scispace - formally typeset
Search or ask a question
Author

Arivuselvan K

Bio: Arivuselvan K is an academic researcher from VIT University. The author has contributed to research in topics: Wireless network & Deep learning. The author has an hindex of 2, co-authored 9 publications receiving 7 citations.

Papers
More filters
Journal ArticleDOI
28 Oct 2020
TL;DR: Deep Neural Network (DNN) classifier, an unsupervised learning approach is used for accurate prediction on Pima Indian Diabetes dataset and Feature Importance model that is bagged with Extra Trees and Random Forest is usedfor feature selection.
Abstract: Highlights •The frameworks evolved for support to medical experiments and algorithms for accurate prediction.•An unsupervised learning approach used for accurate prediction of the dataset of pima indian diabetes.•Early identification of diabetes is vital to lead to sound health and life.•The model achieved 98.16% accuracy and it was better than other state-of-art methods.Diabetes is a severe disease, most of the people are not aware of the risk associated with the disease because of that people die due to diabetic nephropathy, cardiac stroke and some other disorders. Therefore, early identification of diabetes helps to maintain sound health and life. Deep Learning approaches are used to predict diabetes accurately as humans do. In this paper, Deep Neural Network (DNN) classifier, an unsupervised learning approach is used for accurate prediction on Pima Indian Diabetes dataset and Feature Importance model that is bagged with Extra Trees and Random Forest is used for feature selection. The Pima Indian Diabetes dataset (PID) was acquired from the repository of UCI. The existing dataset has experimented with different formats of train test splits. The performance of the model was evaluated through accuracy, specificity, sensitivity, recall and precision. The model acheived 98.16% accuracy with random train-test split and it is observed that, the model obtained better performance than other state-of-art methods.

29 citations

Journal ArticleDOI
TL;DR: A novel and competent image pre-processing techniques are applied to enhance the visual quality of MRI image by using various segmentation algorithms to accurately extract entire thalamus from brain MRI images.
Abstract: In this paper, we presented precise and proficient techniques for measuring the human thalamus, medial dorsal and the pulvinar nucleus with magnetic resonance imaging (MRI). In spite of the fact that thalamic nuclei are not straightforwardly visible on traditional MRI image. We applied a novel and competent image pre-processing techniques to enhance the visual quality of MRI image. In addition to this we have used various segmentation algorithms to accurately extract entire thalamus from brain MRI images. Diffusion MRI is used to extract various nucleus of thalamus. Several optimal features such as textures, morphological are derived from thalamus and medial dorsal regions which are then used to train the artificial neural network model (ANN). Our artificial neural network model accurately classifies between schizophrenic and healthy subjects based on thalamic anatomy for larger sample sizes.

2 citations

Proceedings ArticleDOI
01 Feb 2019
TL;DR: A hybrid approach for watermarking is proposed and tested which incorporates FT (Framelet Transform), PCA (Principal Component Analysis and SVD (Singular Value Decomposition) and the model is robustness against water marking attacks, imperceptibility, capacity and security.
Abstract: Digital data is being created every day and spread across the internet. Since the data is on the internet, it can be accessed and misused by anyone who has access to the internet. Even with encryption technique, when distributed it can be easily decrypted and modified to the persons needs. The problem can be addressed by embedding the information into image, audio, and video using digital watermarking technique. The embedded information can be later retrieved and used for identification and authentication purposes. The challenging task in watermarking is illegal distribution and handling of digital video is turning out. It can be solved by embedding copyright information into bit streams of any video. In recent research, image watermarking technique in which digital images can be embedded with a code. It is done is such a way to ensure non-erasability of the image watermarking. While it ensures non-erasability, it does introduce Gaussian noise during the process of watermarking, the contrast and brightness of the hidden image will be affected due to the watermarking of information and also the entire image consumes a lot of memory after the entire watermarking procedure is done. In this paper, a hybrid approach for watermarking is proposed and tested which incorporates FT (Framelet Transform), PCA (Principal Component Analysis) and SVD (Singular Value Decomposition). The model is robustness against watermarking attacks, imperceptibility, capacity and security.

1 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: It is evident from the obtained results that the proposed model has exhibited an acceptable performance in precisely sensing the individuals with abnormal glucose levels and the cross-validation of the model at multiple folds is being evaluated to analyze the performance.
Abstract: The adequate aging hypothesis seeks to help people live longer, healthy lives. Diabetic patients who stay remotely need an infrastructure to monitor them continuously and provide timely treatment. Ambient assisted living (AAL) encourages the establishment of solutions that may help optimize older people’s assistive environment while also reducing their impairments. The blood glucose levels of diabetic patients are continuously monitored by gold oxide sensors placed over the human body. The signals associated with the glucose levels in the human body are plotted over a spectrogram image using the short-time Fourier transform, which is further classified using the deep learning model based on finetuned AlexNet, which has employed random oversampling and batch normalization for better precision in the results. The model classifies the spectrogram images as low and high glucose levels and normal glucose levels. Thereby alarming the caretakers for effective treatment of the individuals. Body area networks (BANs) gather information from biosensors and send it to a domain controller to assist caretakers and physicians in recommending the physical exercises for their clients. Evaluation criteria such as sensitivity and specificity, precision, and Mathew’s correlation coefficient are used to assess the effectiveness of the proposed model in this current diabetes study. The cross-validation of the model at multiple folds is being evaluated to analyze the performance. It is evident from the obtained results that the proposed model has exhibited an acceptable performance in precisely sensing the individuals with abnormal glucose levels.

39 citations

Journal ArticleDOI
TL;DR: A priority-based model using SDN to control the flow of data packets over the network, gives assurance to the bandwidth enforcement, and reallocation is made through virtual circuits to overcome the gap open at the security of the SDN architecture to detect and identify vulnerabilities.

37 citations

Journal ArticleDOI
TL;DR: This work proposes a machine learning-based healthcare model for accurate and early detection of diabetics and shows few relevant features are needed to enhance the accuracy of the developed model.
Abstract: Diabetes is a chronic hyperglycemic disorder. Every year hundreds of millions of people around the world have diabetes. The presence of irrelevant features and an imbalanced dataset are significant issues to train the model. The availability of patient medical records quantifies symptoms, body characteristics, and clinical laboratory test values that can be used in the study of biostatistics aimed at identifying patterns or characteristics that cannot be detected by current practice. This work proposes a machine learning-based healthcare model for accurate and early detection of diabetics. Five machine learning classifiers such as logistic regression, K-nearest neighbor, Naive Bayes, random forest, and support vector machine are used. Fast correlation-based filter feature selection is used to remove the irrelevant features. The synthetic minority over-sampling technique is used to balance the imbalanced dataset. The model is evaluated with four performance measuring matrices: accuracy, sensitivity, specificity, and area under the curve (AUC). An experimental outcome shows few relevant features are needed to enhance the accuracy of the developed model. The RF classifier achieves the highest accuracy, sensitivity, specificity, and AUC of 97.81%, 99.32%, 98.86%, and 99.35%.

29 citations

Journal ArticleDOI
TL;DR: In this article , a review of machine learning-based approaches for the prevention and management of type 2 diabetes is presented, highlighting the shortcomings or gaps in the existing ML methodologies for diabetes to be addressed in future.
Abstract: Type 2 diabetes has recently acquired the status of an epidemic silent killer, though it is non-communicable. There are two main reasons behind this perception of the disease. First, a gradual but exponential growth in the disease prevalence has been witnessed irrespective of age groups, geography or gender. Second, the disease dynamics are very complex in terms of multifactorial risks involved, initial asymptomatic period, different short-term and long-term complications posing serious health threat and related co-morbidities. Majority of its risk factors are lifestyle habits like physical inactivity, lack of exercise, high body mass index (BMI), poor diet, smoking except some inevitable ones like family history of diabetes, ethnic predisposition, ageing etc. Nowadays, machine learning (ML) is increasingly being applied for alleviation of diabetes health burden and many research works have been proposed in the literature to offer clinical decision support in different application areas as well. In this paper, we present a review of such efforts for the prevention and management of type 2 diabetes. Firstly, we present the medical gaps in diabetes knowledge base, guidelines and medical practice identified from relevant articles and highlight those that can be addressed by ML. Further, we review the ML research works in three different application areas namely-(1) risk assessment (statistical risk scores and ML-based risk models), (2) diagnosis (using non-invasive and invasive features), (3) prognosis (from normoglycemia/prior morbidity to incident diabetes and prognosis of incident diabetes to related complications). We discuss and summarize the shortcomings or gaps in the existing ML methodologies for diabetes to be addressed in future. This review provides the breadth of ML predictive modeling applications for diabetes while highlighting the medical and technological gaps as well as various aspects involved in ML-based diabetes clinical decision support.

13 citations

Journal ArticleDOI
TL;DR: A fuzzy-based manoeuvring model labeled as Fuzzy-based Midvehicle Collision Avoidance System (FMCAS) resolving two road crash scenarios and the appropriate constraint paths estimated using the developed fuzzy- based polynomial fitting addresses the diverse vehicle kinematic issues.
Abstract: This paper offers a fuzzy-based manoeuvring model labeled as Fuzzy-based Midvehicle Collision Avoidance System (FMCAS) resolving two road crash scenarios. The first scenario covers dual situations (a) Mid vehicle collision avoidance with the rear vehicle under no front vehicle condition and (b) Curvilinear path strategy based on real road conditions. While the suitable curvilinear motion to fit the constrained path for parallel parking is the other scenario. Curvilinear fitting strategy on the left and right sides is achieved by the mid (host) vehicle using fuzzy interpolation techniques modeled by FMCAS. Also, the offset-based curvilinear path determined by FMCAS automatically fits the constraint path to avoid vehicle crashes in highly occupied lanes. In this methodology, path constraint is applicable for both scenarios in forward and reverse directions. The appropriate constraint paths estimated using the developed fuzzy-based polynomial fitting addresses the diverse vehicle kinematic issues. Mean square error values of $$3.9443 \times {10}^{-28}$$ m and 0.0148–0.7210 m about the proposed fuzzy respect to crisp and FMCAS are also capable of delivering diverse consequents in highly intact road scenarios. The fuzzy rule base is motivated in this research article to obtain a collision-free environment addressing many collision conditions in the real-time scenario.

9 citations