Online Semi-Supervised Learning Using Max-Flow Algorithm

Ms. Sujata Gawade, Prof. Vina M. Lomte


In a common machine learning methods to classification, one can only make use of a labeled set from training the
classifier. The problem with the labeled instances is those can
be hard, expensive or may be very much time consuming to get
because of the need the help of human annotators. Sometimes
unlabeled data can be easy to get, but there have been some
methods to utilize them. Semi-supervised learning solves these
issues by making use of the huge size of unlabeled data, mixed
with labeled data for creating the better classifiers. Due to the
semi-supervised learning needs minimum human effort as well as
provides greater accuracy. The proposed system working on the
semi supervised learning of online data streams to improve the
classification accuracy. To achieve this, online max flow algorithm
is used, which seeks a maximum feasible flow through a singlesource, single-sink graph. By using labeled and unlabeled data,
graph is learn and updated according to online data stream
arrival. Also for classification, min cut is used. To improve the
classification accuracy and efficiency, system makes use of cosine
similarity and feature selection method respectively. The system
uses KDD dataset for analysis purpose and experimental results
prove that the proposed system achieves higher accuracy and

Full Text:



Zhu, Lei, et al. ”Incremental and Decremental Max-flow for Online Semisupervised Learning.”

Mallapragada, Pavan Kumar, et al. ”Semiboost: Boosting for semisupervised learning.” IEEE transactions on pattern analysis and machine

intelligence 31.11 (2009): 2000-2014.

Dong, Shengwu, and Yi Zhang. ”Research on method of traffic network bottleneck identification based on max-flow min-cut theorem.”

Transportation, Mechanical, and Electrical Engineering (TMEE), 2011

International Conference on. IEEE, 2011.

Dandapat, Sourav Kumar, et al. ”Fair bandwidth allocation in wireless

mobile environment using max-flow.” 2010 International Conference on

High Performance Computing. IEEE, 2010.

Dandapat, Sourav Kumar, et al. ”Smart association control in wireless

mobile environment using max-flow.” IEEE Transactions on Network and

Service Management 9.1 (2012): 73-86.

Imangaliyev, Sultan, et al. ”Online semi-supervised learning: algorithm

and application in metagenomics.” Bioinformatics and Biomedicine

(BIBM), 2013 IEEE International Conference on. IEEE, 2013.

Ditzler, Gregory, and Robi Polikar. ”Semi-supervised learning in nonstationary environments.” Neural Networks (IJCNN), The 2011 International

Joint Conference on. IEEE, 2011.

J. Hernandez, Inaki Inza Cano, Jose Antonio Lozano Alonso, “On

the optimal usage of labelled examples in semi-supervised multi-class

classification problems”,

Gregory Ditzler, Robi Polikar, “Semi-supervised learning in nonstationary environment.”, The 2011 International Joint Conference on

Neural Networks (IJCNN), 03 October 2011 .

Tomasz Weglinski, Anna Fabijanska, “Min-Cut/max-flow segmentation

of hydrocephalus in children from CT datasets”, International Conference

on Signals and Electronic Systems (ICSES), 24 December 2012

Gustavo Carneiro, Jacinto C. Nascimento, “Incremental on-line semisupervised learning for segmenting the left ventricle of the heart from

ultrasound data”, IEEE International Conference on Computer Vision

(ICCV), 2011 .

Oliver Kosut “Max-Flow Min-Cut for Power System Security Index

Computation” , Sensor Array and Multichannel Signal Processing Workshop (SAM), 2014 IEEE 8th.

Selina Chu, Shrikanth Narayanan, C.-C. Jay Kuo, “A Semi-supervised

learning for audio background detection”, IEEE International Conference

on Acoustics, Speech and Signal Processing, 2009.

Y. Y. Boykov, M.-P. Jolly“Interactive Graph Cuts for Optimal Boundary

Region Segmentation of Objects in N-D Images”, Eighth IEEE International Conference on Computer Vision, 2001. ICCV 2001

Dan Snow, Paul Viola and Ramin Zabih, “Exact Voxel Occupancy

with Graph Cuts”, IEEE Conference on Computer Vision and Pattern

Recognition, June 2000


Copyright © IJETT, International Journal on Emerging Trends in Technology