arXiv subjects

M. Naresh Kumar

Publications and source records attributed to M. Naresh Kumar.

11 recordsLinked to original sources

arXiv2020

Mesh Processing Strategies and Fractals for Three Dimensional Morphological Analysis of a Granitic Terrain using IRS LISS IV and Carto DEM

Virtual Reality (VR) enabled applications are becoming very important to visualize the terrain features in 3D. In general 3D datasets generated from high-resolution satellites and DEM occupy large volumes of data. However, lightweight datasets are required to create better user experiences on VR platforms. So, the present study develops a methodology to generate datasets compatible with VR using Indian Remote Sensing satellite (IRS) sensors. A Linear Imaging Self-Scanning System - IV (LISS IV) with 5.8 m spatial resolution and Carto DEM are used for generating the 3D view using the Arc environment and then converted into virtual reality modeling language (VRML) format. In order to reduce the volume of the VRML dataset a quadratic edge collapse decimation method is applied which reduces the number of faces in the mesh while preserving the boundary and/or normal. A granitic terrain in the south-west part of Hyderabad comprising of dyke intrusion is considered for the generation of 3D VR dataset, as it has high elevation differences thus rendering it most suitable for the present study. Further, the enhanced geomorphological features such as hills and valleys, geological structures such as fractures, intrusive (dykes) are studied and found suitable for better interpretation.

cs.GR↗

arXiv2015

Temporal divergence in cropping pattern and its implications on geospatial drought assessment

Time series data on cropping pattern at disaggregated level were analysed and its implications on geospatial drought assessment were demonstrated. An index of Cropping Pattern Dissimilarity (CP-DI) between a pair of years, developed in this study, proved that the cropping pattern of a year has a higher degree of similarity with that of recent past years only and tends to be dissimilar with longer time difference. The temporal divergence in cropping pattern has direct implications on geospatial approach of drought assessment, in which, time series NDVI data are compared for drought interpretation. It was found that, seasonal NDVI profiles of drought year and normal year did not show any anomaly when the cropping patterns were dissimilar and two normal years having dissimilar cropping pattern showed different NDVI profiles. Therefore, it is suggested that such temporal comparisons of NDVI are better restricted to recent past years to achieve more objective interpretation.

q-bio.QM↗

arXiv2015

A new hybrid spectral similarity measure for discrimination of Vigna species

The reflectance spectrum of the species in a hyperspectral data can be modelled as an n-dimensional vector. The spectral angle mapper computes the angle between the vectors which is used to discriminate the species. The spectral information divergence models the data as a probability distribution so that the spectral variability between the bands can be extracted using the stochastic measures. The hybrid approach of spectral angle mapper and spectral information divergence is found to be better discriminator than spectral angle mapper or spectral information divergence alone. The spectral correlation angle is computed as a cosine of the angle of the Pearsonian correlation coefficient between the vectors. The spectral correlation angle is a better measure than the spectral angle mapper as it considers only standardized values of the vectors rather than the absolute values of the vector. In the present paper a new hybrid measure is proposed which is based on the spectral correlation angle and the spectral information divergence. The proposed method has been compared with the hybrid approach of spectral information divergence and spectral angle mapper for discrimination of crops belonging to Vigna species using measures like relative spectral discriminatory power, relative discriminatory probability and relative discriminatory entropy in different spectral regions. Experimental results using the laboratory spectra show that the proposed method gives higher relative discriminatory power in 400nm-700nm spectral region.

q-bio.QM↗

arXiv2015

On the use of Standardized Precipitation Index(SPI) for drought intensity assessment

Monthly rainfall data from June to October for 39 years was used to generate Standardized Precipitation Index (SPI) values based on Gamma distribution for a low rainfall and a high rainfall district of Andhra Pradesh state, India. Comparison of SPI, with actual rainfall and rainfall deviation from the mean indicated that SPI values under-estimate the intensity of dryness/wetness when the rainfall is very low/very high respectively. As a result, the SPI in the worst drought years of 2002 and 2006 in the low rainfall district has indicated only moderate dryness instead of extreme dryness. The range of SPI values of the high rainfall district indicated better stretching, compared to that of the low rainfall district. Further, the SPI values of longer time scale (2-, 3- and 4- months) showed an extended range compared to 1-month, but the sensitivity in drought years has not improved significantly. To ascertain whether non normality of SPI is a possible reason, normality tests were conducted. The Shapiro-Wilk statistic, p-values and absolute value of the median confirmed normal distribution of SPI in both the districts whereas cumulative probability distribution of SPI indicated deviation from normal probability in the lower and upper ranges. Therefore, it is suggested that SPI as a stand alone indicator needs to be interpreted with caution to assess the intensity of drought. Further investigations should include; sensitivity of SPI to the estimated shape and scale at lower and upper bounds of gamma and impact of other distributions such as Pearson III on SPI computation, to complement the above results.

physics.ao-ph↗

arXiv2015

Spatiotemporal Analysis of Meteorological Drought Variability in the Indian Region Using Standardized Precipitation Index

Grid (1° latitude x 1° longitude) level daily rainfall data over India from June to September for the years 1951 to 2007, generated by India Meteorological Department, was analyzed to build monthly time series of Standardized Precipitation Index (SPI). Analysis of SPI was done to study the spatial and temporal patterns of drought occurrence in the country. Geographic spread of SPI derived Area under Dryness (AUD) in different years revealed the uniqueness of 2002 drought with wide spread dryness in July. Mann-Kendal trend analysis and moving average based trends performed on AUD indicated increasing trend in July. The area under moderate drought frequency has increased in the most recent decade. Ranking of years based on Drought Persistency Score (DPS) indicated that the year 1987 was the severe-most drought year in the country. The results of the study have revealed various aspects of drought climatology in India. A similar analysis with the SPI of finer spatial resolution and relating it to crop production would be useful in quantifying the impact of drought in economic terms.

physics.ao-ph↗

arXiv2015

Estimation of the parameters of an infectious disease model using neural networks

In this paper, we propose a realistic mathematical model taking into account the mutual interference among the interacting populations. This model attempts to describe the control (vaccination) function as a function of the number of infective individuals, which is an improvement over the existing susceptible infective epidemic models. Regarding the growth of the epidemic as a nonlinear phenomenon we have developed a neural network architecture to estimate the vital parameters associated with this model. This architecture is based on a recently developed new class of neural networks known as co-operative and supportive neural networks. The application of this architecture to the present study involves preprocessing of the input data, and this renders an efficient estimation of the rate of spread of the epidemic. It is observed that the proposed new neural network outperforms a simple feed-forward neural network and polynomial regression.

cs.NE↗

arXiv2015

A Dynamic Model for Infectious Diseases: The Role of Vaccination and Treatment

Understanding dynamics of an infectious disease helps in designing appropriate strategies for containing its spread in a population. Recent mathematical models are aimed at studying dynamics of some specific types of infectious diseases. In this paper we propose a new model for infectious diseases spread having susceptible, infected, and recovered populations and study its dynamics in presence of incubation delays and relapse of the disease. The influence of treatment and vaccination efforts on the spread of infection in presence of time delays are studied. Sufficient conditions for local stability of the equilibria and change of stability are derived in various cases. The problem of global stability is studied for an important special case of the model. Simulations carried out in this study brought out the importance of treatment rate in controlling the disease spread. It is observed that incubation delays have influence on the system even under enhanced vaccination. The present study has clearly brought out the fact that treatment rate in presence of time delays would contain the disease as compared to popular belief that eradication can only be done through vaccination.

math.DS↗

arXiv2015

A New Methodology for Estimating Internal Credit Risk and Bankruptcy Prediction under Basel II Regime

Credit estimation and bankruptcy prediction methods have been utilizing Altman's $z$ score method for the last several years. It is reported in many studies that $z$ score is sensitive to changes in accounting figures. Researches have proposed different variations to conventional $z$ score that can improve the prediction accuracy. In this paper we develop a new multivariate non-linear model for computing the $z$ score. In addition we develop a new credit risk index by fitting a Pearson type-III distribution to the transformed financial ratios. The results from our study have shown that the new $z$ score can predict the bankruptcy with an accuracy of $98.6\%$ as compared to $93.5\%$ by the Altman's $z$ score. Also, the discriminate analysis revealed that the new transformed financial ratios could predict the bankruptcy probability with an accuracy of $93.0\%$ as compared to $87.4\%$ using the weights of Altman's $z$ score.

econ.GN↗

arXiv2015

Novel Approaches for Predicting Risk Factors of Atherosclerosis

Coronary heart disease (CHD) caused by hardening of artery walls due to cholesterol known as atherosclerosis is responsible for large number of deaths world-wide. The disease progression is slow, asymptomatic and may lead to sudden cardiac arrest, stroke or myocardial infraction. Presently, imaging techniques are being employed to understand the molecular and metabolic activity of atherosclerotic plaques to estimate the risk. Though imaging methods are able to provide some information on plaque metabolism they lack the required resolution and sensitivity for detection. In this paper we consider the clinical observations and habits of individuals for predicting the risk factors of CHD. The identification of risk factors helps in stratifying patients for further intensive tests such as nuclear imaging or coronary angiography. We present a novel approach for predicting the risk factors of atherosclerosis with an in-built imputation algorithm and particle swarm optimization (PSO). We compare the performance of our methodology with other machine learning techniques on STULONG dataset which is based on longitudinal study of middle aged individuals lasting for twenty years. Our methodology powered by PSO search has identified physical inactivity as one of the risk factor for the onset of atherosclerosis in addition to other already known factors. The decision rules extracted by our methodology are able to predict the risk factors with an accuracy of $99.73%$ which is higher than the accuracies obtained by application of the state-of-the-art machine learning techniques presently being employed in the identification of atherosclerosis risk studies.

cs.LG↗

arXiv2013

Performance comparison of State-of-the-art Missing Value Imputation Algorithms on Some Bench mark Datasets

Decision making from data involves identifying a set of attributes that contribute to effective decision making through computational intelligence. The presence of missing values greatly influences the selection of right set of attributes and this renders degradation in classification accuracies of the classifiers. As missing values are quite common in data collection phase during field experiments or clinical trails appropriate handling would improve the classifier performance. In this paper we present a review of recently developed missing value imputation algorithms and compare their performance on some bench mark datasets.

cs.LG↗

arXiv2013

Alternating Decision trees for early diagnosis of dengue fever

Dengue fever is a flu-like illness spread by the bite of an infected mosquito which is fast emerging as a major health problem. Timely and cost effective diagnosis using clinical and laboratory features would reduce the mortality rates besides providing better grounds for clinical management and disease surveillance. We wish to develop a robust and effective decision tree based approach for predicting dengue disease. Our analysis is based on the clinical characteristics and laboratory measurements of the diseased individuals. We have developed and trained an alternating decision tree with boosting and compared its performance with C4.5 algorithm for dengue disease diagnosis. Of the 65 patient records a diagnosis establishes that 53 individuals have been confirmed to have dengue fever. An alternating decision tree based algorithm was able to differentiate the dengue fever using the clinical and laboratory data with number of correctly classified instances as 89%, F-measure of 0.86 and receiver operator characteristics (ROC) of 0.826 as compared to C4.5 having correctly classified instances as 78%,h F-measure of 0.738 and ROC of 0.617 respectively. Alternating decision tree based approach with boosting has been able to predict dengue fever with a higher degree of accuracy than C4.5 based decision tree using simple clinical and laboratory features. Further analysis on larger data sets is required to improve the sensitivity and specificity of the alternating decision trees.

cs.LG↗