Pramoda Patro
@avcoe.org
Assistant Professor, Engineering Sciences
Amrutvahini College of Engineering, Sangamner, Ahmednagar, Maharashtra, India
EDUCATION
M.Sc, M.Tech(CS), P.hD(Math)
RESEARCH INTERESTS
Fuzzy Neural Network, Machine Learning, Fuzzy systems, Artificial Neural Network
Scopus Publications
Scopus Publications
Srinivas Kolli, Muniyandy Elangovan, M Vamsikrishna, and Pramoda Patro
European Alliance for Innovation n.o.
INTRODUCTION: Although decades of experimental and clinical research have shed a lot of light on the pathogenesis of Alzheimer's disease (AD), there are still a lot of questions that need to be answered. The current proliferation of open data-sharing initiatives that collect clinical, routine, and biological data from individuals with Alzheimer's disease presents a potentially boundless wealth of information about a condition.
 METHODS: While it is possible to hypothesize that there is no comprehensive collection of puzzle pieces, there is currently a proliferation of such initiatives. This abundance of data surpasses the cognitive capacity of humans to comprehend and interpret fully. In addition, the psychophysiology mechanisms underlying the whole biological continuum of AD may be investigated by combining Big Data collected from multi-omics studies. In this regard, Artificial Intelligence (AI) offers a robust toolbox for evaluating large, complex data sets, which might be used to gain a deeper understanding of AD. This review looks at the recent findings in the field of AD research and the possible obstacles that AI may face in the future.
 RESULTS: This research explores the use of CAD tools for diagnosing AD and the potential use of AI in healthcare settings. In particular, investigate the feasibility of using AI to stratify patients according to their risk of developing AD and to forecast which of these patients would benefit most from receiving personalized therapies.
 CONCLUSION: To improve these, fuzzy membership functions and rule bases, fuzzy models are trained using fuzzy logic and machine learning.
Debabrata Swain, Sachin Lakum, Samrat Patel, Pramoda Patro, and Jatin
European Alliance for Innovation n.o.
Farming is considered the biggest factor in strengthening the economy of any country. It also has significant effects on GDP growth. However, due to a lack of information and consultation, farmers suffer from significant crop losses every year. Typically, farmers consult agricultural officers for detecting crop diseases. However, the accuracy of predictions made by agricultural officers based on their experience is not always reliable. If the exact issues are not identified at right time then it results in a heavy crop loss. To address this issue, Computational Intelligence, also known as Machine Learning, can be applied based on historical data. In this study, an intelligent crop yield prediction algorithm is developed using various types of regression-based algorithms. The Crop Yield Prediction Dataset from the Kaggle repository is used for model training and evaluation. Among all different regression methods Random Forest has shown the better performance in terms of R2 score and other errors.
Aditya Kumar Sahu, Monalisa Sahu, Pramoda Patro, Gupteswar Sahu, and Soumya Ranjan Nayak
Springer Science and Business Media LLC
R. Hari Kishore, A. Chandra Sekhar, Pramoda Patro, and Debabrata Swain
IEEE
Cloud computing contains lots of processing power and storage. Cloud computing and machine learning (ML) techniques enable large-scale data processing. The enhanced ML-based categorization technique is established in the cloud. However, there is a risk of privacy leaking of training data in the data processing. The computational and communication costs of the information possessor(s) must be maintained to a minimum. This study suggests a multi-key enhanced support vector machine (MK-FHE) and multi-key fully homomorphic encryption (MK-FHE) supervised machine learning method for encrypted data (ESVM).The results suggest that MK-FHE protects data privacy and is more effective in processing.
Thangarasan, Dhana Sony J, Premkumar M, Pramoda Patro, Samson Isaac J, and Maniraj P
IEEE
For the detection and prognosis of heart disease, Internet of Medical Things (IoMT) technology has recently been implemented in healthcare systems. The intended study's main objective is to foresee heart illness using medical data and imaging to classify data. Preprocessing is done on the input dataset to deal with missing values and incorrect data. IoT devices analyse the data they receive from patients, physicians, or nurses using the Modified Imperialist Competitive Algorithm (MICA). The IoT device's analysis of the data allows for effective and informed judgements to be made by humans, robots, and even other IoT devices. A modified imperialist competitive algorithm is suggested in this research in order to pinpoint the essential characteristics of heart disease. The Modified Imperialist Competitive Algorithm is used to select features for the diagnosis of heart disease (MICA). The improved self-adaptive Bayesian algorithm (ISABA) technique is then used to classify the chosen features into normal and abnormal states. For detecting normal sensor data and abnormal sensor data, respectively, the ISABA approach achieved accuracy of 96.85% and 98.31%. With a 96.32% specificity and a 99.15% maximum accuracy in categorizing images, the proposed model outperformed the competition
Kolli Srinivas, J Aswini., Pramoda Patro, and Devendra Kumar
IEEE
4 G/LTE mobile networks resolved this issue. Strong physical layer and adaptable network design enable high-capacity mobile broadband Internet. Despite this, the prevalence of bandwidth-intensive technologies like virtual reality, augmented reality, and others has grown. In addition, the rising popularity of new services places astrain on mobile infrastructure. Applications requiring high availability and low latency, such Internet-of-Vehicles or communications between vehicles (IoV). With the advent of the new 5G technology with its massive MIMO radio interface, these problems are no longer a concern. Networks protected by software-defined networking (SDN)and NFV have added a new level of flexibility that allows network operators to serve services with very high requirements across several industries. Network operators must increase and diversify their intelligence to fully comprehend the operational environment, user behaviours, and user demands. A further goal is to become(self-) networkable proactively and effectively. This chapter will look at how AI may help us in the modern world. Next-generation mobile networks that are both efficient and adaptable may benefit greatly from machine learning in the 5G era and beyond. The evolution of AI and ML in network applications.
Pramoda Patro, Krishna Kumar, G. Suresh Kumar, and Gandharba Swain
Elsevier BV
Abstract Function approximation is an important task in many different fields like economics, engineering, computing, classification, and forecasting. From a finite data set, the basic task of a function approximation method is to find a suitable relationship between variables and their corresponding responses. In the recent past, the improved neural networks including intuitive, interpretable correlated-contours fuzzy rules for classification tasks were proposed. However, the acquired data set can contain large volume of data and noise that degrades the classification ability of the model and increases the computational time. Thus, it is important to consider this problem which was not focused on recent existing works. Furthermore, there are also some neuron regularization issues in the second layer. To solve this issue in this proposed system Bat optimization based feature selection is proposed for optimal selection of features from the available dataset. Then classification is done by using enhanced neural network including intuitive and interpretable correlated-contours fuzzy rules (EC-FR). According to fuzzy rules extraction, an appropriate framework is built-in which similarity-based directional component of data partitioning and also a model to form cloud data is presented. Neurons weight and bias values are computed by adapting wavelet functions. Finally, parameters of the fuzzy neural networks are fine-tuned using the hybrid ant colony particle swarm optimization (HASO). Performance is evaluated primarily in accordance with the subsequent metrics like precision, recall, accuracy, and error rate.
Pramoda Patro, R. Azhagumurugan, R Sathya, Krishna Kumar, T. Rajasanthosh Kumar, and M. Vijaya Sekhar Babu
IEEE
For Remaining useful life (RUL) prediction, this article presents a paradigm that separates the whole bearing life into many health states and then builds unique local regression models for each of those states, rather than searching for an overall regression model with multiple health state assessments. A method that utilised both unsupervised learnings and supervised learning to estimate a bearing’s real-time health status is presented without previous information. The primary technology used to perform health status assessment and RUL prediction is the support vector machine. The efficacy of the suggested framework has been shown via experiments, including accelerated deterioration testing on rolling element bearings.
Anu Yadav, Piyush Kumar Yadav, Srilatha Toomula, Sushma Jaiswal, and Pramoda Patro
IEEE
Maladies to plants have a major impact on both productivity and the economy. To improve agricultural outputs, early identification and treatment of plant diseases are essential. Image analysis is used to detect and categorise a variety of bacterial and fungal capsicum diseases. Using the k-means clustering method, the contaminated region of the capsicum is located, and subsequently, the texture, i.e., GLCM characteristics, are eliminated. Various bacterial and fungal capsicum infections may be characterised by these characteristics (SVM). The KNN and SVM classifiers outperform the tree and linear discriminant classifiers in our application. The technique effectiveness was verified on 62 imageries of healthy and contaminated capsicum and leaf specimens.
Premanand Ghadekar, Shaunak Joshi, Debabrata Swain, Biswaranjan Acharya, Manas Ranjan Pradhan, and Pramoda Patro
Science Publications
Pramoda Patro
Institute of Advanced Scientific Research