Dr.Dharmaiah Devarapalli - Academia.edu (original) (raw)

Uploads

Papers by Dr.Dharmaiah Devarapalli

Research paper thumbnail of A Novel Cluster Algorithms of Analysis and Predict for Brain Derived Neurotrophic Factor (BDNF) Using Diabetes Patients

Advances in Intelligent Systems and Computing, 2017

Brain Derived Neurotrophic Factor (BDNF) is involved Diabetes disease is associated with metaboli... more Brain Derived Neurotrophic Factor (BDNF) is involved Diabetes disease is associated with metabolic syndrome. Disease is mainly Type-2 Diabetes Mellitus (T2DM) parameters related to BDNF also. Today's most people suffered Diabetes Disease. Diabetes Mellitus is a metabolic disorder. Current research is Cluster analyses of T2DM of BDNF data based on predicting the diabetes and identify patients. In this paper, Evaluated as a clustering method for the cluster regarding T2DM of BDNF dataset classifies several clusters. Data Mining is one of the primary methods in clustering. This method examines measurements based on compute minimum, maximum and average values based predict of patients. These algorithms and mathematical problems applied into dataset, evaluate Normalize data and similarity measures based on identifying accurate results. Identification of the BDNF Korley et al. (J Neurotrauma, 33(2):215-225, 2015, [1]) gene these factors help the neurological affected, Change Behavior thing and Mind Depression.

Research paper thumbnail of Classification of Skin Cancer Lesions Using Deep Neural Networks and Transfer Learning

Innovations in Computer Science and Engineering, 2021

Skin cancer is among the life-threatening cancers, but unlike most cancers, skin cancer is observ... more Skin cancer is among the life-threatening cancers, but unlike most cancers, skin cancer is observable and can be detected in early stages, yet not many are aware of its detectability. There are mainly three types of skin cancers, which are basal cell carcinoma, squamous cell carcinoma, and melanoma, where melanoma is the most dangerous type of cancer with a very low survival rate. Skin cancers are not painful, most of the time, even though they appear to be visibly distressing it makes them easily detectable, as cancer is nothing but the abnormal growth of skin cells. A person can detect if a skin lesion is cancerous by taking a picture. Deep neural networks can be used to classify the type of cancer. This can be done by collecting and feeding several clinical images of cancerous skin lesions, segmentation, removing noise, etc., to a deep neural network to train on before detecting cancerous lesions. Our data was scraped from the Internet and few images were collected from the HAM10000 dataset, ISIC Archive, and scraped images from the Web. Every class has 3552 images which are a total of 10,656 images; image augmentation was used to generate images to make all classes have an equal number of images. The first model was a basic CNN model that trained, several times changing the hyperparameter values to fine-tune the model to give accurate results, which gave us 86.5% accuracy and implemented transfer learning with the ImageNet weights of different ImageNet models, where ResNet50 gave us the highest accuracy of 95.6%. We have deployed this into a Web application using JavaScript and tensorflow.js.

Research paper thumbnail of GROCD: Novel Fuzzy Rules Based on Efficient Clustering and Classification of BDNF with Type-2 Diabetes Mellitus

Apple Academic Press eBooks, Apr 4, 2022

Research paper thumbnail of Sentiment Analysis of COVID-19 Tweets Using Classification Algorithms

Lecture notes in networks and systems, 2022

Research paper thumbnail of Implementation of Real-time Face Mask Detection with Convolutional Neural Network (CNN) and OpenCV

Innovations in Computer Science and Engineering, 2022

Research paper thumbnail of Modeling the Interactions between the BDNF Peptides and TrkB Receptor

The BDNF\TrkB signaling system which plays a major role in the regulation of neuronal activity. T... more The BDNF\TrkB signaling system which plays a major role in the regulation of neuronal activity. This neuronal regulation influences the potential role of this system in the therapeutic efficacy of many neurological and psychiatric disorders. Despite these roles decreased levels of BDNF are associated with diabetes and obesity which can be regulated by increasing the insulin sensitivity and glucose tolerance. BDNF mediated signaling through phosphoinositide 3-kinase (PI3K) pathway plays a key role in insulin sensitivity. These beneficial effects of BDNF as antidiabetic agents can be enhanced by the activating BDNF\TrkB signaling. These multiple functionality of BDNF\TrkB complex relies on the protein-protein interactions where those interactions are important in designing pharmacological targets. This apporach focus the use of BDNF peptides in place of BDNF protein in binding to the TrkB receptor. Protein–peptide docking studies were performed to know the interactions of the TrkB and...

Research paper thumbnail of IDS with Honey Pot to Detect Man in Middle Attacks in Cloud Computing

Providing security in cloud computing is challenging issue due to its distributed and multi OS en... more Providing security in cloud computing is challenging issue due to its distributed and multi OS environment. Cloud security mechanisms are deployed at (Virtual Machine Monitor) VMM layer to protect the multi tenant’s privacy and integrity. VMM layer is still vulnerable to Attacks.The main objective of man-in-middle attack is to eavesdrop the user’s privacy and masking their presence making it appear no third party is involving. Due to man-in-middle attack, The VMM gets affected in terms of integrity, confidentiality and availability. In proposed work, we develop IDS to address the security problems like Man-In-Middle Attack. The Intrusion Detection System is implemented is implemented with Honey pot technology to attract the attacker.The Honey pot intrusion detection system capable of detecting known and unknown attacks along with MITM attack in cloud environment.

Research paper thumbnail of Practical Approach for Demand Forecasting for Electricity

For utilities Meter Data Acquisition System (MDAS) is an overall strategy, or process, for buildi... more For utilities Meter Data Acquisition System (MDAS) is an overall strategy, or process, for building decision support systems and environments that support both everyday tactical decision-making and long-term business strategy. The MDAS provides a common infrastructure for receiving meter data from sub stations, Distribution Transformers, HT/LT consumers and processes the data. This data is shared with utility applications like billing system, energy audit systems, etc. The MDAS contains two subsystems - Data Acquisition Server (DAS) connected to cellular or telephone network for managing Advanced Metering Infrastructure (AMI) and the Meter Data Management System (MDMS). AMI is the infrastructure within which date and time-stamped meter data are remotely collected and transmitted to a Data Acquisition Server and then to a centralized MDMS. The DAS will use PSTN or cellular network with GPRS to connect to all data sources such as Data Concentrator Units (DCU) installed at sub stations...

Research paper thumbnail of A Novel Analysis of Diabetes Mellitus by Using Expert System Based on Brain Derived Neurotrophic Factor ( BDNF ) Levels

In this paper a novel concept of designing and building intelligent expert system for the detecti... more In this paper a novel concept of designing and building intelligent expert system for the detection and diagnosis of Diabetes Mellitus is introduced. The expert system classification is based on critical diabetic parameters like Brain-Derived Neurotrophic Factor (BDNF) levels, and Fasting Blood Glucose (FBG). The proposed rulebased expert system constructs large-scale knowledgebase based on the behavior of the BDNF related diabetic data. The system will give an expert decision taking into consideration all the valid ranges of diabetic parameters. The proposed expert system can work effectively even for large sets of patient data.

Research paper thumbnail of Discriminative Feature Selection by Nonparametric Way with Cluster Validation

Feature Selection is the preprocessing process of identifying the subset of data from large dimen... more Feature Selection is the preprocessing process of identifying the subset of data from large dimension data. To identifying the required data, using some Feature Selection algorithms. Like Relief, Parzen-Relief algorithms, it attempts to directly maximize the classification accuracy and naturally reflects the Bayes error in the objective. Proposed algorithmic framework selects a subset of features by minimizing the Bayes error rate estimated by a nonparametric estimator. As an example, we show that the Relief algorithm greedily attempts to minimize the Bayes error estimated by the k-Nearest-Neighbor (kNN) method. In particular, by exploiting the proposed framework, we establish the Parzen-Relief (P-Relief) algorithm based on Parzen window estimator. The Relief algorithm is a popular approach for feature weight estimation. Many extensions of the Relief algorithm are developed. Because of the randomicity and the uncertainty of the instances used for calculating the feature weight vecto...

Research paper thumbnail of A computational intelligence technique for the effective diagnosis of diabetic patients using principal component analysis (PCA) and modified fuzzy SLIQ decision tree approach

Applied Soft Computing

Knowledge inference systems are built to identify hidden and logical patterns in huge data. Decis... more Knowledge inference systems are built to identify hidden and logical patterns in huge data. Decision trees play a vital role in knowledge discovery but crisp decision tree algorithms have a problem with sharp decision boundaries which may not be implicated to all knowledge inference systems. A fuzzy decision tree algorithm overcomes this drawback. Fuzzy decision trees are implemented through fuzzification of the decision boundaries without disturbing the attribute values. Data reduction also plays a crucial role in many classification problems. In this research article, it presents an approach using principal component analysis and modified Gini index based fuzzy SLIQ decision tree algorithm. The PCA is used for dimensionality reduction, and modified Gini index fuzzy SLIQ decision tree algorithm to construct decision rules. Finally, through PID data set, the method is validated in the simulation experiment in MATLAB.

Research paper thumbnail of Bayesian Network and Variable Elimination Algorithm for Reasoning under Uncertainty

A common task for a Bayesian network is to perform inference by computing to determine various pr... more A common task for a Bayesian network is to perform inference by computing to determine various probabilities of interest from the model. We are using an algorithm for construction of Bayesian network from given data input from several data sources such as Oracle, Access, Excel, etc., and variable elimination algorithm for answering probabilistic queries with respect to a Bayesian network. Our algorithm makes use of XML Bayesian Interchange Format to support portability of constructed network within modules of program. The algorithm runs in time and space exponential in the tree width of the network. The variable elimination algorithm acts on a set of factors. Each factor involves a set of variables and each node in a Bayesian network is equipped with a conditional probability function that expresses the likelihood that the node will take on different values given the values of its parents. The initial sets of factors are the network’s conditional probability distributions (tables). ...

Research paper thumbnail of Identification of Deleterious SNPs in TACR1 Gene Using Genetic Algorithm

SpringerBriefs in Applied Sciences and Technology, 2014

Bioinformatics is a specific research and development area. The purpose of bioinformatics mainly ... more Bioinformatics is a specific research and development area. The purpose of bioinformatics mainly deals with data mining and the relationships and patterns in large databases to provide useful information analysis and diagnosis. Single nucleotide polymorphisms (SNP) are one of the major causes of genetic diseases. Identification of disease-causing SNPs can identify better disease diagnosis. Hence, the present study aims at the identification of deleterious SNPs in TACR1 gene. Developing an algorithm plays a vital role in computational intelligence techniques. In this paper, a genetic algorithm (GA) approach is to develop rules and it is presented. The importance of the accuracy, sensitivity, specificity, and comprehensibility of the rules is simplified for the implementation of a GA. The outline of encoding and genetic operators and fitness function of GA are discussed. GA is using to identify deleterious or damaged SNPs.

Research paper thumbnail of TEJU: Fraud Detection and Improving Classification Performance for Bankruptcy Datasets Using Machine Learning Techniques

Research paper thumbnail of Identification of AIDS disease severity based on computational intelligence techniques using clonal selection algorithm

International Journal of Convergence Computing

Research paper thumbnail of Identification of AIDS Disease Severity Using Genetic Algorithm

SpringerBriefs in Applied Sciences and Technology, 2014

Bioinformatics is a data-intentionally the field in Research and Development. The purpose of bioi... more Bioinformatics is a data-intentionally the field in Research and Development. The purpose of bioinformatics data mining(DM) is to observe the relationships and patterns in large databases to provide useful data analysis and results. Evolutionary algorithms play a main role in computational intelligence techniques. An developing situation was created throughout the world regarding the Human immunodeficiency virus infection / Acquired Immunodeficiency Syndrome (HIV/AIDS) disease are mainly stigma. Every country is facing this problem. According to present survey is World health organization (WHO), AIDS disease has its complexity are health disease going present century. A best way to early examine of AIDS may improve the lives of all people affected by AIDS and people may lead healthy life. In this part of we have present an evolutionary algorithm known as Genetic Algorithm(GA) for better results of AIDS Disease using association rule mining. In this computational intelligence techniques we tested the performance of the method using AIDS data set . We presented a better fitness function using coverage, comprehensibility and rule length. This fitness function we achieved promising accuracy

Research paper thumbnail of A Novel Cluster Algorithms of Analysis and Predict for Brain Derived Neurotrophic Factor (BDNF) Using Diabetes Patients

Advances in Intelligent Systems and Computing, 2017

Brain Derived Neurotrophic Factor (BDNF) is involved Diabetes disease is associated with metaboli... more Brain Derived Neurotrophic Factor (BDNF) is involved Diabetes disease is associated with metabolic syndrome. Disease is mainly Type-2 Diabetes Mellitus (T2DM) parameters related to BDNF also. Today's most people suffered Diabetes Disease. Diabetes Mellitus is a metabolic disorder. Current research is Cluster analyses of T2DM of BDNF data based on predicting the diabetes and identify patients. In this paper, Evaluated as a clustering method for the cluster regarding T2DM of BDNF dataset classifies several clusters. Data Mining is one of the primary methods in clustering. This method examines measurements based on compute minimum, maximum and average values based predict of patients. These algorithms and mathematical problems applied into dataset, evaluate Normalize data and similarity measures based on identifying accurate results. Identification of the BDNF Korley et al. (J Neurotrauma, 33(2):215-225, 2015, [1]) gene these factors help the neurological affected, Change Behavior thing and Mind Depression.

Research paper thumbnail of Classification of Skin Cancer Lesions Using Deep Neural Networks and Transfer Learning

Innovations in Computer Science and Engineering, 2021

Skin cancer is among the life-threatening cancers, but unlike most cancers, skin cancer is observ... more Skin cancer is among the life-threatening cancers, but unlike most cancers, skin cancer is observable and can be detected in early stages, yet not many are aware of its detectability. There are mainly three types of skin cancers, which are basal cell carcinoma, squamous cell carcinoma, and melanoma, where melanoma is the most dangerous type of cancer with a very low survival rate. Skin cancers are not painful, most of the time, even though they appear to be visibly distressing it makes them easily detectable, as cancer is nothing but the abnormal growth of skin cells. A person can detect if a skin lesion is cancerous by taking a picture. Deep neural networks can be used to classify the type of cancer. This can be done by collecting and feeding several clinical images of cancerous skin lesions, segmentation, removing noise, etc., to a deep neural network to train on before detecting cancerous lesions. Our data was scraped from the Internet and few images were collected from the HAM10000 dataset, ISIC Archive, and scraped images from the Web. Every class has 3552 images which are a total of 10,656 images; image augmentation was used to generate images to make all classes have an equal number of images. The first model was a basic CNN model that trained, several times changing the hyperparameter values to fine-tune the model to give accurate results, which gave us 86.5% accuracy and implemented transfer learning with the ImageNet weights of different ImageNet models, where ResNet50 gave us the highest accuracy of 95.6%. We have deployed this into a Web application using JavaScript and tensorflow.js.

Research paper thumbnail of GROCD: Novel Fuzzy Rules Based on Efficient Clustering and Classification of BDNF with Type-2 Diabetes Mellitus

Apple Academic Press eBooks, Apr 4, 2022

Research paper thumbnail of Sentiment Analysis of COVID-19 Tweets Using Classification Algorithms

Lecture notes in networks and systems, 2022

Research paper thumbnail of Implementation of Real-time Face Mask Detection with Convolutional Neural Network (CNN) and OpenCV

Innovations in Computer Science and Engineering, 2022

Research paper thumbnail of Modeling the Interactions between the BDNF Peptides and TrkB Receptor

The BDNF\TrkB signaling system which plays a major role in the regulation of neuronal activity. T... more The BDNF\TrkB signaling system which plays a major role in the regulation of neuronal activity. This neuronal regulation influences the potential role of this system in the therapeutic efficacy of many neurological and psychiatric disorders. Despite these roles decreased levels of BDNF are associated with diabetes and obesity which can be regulated by increasing the insulin sensitivity and glucose tolerance. BDNF mediated signaling through phosphoinositide 3-kinase (PI3K) pathway plays a key role in insulin sensitivity. These beneficial effects of BDNF as antidiabetic agents can be enhanced by the activating BDNF\TrkB signaling. These multiple functionality of BDNF\TrkB complex relies on the protein-protein interactions where those interactions are important in designing pharmacological targets. This apporach focus the use of BDNF peptides in place of BDNF protein in binding to the TrkB receptor. Protein–peptide docking studies were performed to know the interactions of the TrkB and...

Research paper thumbnail of IDS with Honey Pot to Detect Man in Middle Attacks in Cloud Computing

Providing security in cloud computing is challenging issue due to its distributed and multi OS en... more Providing security in cloud computing is challenging issue due to its distributed and multi OS environment. Cloud security mechanisms are deployed at (Virtual Machine Monitor) VMM layer to protect the multi tenant’s privacy and integrity. VMM layer is still vulnerable to Attacks.The main objective of man-in-middle attack is to eavesdrop the user’s privacy and masking their presence making it appear no third party is involving. Due to man-in-middle attack, The VMM gets affected in terms of integrity, confidentiality and availability. In proposed work, we develop IDS to address the security problems like Man-In-Middle Attack. The Intrusion Detection System is implemented is implemented with Honey pot technology to attract the attacker.The Honey pot intrusion detection system capable of detecting known and unknown attacks along with MITM attack in cloud environment.

Research paper thumbnail of Practical Approach for Demand Forecasting for Electricity

For utilities Meter Data Acquisition System (MDAS) is an overall strategy, or process, for buildi... more For utilities Meter Data Acquisition System (MDAS) is an overall strategy, or process, for building decision support systems and environments that support both everyday tactical decision-making and long-term business strategy. The MDAS provides a common infrastructure for receiving meter data from sub stations, Distribution Transformers, HT/LT consumers and processes the data. This data is shared with utility applications like billing system, energy audit systems, etc. The MDAS contains two subsystems - Data Acquisition Server (DAS) connected to cellular or telephone network for managing Advanced Metering Infrastructure (AMI) and the Meter Data Management System (MDMS). AMI is the infrastructure within which date and time-stamped meter data are remotely collected and transmitted to a Data Acquisition Server and then to a centralized MDMS. The DAS will use PSTN or cellular network with GPRS to connect to all data sources such as Data Concentrator Units (DCU) installed at sub stations...

Research paper thumbnail of A Novel Analysis of Diabetes Mellitus by Using Expert System Based on Brain Derived Neurotrophic Factor ( BDNF ) Levels

In this paper a novel concept of designing and building intelligent expert system for the detecti... more In this paper a novel concept of designing and building intelligent expert system for the detection and diagnosis of Diabetes Mellitus is introduced. The expert system classification is based on critical diabetic parameters like Brain-Derived Neurotrophic Factor (BDNF) levels, and Fasting Blood Glucose (FBG). The proposed rulebased expert system constructs large-scale knowledgebase based on the behavior of the BDNF related diabetic data. The system will give an expert decision taking into consideration all the valid ranges of diabetic parameters. The proposed expert system can work effectively even for large sets of patient data.

Research paper thumbnail of Discriminative Feature Selection by Nonparametric Way with Cluster Validation

Feature Selection is the preprocessing process of identifying the subset of data from large dimen... more Feature Selection is the preprocessing process of identifying the subset of data from large dimension data. To identifying the required data, using some Feature Selection algorithms. Like Relief, Parzen-Relief algorithms, it attempts to directly maximize the classification accuracy and naturally reflects the Bayes error in the objective. Proposed algorithmic framework selects a subset of features by minimizing the Bayes error rate estimated by a nonparametric estimator. As an example, we show that the Relief algorithm greedily attempts to minimize the Bayes error estimated by the k-Nearest-Neighbor (kNN) method. In particular, by exploiting the proposed framework, we establish the Parzen-Relief (P-Relief) algorithm based on Parzen window estimator. The Relief algorithm is a popular approach for feature weight estimation. Many extensions of the Relief algorithm are developed. Because of the randomicity and the uncertainty of the instances used for calculating the feature weight vecto...

Research paper thumbnail of A computational intelligence technique for the effective diagnosis of diabetic patients using principal component analysis (PCA) and modified fuzzy SLIQ decision tree approach

Applied Soft Computing

Knowledge inference systems are built to identify hidden and logical patterns in huge data. Decis... more Knowledge inference systems are built to identify hidden and logical patterns in huge data. Decision trees play a vital role in knowledge discovery but crisp decision tree algorithms have a problem with sharp decision boundaries which may not be implicated to all knowledge inference systems. A fuzzy decision tree algorithm overcomes this drawback. Fuzzy decision trees are implemented through fuzzification of the decision boundaries without disturbing the attribute values. Data reduction also plays a crucial role in many classification problems. In this research article, it presents an approach using principal component analysis and modified Gini index based fuzzy SLIQ decision tree algorithm. The PCA is used for dimensionality reduction, and modified Gini index fuzzy SLIQ decision tree algorithm to construct decision rules. Finally, through PID data set, the method is validated in the simulation experiment in MATLAB.

Research paper thumbnail of Bayesian Network and Variable Elimination Algorithm for Reasoning under Uncertainty

A common task for a Bayesian network is to perform inference by computing to determine various pr... more A common task for a Bayesian network is to perform inference by computing to determine various probabilities of interest from the model. We are using an algorithm for construction of Bayesian network from given data input from several data sources such as Oracle, Access, Excel, etc., and variable elimination algorithm for answering probabilistic queries with respect to a Bayesian network. Our algorithm makes use of XML Bayesian Interchange Format to support portability of constructed network within modules of program. The algorithm runs in time and space exponential in the tree width of the network. The variable elimination algorithm acts on a set of factors. Each factor involves a set of variables and each node in a Bayesian network is equipped with a conditional probability function that expresses the likelihood that the node will take on different values given the values of its parents. The initial sets of factors are the network’s conditional probability distributions (tables). ...

Research paper thumbnail of Identification of Deleterious SNPs in TACR1 Gene Using Genetic Algorithm

SpringerBriefs in Applied Sciences and Technology, 2014

Bioinformatics is a specific research and development area. The purpose of bioinformatics mainly ... more Bioinformatics is a specific research and development area. The purpose of bioinformatics mainly deals with data mining and the relationships and patterns in large databases to provide useful information analysis and diagnosis. Single nucleotide polymorphisms (SNP) are one of the major causes of genetic diseases. Identification of disease-causing SNPs can identify better disease diagnosis. Hence, the present study aims at the identification of deleterious SNPs in TACR1 gene. Developing an algorithm plays a vital role in computational intelligence techniques. In this paper, a genetic algorithm (GA) approach is to develop rules and it is presented. The importance of the accuracy, sensitivity, specificity, and comprehensibility of the rules is simplified for the implementation of a GA. The outline of encoding and genetic operators and fitness function of GA are discussed. GA is using to identify deleterious or damaged SNPs.

Research paper thumbnail of TEJU: Fraud Detection and Improving Classification Performance for Bankruptcy Datasets Using Machine Learning Techniques

Research paper thumbnail of Identification of AIDS disease severity based on computational intelligence techniques using clonal selection algorithm

International Journal of Convergence Computing

Research paper thumbnail of Identification of AIDS Disease Severity Using Genetic Algorithm

SpringerBriefs in Applied Sciences and Technology, 2014

Bioinformatics is a data-intentionally the field in Research and Development. The purpose of bioi... more Bioinformatics is a data-intentionally the field in Research and Development. The purpose of bioinformatics data mining(DM) is to observe the relationships and patterns in large databases to provide useful data analysis and results. Evolutionary algorithms play a main role in computational intelligence techniques. An developing situation was created throughout the world regarding the Human immunodeficiency virus infection / Acquired Immunodeficiency Syndrome (HIV/AIDS) disease are mainly stigma. Every country is facing this problem. According to present survey is World health organization (WHO), AIDS disease has its complexity are health disease going present century. A best way to early examine of AIDS may improve the lives of all people affected by AIDS and people may lead healthy life. In this part of we have present an evolutionary algorithm known as Genetic Algorithm(GA) for better results of AIDS Disease using association rule mining. In this computational intelligence techniques we tested the performance of the method using AIDS data set . We presented a better fitness function using coverage, comprehensibility and rule length. This fitness function we achieved promising accuracy