Qualification: 
Ph.D, MPhil, MSc, B.Ed.
mayal@asas.kh.amrita.edu

Maya L. Pai currently serves as Assistant Professor (Sr.Gr.) in the Departments of Computer Science and IT and Mathematics, School of Arts & Sciences, Amrita Vishwa Vidyapeetham, Kochi. 

Qualification: Ph. D. (Applied Mathematics), M. Sc. (Mathematics), B. Ed. (Mathematics), M. Phil. (Mathematics), SET.

Publications

Publication Type: Journal Article

Year of Publication Title

2019

Aswathi Anand P. and Maya L. Pai, “Artificial Neural Network Model for Identifying Early Readmission of Diabetic Patients”, OPUS: International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 6, 2019.[Abstract]


Early re-admission of patients increases the cost of health care and it highly influences the reputation of the hospital. Finding readmission in primary stage, allows the hospitals to give special care for those patients, and then can reduce the rate of readmission. In this work develop a new model using deep learning. It is the comparison method between machine learning and deep learning. Usually Logistic regression is use for all kind of prediction. But according to this data artificial neural network model in deep learning give promising result than logistic regression.

More »»

2019

M. .S.Suchithra and Maya L. Pai, “Improving the Prediction Accuracy of Soil Nutrient Classification by Optimizing Extreme Learning Machine Parameters”, Information Processing in Agriculture , 2019.[Abstract]


The soil, Soul of Infinite Life, is the entity responsible for sustaining life on earth. In spite of significant advances in the service sector, agriculture remains the major provider of employment and source of revenue in India. Soil testing is a valuable tool for evaluating the available nutrient status of soil and helps to determine the proper amount of nutrients to be added to a given soil based on its fertility and crop needs. In the current study, the soil test report values are used to classify several significant soil features like village wise soil fertility indices of Available Phosphorus (P), Available Potassium (K), Organic Carbon (OC) and Boron (B), as well as the parameter Soil Reaction (pH). The classification and prediction of the village wise soil parameters aids in reducing wasteful expenditure on fertilizer inputs, increase profitability, save the time of chemical soil analysis experts, improves soil health and environmental quality. These five classification problems are solved using the fast learning classification technique known as Extreme Learning Machine (ELM) with different activation functions like gaussian radial basis, sine-squared, hyperbolic tangent, triangular basis, and hard limit. After the performance analysis of ELMs with diverse activation functions for these soil parameter classifications, the gaussian radial basis function attains the maximum performance for four out of five problems, which goes above 80% in most of the accuracy rate calculations in every problem, followed by hyperbolic tangent, hard limit, triangular basis, and sine-squared. However, the performance of the final classification problem, i.e. the pH classification, gives moderate values with the gaussian radial basis and best performance (near 90%), with the hyperbolic tangent.

More »»

2018

C. Karthika, P. P. Vijayalakshmi, and Maya L. Pai, “The Reach of Television: Viewing Habits and Patterns in Kerala ”, International Journal of Pure and Applied Mathematics , vol. 118, pp. 1319-1332 , 2018.[Abstract]


Today, television has emerged as the major source of entertainment and learning in our country. All kinds of television programs, especially the serials, film clipping, news and news based programmes, sports and cartoons, affect people irrespective of gender, age and other demographic variables. The study was conducted to throw light towards various television viewing habits among the Malayali audience. . A Sample of 1000 respondents from four districts of Kerala were selected for analysis. Structured Questionnaires were distributed to them and the responses were collected. Chi- square test is used to analyze the collected data. The study also highlighted the TV program preferences among the viewers.

More »»

2018

M. S. Suchithra and Maya L. Pai, “Impact of Deep Neural Network on Predicting Application Rate of Fertilizers (Focus on Coconut Trees of Kerala Northern Coastal Plain Agro Ecological Unit)”, International Journal of Pure and Applied Mathematics, vol. 119, pp. 451-466, 2018.[Abstract]


The principle aim of fertilization is to provide the nutrients in the soil to satisfy the requirements of plants. The identification and application of chemical fertilizers that add to the nutrients in the soil, help the agronomist in decision-making regarding crop yield. Different statistical or computational techniques are used for predicting fertilizers. Artificial Intelligence (AI) methods offer a more impressive way of predicting fertilizers under various cropping patterns. Artificial Neural Network (ANN) models can easily interpret complex input structure. This study describes the development of fertilizer’s application rate prediction model for Coconut Tree with the help of ANNs. The prediction model is developed with the soft technique of ANNs through the use of back propagation algorithm and multilayer neural network model. Today's farmers depend on advanced technology to reduce their overall labor and to increase production. In this study, the promising methodology in AI called deep learning is used to predict the application rate of fertilizers for Coconut Tree. The Deep Neural Network (DNN) achieved better accuracy as compared with standard ANN. These two methods are compared in the terms of their performance. The predicted accuracy rate for fertilizers Urea, MOP and Lime using Standard Neural Network Classifier is 85.95%, 81% and 93.39 % respectively. But the same measurement using DNN is 95.1%, 95.05% and 96.7% respectively which shows that DNN performs better than other neural network models in the agricultural system with large data.

More »»

2018

K. S. Varsha and Maya L. Pai, “Rainfall Prediction Using Fuzzy C-Mean Clustering And Fuzzy Rule-Based Classification”, International Journal of Pure and Applied Mathematics , vol. 119, pp. 597-605, 2018.[Abstract]


Rainfall becomes an important aspect in agricultural countries like India. Rainfall prognostication has become one of the most accurately and theoretically demanding issues in the world. The aim of this study is to prognosticate Kerala Monsoon rainfall with an optimized set of parameters like Sea Level Pressure (SLP), Sea Surface Temperature (SST), humidity, zonal (u), and meridional (v) winds. With the aforesaid parameters given as input to a Fuzzy Rule-based classification (FRBCS), the FRBCS classification algorithm is used for training a period of 35 years (1962-1997) summer monsoon rainfall data and validated and tested with another 15 years of (1998-2012) data using the same.

More »»

2018

S. M. S. and Maya L. Pai, “Improving the Performance of Sigmoid Kernels in Multiclass SVM Using Optimization Techniques for Agricultural Fertilizer Recommendation System”, International Conference on Soft Computing Systems. Springer, vol. 837, 2018.[Abstract]


Support Vector Machines (SVM) are advancing rapidly in the field of machine learning due to their enhancing performance in categorization and prediction. But it is also known that the performance of SVM can be affected by different kernel tricks and regularization parameters like Cost and Gamma. The polynomial kernel seems to be more suitable for performing multiclass SVM classification for the dataset used here. In this study, we propose an improved sigmoid kernel SVM classifier by adjusting the cost and gamma parameters with which a better performance can be achieved. The study is conducted for a multiclass soil fertilizer recommendation system for paddy fields. Furthermore, different optimization methods like Genetic Algorithm and Particle Swarm Optimization are used to tune the SVM parameters. Finally, a comparative study on the performance is also done for the different choices of the parameters, pointing out their accuracies.

More »»

2018

V. Reshma, Anand, S., and Maya L. Pai, “A Twitter Based Sentimental Approch On India’s Largest 4G Network “JIO””, Journal of Engineering and Applied Sciences, vol. 13, no. 5, pp. 4600-4603, 2018.[Abstract]


Sentimental analysis states the use of Natural Language Processing (NLP). It is used to track the emotions or sentiments of the people based on a particular product or topic. The micro blogging websites like Facebook and Twitter plays an inevitable role in tracing these emotions. This study mainly focuses on fitting a model based on classification of Tweets as positive and negative using different filters namely Naive Bayesian and filtered classifiers using machine learning tool and to prove how effective and accurate the machine learning tool can be used in data mining to predict Tweets as positive and negative. It is observed that Naive Bayesian filter gives better results than filtered classifier for test data and further can be employed as a tool to study the opinions of people.

More »»

2018

Kavya Johny, Maya L. Pai, and S., A., “Empirical Forecasting and Indian Ocean Dipole Teleconnections of South West Monsoon Rainfall in Kerala”, 131, no. 4, pp. 1055-1065, 2018.[Abstract]


Rainfall is a vital hydrologic variable that has a direct and significant impact on the economic development of monsoon dominated state of Kerala in southern India. An effective approach providing accurate prediction of rainfall makes it possible to take preventive and mitigation measures against natural disasters. In this study, the Ensemble Empirical Mode Decomposition (EEMD) - Artificial Neural Networks (ANN)-Multiple Linear Regression (MLR) hybrid approach is used to forecast the South West Monsoon (SWM) rainfall of Kerala. The EEMD of SWM rainfall of Kerala resulted in a set of orthogonal components of specific periodic scale. The non-linear components are identified and separately modeled using ANN and rest of the components are modeled using linear regression to get their values at a specific time t. Finally, the predicted modes are recombined to get the forecasts of a generic time t. The SWM rainfalls of 1871-1972 are used for model calibration and forecasts are made sequentially for 1973-2014 period, which clearly demonstrated its efficacy in handling non-linear part of SWM rainfall data with a predictive skill of 0.65 for validation data. Further, by considering a dataset of 1961-2014 period, this study has investigated the possible teleconnection of SWM rainfall of Kerala with the Indian Ocean Dipole (IOD) using the cross correlation and EEMD based Time Dependent Intrinsic Correlation (TDIC) analyses. Apart from the strong correlation in the trend component, the analysis has proved the dominancy of negative association of IOD with SWM of Kerala in different process scales with strong positive association at localized time spells. The forecasting strategy demonstrated in the study and the evidence of IOD-SWM rainfall link is an amendment to the efforts for improving the predictability of SWM rainfall in Kerala.

More »»

2018

R. Arya and Maya L. Pai, “Rainfall Prediction Using an Optimised Genetic-Artificial Neural Network Model ”, International Journal of Pure and Applied Mathematics , vol. 119, pp. 669-678, 2018.[Abstract]


In the modern world rainfall is very difficult to predict, because of its non-linearity and complicated happening. So, in order to model and predict advance computing technologies are needed. The objective is to analyse the four-months (June, July, August, and September) of rainfall data of 30 years from 1982-2012 in Goa, India. This paper describes Feed Forward -Back Propagation (FFBP) algorithm to train the networks, and to get optimised results Genetic Algorithm (GA) is used. Promising results are obtained for GA approach than Artificial Neural Network (ANN) alone.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2018

Maya L. Pai, Varsha, K. S., and Arya, R., “Application of Artificial Neural Networks and Genetic Algorithm for the Prediction of Forest Fire Danger in Kerala”, Intelligent Systems Design and Applications, vol. 2. Springer International Publishing, Cham, 2018.[Abstract]


Forest fire prediction is the most significant component of forest fire management. It is necessary because it plays an important role in resource management and recovery efforts. So, in order to model and predict such a calamity, advanced computing technologies are needed. This paper describes a detailed analysis of forest fire prediction methods based on Artificial Neural Network and Genetic algorithm (GA). The objective is to analyse forest fire prediction in Kerala, India. This paper describes Feed Forward–Back Propagation (FFBP) algorithm to train the networks; to get optimised results, GA is used. Promising results are obtained for GA approach than ANN alone

More »»
Faculty Research Interest: