Wyniki wyszukiwania - BazTech

1

Assessment measures of an ensemble classifier based on the distributivity equation to predict the presence of severe coronary artery disease

Rak Ewa, Szczur Adam, Bazan Jan G., Bazan-Socha Stanisława

International Journal of Applied Mathematics and Computer Science

|

2023

|

Vol. 33, no. 3

361--377

EN

The aim of this study is to apply and evaluate the usefulness of the hybrid classifier to predict the presence of serious coronary artery disease based on clinical data and 24-hour Holter ECG monitoring. Our approach relies on an ensemble classifier applying the distributivity equation aggregating base classifiers accordingly. Such a method may be helpful for physicians in the management of patients with coronary artery disease, in particular in the face of limited access to invasive diagnostic tests, i.e., coronary angiography, or in the case of contraindications to its performance. The paper includes results of experiments performed on medical data obtained from the Department of Internal Medicine, Jagiellonian University Medical College, Kraków, Poland. The data set contains clinical data, data from Holter ECG (24-hour ECG monitoring), and coronary angiography. A leave-one-out cross-validation technique is used for the performance evaluation of the classifiers on a data set using the WEKA (Waikato Environment for Knowledge Analysis) tool. We present the results of comparing our hybrid algorithm created from aggregation with the distributive equation of selected classification algorithms (multilayer perceptron network, support vector machine, k-nearest neighbors, naïve Bayes, and random forests) with themselves on raw data.

2

An advanced ensemble modeling approach for predicting carbonate reservoir porosity from seismic attributes

Topór Tomasz, Sowiżdżał Krzysztof

Geology, Geophysics and Environment

|

2023

|

Vol. 49, no. 3

245--260

EN

This study uses a machine learning (ML) ensemble modeling approach to predict porosity from multiple seismic attributes in one of the most promising Main Dolomite hydrocarbon reservoirs in NW Poland. The presented workflow tests five different model types of varying complexity: K-nearest neighbors (KNN), random forests (RF), extreme gradient boosting (XGB), support vector machine (SVM), single layer neural network with multilayer perceptron (MLP). The selected models are additionally run with different configurations originating from the pre-processing stage, including Yeo–Johnson transformation (YJ) and principal component analysis (PCA). The race ANOVA method across resample data is used to tune the best hyperparameters for each model. The model candidates and the role of different pre-processors are evaluated based on standard ML metrics – coefficient of determination (R2), root mean squared error (RMSE), and mean absolute error (MAE). The model stacking is performed on five model candidates: two KNN, two XGB, and one SVM PCA with a marginal role. The results of the ensemble model showed superior accuracy over single learners, with all metrics (R2 0.890, RMSE 0.0252, MAE 0.168). It also turned out to be almost three times better than the neural net (NN) results obtained from commercial software on the same testing set (R2 0.318, RMSE 0.0628, MAE 0.0487). The spatial distribution of porosity from the ensemble model indicated areas of good reservoir properties that overlap with hydrocarbon production fields. This observation completes the evaluation of the ensemble technique results from model metrics. Overall, the proposed solution is a promising tool for better porosity prediction and understanding of heterogeneous carbonate reservoirs from multiple seismic attributes.

3

Performance analysis of data fusion methods applied to epileptic seizure recognition

Ludwig Simone A.

Journal of Artificial Intelligence and Soft Computing Research

|

2022

|

Vol. 12, No. 1

5--17

EN

Epilepsy is a chronic neurological disorder that is caused by unprovoked recurrent seizures. The most commonly used tool for the diagnosis of epilepsy is the electroencephalogram (EEG) whereby the electrical activity of the brain is measured. In order to prevent potential risks, the patients have to be monitored as to detect an epileptic episode early on and to provide prevention measures. Many different research studies have used a combination of time and frequency features for the automatic recognition of epileptic seizures. In this paper, two fusion methods are compared. The first is based on an ensemble method and the second uses the Choquet fuzzy integral method. In particular, three different machine learning approaches namely RNN, ML and DNN are used as inputs for the ensemble method and the Choquet fuzzy integral fusion method. Evaluation measures such as confusion matrix, AUC and accuracy are compared as well as MSE and RMSE are provided. The results show that the Choquet fuzzy integral fusion method outperforms the ensemble method as well as other state-of-the-art classification methods.

4

Development of novel ensemble model using stacking learning and evolutionary computation techniques for automated hepatocellular carcinoma detection

Ksiazek Wojciech, Hammad Mohamed, Plawiak Pawel, Acharya U. Rajendra, Tadeusiewicz Ryszard

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 4

1512--1524

EN

The most common type of liver cancer is hepatocellular carcinoma (HCC), which begins in hepatocytes. The HCC, like most types of cancer, does not show symptoms in the early stages and hence it is difficult to detect at this stage. The symptoms begin to appear in the advanced stages of the disease due to the unlimited growth of cancer cells. So, early detection can help to get timely treatment and reduce the mortality rate. In this paper, we proposes a novel machine learning model using seven classifiers such as K-nearest neighbor (KNN), random forest, Naïve Bayes, and other four classifiers combined to form stacking learning (ensemble) method with genetic optimization helping to select the features for each classifier to obtain highest HCC detection accuracy. In addition to preparing the data and make it suitable for further processing, we performed the normalization techniques. We have used KNN algorithm to fill in the missing values. We trained and evaluated our developed algorithm using 165 HCC patients collected from Coimbra's Hospital and University Centre (CHUC) using stratified cross-validation techniques. There are total of 49 clinically significant features in this dataset, which are divided into two groups such as quantitative and qualitative groups. Our proposed algorithm has achieved the highest accuracy and F1-score of 0.9030 and 0.8857, respectively. The developed model is ready to be tested with huge database and can be employed in cancer screening laboratories to aid the clinicians to make an accurate diagnosis.