Towards a Clinical Practice Guideline Implementation for Asthma Treatment

Lecture Notes in Computer Science

Spencer

2019

The supervised learning classification algorithms are one of the most well known successful techniques for ambient assisted living environments. However the usual supervised learning classification approaches face issues that limit their application especially in dealing with the knowledge interpretation and with very large unbalanced labeled data set. To address these issues fuzzy classification method PROAFTN was proposed. PROAFTN is part of learning algorithms and enables to determine the fuzzy resemblance measures by generalizing the concordance and discordance indexes used in outranking methods. The main goal of this chapter is to show how the combined meta-heuristics with inductive learning techniques can improve performances of the PROAFTN classifier. The improved PROAFTN classifier is described and compared to well known classifiers, in terms of their learning methodology and classification accuracy. Through this chapter we have shown the ability of the metaheuristics when embedded to PROAFTN method to solve efficiency the classification problems.

Section: Proaftn Methodsmentioning

confidence: 99%

Combining Machine Learning and Metaheuristics Algorithms for Classification Method PROAFTN

Al-Obeidat

Lecture Notes in Computer Science

Spencer

2019

“…The PROAFTN method belongs to the class of supervised learning and is used for solving classi¯cation problems. PROAFTN has been applied to the resolution of many real-world practical problems such as acute leukemia diagnosis, 6 asthma treatment, 33 cervical tumor segmentation, 27 Alzheimer's diagnosis, 9 e-Health, 7 optical¯ber design, 30 image processing and classi¯cation, 2 and computer-aided diagnosis image analysis system. 5 PROAFTN has also been applied for intrusion detection and analyzing cyber-attacks.…”

Section: Proaftn Classi¯cation Methodsmentioning

confidence: 99%

PROAFTN Classifier for Feature Selection with Application to Alzheimer Metabolomics Data Analysis

Int. J. Patt. Recogn. Artif. Intell.

Čuperlović-Culf

2019

Early and accurate Alzheimer’s disease (AD) diagnosis remains a challenge. Recently, increasing efforts have been focused towards utilization of metabolomics data for the discovery of biomarkers for screening and diagnosis of AD. Several machine learning approaches were explored for classifying the blood metabolomics profiles of cognitively healthy and AD patients. Differentiation between AD, mild cognitive impairment (MCI) and cognitively healthy subjects remains difficult. In this paper, we propose a new machine learning approach for the selection of a subset of features that provide an improvement in classification rates between these three levels of cognitive disorders. Our experimental results demonstrate that utilization of these selected metabolic markers improves the performance of several classifiers in comparison to the classification accuracy obtained for the complete metabolomics dataset. The obtained results indicate that our algorithms are effective in discovering a panel of biomarkers of AD and MCI from metabolomics data suggesting the possibility to develop a noninvasive blood diagnostic technique of AD and MCI.

“…In this section, we describe the PROAFTN procedure, which belongs to the class of supervised learning, to solve classification problems. PROAFTN has been applied to the resolution of many real‐world practical problems such as medical diagnosis, asthma treatment, and e‐Health 26–29…”

Section: Proaftn Methodsmentioning

confidence: 99%

Alternative approach for learning and improving the MCDA method PROAFTN

Al-Obeidat

2011

Int. J. Intell. Syst.

OBJECTIVES. The objectives of this paper are 1) to propose new techniques to learn and improve the multi-criteria decision analysis (MCDA) method PROAFTN based on machine learning approaches, and 2) to compare the performance of the developed methods with other well-known machine learning classification algorithms. METH-ODS. The proposed learning methods consist of two stages: the first stage involves using the discretization techniques to obtain the required parameters for the PROAFTN method, and the second stage is the development of a new inductive approach to construct PROAFTN prototypes for classification. RESULTS. The comparative study is based on the generated classification accuracy of the algorithms on the datasets. For further robust analysis of the experiments, we used the Friedman statistical measure with the corresponding posthoc tests. CONCLUSION. The proposed approaches significantly improved the performance of the classification method PROAFTN. Based on the generated results on the same datasets, PROAFTN 1 outperforms widely used classification algorithms. Furthermore, the method is simple, no preprocessing is required, and no loss of information during learning.