Applied Sciences, Free Full-Text
Por um escritor misterioso
Last updated 11 março 2025

The domestic cat (Feliscatus) is one of the most attractive pets in the world, and it generates mysterious kinds of sound according to its mood and situation. In this paper, we deal with the automatic classification of cat sounds using machine learning. Machine learning approach for the classification requires class labeled data, so our work starts with building a small dataset named CatSound across 10 categories. Along with the original dataset, we increase the amount of data with various audio data augmentation methods to help our classification task. In this study, we use two types of learned features from deep neural networks; one from a pre-trained convolutional neural net (CNN) on music data by transfer learning and the other from unsupervised convolutional deep belief network that is (CDBN) solely trained on a collected set of cat sounds. In addition to conventional GAP, we propose an effective pooling method called FDAP to explore a number of meaningful features. In FDAP, the frequency dimension is roughly divided and then the average pooling is applied in each division. For the classification, we exploited five different machine learning algorithms and an ensemble of them. We compare the classification performances with respect following factors: the amount of data increased by augmentation, the learned features from pre-trained CNN or unsupervised CDBN, conventional GAP or FDAP, and the machine learning algorithms used for the classification. As expected, the proposed FDAP features with larger amount of data increased by augmentation combined with the ensemble approach have produced the best accuracy. Moreover, both learned features from pre-trained CNN and unsupervised CDBN produce good results in the experiment. Therefore, with the combination of all those positive factors, we obtained the best result of 91.13% in accuracy, 0.91 in f1-score, and 0.995 in area under the curve (AUC) score.

Applied Sciences An Open Access Journal from MDPI

Applied Sciences An Open Access Journal from MDPI

Advanced Science - Wiley Online Library

Applied Sciences An Open Access Journal from MDPI

Applied Sciences, Free Full-Text

Free Delivery & Gift WrappingApplied Sciences, Free Full-Text, vibration at certain rpm

15+ Applied Sciences Books for Free! [PDF]
Help - PubMed

Applied Sciences An Open Access Journal from MDPI

Horticulturae, Free Full-Text
40+ Professional Resume Templates for 2023 - Free Downloads
Recomendado para você
-
Angry Cat Sounds and Pictures Prank Your Dog - Excite Your Dog11 março 2025
-
6 Subtle Signs Your Cat is Secretly Mad At You – Meowingtons11 março 2025
-
Mad Cat Sound /f/, By Bjorem Speech Publications11 março 2025
-
Second Life Marketplace - Sound Effect: Upset Cat *FULL PERM*11 março 2025
-
Second Life Marketplace - Gesture: Cat Raaaaar!!!11 março 2025
-
Different Cat Sounds And What They Mean - Ultimate Pet Nutrition11 março 2025
-
Why Do Cats Hiss?11 março 2025
-
Angry Cat Prank Meme Button for Android - Free App Download11 março 2025
-
Angry Cat11 março 2025
-
What Does It Mean When A Cat Is Screaming?11 março 2025
você pode gostar
-
Microsoft Flight Simulator: Veja os requisitos para rodar o jogo no seu PC11 março 2025
-
Figura Articulável Power Players 30cm - Masko - Sunny - Baianão11 março 2025
-
Desenho de medico atendendo paciente [download] - Designi11 março 2025
-
New Super Tails & Super Silver Funko Figures Announced – SoaH City11 março 2025
-
Pokemon Trading Card Game: Miraidon ex and Regieleki ex VMAX11 março 2025
-
Warner Bros. games and Call of Duty franchise discounted on Steam11 março 2025
-
Download Guide For : Toca Life World Free on PC with MEmu11 março 2025
-
Level List, Backrooms Wiki11 março 2025
-
Assistir anime Ore No Imouto Ga Konna Ni Kawaii Wake Ga Nai Online11 março 2025
-
Demi Lovato - Cool for the Summer [Tradução] (Clipe Legendado) ᴴᴰ11 março 2025