© The Institution of Engineering and Technology
A novel acoustic insect classifier on deep convolutional feature of frequency spectrum images generated by their wingbeat sounds is introduced. By visualising insect wingbeat sound, the proposed method is the first attempt to convert time-series acoustic signal processing to image recognition, which has recently gained significant improvement with convolutional neural networks. Experiments show the better accuracy of the proposed method on the public UCR flying insect datasets compared with the state-of-the-art methods.
References
-
-
1)
-
4. Chen, Y., Why, A., Batista, G., et al: ‘Flying insect classification with inexpensive sensors’, J. Insect Behav., 2014, 27, (5), pp. 657–677, (doi: 10.1007/s10905-014-9454-4).
-
2)
-
6. Sun, Y., Chen, Y., Wang, X., et al: ‘Deep learning face representation from predicting 10,000 classes’. Advances in Neural Information Processing Systems (NIPS), Montreal, Canada, December 2014, pp. 1988–1996, .
-
3)
-
1. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Advances in Neural Information Processing Systems (NIPS), Nevada, USA, December 2012, pp. 1097–1105, .
-
4)
-
3. Girshick, R., Donahue, J., Darrell, T.: ‘Rich feature hierarchies for accurate object detection and semantic segmentation’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Ohio, USA, June 2014, pp. 580–587, .
-
5)
-
2. Ouyang, W., Zeng, X., Wang, X.: ‘Modeling mutual visibility relationship in pedestrian detection’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Oregon, USA, June 2013, pp. 3222–3229, .
-
6)
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.3334
Related content
content/journals/10.1049/el.2017.3334
pub_keyword,iet_inspecKeyword,pub_concept
6
6