Novel algorithm to extract multiple solutions for RNA sequence classification problem

Guannoni, Naoual; Mhamdi, Faouzi; Weitschek, Emanuel; Elloumi, Mourad

doi:10.1109/hpcs48598.2019.9188203

Cited by 1 publication

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BIGBIOCL is inspired by Camur algorithm in order to apply classification methods to big datasets. In 2019, Guannoni et al, [8] proposed a new method that extracts multiple and equivalent classification methods. This method Called" Multiple Part" algorithm that integrates rule-based classification method (Part) and a feature elimination technique in order to obtain more interpretable models in a reduced execution time.…”

Section: Literature Reviewmentioning

confidence: 99%

“…We compare in the experimental study the obtained results of IMPA with results of CAMUR and" Multiple Part" [8]. Our comparison will be based on the number of extracted models, the performance of the models, the number of relevant features and the execution time.…”

Section: Concept and Experimental Studymentioning

confidence: 99%

“…These techniques have been also used to improve diagnosis of diseases such as Alzheimer, Breast Cancer or Meningitis [6] [7] [1].The big limits with the DOI reference number: 10.18293/SEKE2021-137 application of these machine learning algorithms are related to the managing of the huge amount of data. In fact, for biological datasets, a high learning time is needed for data analysis and the extraction of new knowledge from them [8]. Also, all these classical algorithms compute just a single classification method that contains few of features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improved Multiple Part Algorithm (IMPA) to extract multiple solutions for RNA sequence classification problem

Guannoni¹

2021

Proceedings of the 33rd International Conference on Software Engineering and Knowledge Engineering

Self Cite

View full text Add to dashboard Cite

The methods, which extract knowledge from Next Generation Sequencing Data (NGS) are highly requested nowadays. The attention to analysis biomedical data is increasing proportionally. In this work, we focus to elicit and discovery a higher amount of knowledge by computing many classification models in a single run, and therefore to identify most of the features related to an investigated class. Major efforts have been made in this field and a last algorithm is proposed" Multiple Part" for data analysis and extraction of new and more knowledge from them. In this paper, we propose a new version of Multiple Part algorithm which integrates a heuristic evaluation method and a feature elimination technique in order to extract multiple and equivalent solution for biomedical data. In order to prove the validity of our algorithm, we analyze an RNA-seq of cancer diseases data sets extracted from The Cancer Genome Atlas (TCGA). Furthermore, we validate our approach by comparing it with the existing methods. Experimental results show the efficacy of our proposed algorithm.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Concept and Experimental Studymentioning

confidence: 99%