SDSanjay Vasant Dudul

Sanjay Vasant Dudul

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sanjay Vasant Dudul has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Comparative Analysis of Different Wavelet Families, Applied for Steganography on Two Cover Images

    by Archana O. Vyas, Sanjay.V. Dudul

    Transform domain image steganography involves embedding secret image in cover image, before that, any of the transforms is applied to convert it from spatial domain to frequency domain. The transform domain technique applied in the proposed work is the combined technique of DWT and DCT, which ensures advantages of both techniques like robustness and higher imperceptibility. Moreover, encrypted secret image is embedded in two frequency domain transformed cover images, this enhances the security. In this paper, the comparative analysis of application of different discrete wavelet families like Coiflet, Daubechies, Biorthogonal, Reverse biorthogonal and Discrete meyer, for steganography on two cover images "girl" and "Lenna" is presented. The simulation results illustrate the comparative values of MSE and PSNR, on application of different DWT techniques with DCT one by one, on two cover images.

  • Performance analysis of various LMS adaptive filtering algorithms

    by Shrikant J. Honade, Prashant V. Ingole, Sanjay V. Dudul, Nitin A. Shelke

    Adaptive signal processing is extensively used as an area of research from few decades. There are various kinds of adaptive filtering algorithms are available in the literature which are used for different purposes. The work presented in this paper focused mainly on the performance analysis of various versions of most popular LMS (Least Mean Square) adaptive filtering algorithm when it is operated in unknown environment and deciding which algorithm has better performance in terms of minimum mean square error (MSE). From, the experimental results, it is observed that, when a same random input, random noise and desired response are considered for the different algorithms, with variable step size parameter and variable no. of filter taps, it very difficult to form a concrete decision on it, but in broader sense we can say that the performance of LMS sign sign algorithm for M = 2 and NLMS/Complex NLMS algorithm for higher value of M is found to be better in terms of mean square value of error when operated in an unknown situation.


  • Efficient classification of pollen grains using computational intelligence approach

    by V. R. Dhawale, J. A. Tidke, S. V. Dudul

    Pollen grains play an important role in classification system of plants. Pollen morphological characters are very useful in plant classification and identification of plants. Pollen studies are widely used in allergy and epidemiology research, fossil fuel exploration, forensic science, food, pharmaceutical, and cosmetic industry, biotechnology, and so many other fields. Hence classification of pollen grains is a challenge that can be effectively done by computational intelligence approach. The traditional method of pollen classification analyses the pollen morphological characters using microscopy. This procedure is tedious and requires experts from the field of palynology. With a view to extract features from pollen images, a new classification strategy is developed which proposes Image Histogram coefficients in addition to image statistics and shape descriptor. The suitability of classifiers based on Multilayer Perceptron (MLP) Neural Network and Support Vector Machine (SVM) is explored with the optimization of their respective parameters in view of reduction in time as well as space complexity. Performance of two classifiers has been compared with respect to MSE, NMSE, and Classification accuracy. The Average Classification Accuracy of MLP comprising of two hidden layers is found to be superior (95 % on Cross Validation dataset) to SVM based classifier. Finally, optimal Classification strategy has been developed, which could be easily modified to classify more than 10 species. The proposed strategy will provide an effective alternative to traditional method of pollen image analysis for plant taxonomy and species identification, which is obvious from the cross-validation performance on the dataset containing ten different plant species.


  • Neural network based classification of pollen grains

    by V. R. Dhawale, J. A. Tidke, S. V. Dudul

    Palynological data are used in a wide range of applications. A new classification algorithm is proposed for pollen grains. With a view to extract features from pollen images, an classifier algorithm is developed which proposes two-dimensional discrete Walsh-Hadamard Transform domain coefficients in addition to image statistics and shape descriptor. The suitability of classifiers based on Multilayer Perceptron (MLP) Neural Network, Generalized Feedforward (GFF) Neural Network, Support Vector Machine (SVM), Radial Basis Functions (RBF) Neural Networks, Recurrent Neural Networks (RNN) and Modular Neural Network (MNN) is explored with the optimization of their respective parameters in view of reduction in time as well as space complexity. Performance of all six classifiers has been compared with respect to MSE, NMSE, and Classification accuracy. The Average Classification Accuracy of MNN comprising of two hidden layers and four parallel MLP neural networks organized in a typical topology is found to be superior (85 % on Cross Validation dataset) amongst all classifiers. Finally, optimal classifier algorithm has been developed on the basis of the best performance. The algorithm suggested could be easily modified to classify more than 10 species. The classifier algorithm will provide an effective alternative to traditional method of pollen image analysis for plant taxonomy and species identification.


  • Focused Time Delay Neural Network Model for Rainfall Prediction Using Indian Ocean Dipole Index

    by N.A. Charaniya, S.V. Dudul

    Indian monsoon rainfall is a process which is dependent on number of ecological and geographical parameter. This makes it very difficult to accurately predict the monsoon rainfall. As India is agriculture base country a long range monsoon rainfall prediction is crucial for proper planning and management of agriculture strategy. Many researcher have identified influence of the Indian Ocean Dipole (IOD) on the inter annual variability of the Indian summer monsoon rainfall (ISMR). The Indian Ocean Dipole (IOD) is a coupled ocean-atmosphere phenomenon in the Indian Ocean. It is normally characterized by anomalous cooling of SST in the south eastern equatorial Indian Ocean and anomalous warming of SST in the western equatorial Indian Ocean. In this paper a Time lag neural network model with gamma memory processing neuron is proposed for one month ahead prediction of monsoon rainfall in the country based upon the Indian Ocean dipole parameter.


  • Epilepsy diagnosis based on generalized feed forward neural network

    by P. A. Kharat, S. V. Dudul

    Epilepsy is a common neurological disorder that is characterized by recurrent unprovoked seizures. Epilepsy can develop in any person at any age. 0.5% to 2% of people will develop epilepsy during their lifetime. This paper aims to develop the clinical decision support system (DSS) for the diagnosis of epilepsy. In this paper a simple, reliable and economical Neural Network (NN) based DSS was proposed for the diagnosis of epilepsy. The generalized feed forward neural network (GFFNN) was designed for the diagnosis. Eleven statistical parameters along with the 64 FFT were extracted for the electroencephalogram (EEG) signal. Data used for the experimentation purpose was obtained from the University of Bonn. The classification rate of GFFNN was 100 % for the training data and 86.67% for the cross validation data.


  • Clinical decision support system based on Jordan/Elman neural networks

    by P. A. Kharat, S.V. Dudul

    Epilepsy is a common neurological disorder that is characterized by recurrent unprovoked seizures. About 40 to 50 million people worldwide have epilepsy. In this paper the authors present clinical decision support system (DSS) for the diagnosis of epilepsy. The validity of neural network to diagnose the epilepsy is checked and the most suitable neural network is recommended for the diagnosis of epilepsy. Three different diagnosis of Normal, Epileptic (interictal) and Epileptic (ictal), where estimated by a neural network. The results showed that we were able to achieve 100% results for testing data by using Jordan/Elman neural network.


  • Committee of artificial neural networks for monthly rainfall prediction using wavelet transform

    by Nizar Ali Charaniya, Sanjay V. Dudul

    The importance of long-range prediction of rainfall pattern for devising and planning agriculture strategies cannot be overemphasized. Prediction of rainfall pattern remains a difficult problem and the desired level of accuracy has not been reached. In this paper, a committee of artificial neural networks (ANNs) based model with wavelet decomposition is proposed for prediction of monthly rainfall on accounts of the preceding events of rainfall data. Wavelet transform is used for extraction of approximate and detail coefficient of the rainfall data series. These coefficients are used along with a ANN for learning and knowledge extraction processes. The model has been tested on rainfall data for different geographical region of India and also for entire country. The proposed model is capable of forecasting monthly rainfall one month in advance.