In this study, the effect of Short-time Mean and Variance Normalization (STMVN), Shorttime Cepstral Mean and Scale Normalization (STMSN), Min-Max Normalization, Z-Score Normalization and Standard Deviation Normalization techniques on the classification performance was investigated in determining speakers' gender. In the study, voice records which belongs to 192 male and 192 female speakers from TIMIT data set were used as data set. Features were extracted from Mel Frequency Cepstral Coefficients (MFCC) technique by using voice records and extracted features' dimension was reduced to Principal Component Analysis (PCA), then normalized with different techniques. Support Vector Machine (SVM) was used as classifier. As a result of study, it was observed that, the highest accuracy in speakers' gender estimation is obtained as 98.18% from features which were normalized with Standard Deviation Normalization technique and other normalization techniques were reduced accuracy.
Bu çalışmada, Harmoni Arama algoritmasının (Harmony Search algorithm, HSA) mevcut veriden faydalanarak başlangıç çözümlerini üretme yaklaşımı ile güçlendirilmiş varyantı olan Kaynak-Bağlantılı Harmoni Arama algoritmasının (Source-Linked HSA, slinkHSA) performansı elektroensefalografi (EEG) sinyallerinde gürültü minimizasyonu gerektiren büyük veri optimizasyonu üzerinden incelenmiştir. slinkHSA ile elde edilen sonuçlar diğer meta-sezgisel teknikler tarafından bulunan sonuçlar üzerinden kıyaslanmıştır. Karşılaştırmalar, başlangıç harmonilerini EEG sinyalleri kullanılarak üretmenin çözümlerinin kalitesini önemli ölçüde katkıda bulunduğunu ve algoritmanın yakınsama hızını artırdığını göstermiştir.
Theoretical applications and practical network algorithms are not very cost-effective, and most of the algorithms in the commercial market are implemented in the cutting-edge devices. Open-source network simulators have gained importance in recent years due to the necessity to implement network algorithms in more realistic scenarios with reasonable costs, especially for educational purposes and scientific researches. Although there have been various simulation tools, NS2 and NS3, OMNeT++ is more suitable to demonstrate network algorithms because it is convenient for the model establishment, modularization, expandability, etc. OMNeT++ network simulator is selected as a testbed in order to verify the correctness of the network algorithms. The study focuses on the algorithms based on centralized and distributed approaches for multi-hop networks in OMNeT++. Two network algorithms, the shortest path algorithm and flooding-based asynchronous spanning tree algorithm, were examined in OMNeT++. The implementation, analysis, and visualization of these algorithms have also been addressed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.