Due to its relevant real-life applications, the recognition of emotions from speech signals constitutes a popular research topic. In the traditional methods applied for speech emotion recognition, audio features are typically aggregated using a fixed-duration time window, potentially discarding information conveyed by speech at various signal durations. By contrast, in the proposed method, audio features are aggregated simultaneously using time windows of different lengths (a multi-time-scale approach), hence, potentially better utilizing information carried at phonemic, syllabic, and prosodic levels compared to the traditional approach. A genetic algorithm is employed to optimize the feature extraction procedure. The features aggregated at different time windows are subsequently classified by an ensemble of support vector machine (SVM) classifiers. To enhance the generalization property of the method, a data augmentation technique based on pitch shifting and time stretching is applied. According to the obtained results, the developed method outperforms the traditional one for the selected datasets, demonstrating the benefits of using a multi-time-scale approach to feature aggregation.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Objectives: This research work exclusively aims to develop a novel heart disease prediction framework including three major phases, namely proposed feature extraction, dimensionality reduction, and proposed ensemble-based classification. Methods: As the novelty, the training of NN is carried out by a new enhanced optimization algorithm referred to as Sea Lion with CanberraDistance (S-CDF) via tuning the optimal weights. The improved S-CDF algorithm is the extended version of the existing “Sea Lion Optimization (SLnO)”. Initially, the statistical and higher-order statistical features are extracted including central tendency, degree of dispersion, and qualitative variation, respectively. However, in this scenario, the “curse of dimensionality” seems to be the greatest issue, such that there is a necessity of dimensionality reduction in the extracted features. Hence, the principal component analysis (PCA)- based feature reduction approachis deployed here. Finally, the dimensional concentrated features are fed as the input to the proposed ensemble technique with “Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN)” with optimized Neural Network (NN) as the final classifier. Results: An elaborative analyses as well as discussion have been provided by concerning the parameters, like evaluation metrics, year of publication, accuracy, implementation tool, and utilized datasets obtained by various techniques. Conclusions: From the experiment outcomes, it is proved that the accuracy of the proposed work with the proposed feature set is 5, 42.85, and 10% superior to the performance with other feature sets like central tendency + dispersion feature, central tendency qualitative variation, and dispersion qualitative variation, respectively. Results: Finally, the comparative evaluation shows that the presented work is appropriate for heart disease prediction as it has high accuracy than the traditional works.
The paper presents an ensemble classification method based on clustering, along with its implementation in the Python programming language. An illustrative example showing the method behavior is provided, and the results of a computational experiment performed on real life data sets are reported.
4
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The use of ensemble of classifiers for classification of medical data derived from diagnostic devices has been proposed in this research. The experimental studies were carried out on three datasets concerning different medical problems: arrhythmia, breast cancer and coronary artery disease using SPECT images. The comparison of single classification algorithms (kNN- IBk, C4.5 - J48, Naïve Bayes, Random Tree and SMO) with bagging, boosting and majority voting using all single classifiers was performed. Experimental studies have proved that hybrid classifiers outperformed single classification in all cases in terms of accuracy, precision, sensitivity and root squared mean error, regardless of the dataset.
PL
W ramach niniejszej pracy zaproponowane zostało zastosowanie komitetów klasyfikatorów w procesie klasyfikacji danych pochodzących z urządzeń medycznych. Badania eksperymentalne zostały przeprowadzone na trzech zbiorach danych dotyczących różnych problemów medycznych: arytmii, nowotworu piersi oraz choroby wieńcowej. Przeprowadzono porównanie pojedynczych technik klasyfikacji (kNNIBk, C4.5 - J48, Naïve Bayes, Random Tree oraz SMO) z metodami hybrydowymi (bagging, boosting oraz głosowanie większościowe). Badania eksperymentalne wykazały skuteczność klasyfikacji z zastosowaniem komitetów klasyfikatorów – w wszystkich badanych przypadkach rezultaty klasyfikacji hybrydowej były lepsze od wyników najlepszego pojedynczego klasyfikatora biorąc pod uwagę dokładność, precyzję, czułość oraz błąd średniokwadratowy.
5
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Several recent studies have explored the virtues of behavioral targeting and personalization for online advertising. In this paper, we add to this literature by proposing a cost-effective methodology for the prediction of demographic website visitor profiles that can be used for web advertising targeting purposes. The methodology involves the transformation of website visitors' clickstream patterns to a set of features and the training of Random Forest classifiers that generate predictions for gender, age, level of education and occupation category. These demographic predictions can support online advertisement targeting (i) as an additional input in personalized advertising or behavioral targeting, or (ii) as an input for aggregated demographic website visitor profiles that support marketing managers in selecting websites and achieving an optimal correspondence between target groups and website audience composition. The proposed methodology is validated using data from a Belgian web metrics company. The results reveal that Random Forests demonstrate superior classification performance over a set of benchmark algorithms. Further, the ability of the model set to generate representative demographic website audience profiles is assessed. The stability of the models over time is demonstrated using out-of-period data.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.