TY - GEN
T1 - LSTM-based mosquito genus classification using their wingbeat sound
AU - Toledo, Edmundo
AU - Gonzalez, Jose
AU - Nakano, Mariko
AU - Robles, Daniel
AU - Hernandez, Adrian
AU - Perez, Hector
AU - Lanz, Humberto
AU - Cime, Jorge
N1 - Publisher Copyright:
© 2021 The authors and IOS Press. All rights reserved.
PY - 2021/9/8
Y1 - 2021/9/8
N2 - In this paper, we propose Long-Short Term Memory (LSTM)-based mosquito's genus classification, in which the time-frequency features are extracted from the wingbeat sound of mosquitos of three genera, Aedes, Anopheles and Culex. The extracted features are fed into the proposed LSTM-based classifier. We evaluated three time-frequency features, which are: Mel Spectrogram, Log-Mel spectrogram, and Mel-frequency Cepstral Coefficients (MFCC). The proposed scheme is composed by two LSTM layers and one Fully Connected layer connected to a SoftMax activation function. The classification accuracies using the three features are 92.97(±0.2)%, 96.71(±0.2)% and 96.65(±0.2)%, respectively. The Area Under Curve (AUC) of the Receiver Operating Characteristics (ROC) for each feature are also obtained, which are 0.9944, 0.9986 and 0.9987, respectively. The proposed classifier requires approximately 62,000 trainable parameters. This number is much smaller than that required for the state-of-Arts CNNs, such as AlexNet and Vgg16. This compact configuration of the proposed scheme takes advantage of the mobile and IoT implementation, because the number of trainable parameters is directly proportional to the amount of memory and CPU required.
AB - In this paper, we propose Long-Short Term Memory (LSTM)-based mosquito's genus classification, in which the time-frequency features are extracted from the wingbeat sound of mosquitos of three genera, Aedes, Anopheles and Culex. The extracted features are fed into the proposed LSTM-based classifier. We evaluated three time-frequency features, which are: Mel Spectrogram, Log-Mel spectrogram, and Mel-frequency Cepstral Coefficients (MFCC). The proposed scheme is composed by two LSTM layers and one Fully Connected layer connected to a SoftMax activation function. The classification accuracies using the three features are 92.97(±0.2)%, 96.71(±0.2)% and 96.65(±0.2)%, respectively. The Area Under Curve (AUC) of the Receiver Operating Characteristics (ROC) for each feature are also obtained, which are 0.9944, 0.9986 and 0.9987, respectively. The proposed classifier requires approximately 62,000 trainable parameters. This number is much smaller than that required for the state-of-Arts CNNs, such as AlexNet and Vgg16. This compact configuration of the proposed scheme takes advantage of the mobile and IoT implementation, because the number of trainable parameters is directly proportional to the amount of memory and CPU required.
KW - Long-Short Term Memory
KW - Mosquito classification
KW - Time-frequency features
KW - Wingbeat sound
UR - http://www.scopus.com/inward/record.url?scp=85116437511&partnerID=8YFLogxK
U2 - 10.3233/FAIA210028
DO - 10.3233/FAIA210028
M3 - Contribución a la conferencia
AN - SCOPUS:85116437511
T3 - Frontiers in Artificial Intelligence and Applications
SP - 293
EP - 302
BT - New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 20th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2021
A2 - Fujita, Hamido
A2 - Perez-Meana, Hector
PB - IOS Press BV
T2 - 20th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2021
Y2 - 21 September 2021 through 23 September 2021
ER -