Dr Anita Patrot
@mlacw.org
Assistant Professor
Maharani Lakshmi Ammanni College for Women Autonomous
EDUCATION
BCA, MSc(CS), P.hD,KSET,JRF
RESEARCH INTERESTS
Image Processing, Pattern Recognition
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Harish H, Anita Patrot, Bhavan S, Gousiya S, and Livitha A
IEEE
A significant fraction of the population is affected by the common degenerative joint condition known as knee osteoarthritis (OA), which can cause pain, stiffness, and functional difficulties. The ability to detect knee OA early and accurately can lead to proactive measures and individualized treatment plans. CNNs and the VGG model are two examples of Models of deep learning that recently displayed notable performance in a range of image recognition applications. The goal of this research paper is to use CNN and the VGG architecture to create a knee osteoarthritis model for prediction. The suggested method involves a sizable dataset of knee radiography images to train a CNN model, specifically the VGG model.
H. Harish, Anita Patrot, A. Sreenivasa Murthy, M. V. Anushri, S. Meghana, and M. Vinutha
Springer Nature Switzerland
Anita Patrot, Harish H, Shambbavi B, Geetha P L, and Sahana
IEEE
The large financial transactions in fantasy sports show how popular is sports outcome prediction have become important in recent years. Basketball, especially the National Basketball Association (NBA) of the United States well-liked sports in the world that attracts investment and millions of fans on a global scale. This paper offer a novel intelligent machine learning framework with the goal of identifying the key factors that have the greatest impact on NBA game outcomes. Techniques of machine learning determines the result of an NBA using previously played games, and various variable quantities that influence the game results. Numerous machine learning techniques have been used to accomplish the goals.
Aziz Makandar and Anita Patrot
Springer Singapore
Aziz Makandar and Anita Patrot
IEEE
Increasing suspicious instructions of various malware through a challenge to the malware analysts to identify and classify samples belongs to the malicious family. They have witnessed the very fast increase in both the number and complexity of malware set of instructions. Malware invest profoundly in technology and capability to reorganize the process of building and mutate existing malware set of instructions to avoid traditional protection. Classify malware variants by applying image processing techniques. The textures play an important role in many image processing applications. In this paper we proposed the Support Vector Machine (SVM) multi-class malware image classification challenge from an image processing perspective. The multi-resolution and wavelets are used to build effective texture feature vector using Gabor Wavelet, GIST and Discrete wavelet Transform and other features. The proposed algorithm experimented on Malimg Dataset of malware total 12,470 samples are used. In that 1610 samples are trained and 1710 samples are tested on 8 malware family which is randomly selected from the dataset. We compare this approach to existing malware classification approaches previously published research work. This is an efficient and more accurate malware detection algorithm using Wavelet Transform with machine learning classifiers techniques to detect malware samples more capably compare to existing work.
Aziz Makandar and Anita Patrot
IEEE
This article a model of detection of malware classification is build using image processing techniques. In that image similarity approach is used to detect and retrieve of viruses in the form of malwares. Experimental result analysis done on Malimg data set for experiments and show that using image processing techniques such as Normalization of malware gray scale images then apply wavelet transform using Discrete Wavelet Transform at three level decomposition with PCA. The dimensionality reduction is done on normalized image such as preprocessed malware. After decomposition we apply wavelet based on Statistical Features (SF) such as mean, RMS, Standard Deviation & Variance. This model produces the TP (True Positive) and FP (False Positive) that are used to measures results for Image matching based malware detection framework. The proposed algorithm gives 92.92% accuracy and 92.38 %precision on Mahenuer dataset, and also on 88.75% accuracy and 90.15% precision on Malimg dataset.
Aziz Makandar and Anita Patrot
IEEE
Today major and serious threat on internet is malicious software or data which damage the system. Malware variants identification and classification is the one of the most important research problem in digital forensics. Malware binaries are set of instructions which may affect your system without your authority. Many researchers worked in this area mainly relied on specific API calls, sequences of bytes, statistic and dynamic analysis is used for detection and classification of malware. The proposed method malware is represented as 2Dimensional gray scale image is observed malware images of all the available variants and their texture similarity, which motivate to classify malware based on texture features. The texture plays a very significant role in identify and classify malware. The objective of this paper is to identify a behavior of malicious data based on global features using Gabor wavelet transform and GIST. The experiment done on Mahenhur dataset which includes 3131 binaries samples comprising 24 unique malware families. The algorithm has been implemented using feed forward Artificial Neural Networks (ANN) it gives their overview uniqueness. The experimental results are promising to effectively detecting and classifying malware with good accuracy 96.35 %.