• I. Poonkody
• A. Revathi
• Dr. P. Sumathi

Biological data has been generated by the human genome and the sequencing projects for other organisms. The massive demand for analysis and interpretation of these data is being managed by the emerging science of bioinformatics. It is an interdisciplinary field, which connects computer science, mathematics, physics, biology and medicine. The data mining technique uses the protein data set to diagnose the various diseases. Due to less accuracy and more complexity, the need for better disease diagnosing technique arises. At this juncture, an improved disease diagnosing technique with less complexity and more accurate Ensembled Decision Tree with Gradient Descent Logit Boost Classification (EDT-GDLBC) technique was introduced. This paper describes the way to construct the decision trees which are base learners, that not only identifies the abnormal sequences based on their relationship between training and testing protein data sequences, but also diagnose diseases accurately with minimum time.

Disease diagnosis, protein sequences, decision tree, bivariate correlation, gradient descent logit boost classifier

"GRADIENT DESCENT LOGIT BOOST CLASSIFICATION TECHNIQUE FOR DIAGONISING CANCER DISEASES ACCURATELY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.276-280, March-2019, Available :http://www.jetir.org/papers/JETIRAQ06057.pdf

"GRADIENT DESCENT LOGIT BOOST CLASSIFICATION TECHNIQUE FOR DIAGONISING CANCER DISEASES ACCURATELY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp276-280, March-2019, Available at : http://www.jetir.org/papers/JETIRAQ06057.pdf