B-Scopus
Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/3730
Browse
14 results
Search Results
Item LEVERAGING PRETRAINED TRANSFORMERS FOR ENHANCED AIR QUALITY INDEX PREDICTION MODEL (Article PDF)(Institute of Advanced Engineering and Science, 2025) Velusamy, Santhana Lakshmi; Madhaya Shanmugam, VijayaAir pollution mitigation is essential to ensure sustainable development, as it directly affects climate change, economic productivity, and social well-being. Despite the availability of numerous prediction techniques, machine learning (ML) remains the optimal solution for forecasting air pollution. Constructing a prediction model for a region with limited data poses a challenge. This study presents a novel technique that combines temporal fusion transformer (TFT) with transfer learning to create an inventive air quality index (AQI) prediction model, effectively utilizing temporal insights and prior knowledge. The TFT is an advanced deep neural architecture engineered to enhance time series forecasting through the fusion of sequence modelling and global temporal patterns. By fusing TFT with transfer learning, the research pioneers a fresh approach to AQI prediction for region with data scarcity issue, capitalizing on cross-domain knowledge transfer. Utilizing meteorological and pollutant data from the Cochin region, a hybrid AQI prediction model is constructed through TFT and transfer learning. Employing a preexisting TFT model trained on Trivandrum data, transfer learning technique is utilized to adapt the model for predicting AQI in the Cochin region. The study demonstrates that integrating TFT with transfer learning yields superior accuracy compared to an exclusive TFT-based approach.Item EFFICIENT PREDICTION OF PHISHING WEBSITES USING SUPERVISED LEARNING ALGORITHMS (Conference Paper)(Elsevier B.V, 2012-12-09) Lakshmi V, Santhana; Vijaya, M SPhishing is one of the luring techniques used by phishing artist in the intention of exploiting the personal details of unsuspected users. Phishing website is a mock website that looks similar in appearance but different in destination. The unsuspected users post their data thinking that these websites come from trusted financial institutions. Several antiphishing techniques emerge continuously but phishers come with new technique by breaking all the antiphishing mechanisms. Hence there is a need for efficient mechanism for the prediction of phishing website. This paper employs Machine-learning technique for modelling the prediction task and supervised learning algorithms namely Multi layer perceptron, Decision tree induction and Naïve bayes classification are used for exploring the results. It has been observed that the decision tree classifier predicts the phishing website more accurately when comparing to other learning algorithms.Item ARTIFICIAL INTELLIGENT MODELS FOR AUTOMATIC DIAGNOSIS OF FOETAL CARDIAC ANOMALIES: A META-ANALYSIS(Springer Link, 2023-01-01) Divya, M O; Vijaya, M SThe foetal anomaly scanning is one of the most challenging areas where accuracy of diagnosis much fluctuating with respect to the expertise of the radiologist and the mental equilibrium of the radiologist at the time of scanning. Amongst the various anomalies, foetal heart anomaly diagnosis expects precise and sensitive intellectual presence since perilous congenital heart diseases are one of the common causes resulting in the major population of infant mortality or into permanent natal faults. The accuracy of manual diagnosis of foetal cardiac abnormalities from the ultrasound scan images vary based on the human expertise and the presence of mind. Therefore, the scope of computer-assisted judgement can produce accurate diagnosis irrespective of the operator’s profile. Numerous researches are going on to explore the scope of computer-assisted judgement of abnormalities using ultrasound imaging technique (USIT), specifically using machine learning and deep learning models. This work exploits the opportunities of computer-assisted diagnosis in foetal cardiac anomaly diagnosis as this is one of the most sensitive areas where appropriate diagnosis can save a life and a wrong diagnosis may lose a life unnecessarily.Item MALWARE FAMILY CLASSIFICATION MODEL USING USER DEFINED FEATURES AND REPRESENTATION LEARNING(Springer Link, 2020-11-20) Gayathri, T; Vijaya, M SMalware is very dangerous for system and network user. Malware identification is essential tasks in effective detecting and preventing the computer system from being infected, protecting it from potential information loss and system compromise. Commonly, there are 25 malware families exists. Traditional malware detection and anti-virus systems fail to classify the new variants of unknown malware into their corresponding families. With development of malicious code engineering, it is possible to understand the malware variants and their features for new malware samples which carry variability and polymorphism. The detection methods can hardly detect such variants but it is significant in the cyber security field to analyze and detect large-scale malware samples more efficiently. Hence it is proposed to develop an accurate malware family classification model contemporary deep learning technique. In this paper, malware family recognition is formulated as multi classification task and appropriate solution is obtained using representation learning based on binary array of malware executable files. Six families of malware have been considered here for building the models. The feature dataset with 690 instances is applied to deep neural network to build the classifier. The experimental results, based on a dataset of 6 classes of malware families and 690 malware files trained model provides an accuracy of over 86.8% in discriminating from malware families. The techniques provide better results for classifying malware into families.Item A DEEP LEARNING OF AUTISM SPECTRUM DISORDER USING NAÏVE BAYES, IBK AND J48 CLASSIFIERS(Blue Eyes Intelligence Engineering & Sciences Publication, 2019-07) Gomathi, SDeciding the right classification algorithm to classify and predict the disease is more important in the health care field. The eminence of prediction depends on the accuracy of the dataset and the machine learning method used to classify the dataset. Predicting autism behaviors through laboratory or image tests is very time consuming and expensive. With the advancement of machine learning (ML), autism can be predicted in the early stage. The main objective of the paper is to analyze the three classifiers Naïve Bayes, J48 and IBk (k-NN). An Autism Spectrum Disorder (ASD) diagnosis dataset with 21 attributes is obtained from the UCI machine learning repository. The attributes have experimented with the three classifiers using WEKA tool. 10-fold cross validation is used in all three classifiers. In the analysis, J48 shows the best accuracy compared with the other two classifiers. The architecture diagram is shown to depict the flow of the analysis. The Confusion matrix with other relevant results and figures are shown.Item MACHINE LEARNING-BASED MODEL FOR IDENTIFICATION OF SYNDROMIC AUTISM SPECTRUM DISORDER(Springer Link, 2019) Pream Sudha, V; Vijaya, M SAutism spectrum disorder (ASD) is characterized by a set of developmental disorders with a strong genetic origin. The genetic cause of ASD is difficult to track, as it includes a wide range of developmental disorders, a spectrum of symptoms and varied levels of disability. Mutations are key molecular players in the cause of ASD, and it is essential to develop effective therapeutic strategies that target these mutations. The development of computational tools to identify ASD originated by genetic mutations is vital to aid the development of disease-specific targeted therapies. This chapter employs supervised machine learning techniques to construct a model to identify syndromic ASD by classifying mutations that underlie these phenotypes, and supervised learning algorithms, namely support vector machines, decision trees and multilayer perceptron, are used to explore the results. It has been observed that the decision tree classifier performs better compared to other learning algorithms, with an accuracy of 94%. This model will provide accurate predictions in new cases with similar genetic background and enable the pathogenesis of ASD.Item SUPPORT VECTOR REGRESSION FOR PREDICTING BINDING AFFINITY IN SPINOCEREBELLAR ATAXIA(Springer Link, 2019) Asha, P R; Vijaya, M SSpinocerebellar ataxia (SCA) is an inherited disorder. It arises mainly due to gene mutations, which affect gray matter in the brain causing neurodegeneration. There are certain types of SCA that are caused by repeat mutation in the gene, which produces differences in the formation of protein sequence and structures. Binding affinity is very essential to know how tightly the ligand binds with the protein. In this work, a binding affinity prediction model is built using machine learning. To build the model, predictor variables and their values such as binding energy, IC50, torsional energy and surface area for both ligand and protein are extracted from the complex using AutoDock, AutoDock Vina and PyMOL. A total of 17 structures and 18 drugs were used for learning the support vector regression (SVR) model. Experimental results proved that the SVR-based affinity prediction model performs better than other regression models.Item DECISION TREE BASED MODEL FOR THE CLASSIFICATION OF PATHOGENIC GENE SEQUENCES CAUSING ASD(Springer Link, 2018-08-21) Pream Sudha, V; Vijaya, M SPathogenic gene identification is an important research problem in biomedical domain. The genetic cause of ASD, which is a multifaceted developmental disability is hard to research. Hence, there is a critical need for inventive approaches to further portray the genetic basis of ASD which will enable better filtering and specific therapies. This paper adopts machine learning techniques to classify gene sequences which are the significant drivers of syndromic and asyndromic ASD. The synthetic dataset with 150 sequences of six different categories of genes were prepared and coding measures of gene sequences were taken as attributes for gene identification. Pattern learning algorithms like support vector machine, decision tree and Multiplayer perceptron were used to train the model. The model was evaluated using 10 fold cross validation and the results are reported. The study reveals that Decision trees outperform other classifiers with an accuracy of 97.33%Item BINDING AFFINITY PREDICTION MODELS FOR SPINOCEREBELLAR ATAXIA USING SUPERVISED LEARNING(Springer Link, 2018-08-21) Asha, P R; Vijaya, M SSpinocerebellar Ataxia (SCA) is an inherited disorder flow in the family, even when one parent is affected. Disorder arises mainly due to mutations in the gene, which affects the gray matter in the brain and causes neuron degeneration. There are certain types of SCA that are caused by repeat mutation in the gene, which produces differences in the formation of protein sequence and structures. Binding affinity is essential to know how tightly the ligand binds to the protein. In this work, the binding affinity prediction model is built using machine learning. To build the model, features like Binding energy, IC50, Torsional energy and surface area for both ligand and protein are extracted from Auto dock, auto dock vina and PYmol from the complex. A total of 17 structures and 18 drugs were used for building the model. This paper proposes a predictive model using applied mathematics, machine learning regression techniques like rectilinear regression, Artificial neural network (ANN) and Random Forest (RF). Experimental results show that the model built using Random Forest outperforms in predicting the binding affinity.Item SHALLOW LEARNING MODEL FOR DIAGNOSING NEURO MUSCULAR DISORDER FROM SPLICING VARIANTS(Emerald Publishing Limited, 2017-08-07) Sathyavikasini, Kalimuthu; Vijaya, VijayakumarDiagnosing genetic neuromuscular disorder such as muscular dystrophy is complicated when the imperfection occurs while splicing. This paper aims in predicting the type of muscular dystrophy from the gene sequences by extracting the well-defined descriptors related to splicing mutations. An automatic model is built to classify the disease through pattern recognition techniques coded in python using scikit-learn framework.