Qualification: 
MCA, MPhil
anisha@asas.kh.amrita.edu

G. S. Anisha currently serves as Faculty Associate in the Department of Computer Science and I.T., School of Arts & Sciences, Amrita Vishwa Vidyapeetham, Kochi.

Publications

Publication Type: Journal Article

Year of Publication Title

2019

Pratibha Devishri S, Ragin O R, and G.S. Anisha, “Comparative Study of Classification Algorithms in Chronic Kidney Disease ”, International Journal of Recent Technology and Engineering (IJRTE) , vol. 8, no. 1, 2019.[Abstract]


Chronic Kidney Disease is a very dangerous health problem that has been spreading globally due to alterations in life style such as food habits, changes in the atmosphere, etc. So it is essential to decide on any remedy to avoid and to predict the disease in early stage which helps to avoid wastage of life. We show that feature selection approach is well suited for chronic kidney disease prediction. Principal Component Analysis is one of the feature selection techniques that filters out less important attributes; it also picks attributes of importance from the dataset. We also compare different data classification approaches in terms of how accurately they predict chronic kidney disease. We examine Decision stump, Rep tree, IBK, K-star, SGD and SMO classifiers using performance measures like Kappa statistics, Receiver Operating Characteristic, Mean Absolute Error and Root mean squared Error using WEKA. Accuracy measures used to compare classifiers are Recall, F-measure and Precision by implementing on WEKA. WEKA-a software for data mining that uses collection of algorithm for data mining. It is possible to apply these algorithms directly to the data or call them from java code. Results obtained show better accuracy measures for Decision stump and Rep tree where the mean absolute error were less with error rate of 0.010 and 0.012 respectively.

More »»

2019

Aishwarya Harish, S. Ashwini, and G.S. Anisha, “Quantisation of Different Color Spaces in Image Retrieval – An Analysis”, International Journal of Innovative Technology and Exploring Engineering (IJITEE) , vol. 8, no. 6, 2019.[Abstract]


We study Content-Based Image Retrieval (CBIR) and in this domain, we compare the performance of different quantized color spaces. This technique is one of the best image retrieval technique that is used worldwide as it produces much better results as compared to the predecessors’ techniques. CBIR technique makes use of color, texture and shape as the important features for quantization. In our paper, we focus on the color of the images as color has more ability to increase the accuracy of the retrieval. We need to perform queries with images as key. This query image is usually selected from a large image database. The image database that can be used is the Corel’s database (10,000 images).In the first stage of our process, we extract the color features from the image that is the query key; other images present in the dataset are also retrieved; a color descriptor represents the extracted color feature; for this purpose, we use the color histogram. Color histogram helps making the comparison between the images to be more precise. Secondly, the histogram is quantized to reduce computational complexity. The third stage involves the use of distance matrix for similarity measurement. We use Euclidean distance for similarity measure. Currently in wide use are many color spaces such as RGB, HSV, CLE Lab and CLE Luv. We also make a comparative study of how image retrieval performs using RGB and HSV color spaces. In the paper we also provide different tables based on the implementation that clearly helps us to prove which color space has a major play in better retrieval. Based on the implementation tables provided in the below sections, we reach the conclusion that HSV has better image retrieval.

More »»
Faculty Research Interest: