No abstract

With data sizes constantly expanding, and with classical machine learning algorithms that analyze such data requiring larger and larger amounts of computation time and storage space, the need to distribute computation and memory requirements among several computers has become apparent. Although substantial work has been done in developing distributed binary SVM algorithms and multi-class SVM algorithms individually, the field of multi-class distributed SVMs remains largely unexplored. This research proposes a novel algorithm that implements the Support Vector Machine over a multi-class dataset and is efficient in a distributed environment (here, Hadoop). The idea is to divide the dataset into half recursively and thus compute the optimal Support Vector Machine for this half during the training phase, much like a divide and conquer approach. While testing, this structure has been effectively exploited to significantly reduce the prediction time. Our algorithm has shown better computation time during the prediction phase than the traditional sequential SVM methods (One vs. One, One vs. Rest) and out-performs them as the size of the dataset grows. This approach also classifies the data with higher accuracy than the traditional multiclass algorithms.

Data mining algorithms are originally designed by assuming the data is available at one centralized site.These algorithms also assume that the whole data is fit into main memory while running the algorithm. But in today's scenario the data has to be handled is distributed even geographically. Bringing the data into a centralized site is a bottleneck in terms of the bandwidth when compared with the size of the data. In this paper for multiclass SVM we propose an algorithm which builds a global SVM model by merging the local SVMs using a distributed approach(DSVM). And the global SVM will be communicated to each site and made it available for further classification. The experimental analysis has shown promising results with better accuracy when compared with both the centralized and ensemble method. The time complexity is also reduced drastically because of the parallel construction of local SVMs. The experiments are conducted by considering the data sets of size 100s to hundred of 100s which also addresses the issue of scalability.

No abstract

Abstract-Support Vector Machines (SVMs) were primarily designed for 2-class classification. But they have been extended for N-class classification also based on the requirement of multiclasses in the practical applications. Although N-class classification using SVM has considerable research attention, getting minimum number of classifiers at the time of training and testing is still a continuing research. We propose a new algorithm CBTS-SVM (Centroid based Binary Tree Structured SVM) which addresses this issue. In this we build a binary tree of SVM models based on the similarity of the class labels by finding their distance from the corresponding centroids at the root level. The experimental results demonstrates the comparable accuracy for CBTS with OVO with reasonable gamma and cost values. On the other hand when CBTS is compared with OVA, it gives the better accuracy with reduced training time and testing time. Furthermore CBTS is also scalable as it is able to handle the large data sets.