Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
23 results
Search Results
Item Identification of Voicing Assimilation From Children’s Speech(Institute of Electrical and Electronics Engineers Inc., 2017) Ramteke, P.B.; Madugula, M.; Suresh, S.; Koolagudi, S.G.In this paper, an attempt has been made for the automatic identification of the voicing assimilation or harmony process. In these processes the voiced sounds are replaced by unvoiced sounds and vice versa. The phonological processes appear in the children represent the age wise speech learning ability, where the processes start to disappear as children grow. Speech Language Pathologists (SLPs) analyse these processes to evaluate the learning ability of the children. The pitch is present in voiced speech and absent in unvoiced region of speech. This gives the clear view of the assimilation; hence pitch is explored for the identification of voicing assimilation. Features extracted from the test words (mispronounced words) are compared with the reference/correct words using Dynamic Time Warping (DTW) and region of mispronunciation is identified from the properties of DTW curve. The highest accuracy of identifying voicing assimilation achieved using pitch feature is 88%. © INDIACom-2017.Item Damage identification and assessment using image processing on post-disaster satellite imagery(Institute of Electrical and Electronics Engineers Inc., 2017) Joshi, A.R.; Tarte, I.; Suresh, S.; Koolagudi, S.G.Natural disasters such as earthquakes and tsunamis often have a devastating effect on human life and cause noticeable damage to infrastructure. Active research has been ongoing to mitigate the impact of these catastrophes and preclude the economic losses. The existing methods that utilize pre-event and post-event images not only require the immediate and guaranteed availability of the appropriate data set but are also encumbered by manual mapping of the images, necessitating the indication of corresponding control points in the two images. This paper highlights the use of only post-event imagery in the absence of reference data to achieve a more timely delivery to produce damage maps as the output. This eliminates the need for manual georeferencing of images. Our method incorporates simple linear iterative clustering (SLIC) for segmenting the images into uniform superpixels and extraction of 62 features for each superpixel. We used various classifiers of which Random Forest classifier was found to give a comparatively high accuracy of 90.4% over others. To enumerate the accuracy of the method proposed, we used 1500 data regions of which 20% were used for testing, and 80% were used for training. The aerial images taken by GeoEye1 after the 2011 Christchurch earthquake and 2011 Japan earthquake and tsunami are utilized in this study to detect building damage. In the case of availability of ground truth, we compare the histograms of the pre- and post-imagery to quantify similarity as the SSD (Sum of Squared Distances) value and thus, our approach produces an assessment as an output map displaying the extent of damage in the area covered by each superpixel. We consider 6 levels of damage ranging from 1 to 6, where 1 signifies no damage, and 6, maximum damage. © 2017 IEEE.Item A Framework for Quality Enhancement of Multispectral Remote Sensing Images(Institute of Electrical and Electronics Engineers Inc., 2018) Suresh, S.; Das, D.; Lal, S.Researches in satellite image enhancement have been particularly confined to two major areas-contrast enhancement and image de noising of remote sensing images. The processing of relatively dark or shadowed images necessitates the need for robust remote sensing enhancement techniques. In this paper, a robust framework for quality enhancement of multispectral remote sensing images is proposed. The quantitative results of proposed algorithm and other existing remote sensing enhancement algorithms are calculated in terms of DE, NIQMC, BIQME, PisDist and CM on different remote sensing and other image databases. Results reveal that visual enhancement of the proposed algorithm is better than other existing remote sensing enhancement algorithms. Finally, the simulation experimental results show that proposed algorithm is effective and efficient for remotes sensing as well as natural images. © 2017 IEEE.Item Influence of Process Parameters on Microstructural Properties of L-DED Produced Ti64 Alloy(Springer Science and Business Media Deutschland GmbH, 2025) Suresh, S.; Kuriachen, B.; Kumar, V.; Bontha, S.; Gurugubelli, R.C.Additive manufacturing (AM) techniques have revolutionized the manufacturing of complex and customized parts across various applications. However, they are known for producing titanium parts with high anisotropy and low ductility, due to high cooling gradient in the build direction and the presence of martensite phase in microstructure respectively. These are inherent problems which limit their application in critical engineering fields. Laser—Direct Energy Deposition (L-DED) produced parts also have the same disadvantages. Thus, the primary objective of this paper is to identify the optimal combination of process parameters for L-DED that can mitigate these inherent limitations. Keeping the parameters such as powder size, orientation angle and hatch angle as constant, the laser power and scan speed are varied to fabricate 9 different sets of samples using L-DED. The research methodology includes an analysis of the microstructure, focusing on grain width, phase distribution, lath characteristics and presence of defects, if any. Microscopy and XRD techniques were used to observe the microstructure. Additionally, hardness studies were performed to evaluate the changes in material hardness. It was noticed that laser power significantly influences β width and α’ length while scan speed has a lesser dominant effect on both of them. The findings will contribute to the development of process-structure-property relations for L-DED-produced Ti64 and further, optimized manufacturing strategies for producing titanium parts with reduced anisotropy and increased ductility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.Item Adsorption of benzene vapor onto activated biomass from cashew nut shell: Batch and column study(Bentham Science Publishers, 2012) Suresh, S.; Vijayalakshmi, G.; Rajmohan, B.; Subbaramaiah, V.The preparation of chemically modified activated cashew nut shell (ACNSB) of different impregnation ratios and their effects in adsorption of benzene vapor were studied. Effects of chemical pre-impregnation using phosphoric acid at different ratios (1:1 and 2:1) were investigated in order to patent. Physico-chemical characterization including surface area, scanning electron microscopy, energy dispersive X-ray spectroscopy, High-resolution Transmission Electron Microscopy and Fourier transform infrared spectroscopy of the ACNSB before and after benzene adsorption have been done to understand the adsorption mechanism. Optimum conditions for benzene removal were found to be, adsorbent dose m=10 g/l of solution and time (t) 120 min for the C0 range of 300-500 mg/l. Adsorption of benzene followed pseudosecond-order kinetics. Langmuir and R-P isotherms were found to best represented data for benzene adsorption onto ACSNB. In ACNSB column experiments, it can be concluded that concentration of benzene increases with the longer breakthrough time and hence higher adsorption capacity. ACSNB are many advantages includes simple and fast, organic solvent recovery, economical, energy savings, environmentally safe aspect and minimize the waste management problem. © 2012 Bentham Science Publishers.Item An efficient cuckoo search algorithm based multilevel thresholding for segmentation of satellite images using different objective functions(Elsevier Ltd, 2016) Suresh, S.; Lal, S.Satellite image segmentation is challenging due to the presence of weakly correlated and ambiguous multiple regions of interest. Several bio-inspired algorithms were developed to generate optimum threshold values for segmenting such images efficiently. Their exhaustive search nature makes them computationally expensive when extended to multilevel thresholding. In this paper, we propose a computationally efficient image segmentation algorithm, called CSMcCulloch, incorporating McCulloch's method for lévy flight generation in Cuckoo Search (CS) algorithm. We have also investigated the impact of Mantegna?s method forlévy flight generation in CS algorithm (CSMantegna) by comparing it with the conventional CS algorithm which uses the simplified version of the same. CSMantegna algorithm resulted in improved segmentation quality with an expense of computational time. The performance of the proposed CSMcCulloch algorithm is compared with other bio-inspired algorithms such as Particle Swarm Optimization (PSO) algorithm, Darwinian Particle Swarm Optimization (DPSO) algorithm, Artificial Bee Colony (ABC) algorithm, Cuckoo Search (CS) algorithm and CSMantegna algorithm using Otsu's method, Kapur entropy and Tsallis entropy as objective functions. Experimental results were validated by measuring PSNR, MSE, FSIM and CPU running time for all the cases investigated. The proposed CSMcCulloch algorithm evolved to be most promising, and computationally efficient for segmenting satellite images. Convergence rate analysis also reveals that the proposed algorithm outperforms others in attaining stable global optimum thresholds. The experiments results encourages related researches in computer vision, remote sensing and image processing applications. © 2016 Elsevier Ltd. All rights reserved.Item Multilevel thresholding based on Chaotic Darwinian Particle Swarm Optimization for segmentation of satellite images(Elsevier Ltd, 2017) Suresh, S.; Lal, S.This paper proposes an improved variant of Darwinian Particle Swarm Optimization algorithm based on chaotic functions. Most of the evolutionary algorithms faces the problem of getting trapped in local optima in its search for global optimum solutions. This is highly influenced by the use of random sequences by different operators in these algorithms along their run. The proposed algorithm replaces random sequences by chaotic sequences mitigating the problem of premature convergence. Experiments were conducted to investigate the efficiency of 10 defined chaotic maps and the best one was chosen. Performance of the proposed Chaotic Darwinian Particle Swarm Optimization (CDPSO) algorithm is compared with chaotic variants of optimization algorithms like Cuckoo Search, Harmony Search, Differential Evolution and Particle Swarm Optimization exploiting the chosen optimal chaotic map. Various histogram thresholding measures like minimum cross entropy and Tsallis entropy were used as objective functions and implemented for satellite image segmentation scenario. The experimental results are validated qualitatively and quantitatively by evaluating the mean, standard deviation of the fitness values, PSNR, MSE, SSIM and the total time required for the execution of each optimization algorithm. © 2017 Elsevier B.V.Item A Novel Adaptive Cuckoo Search Algorithm for Contrast Enhancement of Satellite Images(Institute of Electrical and Electronics Engineers, 2017) Suresh, S.; Lal, S.; Chintala, C.S.; Kiran, M.S.Owing to the increased demand for satellite images for various practical applications, the use of proper enhancement methods are inevitable. Visual enhancement of such images mainly focuses on improving the contrast of the scene procured, conserving its naturalness with minimum image artifacts. Last one decade traced an extensive use of metaheuristic approaches for automatic image enhancement processes. In this paper, a robust and novel adaptive Cuckoo search based Enhancement algorithm is proposed for the enhancement of various satellite images. The proposed algorithm includes a chaotic initialization phase, an adaptive Levy flight strategy and a mutative randomization phase. Performance evaluation is done by quantitative and qualitative results comparison of the proposed algorithm with other state-of-the-art metaheuristic algorithms. Box-and-whisker plots are also included for evaluating the stability and convergence capability of all the algorithms tested. Test results substantiate the efficiency and robustness of the proposed algorithm in enhancing a wide range of satellite images. © 2008-2012 IEEE.Item Modified differential evolution algorithm for contrast and brightness enhancement of satellite images(Elsevier Ltd, 2017) Suresh, S.; Lal, S.Satellite images normally possess relatively narrow brightness value ranges necessitating the requirement for contrast stretching, preserving the relevant details before further image analysis. Image enhancement algorithms focus on improving the human image perception. More specifically, contrast and brightness enhancement is considered as a key processing step prior to any further image analysis like segmentation, feature extraction, etc. Metaheuristic optimization algorithms are used effectively for the past few decades, for solving such complex image processing problems. In this paper, a modified differential Modified Differential Evolution (MDE) algorithm for contrast and brightness enhancement of satellite images is proposed. The proposed algorithm is developed with exploration phase by differential evolution algorithm and exploitation phase by cuckoo search algorithm. The proposed algorithm is used to maximize a defined fitness function so as to enhance the entropy, standard deviation and edge details of an image by adjusting a set of parameters to remodel a global transformation function subjective to each of the image being processed. The performance of the proposed algorithm is compared with ten recent state-of-the-art enhancement algorithms. Experimental results demonstrate the efficiency and robustness of the proposed algorithm in enhancing satellite images and natural scenes effectively. Objective evaluation of the compared methods was done using several full-reference and no-reference performance metrics. Qualitative and quantitative evaluation results proves that the proposed MDE algorithm outperforms others to a greater extend. © 2017 Elsevier B.V.Item Two-Dimensional CS Adaptive FIR Wiener Filtering Algorithm for the Denoising of Satellite Images(Institute of Electrical and Electronics Engineers, 2017) Suresh, S.; Lal, S.In the recent years, researchers are quite much attracted in designing two-dimensional (2-D) adaptive finite-impulse response (FIR) filters driven by an optimization algorithm to self-adjust the filter coefficients, with applications in different domains of research. For signal processing applications, FIR Wiener filters are commonly used for noisy signal restorations by computing the statistical estimates of the unknown signal. In this paper, a novel 2-D Cuckoo search adaptive Wiener filtering algorithm (2D-CSAWF) is proposed for the denoising of satellite images contaminated with Gaussian noise. Till date, study based on 2-D adaptive Wiener filtering driven by metaheuristic algorithms was not found in the literature to the best of our knowledge. Comparisons are made with the most studied and recent 2-D adaptive noise filtering algorithms, so as to analyze the performance and computational efficiency of the proposed algorithm. We have also included comparisons with recent adaptive metaheuristic algorithms used for satellite image denoising to ensure a fair comparison. All the algorithms are tested on the same satellite image dataset, for denoising images corrupted with three different Gaussian noise variance levels. The experimental results reveal that the proposed novel 2D-CSAWF algorithm outperforms others both quantitatively and qualitatively. Investigations were also carried out to examine the stability and computational efficiency of the proposed algorithm in denoising satellite images. © 2008-2012 IEEE.
- «
- 1 (current)
- 2
- 3
- »