Non-Probabilistic K-Nearest Neighbor for Automatic News Classification Model with K-Means Clustering
The news classification is the branch of text classification or text mining. The researchers have already done a lot of work on the text classification models with different approaches. The news works has to be classified in the form of various categories such as sports, political, technology, business, science, health, regional and many other similar categories. The researchers have already worked with many supervised and unsupervised methods for the purpose of news classification. The supervised models have been found more efficient for the purpose of news classification. The k-means algorithm has been used for the classification of the keywords into the multiple groups. The k-nearest neighbor (kNN) classification algorithm has been utilized to estimate the category of the news in the processing. The proposed model has been recorded with the average accuracy of the 93.28% obtained after averaging the accuracy of all test cases, which higher than the previous best performer naïve bayes and SVM based news classifier, which has posted nearly 83.5% of accuracy for classifying the news data. The proposed model has been tested with the 91%, 95%, 90% and 97% of the accuracy over the input test cases of S1, S2, S3 and S4 respectively, which higher than all of the existing models. Hence the proposed model can be declared as the better solution than the previous classification models.
Published by: Akanksha Gupta
Author: Akanksha Gupta
Paper ID: V2I4-1139
Paper Status: published
Published: July 2, 2016
Study of Different Techniques for Human Identification using Finger Knuckle Approach
There are different biometric modalities used to identify person which includes palmprint, face, fingerprint, iris and hand geometry. Apart from these biometric modalities, finger knuckle print also used as one of the cost effective biometric identifier. Finger knuckle print is defined by the back side of fingers. On the back side of fingers there are three joints named as Metacarpophalangeal (MCP) joint, Proximal InterPhalangeal (PIP) joint, distal InterPhalangeal (DIP) joint. The joint which connects hand with the fingers is known as MCP joint and the pattern generated on MCP joint is referred as second minor finger knuckle print. The joint in the middle of finger is known as PIP joint and the pattern generated on this joint is referred as major finger knuckle print. The joint on the tip of finger is known as DIP joint and the pattern generated on this joint is referred as minor finger knuckle print.
Published by: Sanjna Singla, Supreet Kaur
Author: Sanjna Singla
Paper ID: V2I4-1138
Paper Status: published
Published: July 1, 2016
A Closer Overview on Blur Detection-A Review
The image blurring is caused by motion and out of focus parameters and type of blur can be classified as global blur and local blur.in this paper the most challenging spatially varying blured detection schemes are proposed..In this the blur detection techniques for digital images are used in order to determine the blur detection several classifiers are used.In this paper we reviewed SVM & DCT based different blur detections.
Published by: Ravi Saini, Sarita Bajaj
Author: Ravi Saini
Paper ID: V2I4-1137
Paper Status: published
Published: July 1, 2016
The Art of Scheduling in Cloud Computing
Cloud computing is one of the fastest growing technologies which has replaced machine paradigm shift. Cloud computing provides very large scalable and virtualised resources over Internet. In Cloud computing, there are many jobs that are required to be executed by available resources while achieving best performance, minimal total time for completion, shortest response time, utilization of resource etc. To achieve these objectives we need to design, develop and propose a scheduling algorithm. In this paper we are surveying various types of scheduling techniques and issues related to them in Cloud computing. Here we have also surveyed various existing algorithms to find their appropriation according to our needs and their shortcomings.
Published by: Harshita Vashishth, Kamal Prakash
Author: Harshita Vashishth
Paper ID: V2I4-1136
Paper Status: published
Published: July 1, 2016
Breast Cancer: Classification of Breast Masses Mammograms using Artificial Neural Network and Support Vector Machine
This paper presents the diagnosis of breast cancer by using ANN and SVM. To deal with the different kinds of abnormalities causing Cancer, this report consists of all the modalities which help in detecting cancer and well as different methods of feature extraction. Such modalities can be named as: Mammography, Ultrasound, MRI etc [1]. Currently, Electrical impedance and nuclear medicine are used widely for diagnosis. These modalities Based on the image processing i.e. identification of abnormality is done through the reading and retrieving information from images. But this research is based on mammogram images. Before retrieving information one should know about all kinds of abnormalities like: micro classification, masses, architectural distortion, asymmetry, and breast density etc.[2]. And after the process of extracting the abnormal part or can say that ROI (Region of Interest) on which the treatment is applied. To extract ROI various methods are used like region growing, edge detection, segmentation etc. [3][4]. Then, feature extraction is done from which a lot of features are extracted on which feature selection is applied to get higher accuracy. After going through all researches done till now here I have got the conclusion that for determining the presence of cancer researcher uses different features but till now only few researcher used two features named shape and texture which needs good classification technique[1]. Then, classify into classes of normal and abnormal classes. From the statistical study it has been found that the trend in increasing cancer every year, thus, the best and most effective way to cure cancer is the removal of cancerous part.
Published by: Kamaldeep Kaur, Er. Pooja
Author: Kamaldeep Kaur
Paper ID: V2I3-1200
Paper Status: published
Published: June 29, 2016
Wireless Sensor Network: A Review
Wireless Sensor Networks (WSN) consists of nodes with limited power deployed in the area of interest. Nodes cooperate to collect, transmit and forward data to a base station. In WSN, clustering and scheduling techniques ensure collecting data in an energy efficient manner. In this work, we have reviewed many papers relating to clustering and scheduling of sensor network. After reviewing many papers and considering the latest one as the base paper we believe that the work done in it is the latest one, modifications in the work is suggested in report. This review give the basic description of wireless sensor network and their importance in energy efficiency and give a brief about most famous protocol is described leach and their improved version.
Published by: Sashi, Pooja Dhankar
Author: Sashi
Paper ID: V2I3-1199
Paper Status: published
Published: June 29, 2016
