No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
WEKA VS. RAPID MINER: TOWARDS A COMPREHENSIVE COMPARISON FOR DIAGNOSIS OF AUTISM USING ENSEMBLES
Abstract
Autism is the most well-known disorder that received high interest from researchers recently. This disorder may be in all ages of people. All exist datasets suffer from low quality for data analysis. Most of the related works focus on base classifiers. In this article, we suggested a comprehensive comparison to improve the diagnosis of autism disorder using effective pre-processing and ensemble methods. The pre-processing stage consists of resolving missing values and outliers. Also, the ensemble methods include voting, boosting, bagging, and stacking. For the evaluation of comparisons, two popular data mining tools are applied. The obtained results prove that our work promotes classification performance rather than the base methods in terms of precision, recall, accuracy, and F1. The highest values for these criteria are obtained 100%.
... Then, with an end goal to address the deficiencies of the primary model, a subsequent model is created. Up until the whole planning instructive list is precisely expected or the best number of models is reached,This framework is reiterated and new models are added Subsequent to entering the information into the mining apparatuses and applying pre-handling methods, we got good results [12]. Voting: One of the techniques that gives good results with medical records is one of the machine learning techniques. ...
... It yielded results at a speed of practically 100 percent without preprocessing, yet preprocessing with Quick Digger achieved results at a high speed of 100%. It was a fair repercussion for aiding portrayal execution and doing the assumption system, yet these datasets still ought to be updated and work on better gauge [12] . Bagging: In this section, we use the process of mobilization, to decrease difference inside an uproarious dataset, the gathering learning approach known as packing, otherwise called bootstrap collection, is broadly used. ...
... After that, pre-processing techniques and this technique were applied. The work was divided into an education part and a test part [12] . Stacking: One of the techniques that gives good results with medical records is one of the machine learning techniques. ...
The term heart disease refers to a variety of diseases that affect the function of the heart. These diseases may affect the heart muscle, its valves, and the membrane surrounding it, or the primary arteries and veins to and from the heart. Heart diseases begin with acute pain attacks because of A blockage in one of the veins that delivers blood and oxygen to the heart, and thus the rate of oxygen reaching the heart decreases, or it may stop completely, causing heart attacks, angina pectoris, and other chronic diseases, which might represent a danger to the patient's life. According to the Centers for Disease Control and Prevention (CDC), heart disease is the leading cause of death in the United States, accounting for a quarter of all deaths. Due to the seriousness of this disease, many researchers have been motivated to search for methods and algorithms that reduce the risk of this research, and there are previous works in this way. preprocessing such as replace missing value with mean and detect outliers with KNN K-near nieghbar, then this work was evaluated using the following criteria: accuracy, f-measure , Recall, precision Among the results, the highest value was obtained in this research, reaching 100 with the bagging algorithm. Manuscript Information
Background and Objectives: Autism is the most well-known disease that occurs in any age people. There is an increasing concern in appealing machine learning techniques to diagnose these incurable conditions. But, the poor quality of most datasets contains the production of efficient models for the forecast of autism. The lack of suitable pre-processing methods outlines inaccurate and unstable results. For diagnosing the disease, the techniques handled to improve the classification performance yielded better results, and other computerized technologies were applied.
Methods: An effective and high performance model was introduced to address pre-processing problems such as missing values and outliers. Several based classifiers applied on a well-known autism data set in the classification stage. Among many alternatives, we remarked that combine replacement with the mean and improvement selection with Random Forest and Decision Tree technologies provide our obtained highest results.
Results: The best-obtained accuracy, precision, recall, and F-Measure values of the MVO-Autism suggested model were the same, and equal 100% outperforms their counterparts.
Conclusion: The obtained results reveal that the suggested model can increase classification performance in terms of evaluation metrics. The results are evidence that the MVO-Autism model outperforms its counterparts. The reason is that this model overcomes both problems.
ResearchGate has not been able to resolve any references for this publication.