Comparison of Novel Semi supervised Text classification using BPNN by Active search with KNN Algorithm
Journal Title: International Journal on Computer Science and Engineering - Year 2014, Vol 6, Issue 5
Abstract
With the availability of huge amount of text in internet, news, institutes, organization etc need of automatic text classification also increases, The proposed work comprised to deal with the major challenge of getting labeled data for training in classifier, since the availability of labeled data is expensive, time consuming, it also requires the involvement of annotator . A novel semi supervised test classification algorithm based on Back Propagation Neural Network is proposed which makes use of web assisted unlabeled data by Active search, this algorithm is compared with standard KNN algorithm on test data and standard data Mini Newsgroup. Experimental results state that the proposed algorithm outperforms KNN with Micro averaged F1measure.
Authors and Affiliations
Mahak Motwani , Aruna Tiwari
Keywords
Related Articles
- EP ID EP105206
- DOI -
- Views 125
- Downloads 0
Fingerprint Identification System in library and Information Center
AFIS is dramatically improving in the last decade. It can use in Library and Information Center for providing better security. The application of AFIS in Library and Information Center will protect from thief, mutilation...
Biometric Template Security Using Invisible Watermarking With Minimum Degradation in Quality of Template
In this paper, we present an approach to enhance the Biometric Template Security by using Invisible Watermarking. For embedding the watermark in the Biometric Template, we used Parity Checker Method [2]. The use of Parit...
Service Based Architecture for Manufacturing Sector
SOA has been widely and quickly adopted in different rganizations during recent years. SOA enables to solve integration complexity problem and facilitates broadscale interoperability and unlimited collaboration across t...
Adaptive Local Image Registration: Analysis on Filter Size
Adaptive Local Image Registration is a Local Image Registration based on an Adaptive Filtering frame work. A filter of appropriate size convolves with reference image and gives the pixel values corresponding to the disto...
MRI Brain Image Segmentation Algorithm Using Watershed Transform and Kernel Fuzzy C-Means Clustering on Level Set Method
A new method for image segmentation is proposed in this paper, which combines the watershed transform, KFCM and level set method. The watershed transform is first used to presegment the image so as to get the initial par...