In this paper, an Extreme Learning Machine (ELM) based technique forMulti-label classification problems is proposed and discussed. In multi-labelclassification, each of the input data samples belongs to one or more than oneclass labels. The traditional binary and multi-class classification problemsare the subset of the multi-label problem with the number of labelscorresponding to each sample limited to one. The proposed ELM based multi-labelclassification technique is evaluated with six different benchmark multi-labeldatasets from different domains such as multimedia, text and biology. Adetailed comparison of the results is made by comparing the proposed methodwith the results from nine state of the arts techniques for five differentevaluation metrics. The nine methods are chosen from different categories ofmulti-label methods. The comparative results shows that the proposed ExtremeLearning Machine based multi-label classification technique is a betteralternative than the existing state of the art methods for multi-labelproblems.
展开▼
