Multiple Features Based Two-stage Hybrid Classifier Ensembles for Subcellular Phenotype Images Classification

International Journal of Biometric and Bioinformatics

Tuan D. Pham¹  Bailing Zhang¹ 

关键词: subcellular phenotype images classification;    hybrid classifier;    image feature extraction;   

DOI  :  

学科分类：计算机科学（综合）

来源: Computer Science Journals

【 摘 要 】

Subcellular localization is a key functional characteristic of proteins. As an interesting ``bio-image informatics`` application, an automatic, reliable and efficient prediction system for protein subcellular localizationcan be used for establishing knowledge of the spatial distribution of proteins within living cells and permits to screen systems for drug discovery or for early diagnosis of a disease. In this paper, we propose atwo-stage multiple classifier system to improve classification reliability by introducing rejection option. The system is built as acascade of two classifier ensembles. The first ensemble consists of set of binary SVMs which generalizes to learn ageneral classification rule and the second ensemble, which also include threedistinctclassifiers, focus on the exceptions rejected by the rule. A new way to induce diversity for the classifier ensembles is proposed bydesigning classifiers that are based on descriptions of different feature patterns. In addition to the Subcellular Location Features (SLF) generally adopted in earlier researches, three well-known texture feature descriptions have been applied to cell phenotype images, which are the local binary patterns (LBP), Gabor filtering and Gray Level Coocurrence Matrix (GLCM). The different texture feature setscan provide sufficient diversity among base classifiers, which is known as a necessary condition for improvement in ensemble performance. Using the public benchmark2D HeLa cell images, a high classification accuracy 96% is obtainedwith rejection rate $21\%$ from the proposed systemby taking advantages of the complementary strengths of feature construction and majority-voting based classifiers` decision fusions.

【 授权许可】

Unknown