Kanendra Naidu

Development of a novel voice verification system using wavelets

This paper presents a novel voice verification system using wavelet transforms. The conventional signal processing techniques assume the signal to be stationary and are ineffective in recognizing non stationary signals such as the voice signals. Voice signals which are more dynamic could be analyzed with far better accuracy using wavelet transform. The developed voice recognition system is word dependant voice verification system combining the RASTA and LPC. The voice signal is filtered using the special purpose voice signal filter using the relative spectral algorithm (RASTA). The signals are de-noised and decomposed to derive the wavelet coefficients and thereby a statistical computation is carried out. Further the formant or the resonance of the voices signal is detected using the linear predictive coding (LPC). With the statistical computation on the coefficients alone, the accuracy of the verifying sample individual voice to his own voice is quite high (around 75% to 80%). The reliability of the signal verification is strengthened by combining entailments from these two completely different aspects of the individual voice. For voice comparison purposes four out five individuals are verified and the results show higher percentage of accuracy. The accuracy of the system can be improved by incorporating advanced pattern recognition techniques such as hidden Markov model (HMM).

Performance investigation of ABC algorithm in multi-area power system with multiple interconnected generators

Abstract This paper presents an extensive study on the application of Artificial Bee Colony (ABC) algorithm for load frequency control (LFC) in multi-area power system with multiple interconnected generators. The LFC model incorporates various possible physical constraints and non-linearities such as generation rate constraint, time delay, dead zone and boiler. The ABC algorithm is used to find the optimum PID controller parameters. The tuning performance of the algorithm is comparatively investigated against different optimization technique such as evolutionary programming (EP), genetic algorithm (GA), gravitational search algorithm (GSA) and particle swarm optimization (PSO). The robustness analysis of the system is also evaluated by investigating the dynamic response of the controller with load demand at varying time step, tuning based on different performance criterion and by varying the load demand. The performance of the system is evaluated based on the settling time and maximum overshoot value of the frequency deviation response. The performance of ABC is also verified against an exhaustive search based on interval halving method. Despite employing a single controller for multiple interconnected generators, the optimized controller is able to successfully damp oscillations in the system response and regulate the area control error back to zero in minimal amount of time. The results indicate the superiority of the ABC algorithm’s search mechanism in finding the optimum set of PID controller’s gain.

Fault Types Classification Accuracy Considering Four Different Methods

This research introduces four different tools designed for fault type classifications at distribution network. The proposed designs are using Artificial Neural Network, Fuzzy Logic, conventional method and Support Vector Machine as the research techniques with input data obtained from PSCAD simulation. The circuit configuration for fault disturbance at the distribution network was simulated by PSCAD simulation program. The research techniques were applied with multiples input values of voltage and current that extracted from the PSCAD simulation. This research testifies the output result by using different fault resistance values; 0.01Ω, 10Ω, 30Ω, 50Ω and 70Ω. Voltage sag and current swell of phase a, b and c that were obtained from the PSCAD simulation have been used as the input variables for the four different research tools design. The acquired results that represented in average accuracy (%) shows that voltage sag and current swell can draw a satisfying accuracy in classifying the fault type.