Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
16 results
Search Results
Item Developing regression models for predicting pan evaporation from climatic data - A comparison of multiple least-squares, principal components, and partial least-squares approaches(2007) Kovoor, G.M.; Nandagiri, L.Regression models for predicting daily pan evaporation depths from climatic data were developed using three multivariate approaches: multiple least-squares regression (MLR), principal components regression (PCR), and partial least-squares (PLS) regression. The objective was to compare the prediction accuracies of regression models developed by these three approaches using historical climatic datasets of four Indian sites that are located in distinctly different climatic regimes. In all cases (three approaches applied to four climatic datasets), regression models were developed using a part of the data and subsequently validated with the remaining data. Results indicated that although performances of the regression models varied from one climate to another, more or less similar prediction accuracies were obtained by all three approaches, and it was difficult to identify the best approach based on performance statistics. However, the final forms of the regression models developed by the three approaches differed substantially from one another. In all cases, the models derived using PLS contained the smallest number of predictor variables; between two to three out of a possible maximum of six predictor variables. The MLR approach yielded models with three to six predictor variables, and PCR models included all six predictor variables. This implies that the PLS regression models are the most parsimonious in terms of input data required for estimating epan from climate variables, and yet yield predictions that are almost as accurate as the more data-intensive MLR and PCR models. © 2007 ASCE.Item An extreme learning machine approach for modeling evapotranspiration using extrinsic inputs(Elsevier B.V., 2016) Patil, A.P.; Deka, P.C.Precise estimation of evapotranspiration is crucial for accurate crop-water estimation. Recently machine learning (ML) techniques like artificial neural network (ANN) are being widely used for modeling the process of evapotranspiration. However, ANN faces issues like trapping in local minima, slow learning and tuning of meta-parameters. In this study an improved extreme learning machine (ELM) algorithm was used to estimate weekly reference crop evapotranspiration (ETo). The study was carried out for Jodhpur and Pali meteorological weather stations located in the Thar Desert, India. The study evaluated the performance of three different input combinations. The first input combination used locally available maximum and minimum air temperature data while the second and third combination used ETo values from another station (extrinsic inputs) along with the locally available temperature data as inputs. The performance of ELM models was compared with the empirical Hargreaves equation, ANN and least-square support vector machine (LS-SVM) models. Root mean squared error (RMSE), Nash-Sutcliffe model efficiency coefficient (NSE) and threshold statistics (TS) were used for comparing the performance of the models. The performance of ELM model was found to be better than the Hargreaves and ANN model. The LS-SVM and ELM displayed similar performance. ELM3 models, with 36 and 33 neurons in hidden layer were found to be the best models (RMSE of 0.43 for Jodhpur and 0.33 for Pali station) for estimating weekly ETo at Jodhpur and Pali stations respectively. The results showed that ELM is a simple yet efficient algorithm which exhibited good performance; hence, can be recommended for estimating weekly ETo. Furthermore, it was also found that use of ETo values from another station can help in improving the efficiency of ML models in limited data scenario. © 2016 Elsevier B.V.Item Prediction model for peninsular Indian summer monsoon rainfall using data mining and statistical approaches(Elsevier Ltd, 2017) Vathsala, H.; Koolagudi, S.G.In this paper we discuss a data mining application for predicting peninsular Indian summer monsoon rainfall, and propose an algorithm that combine data mining and statistical techniques. We select likely predictors based on association rules that have the highest confidence levels. We then cluster the selected predictors to reduce their dimensions and use cluster membership values for classification. We derive the predictors from local conditions in southern India, including mean sea level pressure, wind speed, and maximum and minimum temperatures. The global condition variables include southern oscillation and Indian Ocean dipole conditions. The algorithm predicts rainfall in five categories: Flood, Excess, Normal, Deficit and Drought. We use closed itemset mining, cluster membership calculations and a multilayer perceptron function in the algorithm to predict monsoon rainfall in peninsular India. Using Indian Institute of Tropical Meteorology data, we found the prediction accuracy of our proposed approach to be exceptionally good. © 2016 Elsevier LtdItem 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.Item Multispectral satellite image denoising via adaptive cuckoo search-based wiener filter(Institute of Electrical and Electronics Engineers Inc., 2018) Suresh, S.; Lal, S.; Chen, C.; Çelik, T.Satellite image denoising is essential for enhancing the visual quality of images and for facilitating further image processing and analysis tasks. Designing of self-tunable 2-D finite-impulse response (FIR) filters attracted researchers to explore its usefulness in various domains. Furthermore, 2-D FIR Wiener filters which estimate the desired signal using its statistical parameters became a standard method employed for signal restoration applications. In this paper, we propose a 2-D FIR Wiener filter driven by the adaptive cuckoo search (ACS) algorithm for denoising multispectral satellite images contaminated with the Gaussian noise of different variance levels. The ACS algorithm is proposed to optimize the Wiener weights for obtaining the best possible estimate of the desired uncorrupted image. Quantitative and qualitative comparisons are conducted with 10 recent denoising algorithms prominently used in the remote-sensing domain to substantiate the performance and computational capability of the proposed ACSWF. The tested data set included satellite images procured from various sources, such as Satpalda Geospatial Services, Satellite Imaging Corporation, and National Aeronautics and Space Administration. The stability analysis and study of convergence characteristics are also performed, which revealed the possibility of extending the ACSWF for real-time applications as well. © 1980-2012 IEEE.Item Modeling duration of lateral shifts in mixed traffic conditions(American Society of Civil Engineers (ASCE) onlinejls@asce.org, 2018) Asaithambi, G.; Joseph, J.Traffic on urban roads in developing countries is characterized by wide mix of vehicles with loose lane discipline, which results in parallel movement of vehicles in the same lane. Hence, vehicles not only interact longitudinally with the vehicles ahead but also laterally with vehicles to the sides. Lateral movements have a significant impact on the characteristics of traffic flow and therefore are of great importance in microscopic traffic simulation models. Existing simulation models for mixed traffic conditions model lateral shifts (lateral movements) as an instantaneous process but neglects detailed modeling. However, the duration for lateral shifts is generally in the range of 0.5-15 s. The omission of lateral shift duration from simulation models may have a significant impact on simulation outputs. Also, different vehicle types may have different lateral shift durations due to variations in their physical and operational characteristics. This paper attempts to develop a vehicle-specific lateral shift duration model by considering different explanatory variables such as direction of lateral shift, available space gaps, speeds of subject vehicle and surrounding vehicles, vehicle types, and clearance. The models were estimated using trajectory data collected during medium-flow conditions from an urban arterial in Chennai city, India. The findings from this study have direct implications on modeling lateral shifts in microscopic traffic simulations to be developed specifically for mixed traffic conditions. © 2018 American Society of Civil Engineers.Item An automated mathematical morphology driven algorithm for water body extraction from remotely sensed images(Elsevier B.V., 2018) Rishikeshan, C.A.; Ramesh, H.The detection and extraction of water bodies from satellite imagery is very important and useful for several planning and developmental activities such as shoreline identification, mapping riverbank erosion, watershed extraction and water resource management. Popular techniques for water body extraction like those based on the normalized difference water index (NDWI) require reflectance information in the green and near-infrared (NIR) bands of the light spectrum. Moreover, some commonly used approaches may perform differently according to the spatial resolution of the images. In this regard, mathematical morphological (MM) techniques for image processing have been employed for spatial feature extraction as they preserve edges and shapes. This study proposes a flexible MM driven approach which is very effective for the extraction of water bodies from several satellite images with different spatial resolution. MM provides effective tools for processing image objects based on size and shape and is particularly adapted for water bodies that have typically specific spatial characteristics. In greater details, the proposed extraction algorithm preserves the actual size and shape of the water bodies since it is based on morphological operators based on geodesic reconstruction. Moreover, the choice of the filter size (called structural element (SE) in MM) in the proposed algorithm is done dynamically allowing one to retain the most precise results from different set of inputs images of different spatial resolution and swath. The availability of more than one spectral band of satellite imagery is not necessary for the proposed algorithm as it utilizes only a single band for its computation. This makes it convenient to apply in single band imageries obtained from satellites such as Cartosat thereby making the proposed approach effective over commonly used methods. The accuracy assessment was carried out and compared with the maximum likelihood (ML) classifier and methods based on spectral indices. In all the five test datasets, extraction accuracy of the proposed MM approach was significantly higher than that of spectral indices and ML methods. The results drawn from visual and qualitative assessments indicated its capability and efficiency in water body extraction from different satellite images. © 2018 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS)Item E-learning adoption based on gender differences: Insight from India(Inderscience Publishers, 2020) Vanitha, P.S.; Alathur, S.Aim of this study is to explore the adoption of e-learning across gender. This study identifies how the factors influence e-learning adoption based on gender. The theories pertinent to gender difference are reviewed. Using a quantitative questionnaire survey method, 425 responses were collected from various higher education institutions from southern India. Using this data set acceptance of the hypothesis on e-learning adopted among different gender was statistically reported. Partial least square-structure equation model (PLE-SEM) is carried out to find the similarities and dissimilarities among male and female users in e-learning adoption. The current research focused on two dimensions: learner and technology. Further research can focus on the economy, religion and other possible factors. Earlier studies less reported on influence on the e-learning adoption based on different genders in India. Therefore, the current study focus on gender-based e-learning adoption in the Indian context. © © 2020 Inderscience Enterprises Ltd.Item A Perceptually Inspired Variational Model for Enhancing and Restoring Remote Sensing Images(Institute of Electrical and Electronics Engineers Inc., 2021) Padikkal, P.; Febin, I.P.Perceptually inspired algorithms have captured the recent attention of scientists and engineers due to their inherent capability to enhance the contrast of images, especially from the remote sensing domain. In this letter, we propose a perceptually inspired retinex model relying on the variational framework for enhancing and denoising satellite images captured by various imaging devices. A variational framework incorporates priors and data fidelity aspects in the designed functional, whose optimized solution yields the desired output. The model respects the distribution of the noise while enhancing the data. The overall performance is demonstrated using the visual and quantitative measures. © 2004-2012 IEEE.Item An optimum datasets analysis for monitoring crops using remotely sensed Sentinel-1A SAR data(Taylor and Francis Ltd., 2023) Salma, S.; Keerthana, N.; Dodamani, B.M.To effectively monitor crops, it is necessary to select extremely redundant satellite images and to know the number of acquisitions required for a specific period to analyse cropping patterns, thereby reducing analysis time. In this paper, we have examined an empirical analysis for the optimum dataset (OptD) selection required to monitor the crops. Sentinel-1 dual-polarized SAR datasets were used in this study to illustrate the effectiveness of optimum datasets required for the considered crops (ginger, tobacco, rice, cabbage, and pumpkin). In this work, at first, the entropy and alpha bands were treated as cluster centres for crop decomposition and its scattering mechanism using the cluster-based K-means unsupervised classification technique. The clusters are plotted on the H-α plane to get the H-α plot of dual-polarization SAR data for target decomposition. To understand the dominance of scattering type with crop growth stage, the obtained scattering distribution from the H-alpha plot is scaled to a percentage analysis. Based on qualitative observations of the percent scattering distribution of crop pixels over a h-alpha plot and backscattering coefficient behaviour at different crop growth stages, an empirical approach has been used to select dataset reduction. It has been suggested that the combination of successive repeated data with similar scattering analysis of combined h-alpha plots and backscattering analysis is the best reduced dataset selection for effective crop monitoring. From the analysis, the optimum dataset required for monitoring Ginger (from the flourishing stage), Tobacco, Paddy, Cabbage, and Pumpkin has been identified, and found that the tobacco crop requires fewer datasets, whereas the rice crop requires a greater number of datasets for monitoring. Despite the challenges associated with, p-bias for the crops was achieved at good levels, given that, lowering the datasets to obtain the optimal number without significantly reducing the accuracy of the data. © 2023 Informa UK Limited, trading as Taylor & Francis Group.