TY - GEN
T1 - A CNN-based mosquito classification using image transformation of wingbeat features
AU - Luna-Gonzalez, Jose Alvaro
AU - Robles-Camarillo, Daniel
AU - Nakano-Miyatake, Mariko
AU - Lanz-Mendoza, Humberto
AU - Perez-Meana, Hector
N1 - Publisher Copyright:
© 2020 The authors and IOS Press. All rights reserved.
PY - 2020/9/15
Y1 - 2020/9/15
N2 - In this paper, a classification of mosquito's specie is performed using mosquito wingbeats samples obtained by optical sensor. Six world-wide representative species of mosquitos, which are Aedes aegypti, Aedes albopictus, Anopheles arabiensis, Anopheles gambiae and Culex pipiens, Culex quinquefasciatus, are considered for classification. A total of 60, 000 samples are divided equally in each specie mentioned above. In total, 25 audio feature extraction algorithms are applied to extract 39 feature values per sample. Further, each audio feature is transformed to a color image, which shows audio features presenting by different pixel values. We used a fully connected neural networks for audio features and a convolutional neural network (CNN) for image dataset generated from audio features. The CNN-based classifier shows 90.75% accuracy, which outperforms the accuracy of 87.18% obtained by the first classifier using directly audio features.
AB - In this paper, a classification of mosquito's specie is performed using mosquito wingbeats samples obtained by optical sensor. Six world-wide representative species of mosquitos, which are Aedes aegypti, Aedes albopictus, Anopheles arabiensis, Anopheles gambiae and Culex pipiens, Culex quinquefasciatus, are considered for classification. A total of 60, 000 samples are divided equally in each specie mentioned above. In total, 25 audio feature extraction algorithms are applied to extract 39 feature values per sample. Further, each audio feature is transformed to a color image, which shows audio features presenting by different pixel values. We used a fully connected neural networks for audio features and a convolutional neural network (CNN) for image dataset generated from audio features. The CNN-based classifier shows 90.75% accuracy, which outperforms the accuracy of 87.18% obtained by the first classifier using directly audio features.
KW - Audio processing
KW - Classification
KW - Convolutional neural networks
KW - Feature extraction
KW - Image-transformed information
KW - Mosquitoes
UR - http://www.scopus.com/inward/record.url?scp=85092714753&partnerID=8YFLogxK
U2 - 10.3233/FAIA200559
DO - 10.3233/FAIA200559
M3 - Contribución a la conferencia
AN - SCOPUS:85092714753
T3 - Frontiers in Artificial Intelligence and Applications
SP - 127
EP - 137
BT - Knowledge Innovation Through Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 19th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2020
A2 - Fujita, Hamido
A2 - Selamat, Ali
A2 - Omatu, Sigeru
PB - IOS Press BV
T2 - 19th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2020
Y2 - 22 September 2020 through 24 September 2020
ER -