Browsing by Subject "feature selection"

Now showing 1 - 4 of 4

Access status: Open Access ,
Analysis of data pre-processing methods for sentiment analysis of reviews
(Wydawnictwa AGH, 2019) Parlar, Tuba; Özel, Selma Ayşe; Song, Fei
The goals of this study are to analyze the effects of data pre-processing methods for sentiment analysis and determine which of these pre-processing methods (and their combinations) are effective for English as well as for an agglutinative language like Turkish. We also try to answer the research question of whether there are any differences between agglutinative and non-agglutinative languages in terms of pre-processing methods for sentiment analysis. We find that the performance results for the English reviews are generally higher than those for the Turkish reviews due to the differences between the two languages in terms of vocabularies, writing styles, and agglutinative property of the Turkish language.
Access status: Open Access ,
Applying Hunger Game Search (HGS) for selecting significant blood indicators for early prediction of ICU COVID-19 severity
(Wydawnictwa AGH, 2023) Sayed, Safynaz AbdEl-Fattah; ElKorany, Abeer; Sayed, Sabah
This paper introduces an early prognostic model for attempting to predict the severity of patients for ICU admission and detect the most significant features that affect the prediction process using clinical blood data. The proposed model predicts ICU admission for high-severity patients during the first two hours of hospital admission, which would help assist clinicians in decision-making and enable the efficient use of hospital resources. The Hunger Game search (HGS) meta-heuristic algorithm and a support vector machine (SVM) have been integrated to build the proposed prediction model. Furthermore, these have been used for selecting the most informative features from blood test data. Experiments have shown that using HGS for selecting features with the SVM classifier achieved excellent results as compared with four other meta-heuristic algorithms. The model that used the features that were selected by the HGS algorithm accomplished the topmost results (98.6 and 96.5%) for the best and mean accuracy, respectively, as compared to using all of the features that were selected by other popular optimization algorithms.
Access status: Open Access ,
Assessment of nature-inspired algorithms for text feature selection
(Wydawnictwa AGH, 2022) Çoban, Önder
This paper provides a comprehensive assessment of basic feature selection (FS) methods that have originated from nature-inspired (NI) meta-heuristics, two well-known filter-based FS methods are also included for comparison. The performances of the considered methods are compared on four balanced highdimensional and real-world text data sets regarding the accuracy, the number of selected features, and computation time. This study differs from existing studies in terms of the extent of experimental analyses that were performed under different circumstances where the classifier, feature model, and term-weighting scheme were different. The results of the extensive experiments indicated that basic NI algorithms produce slightly different results than filter-based methods for the text FS problem. However, filter-based methods often provide better results by using lower numbers of features and computation times.
Access status: Open Access ,
Zastosowanie kwantowych algorytmów genetycznych do selekcji cech
(Wydawnictwa AGH, 2009) Jopek, Łukasz; Nowotniak, Robert; Postolski, Michał; Babout, Laurent; Janaszewski, Marcin Sławomir
In the article a feature selection problem for k-NN classifier in image segmentation has been analyzed. Feature selection has been considered as a two criteria combinatorial optimization problem. An objective of optimization process was to find a feature subset of image points, allowing good quality of segmentation in satisfactory time. A fitness function for feature subsets has been proposed, taking into account time needed for calculation of feature values and quality of segmentation. Three population-based heuristic methods of optimization have been compared: simple genetic algorithm and its two modifications, inspired by principles of quantum computing: QiGA (Quantum-Inspired Genetic Algorithm) and GAQPR (Genetic Algorithm with Quantum Probability Representation). Results of experiments with artificial and tomography textures have been presented.