Bulusu Deekshatulu - Academia.edu (original) (raw)

Uploads

Papers by Bulusu Deekshatulu

IEEE Transactions on Applications and Industry, 1963

ABSTRACT

IEEE Transactions on Applications and Industry, 1963

ABSTRACT

Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05., 2000

... based on visual and graphical inspection and they have not defined or estimated the quality a... more ... based on visual and graphical inspection and they have not defined or estimated the quality and degree of the ... PCA removes the redundancy of information content. ... By applying Shannon's entropy in evaluating the information content of an image, the formula is modified as: ...

2013 International Mutli-Conference on Automation, Computing, Communication, Control and Compressed Sensing (iMac4s), 2013

ABSTRACT Medical data mining is used to extract knowledgeable information from a huge amount of m... more ABSTRACT Medical data mining is used to extract knowledgeable information from a huge amount of medical data. Associative classification is a rule based new approach which integrates association rule mining and classification, if applied on medical data sets, lends them to an easier interpretation. It selects a small set of high quality rules and uses these rules for prediction. Heart disease rates among the major cause of mortality in developing countries and is rapidly becoming so in developing countries like India. India is the second most populous country in the world with an estimated population of over 1 billion. Rapid industrialization and urbanization have resulted in tremendous growth in the economy over the last decade. Concurrently India has also seen an exponential rise in prevalence of Heart disease. It has predicted that CVD will be the most important cause of mortality in India by the year 2015, and A. P is in risk of CVD. Hence a decision support system should be proposed to predict the risk score of a patient, which will help in taking precautionary steps like balanced diet and medication which will in turn increase life time of a patient. Through this paper we propose a lazy associative classification for prediction of heart disease in Andhra Pradesh and present some experimental results which will help physicians to take accurate decisions.

Digital Image Processing and Visual Communications Technologies in the Earth and Atmospheric Sciences, 1990

ABSTRACT

IEEE Transactions on Applications and Industry, 1964

ABSTRACT

2010 Second Vaagdevi International Conference on Information Technology for Real World Problems, 2010

ABSTRACT

IEEE Transactions on Systems, Man, and Cybernetics, 1975

A hypothesis is proposed that predicts regions where however, is purely empirical in the sense th... more A hypothesis is proposed that predicts regions where however, is purely empirical in the sense that there is no fixations are most likely to occur on a visual pattern viewed by a human "theory" associated with it, and it is not based on any test subject. A scheme is developed for evaluating a fixation probability density function for any given pattern, based on an assumed fixation physiological or psychological considerations. The present probability density function for a pattern consisting of a single dot. hypothesis seeks to eliminate some of these limitations by Predictions of the hypothesis agree with experimental data available using a different approach to the problem. in the literature. When the hypothesis is used in conjunction with some assumptions, it also provides interpretations for some well-known DEVELOPMENT OF HYPOTHESIS geometrical illusions, such as the Muller-Lyer illusion. It is hoped that The analysis is at present restricted to simple twoa study of this kind will aid in understanding some aspects of the mechdimensional outline patters. When such a pattern is being anisms subserving human visual pattern recognition. viewed, the location of the point of fixation at any given ''idcdb h t o,i=12***n

Surveillance of water quality by remote sensing technique can be persued with advantage. An attem... more Surveillance of water quality by remote sensing technique can be persued with advantage. An attempt has been made in this paper to obtain regional models of water quality of inland tanks and lakes. Stepwise multiple linear regression analysis between water quality parameters and several functions of Exotech radiometer band reflectance values, namely, bands alone, bands and their ratios, and, bands and their products are evaluated with respect to performance of the regression parameters. It is seen, that, the pairwise product of the reflectance in different bands is better correlated than the bands and their ratios. A possible explanation for this could be the higher order non-linear relation between the water quality parameters and the spectral bands.

Content Based Image Retrieval (CBIR) has become one of the most active research areas in the past... more Content Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many indexing techniques are based on global features distribution such as Gabor Wavelets. In this paper we present a new approach for global feature extraction using an emerging technique known as Independent Component Analysis (ICA). ICA is a generative model for observed multivariate data, which are assumed to be mixtures of some unknown latent variables. It is a statistical and computational technique for revealing hidden factors that underlies set of random variable measurements of signals. The objective of ICA is to represent a set of multidimensional measurement vectors in a basis where the components are statistically independent. Present papers deals with the comparative study between ICA feature vectors and Gabor feature vectors for 180 different texture and natural images in a databank. Result analysis show that extracting color and texture information by ICA provides significantly improved results in terms of retrieval accuracy, computational complexity and storage space of feature vectors as compared to Gabor approaches.

Area morphology filters are capable of removing objects in a image based on the object area solel... more Area morphology filters are capable of removing objects in a image based on the object area solely. These operators can be effectively used for content based image retrieval. But the traditional levelset based implementations are not practical due to the time consuming nature of these operators. Here we present a fast implementation of area morphology based on bitplanes. The bitplane based area morphological segmenation technique is applied for CBIR. The experiments indicate that our segmentation mechanism is good and fast compared to the existing fast area morphological segmentation techniques. Similarity matching for CBIR is done using Integrated Region matching.

Content-based image retrieval is an important area of research involving techniques of image proc... more Content-based image retrieval is an important area of research involving techniques of image processing, information retrieval, and data mining. Mathematical morphology is a powerful set of tools in image processing and normally used for filtering, shape description etc.. Sequence data mining and clustering are the popular data mining techniques that are successfully applied to varieties of applications. In the present work, we demonstrate that the pattern spectrum, a well known morphological technique, can be used to capture emotions in a face image. We also show, by devising a novel data mining technique for sequence database, that the set of pattern spectra corresponding to face image database can be searched to retrieve faces having emotion similar to that of a query image. We make use of link-based clustering combined with density based clustering to handle the data mining tasks. We demonstrate the efficiency of our system experimentally.

Space technology has introduced new dimensions into the study and understanding of Earth's pr... more Space technology has introduced new dimensions into the study and understanding of Earth's processes and in improving the quality of life for the humanity. The benefits from the space technology are mostly confined to the space faring nations. United Nations Office for Outer Space Affairs (UN-OOSA) has taken initiative to disseminate the scientific and technology knowledge to developing countries through

Associative classification is a recent and rewarding technique which integrates association rule ... more Associative classification is a recent and rewarding technique which integrates association rule mining and classification to a model for prediction and achieves maximum accuracy. Associative classifiers are especially fit to applications where maximum accuracy is desired to a model for prediction. There are many domains such as medical where the maximum accuracy of the model is desired. Heart disease is a single largest cause of death in developed countries and one of the main contributors to disease burden in developing countries. Mortality data from the registrar general of India shows that heart disease are a major cause of death in India, and in Andhra Pradesh coronary heart disease cause about 30%of deaths in rural areas. Hence there is a need to develop a decision support system for predicting heart disease of a patient. In this paper we propose efficient associative classification algorithm using genetic approach for heart disease prediction. The main motivation for using ge...

Lecture Notes in Computer Science, 2015

International Conference on Circuits, Communication, Control and Computing, 2014

ABSTRACT Recent survey shows that heart disease is a leading cause of death in India and in world... more ABSTRACT Recent survey shows that heart disease is a leading cause of death in India and in world wide. Significant life savings can be achieved, if a timely and cost effective clinical decision system is developed. Adverse reactions occur if a disease is not diagnosed properly. A clinical decision support system can assist health care professionals for early diagnosis of heart disease from patient’s medical data. Machine learning and modern data mining methods are useful for predicting and classifying heart disease. In this paper we wish to develop effective alternating decision tree approach for early diagnosis of heart disease. Alternating decision tree is a new type of classification rule. It is a generalization of decision trees, voted decision stumps and voted decision trees. We have applied our approach on heart disease patient records collected from various hospitals in Hyderabad. Optimization of features improves efficiency of earning algorithm. We used PCA to determine essential features of heart disease data. Experimental results show that our decision support system achieves high accuracy and proving its usefulness in the diagnosis of heart disease

2012 12th International Conference on Intelligent Systems Design and Applications (ISDA), 2012

ABSTRACT Medical data mining is the search for relationships and patterns within the medical data... more ABSTRACT Medical data mining is the search for relationships and patterns within the medical data that could provide useful knowledge for effective medical diagnosis. Extracting useful information from these data bases can lead to discovery of rules for later diagnosis tools. Generally medical data bases are highly voluminous in nature. If a training data set contains irrelevant and redundant features classification may produce less accurate results. Feature selection as a pre-processing step in used to reduce dimensionality, removing irrelevant data and increasing accuracy and improves comprehensibility. Associative classification is a recent and rewarding technique that applies the methodology of association into classification and achieves high classification accuracy. Most associative classification algorithms adopt exhaustive search algorithms like in Apriori, and generate huge no. of rules from which a set of high quality of rules are chosen to construct efficient classifier. Hence generating a small set of high quality rules to build classifier is a challenging task. Cardiovascular diseases are the leading cause of death globally and in India more deaths are due to CHD. Cardiovascular disease is an increasingly an important cause of death in Andhra Pradesh. Hence there is an urgent need to develop a system to predict the heart disease of people. This paper discusses prediction of risk score for heart disease in Andhra Pradesh. We generated class association rules using feature subset selection. These generated rules will help physicians to predict the heart disease of a patient.

Procedia Technology, 2013

Data mining techniques have been widely used to mine knowledgeable information from medical data ... more Data mining techniques have been widely used to mine knowledgeable information from medical data bases. In data mining classification is a supervised learning that can be used to design models describing important data classes, where class attribute is involved in the construction of the classifier. Nearest neighbor (KNN) is very simple, most popular, highly efficient and effective algorithm for pattern recognition.KNN is a straight forward classifier, where samples are classified based on the class of their nearest neighbor. Medical data bases are high volume in nature. If the data set contains redundant and irrelevant attributes, classification may produce less accurate result. Heart disease is the leading cause of death in INDIA. In Andhra Pradesh heart disease was the leading cause of mortality accounting for 32%of all deaths, a rate as high as Canada (35%) and USA.Hence there is a need to define a decision support system that helps clinicians decide to take precautionary steps. In this paper we propose a new algorithm which combines KNN with genetic algorithm for effective classification. Genetic algorithms perform global search in complex large and multimodal landscapes and provide optimal solution. Experimental results shows that our algorithm enhance the accuracy in diagnosis of heart disease.

IEEE Transactions on Applications and Industry, 1963

ABSTRACT

IEEE Transactions on Applications and Industry, 1963

ABSTRACT

Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05., 2000

... based on visual and graphical inspection and they have not defined or estimated the quality a... more ... based on visual and graphical inspection and they have not defined or estimated the quality and degree of the ... PCA removes the redundancy of information content. ... By applying Shannon's entropy in evaluating the information content of an image, the formula is modified as: ...

2013 International Mutli-Conference on Automation, Computing, Communication, Control and Compressed Sensing (iMac4s), 2013

ABSTRACT Medical data mining is used to extract knowledgeable information from a huge amount of m... more ABSTRACT Medical data mining is used to extract knowledgeable information from a huge amount of medical data. Associative classification is a rule based new approach which integrates association rule mining and classification, if applied on medical data sets, lends them to an easier interpretation. It selects a small set of high quality rules and uses these rules for prediction. Heart disease rates among the major cause of mortality in developing countries and is rapidly becoming so in developing countries like India. India is the second most populous country in the world with an estimated population of over 1 billion. Rapid industrialization and urbanization have resulted in tremendous growth in the economy over the last decade. Concurrently India has also seen an exponential rise in prevalence of Heart disease. It has predicted that CVD will be the most important cause of mortality in India by the year 2015, and A. P is in risk of CVD. Hence a decision support system should be proposed to predict the risk score of a patient, which will help in taking precautionary steps like balanced diet and medication which will in turn increase life time of a patient. Through this paper we propose a lazy associative classification for prediction of heart disease in Andhra Pradesh and present some experimental results which will help physicians to take accurate decisions.

Digital Image Processing and Visual Communications Technologies in the Earth and Atmospheric Sciences, 1990

ABSTRACT

IEEE Transactions on Applications and Industry, 1964

ABSTRACT

2010 Second Vaagdevi International Conference on Information Technology for Real World Problems, 2010

ABSTRACT

IEEE Transactions on Systems, Man, and Cybernetics, 1975

A hypothesis is proposed that predicts regions where however, is purely empirical in the sense th... more A hypothesis is proposed that predicts regions where however, is purely empirical in the sense that there is no fixations are most likely to occur on a visual pattern viewed by a human "theory" associated with it, and it is not based on any test subject. A scheme is developed for evaluating a fixation probability density function for any given pattern, based on an assumed fixation physiological or psychological considerations. The present probability density function for a pattern consisting of a single dot. hypothesis seeks to eliminate some of these limitations by Predictions of the hypothesis agree with experimental data available using a different approach to the problem. in the literature. When the hypothesis is used in conjunction with some assumptions, it also provides interpretations for some well-known DEVELOPMENT OF HYPOTHESIS geometrical illusions, such as the Muller-Lyer illusion. It is hoped that The analysis is at present restricted to simple twoa study of this kind will aid in understanding some aspects of the mechdimensional outline patters. When such a pattern is being anisms subserving human visual pattern recognition. viewed, the location of the point of fixation at any given ''idcdb h t o,i=12***n

Surveillance of water quality by remote sensing technique can be persued with advantage. An attem... more Surveillance of water quality by remote sensing technique can be persued with advantage. An attempt has been made in this paper to obtain regional models of water quality of inland tanks and lakes. Stepwise multiple linear regression analysis between water quality parameters and several functions of Exotech radiometer band reflectance values, namely, bands alone, bands and their ratios, and, bands and their products are evaluated with respect to performance of the regression parameters. It is seen, that, the pairwise product of the reflectance in different bands is better correlated than the bands and their ratios. A possible explanation for this could be the higher order non-linear relation between the water quality parameters and the spectral bands.

Content Based Image Retrieval (CBIR) has become one of the most active research areas in the past... more Content Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many indexing techniques are based on global features distribution such as Gabor Wavelets. In this paper we present a new approach for global feature extraction using an emerging technique known as Independent Component Analysis (ICA). ICA is a generative model for observed multivariate data, which are assumed to be mixtures of some unknown latent variables. It is a statistical and computational technique for revealing hidden factors that underlies set of random variable measurements of signals. The objective of ICA is to represent a set of multidimensional measurement vectors in a basis where the components are statistically independent. Present papers deals with the comparative study between ICA feature vectors and Gabor feature vectors for 180 different texture and natural images in a databank. Result analysis show that extracting color and texture information by ICA provides significantly improved results in terms of retrieval accuracy, computational complexity and storage space of feature vectors as compared to Gabor approaches.

Area morphology filters are capable of removing objects in a image based on the object area solel... more Area morphology filters are capable of removing objects in a image based on the object area solely. These operators can be effectively used for content based image retrieval. But the traditional levelset based implementations are not practical due to the time consuming nature of these operators. Here we present a fast implementation of area morphology based on bitplanes. The bitplane based area morphological segmenation technique is applied for CBIR. The experiments indicate that our segmentation mechanism is good and fast compared to the existing fast area morphological segmentation techniques. Similarity matching for CBIR is done using Integrated Region matching.

Content-based image retrieval is an important area of research involving techniques of image proc... more Content-based image retrieval is an important area of research involving techniques of image processing, information retrieval, and data mining. Mathematical morphology is a powerful set of tools in image processing and normally used for filtering, shape description etc.. Sequence data mining and clustering are the popular data mining techniques that are successfully applied to varieties of applications. In the present work, we demonstrate that the pattern spectrum, a well known morphological technique, can be used to capture emotions in a face image. We also show, by devising a novel data mining technique for sequence database, that the set of pattern spectra corresponding to face image database can be searched to retrieve faces having emotion similar to that of a query image. We make use of link-based clustering combined with density based clustering to handle the data mining tasks. We demonstrate the efficiency of our system experimentally.

Space technology has introduced new dimensions into the study and understanding of Earth's pr... more Space technology has introduced new dimensions into the study and understanding of Earth's processes and in improving the quality of life for the humanity. The benefits from the space technology are mostly confined to the space faring nations. United Nations Office for Outer Space Affairs (UN-OOSA) has taken initiative to disseminate the scientific and technology knowledge to developing countries through

Associative classification is a recent and rewarding technique which integrates association rule ... more Associative classification is a recent and rewarding technique which integrates association rule mining and classification to a model for prediction and achieves maximum accuracy. Associative classifiers are especially fit to applications where maximum accuracy is desired to a model for prediction. There are many domains such as medical where the maximum accuracy of the model is desired. Heart disease is a single largest cause of death in developed countries and one of the main contributors to disease burden in developing countries. Mortality data from the registrar general of India shows that heart disease are a major cause of death in India, and in Andhra Pradesh coronary heart disease cause about 30%of deaths in rural areas. Hence there is a need to develop a decision support system for predicting heart disease of a patient. In this paper we propose efficient associative classification algorithm using genetic approach for heart disease prediction. The main motivation for using ge...

Lecture Notes in Computer Science, 2015

International Conference on Circuits, Communication, Control and Computing, 2014

ABSTRACT Recent survey shows that heart disease is a leading cause of death in India and in world... more ABSTRACT Recent survey shows that heart disease is a leading cause of death in India and in world wide. Significant life savings can be achieved, if a timely and cost effective clinical decision system is developed. Adverse reactions occur if a disease is not diagnosed properly. A clinical decision support system can assist health care professionals for early diagnosis of heart disease from patient’s medical data. Machine learning and modern data mining methods are useful for predicting and classifying heart disease. In this paper we wish to develop effective alternating decision tree approach for early diagnosis of heart disease. Alternating decision tree is a new type of classification rule. It is a generalization of decision trees, voted decision stumps and voted decision trees. We have applied our approach on heart disease patient records collected from various hospitals in Hyderabad. Optimization of features improves efficiency of earning algorithm. We used PCA to determine essential features of heart disease data. Experimental results show that our decision support system achieves high accuracy and proving its usefulness in the diagnosis of heart disease

2012 12th International Conference on Intelligent Systems Design and Applications (ISDA), 2012

ABSTRACT Medical data mining is the search for relationships and patterns within the medical data... more ABSTRACT Medical data mining is the search for relationships and patterns within the medical data that could provide useful knowledge for effective medical diagnosis. Extracting useful information from these data bases can lead to discovery of rules for later diagnosis tools. Generally medical data bases are highly voluminous in nature. If a training data set contains irrelevant and redundant features classification may produce less accurate results. Feature selection as a pre-processing step in used to reduce dimensionality, removing irrelevant data and increasing accuracy and improves comprehensibility. Associative classification is a recent and rewarding technique that applies the methodology of association into classification and achieves high classification accuracy. Most associative classification algorithms adopt exhaustive search algorithms like in Apriori, and generate huge no. of rules from which a set of high quality of rules are chosen to construct efficient classifier. Hence generating a small set of high quality rules to build classifier is a challenging task. Cardiovascular diseases are the leading cause of death globally and in India more deaths are due to CHD. Cardiovascular disease is an increasingly an important cause of death in Andhra Pradesh. Hence there is an urgent need to develop a system to predict the heart disease of people. This paper discusses prediction of risk score for heart disease in Andhra Pradesh. We generated class association rules using feature subset selection. These generated rules will help physicians to predict the heart disease of a patient.

Procedia Technology, 2013

Data mining techniques have been widely used to mine knowledgeable information from medical data ... more Data mining techniques have been widely used to mine knowledgeable information from medical data bases. In data mining classification is a supervised learning that can be used to design models describing important data classes, where class attribute is involved in the construction of the classifier. Nearest neighbor (KNN) is very simple, most popular, highly efficient and effective algorithm for pattern recognition.KNN is a straight forward classifier, where samples are classified based on the class of their nearest neighbor. Medical data bases are high volume in nature. If the data set contains redundant and irrelevant attributes, classification may produce less accurate result. Heart disease is the leading cause of death in INDIA. In Andhra Pradesh heart disease was the leading cause of mortality accounting for 32%of all deaths, a rate as high as Canada (35%) and USA.Hence there is a need to define a decision support system that helps clinicians decide to take precautionary steps. In this paper we propose a new algorithm which combines KNN with genetic algorithm for effective classification. Genetic algorithms perform global search in complex large and multimodal landscapes and provide optimal solution. Experimental results shows that our algorithm enhance the accuracy in diagnosis of heart disease.