Lyapunov exponent and Detrended fluctuation analysis which are extracted from heart rate signals. The inclusion of Artificial Neural Networks (ANNs) in the complex investigating algorithms yield very interesting recognition and classification capabilities across a broad spectrum of biomedical problem domains. ANN classifier was used for the classification and an accuracy of 90.56% was achieved.

Classification of cardiac signals using time domain methods

B. Anuradha, K. Suresh Kumar and V. C. Veera Reddy

Electrocardiography (ECG) deals with the electrical activity of the heart. The condition of cardiac health is given by ECG and heart rate. A study of the non-linear dynamics of ECG signals for arrhythmia characterization is considered. The statistical analysis of the calculated features indicate that they differ significantly between normal heart rhythm and the different arrhythmia types and hence, can be rather useful in ECG arrhythmia detection. The discrimination of ECG signals using statistical parameters is of crucial importance in the cardiac disease therapy. The four statistical parameters considered for cardiac arrhythmia classification of the ECG signals are the standard deviation of the NN intervals (SDNN), the standard deviation of differences between adjacent NN intervals (SDSD), the root mean square successive difference of intervals which are extracted from heart rate signals (RMSSD) and the proportion derived by dividing NN50 by the total number of NN intervals (pNN50). The inclusion of Adaptive neuro fuzzy interface system (ANFIS) in the complex investigating algorithms yield very interesting recognition and classification capabilities across a broad spectrum of biomedical problem domains. Using the computed statistical parameter classification was done using Analytical method and an accuracy of 66% was achieved. The ANFIS method was compared with Analytical method. ANFIS classifier was used for the classification and an accuracy of 94% was achieved which shows that ANFIS classifier is the best of the two methods compared.

A decision support system for improving forecast using genetic algorithm and tabu search

Zuhaimy Ismail

The intrinsic uncertainties associated with demand forecasting become more acute when it is required to provide invaluable dimensions for the decision-making process. The concept of decision support system (DSS) is very broad and it can take many different forms. In general, we can say that a DSS is a computerized system for assisting decision making.  Forecasting models has been recognized as one of the tools used in DSS. The need and relevance of forecasting tools has become a much-discussed issue and this has led to the development of various new tools and methods for forecasting in the last two decades. One traditional tool for forecasting time series data is the Winter’s method with three parameters that determine the accuracy of the model. The search for the best parameter value of a, b and g and their combinations using trial and error method is time consuming. Hence, a good optimization technique is required to select the best parameter value to minimize the fitness function. We employ the unique search of Genetic Algorithm (GA) to generate and search for the best value and due to the nature of GA that is based on random search; the near optimum solution could be improved by the introduction of a more systematic search known as Tabu Search (TS). Our study shows that combining both GA and TS search methods generate a more accurate forecast. 

Unsteady MHD memory flow with oscillatory suction, variable free stream and heat source

S. Mustafa , Rafiuddin and M. V. Ramana Murthy

Ohmic disspitaion effect on unsteady boundary layer flow and heat transfer of an incompressible electrically conducting memory fluid over a continuous moving horizontal non-conducting surface in the presence of transverse magnetic field, an oscillating free stream and volumetric rate of heat generation (or absorption) is investigated, neglecting induced magnetic field in comparison to the applied magnetic field. The velocity and temperature distributions are obtained numerically and presented in graphical form. The expressions of skin friction coefficient and rate of heat transfer in terms of Nusselt number at the surface are derived, numerically and their numerical values for various values of physical parameters are presented in Tabular form.

Capacitor placement using fuzzy and particle swarm optimization method for maximum annual savings

M. Damodar Reddy and V. C. Veera Reddy

This paper presents a fuzzy and Particle Swarm Optimization (PSO) method for the placement of capacitors on the primary feeders of the radial distribution systems to reduce the power losses and to improve the voltage profile. A two-stage methodology is used for the optimal capacitor placement problem. In the first stage, fuzzy approach is used to find the optimal capacitor locations and in the second stage, Particle Swarm Optimization method is used to find the sizes of the capacitors. The sizes of the capacitors corresponding to maximum annual savings are determined by considering the cost of the capacitors. The proposed method is tested on 15-bus, 34-bus and 69-bus test systems and the results are presented.

Fingerprint image denoising using curvelet transform

G. Jagadeeswar Reddy, T. Jaya Chandra Prasad and M. N. Giri Prasad

Abstract:

Curvelet transform is the new member of the evolving family of multiscale geometric transforms. It offers an effective solution to the problems associated with image denoising using wavelets. Finger prints possess the unique properties of distinctiveness and persistence. However, their image contrast is poor due to mixing of complex type of noise. In this paper an attempt has been made to present the results of denoising of such images using both wavelet and curvelet transforms. The results obtained demonstrate that the curvelet transform based reconstructions are visually sharper than the wavelet reconstructions. The recovery of edges and of the faint linear and curvilinear features is of particularly superior quality. The results obtained are in accordance with the expected predictions of the existing theory of curvelet transforms.

Finite element analysis of tunnels using the elastoplastic-viscoplastic bounding surface model

Qassun S. Mohammed Shafiqu, Mohd R. Taha and Zamri H. Chik

Finite element analyses of tunnels in saturated porous medium were performed using the elastoplastic-viscoplastic bounding surface model. In this paper, the model and the finite element formulation are described and examples of model prediction and accuracy of the finite element formulation are given. The transient analysis of tunnel problem is then carried out, and the comparison of the finite element results with the field measurements demonstrate the ability of the bounding surface model to solve problems of tunneling in saturated porous medium.

Transient analysis of induction generator jointed to network at balanced and unbalanced short circuit faults

Bahareh Ranjbar and Rahman Dashti

Abstract:

In wind power stations, induction machines are used as induction generators. Transient stability analysis of induction generator used in wind power station, joint to infinite bus, before and after balanced and unbalanced short circuit faults is one of the main issue in power system security and operation. It is necessary to know the transient behavior of induction generator, when joint to network, in usual faults. In this paper, active power, torque and speed of induction generator at balanced and unbalanced short circuit faults with dynamic equation of induction machine are studied. With single equation of induction machine, transient active power, torque and speed are measured. Induction generators used in wind power system before and after three phase fault, two phase fault, single phase fault and two phase to earth fault conditions are analysed. The natural approximation to derive analytical formulas for transient conditions is proposed, and the transient behavior of induction generator is analyzed by the single equations. This paper includes three parts: modeling, simulation and analysis of results.

Extraction of Neem oil (Azadirachta indica A. Juss) using n-hexane and ethanol: Studies of oil quality, kinetic and thermodynamic

Maria Yuliana Liauw, F. A. Natan, P. Widiyanti, D. Ikasari, N. Indraswati and F. E. Soetaredjo

Abstract:

In the present study, Neem oil extraction from Neem seeds (Azadirachta indica A. Juss) with n-hexane and ethanol are presented. Effects of particle size, temperature and type of solvent on the extraction kinetic and thermodynamic parameters were studied. Results showed that the maximum oil yields were 41.11% for ethanol and 44.29% for n-hexane at 50^oC and 0.425-0.71mm particle size. The psycho-chemical characteristics analysis showed that increasing temperature decreased iodine value but caused saponification, acid, and peroxide value became higher, which means higher extraction temperature result on higher oil yield but lower oil quality. The kinetic of Neem oil extraction was derived from mass transfer rate equation. It was found that  and  are positive, while is negative indicating that this process is endotermic, irreversible, and spontaneous.

Design and development of a robust control adjustable electrical DC drive system using PI controller

Liaquat Ali Khan, Abrar Ahmed, Umar Abdul Ahad and Syed Zahid Hussain

Abstract:

Electrical drives lie at the heart of most industrial processes and make a major contribution to the comfort and high quality products we all take for granted. Electrical drives involving different types of electrical motors turn the wheels of industry. In an industrialized country, more than 60% of the generated electrical energy is used in motor drives. The application of electrical drives spread from low fractional horse power applications in instruments to the industrial applications. Wide power, torque and speed ranges, adaptability to almost every operating condition, high efficiency, fast response, control simplicity, ability to operate as a generator in braking mode and various mechanical design types make the electrical drive very competitive among the other drive types. This work is based on the Robust Control Adjustable Electrical DC Drive System using PI (Proportional Integrator) controller. It encompasses the development of the DC drive. It also includes the design and fabrication of the mechanical load wheel structure. Thus the work finally gave a product in the form of a test jig for checking the wear and tear of a small metallic material after being spring pressed and scrubbed on the edged copper face of the aluminum disk wheel. The integrity of the system is based on keeping the wheel speed constant. In nullifying the steady state error the PI control algorithm was eventually used with root locus design method that could enable finding the PI coefficients. It turns out to be a robust and resilient drive that keeps the load wheel speed invariable at disturbances. The theoretical model is validated with the experimental results.

Abstract: