Browsing by Author "Sathishkumar, V. E."

Now showing 1 - 5 of 5

A Distributed Framework for Predictive Analytics Using Big Data and MapReduce Parallel Programming
(HINDAWI, 2023-02-01) Natesan, P.; Sathishkumar, V. E.; Mathivanan, Sandeep Kumar; Jayagopal, Prabhu; Allayear, Shaikh Muhammad
With the advancement of Internet technologies and the rapid increase of World Wide Web applications, there has been tremendous growth in the volume of digital data. This takes the digital world into a new era of big data. Various existing data processing technologies are not consistent and scalable in handling the complexity as well as the large-size datasets. Recently, there are many distributed data processing, and programming models have been proposed and implemented to handle big data applications. The open-source-implemented MapReduce programming model in Apache Hadoop is the foremost model for data exhaustive and also computational-intensive applications due to its inherent characteristics of scalability, fault tolerance, and simplicity. In this research article, a new approach for the prediction of target labels in big data applications is developed using a multiple linear regression algorithm and MapReduce programming model, named as MR-MLR. This approach promises optimum values for MAE, RMSE, and determination coefficient (R2) and thus shows its effectiveness in predictions in big data applications.
Diagnosis of Retinal Diseases Based on Bayesian Optimization Deep Learning Network Using Optical Coherence Tomography Images
(Daffodil International University, 2022-04-15) Subramanian, Malliga; Kumar, M. Sandeep; Sathishkumar, V. E.; Prabhu, Jayagopal; Karthick, Alagar; Ganesh, S. Sankar; Meem, Mahseena Akter
Retinal abnormalities have emerged as a serious public health concern in recent years and can manifest gradually and without warning. These diseases can affect any part of the retina, causing vision impairment and indeed blindness in extreme cases. This necessitates the development of automated approaches to detect retinal diseases more precisely and, preferably, earlier. In this paper, we examine transfer learning of pretrained convolutional neural network (CNN) and then transfer it to detect retinal problems from Optical Coherence Tomography (OCT) images. In this study, pretrained CNN models, namely, VGG16, DenseNet201, InceptionV3, and Xception, are used to classify seven different retinal diseases from a dataset of images with and without retinal diseases. In addition, to choose optimum values for hyperparameters, Bayesian optimization is applied, and image augmentation is used to increase the generalization capabilities of the developed models. This research also provides a comparison of the proposed models as well as an analysis of them. The accuracy achieved using DenseNet201 on the Retinal OCT Image dataset is more than 99% and offers a good level of accuracy in classifying retinal diseases compared to other approaches, which only detect a small number of retinal diseases.
Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning
(Daffodil International University, 2022-07-21) Subedi, Bharat; Sathishkumar, V. E.; Maheshwari, V.; Kumar, M. Sandeep; Jayagopal, Prabhu; Allayear, Shaikh Muhammad
As training deep neural networks enough requires a large amount of data, there have been a lot of studies to deal with this problem. Data augmentation techniques are basic solutions to increase training data using existing data. Geometric transformations and color space augmentations are well-known augmentation techniques, but they still require some manual work and can generate limited types of data only. Therefore, there are many interests in generative-model-based augmentation lately, which can learn the distribution of data. This study proposes a set of GAN-based data augmentation methods that can generate good quality training data. The proposed networks, f-DAGAN (data augmentation generative adversarial networks), have been motivated by the DAGAN that learns data distribution from two real data. The basic f-DAGAN uses dual discriminators handling both generated data and generated feature spaces for better learning the given data. The other versions of f-DAGANs have been proposed for generating hard or easy data that have additional dual classifiers for both generated data and feature spaces to control the generator. Hard data is useful for optimized training to increase the target performance such as classification accuracy. Easy data generation can be used especially in few-shot learning. The quality of generated data has been validated in two ways: using t-SNE visualization of generated data and classification accuracy by training with generated data using the MNIST data set. The t-SNE representations show that data generated by f-DAGAN are evenly distributed for every class better than the exiting generative model-based augmentation methods. The f-DAGAN also shows the best classification accuracy by training with generated data. The f-DAGAN version for easy and hard data generation generates data well from five-shot learning and performs well in sample data generation experiments.
Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images
(Daffodil International University, 2022-09-12) Shanmugavadivel, Kogilavani; Sathishkumar, V. E.; Kumar, M. Sandeep; Maheshwari, V.; Prabhu, J.; Allayear, Shaikh Muhammad
The level of patient’s illness is determined by diagnosing the problem through different methods like physically examining patients, lab test data, and history of patient and by experience. To treat the patient, proper diagnosis is very much important. Arrhythmias are irregular variations in normal heart rhythm, and detecting them manually takes a long time and relies on clinical skill. Currently machine learning and deep learning models are used to automate the diagnosis by capturing unseen patterns from datasets. This research work concentrates on data expansion using augmentation technique which increases the dataset size by generating different images. The proposed system develops a medical diagnosis system which can be used to classify arrhythmia into different categories. Initially, machine learning techniques like Support Vector Machine (SVM), Naïve Bayes (NB), and Logistic Regression (LR) are used for diagnosis. In general deep learning models are used to extract high level features and to provide improved performance over machine learning algorithms. In order to achieve this, the proposed system utilizes a deep learning algorithm known as Convolutional Neural Network-baseline model for arrhythmia detection. The proposed system also adopts a novel hyperparameter tuned CNN model to acquire optimal combination of parameters that minimizes loss function and produces better result. The result shows that the hyper-tuned model outperforms other machine learning models and CNN baseline model for accurate classification of normal and other five different arrhythmia types.
IoT-Based Intelligent System for Internal Crack Detection in Building Blocks
(Daffodil International University, 2022-06-13) Babu, J. Chinna; Kumar, M. Sandeep; Jayagopal, Prabhu; Sathishkumar, V. E.; Rajendran, Sukumar; Kumar, Sanjeev; Karthick, Alagar; Mahseena, Akter Meem
Cracks that are detected in concrete structures represent significant damage, and they can lead to a detrimental effect on the structure’s durability. Their identification in a timely manner can help ensure structural safety and guide in-depth maintenance operation. Automatic detection of such cracks has been proposed using internal crack detection utilizing ultrasonic sensors in concrete. Cracks within the concrete can be detected using ultrasonic sensors. In this investigation, we introduced an intelligent method that is aimed at developing a crack detection scheme using ultrasonic sensors. These ultrasonic sensors are used for the detection of cracks in buildings which cannot be seen with our naked eyes; they are capable of alerting authorities via SMS message and providing the cracks’ location via GSM and GPS modules. To monitor internal cracks in the concrete cubes and cylinders, the ultrasonic sensors can be fixed at the centre of the cube which will be used for interval crack monitoring based on crack detection technology. The grade of concrete used for testing is M25, and it is well mixed with the ingredients of cement, fine aggregate, coarse aggregate, and water. The concrete is placed in the cube moulds having the dimensions . The cylinders used in the case of the experimental analysis are of the dimensions of 150 mm diameter and 300 mm height. These specimens are cast and kept in the curing tank for 28 days to attain the maximum strength. After completion of the curing period, the specimens were taken out from the tank and weighed. After this weighing process, the cubes and cylinders are about 8.884 kg and 13.399 kg, respectively. The information about the cracks can be displayed on the LCD, and also, the transmitted short message about the cracks can be exchanged between the devices using IoT.