A Multi-Label Classification Approach Based on Correlations Among Labels
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2015, Vol 6, Issue 2
Abstract
Multi label classification is concerned with learning from a set of instances that are associated with a set of labels, that is, an instance could be associated with multiple labels at the same time. This task occurs frequently in application areas like text categorization, multimedia classification, bioinformatics, protein function classification and semantic scene classification. Current multi-label classification methods could be divided into two categories. The first is called problem transformation methods, which transform multi-label classification problem into single label classification problem, and then apply any single label classifier to solve the problem. The second category is called algorithm adaptation methods, which adapt an existing single label classification algorithm to handle multi-label data. In this paper, we propose a multi-label classification approach based on correlations among labels that use both problem transformation methods and algorithm adaptation methods. The approach begins with transforming multi-label dataset into a single label dataset using least frequent label criteria, and then applies the PART algorithm on the transformed dataset. The output of the approach is multi-labels rules. The approach also tries to get benefit from positive correlations among labels using predictive Apriori algorithm. The proposed approach has been evaluated using two multi-label datasets named (Emotions and Yeast) and three evaluation measures (Accuracy, Hamming Loss, and Harmonic Mean). The experiments showed that the proposed approach has a fair accuracy in comparison to other related methods.
Authors and Affiliations
Raed Alazaidah, Fadi Thabtah, Qasem Al-Radaideh
Keywords
Related Articles
- EP ID EP111113
- DOI 10.14569/IJACSA.2015.060208
- Views 75
- Downloads 0
Real Time RNA Sequence Edition with Matrix Insertion Deletion for Improved Bio Molecular Computing using Template Match Measure
The RNA sequence editing has become a challenging task in the molecular computing. There are number of approaches that have been discussed earlier for the problem RNA editing in bio molecular computing, but they suffer t...
Knowledge Sharing Protocol for Smart Spaces
In this paper we present a novel knowledge sharing protocol (KSP) for semantic technology empowered ubiquitous computing systems. In particular the protocol is designed for M3 which is a blackboard based semantic interop...
Assessing Trends of Existing Research Contribution Towards Internet-of-Things
With the growing demands of system automation, technology integration, and non-human intervention technique, Internet-of-Things (IoT) has evolved as a boon and value-added services over pervasive computing. IoT comprises...
Construction of TVET M-Learning Model based on Student Learning Style
Mobile learning or m-learning is emerging as the innovation of virtual learning that used mobile devices for teaching and learning which can be accessed readily at hand anywhere either in classroom or group. Whereas prel...
A Guideline for Decision-making on Business Intelligence and Customer Relationship Management among Clinics
Business intelligence offers the capability to gain insights and perform better in decision-making by using a particular set of technologies and tools. A company’s success to a certain extent depends on customers. The co...