Abstract Multi-Label Classification (MLC) is a general type of classification that has attracted many researchers in the last few years. Two common approaches are being used to solve the problem of MLC: Problem Transformation Methods (PTMs) and Algorithm Adaptation Methods (AAMs). This Paper is more interested in the first approach; since it is more general and applicable to any domain. In specific, this paper aims to meet two objectives. The first objective is to propose a new multi-label ranking algorithm based on the positive pairwise correlations among labels, while the second objective aims to propose new simple PTMs that are based on labels correlations, and not based on labels frequency as in conventional PTMs. Experiments showed that the proposed algorithm overcomes the existing methods and algorithms on all evaluation metrics that have been used in the experiments. Also, the proposed PTMs show a superior performance when compared with the existing PTMs.

References

[1] Alazaidah R., Ahmad F., and Mohsen M.,“A Comparative Analysis Between the three Main Approaches that Are Being Used to Solve the Problem of Multi Label Classification,” International Journal of Soft Computing, vol.12, no. 4, pp. 218-223, 2018.

[2] Alazaidah R., Ahmad F., Mohsen M., and Farhan M., “Evaluating Conditional and Unconditional Correlations Capturing Strategies in Multi Label Classification,” Evaluating Conditional and Unconditional Correlations Capturing Strategies in Multi Label Classification, vol. 1, no. x, pp. 57-61, 2018.

[3] Alazaidah R., Thabtah F., and Al-Radaideh Q., “A Multi-Label Classification Approach Based on Correlations Among Labels,” International Journal of Advanced Computer Science and Applications, vol. 6, no. 2, pp. 52-59, 2015.

[4] Al-luwaici M., Junoh A., Ahmad F., Mohsen, M., and Alazaidah R., “Open Research Directions for Multi Label Learning,” in Proceedings of IEEE Symposium on Computer Applications and Industrial Electronics, Penang, 2018.

[5] Alzubi O., Alzubi J., Tedmori S., Rashaideh H., and Almomani O., “Consensus-Based Combining Method for Classifier Ensembles,” The International Arab Journal of Information Technology, vol.15, no.1, pp. 76-86, 2018.

[6] Fürnkranz J., Hüllermeier E., Mencía E., and Brinker K., “Multilabel Classification via Calibrated Label Ranking,” Machine Learning, vol. 73, pp. 133-153, 2008.

[7] Gibaja E. and Ventura S., “A Tutorial on Multi Label Learning,” ACM Computing Surveys, vol. 47, no. 3, 2015.

[8] Goncalves E., Plastino A., and Freitaso A., “A Genetic Algorithm for Optimizing the Label Ordering in Multi-Label Classifier Chains,” in Proceedings of the IEEE 25th International Conference on Tools with Artificial Intelligence, Herndon, pp. 469-476, 2013.

[9] Gonçalves T. and Quaresma P., “Using ir Techniques to Improve Automated Text Classification,” in Proceedings of International Conference on Application of Natural Language to Information Systems, Berlin, pp. 374-379, 2004.

[10] Quinlan J., “C4.5: Programs for Machine Learning,” Morgan Kaufmann Series in Machine Learning, 1994.

[11] Read J., “A Pruned Problem Transformation Method for Multi-Label Classification,” in Proceedings of New Zealand Computer Science Research Student Conference, New Zealand, 2008.

[12] Read J., Pfahringer B., Holmes G., and Frank E., “Classifier Chains for Multi-Label Classification,” Machine Learning, vol. 85, no. 3, pp. 333-359, 2011.

[13] Tsoumakas G. and Vlahavas I., “Random K- Labelsets: an Ensemble Method for Multilabel Classification,” in Proceedings of Machine 0 1 2 3 4 5 6 7 MLR-PPC-HAPCFMLR-PPC-HSDF MLR-PPC-HAPCSDF MLR-PPC-LFLMLR-PPC-MFLMLR-PPC-HAPCFMLR-PPC-HSDF MLR-PPC-HAPCSDF MLR-PPC-LFLMLR-PPC-MFLMLR-PPC-HAPCFMLR-PPC-HSDF MLR-PPC-HAPCSDF MLR-PPC-LFLMLR-PPC-MFLMLR-PPC-HAPCFMLR-PPC-HSDF MLR-PPC-HAPCSDF MLR-PPC-LFLMLR-PPC-MFL SceneEmotionsFlagsYeast Running Time (S) Multi Label Ranking Based on Positive Pairwise Correlations Among Labels 449 Learning: European Conference on Machine Learning, Warsaw, pp. 406-417, 2007.

[14] Tsoumakas G., Katakis I., and Vlahavas I., “Mining Multi-Label Data,” Data Mining and Knowledge Discovery Handbook, Springer Boston, pp. 667-685, 2009.

[15] Xu S., Yang X., Yu H., Yu D., Yang J., and Tsang E., “Multi-Label Learning with Label- Specific Feature Reduction,” Knowledge-Based Systems, vol. 14, pp. 52-61, 2016.

[16] Zhang M. and Zhou Z., “A Review on Multi- Label Learning Algorithms,” IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 8, pp. 1819-1837, 2014.

[17] Zhang M. and Zhou Z., “ML-KNN: A Lazy Learning Approach to Multi-Label Learning,” Pattern Recognition, vol. 40, no. 7, pp. 2038- 2048, 2007. Raed Alazaidah is a PhD candidate in Universiti Utara Malaysia- Malaysia. He holds a Bachelor degree of computer science from Al- Albayt university-Jordan in 1999, and a Master degree in computer science (with honors) from Philadelphia university-Jordan in 2013. As academician, he involves with two main research interests: machine learning and data mining tasks, especially classification. Farzana Ahmad is a senior lecturer at School of Computing, Universiti Utara Malaysia, MALAYSIA. She holds a Bachelor degree of Computer Science (with Honours) from Universiti Sains Malaysia in 2003 and a Master degree in Computer Science from the same university later in 2005. She pursued her Ph.D. in Computer Science (Bioinformatics) from Universiti Teknologi Malaysia in 2012 and her doctoral work involves the development of synergy network for breast cancer progression. Her passion is to understand gene regulatory network (GRN) that underlie disease progression. With such objective, she has developed a novel synergy network that able to incorporate heterogeneous data in order to predict the disease proliferations. Currently, her new interest is in neuroscience and neuroinformatics. Mohamad Mohsin currently is the Deputy Dean of UUM CAS Student Development and Alumni Office and a senior lecturer at School of Computing, UUM College of Arts and Sciences, UUM. As academician, he involves with Artificial Intelligent (AI) related research, a part of computer science branch that studies how machine can own intelligent as human (broad AI definition!). What he do is generally to discover the secret of machine learning principle, algorithm, intelligent system, and its capability to infer human cognition and decision-making process. In deep, his main research interests are in machine learning and data mining projects that seek hidden information from huge, complex data set and finally generate/built models to ease human decision-making process. With the emergence of big data era, the data complexity and the challenge to understand them has double that makes this work more interesting. At the moment, most of his researches are in anomaly detection and predictive modeling main in climate change studies and outbreak. Now he is engaging with artificial immune system, several bio-inspired approaches, and text mining based research.