Dr.K.Kalaivani
@vbithyd.ac.in
Assistant Professor
Vignana Bharathi Institute of Technology Aushapur (V), Ghatkesar (M), Medchal Dist, Hyderabad, Telangana – 501301.
RESEARCH INTERESTS
MACHINE LEARNING
DEEP LEARNING
SOFT COMPUTING
DATA MINING
Scopus Publications
Scholar Citations
Scholar h-index
Scopus Publications
K. Kalaivani, N. Uma Maheswari, and R. Venkatesh
Informa UK Limited
Cardiac disease is the predominant cause of global death mainly due to its hidden symptoms and late diagnosis. Hence, early detection is important to improve quality of life. Though traditional researches attempted to predict heart disease, most of them lacked with respect to accuracy. To solve this, the present study proposes a hybridized Ant Lion Crow Search Optimization Genetic Algorithm (ALCSOGA) to perform effective feature selection. This hybrid optimization encompasses Ant Lion, Crow Search and Genetic Algorithm. Ant lion algorithm determines the elite position. While, the Crow Search Algorithm utilizes the phenomenon of position and memory of each crow for evaluating the objective function. Both these algorithms are fed into Genetic Algorithm to improve the performance of feature selection process. Then, Stochastic Learning rate optimized Long Short Term Memory (LSTM) is proposed to classify the extracted optimized features. Finally, comparative analysis is performed in terms of accuracy, recall, F1-score, and precision. Moreover, statistical analysis is performed with respect to Sum of Squares (SS), degree of freedom (df), F Critical (F crit), F Statistics (F), p, and Mean Square (MS) value. Analytical results revealed the efficiency of proposed system over conventional methods and thereby confirming its efficiency for predicting heart disease.
Kalaivani K., Uma Maheswari N., and Venkatesh R.
Bentham Science Publishers Ltd.
Background: Cardiovascular Disease (CVD) is one of the primary diseases that causes death every year. An approximation of roughly about 17.5 million people dies due to CVD, signifying about 31% of global deaths. Based on the statistics, every 34 seconds, a person dies due to heart disease. Various classification algorithms have been developed and utilized as classifiers to support doctors who are ineffectually diagnosed with heart disease. Aims: The main aim of this work is to improve the performance of the heart disease approach using image processing algorithm. To improve the effectiveness and efficiency of classification performance for heart disease diagnosis, an optimized neural network was proposed based on the feature extraction and selection approach for handling features. Objective: The objective of this investigation is to diagnose heart diseases using feature extraction, reduction based classification and image processing methods. The proposed model comprises of two subsets: Feature extraction using gray scale properties and Moth flame optimization (MFO) for effectual feature selection, followed by a classification technique using Generalized Regression Neural Network. The first system includes three stages: (i) Pre-processing of the dataset (ii) feature extraction (iii) performing MFO for efficient selection. In the second method, GRNN is proposed. The heart data set obtained from ACDC Challenge, was utilized for performing the computation. Methods: The image obtained from the MRI-scanner is in the NIfTI image format. The pre-process step used in this is to convert the image type from INT16 to uint8 to improve the quality of image viewing and for feature extraction process. In this phase, the texture properties from the pre-processed image are calculated and the value is in the numeric format. These values are the feature attributes of the dataset. The feature attributes of the image are given as input for the moth flame optimization process and output is the feature selected from the optimization process. The whole process is performed on the feature attributes of the image by determining the optimal feature for the classifier by reducing its error rate. The optimal feature from the moth flame optimization is used for training and testing the network. The classifier used in this approach is a single neural network classifier with a regression nature. Due to the regression property, the network is well trained with the feature. The Generalized regression neural network is used for classifying heart diseases. Results: The proposed method achieves the accuracy of 96.23%, sensitivity of 95.41% and specificity of 96.75%. These values are calculated based on the confusion matrix of the classifier. Conclusion: In this, the feature extraction using the gray scale properties plays an important role to determine the feature attributes from the MRI heart images. The Moth flame optimization able to produce an accuracy of 97.23% using GRNN for classification with minimum single attribute mean of the image. It also outperformed the other methods, either the feature extraction based classification or the feature reduction based classification.
K. Kalaivani and M. Chinnadurai
Computers, Materials and Continua (Tech Science Press)
K Kalaivani and N Uma Maheswari
IEEE
Big Data is owing to the fact that we are creating a massive amount of data every day. Big data is a huge quantity of data that includes all sorts of concept like social media analytics, next-generation data-management capabilities, real-time data, and much more. It contains structured and unstructured data. Dealing with a large volume of data in extracting useful information or knowledge from those big data is infeasible. In many situations, the knowledge for extraction process has to be very well-organized and close to real time since storing all pragmatic data is almost infeasible. The unprecedented data volumes require an effective data analysis and prediction platform to achieve fast response and realtime classification for such Big Data. To explore Big Data, we have analyzed several challenges at the data, model, and system levels. As Big Data are often stored at different locations, the data volumes may continuously grow. So an effective computing platform will have to take distributed large-scale data storage into consideration for computing. The key characteristics of the Big Data are huge with heterogeneous and diverse data sources also autonomous with distributed, decentralized control and complex to evolve in data and knowledge associations. Big Data occupies the medical area in a wide manner. Especially during the period of pregnancy, the blood sugar for women goes up. Gestational diabetes occurs even women who have not had diabetes need treatment for diabetes during the pregnancy. This should be treated with a more frequent checkup. If these are not carried out in a proper manner, then it may lead to a serious problem for both mother and baby. Here we discuss the big data, big data in medicine and the proposed solution lead to maintain the blood-glucose level for pregnancy women by frequent checkup and intimate to their relatives or friends regarding the variations in the blood-glucose level through the Internet connectivity.
K. Kalaivani and C. Suguna
IEEE
Botnet is a number of computers connected through internet that can send malicious content such as spam and virus to other computers without the knowledge of the owners. In peer-to-peer (p2p) architecture, it is very difficult to identify the botnets because it does not have any centralized control. In this paper, we are going to use a security principle called data provenance integrity. It can verify the origin of the data. For this, the certificate of the peers can be exchanged. A reputation based trust model is used for identifying the authenticated peer during file transmission. Here the reputation value of each peer can be calculated and a hash table is used for efficient file searching. The proposed system can also verify the trustworthiness of transmitted data by using content auditing. In this, the data can be checked against trained data set and can identify the malicious content.
D. Dhivyalakshmi, K. Kalaivani, V. Tamilarasi, and P. Bhavani
IEEE
In our proposed model we implement Rate Auditing Tool (RAT) to monitor each and every rating manipulation. It checks whether the time logged in and logged out matches the stipulated time for viewing any videos or messages and giving appropriate rating. It monitors either the video provided is fully or atleast partly viewed thus accordingly their ratings given. It also checks whether the login in network which is providing rating is either from same location or its location varies each and every time from vast geographical location. It also checks whether from same ip address multiple logins giving ratings continuously. Thus by doing this the attacker is also detected and given counter measure to their attacks.
K. Kalaivani and A. P. V. Raghavendra
IEEE
Clustering is an attractive and important task in data mining which is used in many applications. However earlier work on clustering focused on only categorical data which is based on attribute values for grouping similar kind of data items thus will leads to convergence problem of clustering process. This proposed work is to enhance the existing k-means clustering process based on the categorical and mixed data types in efficient manner. The goal is to use integrated clustering approach based on high dimensional categorical data that works well for data with mixed continuous and categorical features. The experimental results of the proposed method on several data sets are suggest that the link based cluster ensemble algorithm integrate with proposed k-means algorithm to produce accurate clustering results. In this proposed algorithm prove the convergence property of clustering process, thus will improve the accuracy of clustering results. The scope of this proposed work is used to provide the accurate and efficient results, whenever the user wants to access the data from the database.
K. Kalaivani and A. P. V. Raghavendra
IEEE
Clustering is a useful and efficient task in data mining which is used in database related applications. Existing work on clustering focused on only categorical data which is based on attribute values for grouping similar kind of data. This paper is based on clustering the continuous and categorical data set in efficient manner. The goal is to use integrated clustering approach based on high dimensional categorical data that works well for data with mixed continuous and categorical features. The exprimental results of the proposed method on several data sets suggests that the link based cluster ensemble algorithm when integrate with k-means algorithm to produce final results. The scope of this proposed work is used to provide the accurate and efficient results, whenever the user wants to access the data from the database.