Compression of Anuran Vocalizations for Species Classification Using Wireless Sensor Networks

• Javier J. M. Diaz UFAM
• Juan G. Colonna UFAM
• Rodrigo B. Soares UFAM
• Eduardo F Nakamura UFAM / FUCAPI
• Carlos M. S. Figueiredo FUCAPI

Abstract

One of the most common problems in Wireless Sensor Networks (WSN) is to collect enough data to analyze some phenomenon and to maximize the network lifetime. By using an anura (frogs and toads) classification example, this paper shows how it is possible to significantly decrease the amount of samples collected without compromising the classification results. To do that, is proposed a methodology using Compressive Sensing (CS) that allows partially collected signal reconstruction. This is done by using a sparse basis that best represents the information used by the classifying software. We show how it is possible to keep a classification rate near to 98% using only 10% of the original data, beside the impact of this compression on the energy consumption, delivery rate and average delay of the network

References

Aelterman, J., Luong, H. Q., Goossens, B., Pi, A. U., and Philips, W. (2010). Compass: a joint framework for parallel imaging and compressive sensing in mri. Image Proceesing (ICIP).

Baraniuk, R. (2007). Compreesive sensing. IEEE Signal Processing Magazine.

Buluso, N. and Hu, W. (2008). Lightweight acoustic classification for cane toad monitoring. Asimolar Conference on Signals, Systems and Computers.

Candes, E. J. and Waking, M. B. (2008). An introduction to compressed sampling. Signal Processing Magazine.

Carey, C., Heyer, W. R., Wilkinson, J., a. Alford, R., Arntzen, J. W., Halliday, T., Hungerford, L., Lips, K. R., Middleton, E. M., a. Orchard, S., and Rand, S. (2001). Amphibian declines and environmental change: Use of remote-sensing data to identify environmental correlates. Conservation Biology.

Cheng, X., Wang, F., and Liu, J. (2008). Hybrid push-pull for data diffusion in sensor networks without location information. International Conference on Communications (ICC).

Colonna, J. G., Nakamura, E. F., and dos Santos, E. M. (2011). Classificação de anuros baseado em vocalizações para monitoramento ambiental pervasivo. Simpósio Brasileiro de Computação Ubíqua (SBCUP).

Davis, S. and Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech, and Signal Processing.

Fall, K. and Varadhan, K. (2010). The ns manual. [link].

Figueiredo, M. A. T., Nowak, R. D., and Wright, S. J. (2007). Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems. IEEE Journal of Selected Topics in Signal Processing.

Gowrishankar, S., Basavaraju, T. G., Manjaiah, D. H., and Sarkar, S. K. (2008). Issues in wireless sensor networks. Proceedings of the World Congress on Engineering.

Hempstead, Q. W. and Yang, M. (2006). A realistic power consumption model for wireless sensor network devices. Sensor and Ad Hoc Communications and Networks (SECON).

Hu, W., Tran, V. N., Bulusu, N., Chou, C. T., Jha, S., and Taylor, A. (2005). The design and evaluation of a hybrid sensor network for cane-toad monitoring. Symposium on Information Processing in Sensor Networks.

Huang, J. C., Yang, Y. J., Yang, D. X., and Chen, J. Y. (2009). Frog classification using machine learning techniques. Expert Systems with Applications.

Ji, S. and Carin, L. (2007). Bayesian compressive sensing and projection optimization. International Conference on Machine Learning (ICML).

Ji, S., Dunson, D., and Carin, L. (2009). Multi-task compressive sensing. IEEE Transactions on Signal Processing.

Luo, J., Xiang, L., and Rosenberg, C. (2010). Does compressed sensing improve the throughput of wireless sensor networks? IEEE International Conference on Communications (ICC).

Mainwaring, A., Polastre, J., Szewczyk, R., and Culler, D. (2002). Wireless sensor networks for habitat monitoring. Proceedings of the 1st ACM international workshop on Wireless sensor networks and applications.

Riede, K. (1993). Monitoring biodiversity: analysis of amazonian rainforest sounds. Ambio.

Rocha, V. and Gonçalves, G. (2008). Sensing the world: Challenges on wsns. Automation, Quality and Testing, Robotics. (AQTR).

Taylor, A., Watson, G., Grigg, G., and a. McCallum, H. (1996). Monitoring frog communities: An application of machine learning. Proceedings of the 8th Innovative Applications of Artificial Intelligence Conference (IAAI).

Wang, J., Cho, J., and Lee, S. (2011). An adaptive power-aware multi-hop routing algorithm for wireless sensor networks. Information Technology: New Generations (ITNG).