Title :
Machine learning algorithms for data categorization and analysis in communication
Author_Institution :
Coll. of literature & Commun., Hubei Univ. for Nat., Enshi, China
Abstract :
Machine learning and pattern recognition contains well-defined algorithms with the help of complex data, provides the accuracy of the traffic levels, heavy traffic hours within a cluster. In this paper the base stations and also the noise levels in the busy hour can be predicted. 348 pruned tree contains 23 nodes with busy traffic hour provided in east Godavari. Signal to noise ratio has been predicted at 55, based on CART results. About 53% instances provided inside the cluster and 47% provided outside the cluster. DBScan clustering provided maximum noise from srikakulam. MOR (Number of originating calls successful) predicted as best associated attribute based on Apriori and Genetic search 12:1 ratio.
Keywords :
data analysis; learning (artificial intelligence); mobility management (mobile radio); pattern clustering; search problems; telecommunication computing; telecommunication traffic; CART results; DBScan clustering; J48 pruned tree; MOR; base stations; communication; data analysis; data categorization; east Godavari; genetic search; heavy traffic hours; machine learning algorithms; pattern recognition; traffic levels; Algorithm design and analysis; Classification algorithms; Clustering algorithms; Data mining; Machine learning; Mobile communication; Prediction algorithms; Data mining; MOR; Traffic;
Conference_Titel :
Information Security and Intelligence Control (ISIC), 2012 International Conference on
Conference_Location :
Yunlin
Print_ISBN :
978-1-4673-2587-5
DOI :
10.1109/ISIC.2012.6449693
