Fault Detection and Identification of COSMED K4b2 Based On PCA and Neural Network

COSMED K4b2 is a portable electrical device designed to test pulmonary functions. It is ideal for many applications that need the measurement of the cardio-respiratory response either in the field or in the lab is capable with the capability to delivery real time data to a sink node or a PC base station with storing data in the memory at the same time. But the actual sensor outputs and data received may contain some errors, such as impulsive noise which can be related to sensors, low batteries, environment or disturbance in data acquisition process. These abnormal outputs might cause misinterpretations of exercise or living activities to persons being monitored. In our paper we propose an effective and feasible method to detect and identify errors in applications by principal component analysis (PCA) and a back propagation (BP) neural network.

• Jing Zhou
• Steven Su
• Aihuang Guo

• BP Neural Network
• Exercising Testing
• Fault Detection and Identification
• Principal Component Analysis.

[1] COSMED K4b2 Cardio Pulmonary Exercise Testing (Online).Available:
http://www.cosmed.com/images/pdf/productliterature/K4b2_Brochure_
EN_C09052-02-93_A4_web.pdf.
[2] R. Duffield, B. Dawson, H. Pinnington, and P. Wong, "Accuracy and
reliability of a Cosmed K4b 2 portable gas," Sci Med Sport, vol. 7, no.1,
pp. 11-22, Jan. 2004.
[3] C. Srl, "K4b2 User manual, XVIII Edition," Rome, Italy:
http://www.cosmed.it.
[4] W.Haerdle and L. Simar, Applied Multivariate Statistical Analysis,
Second Edition. Heidelberg: Springer, pp. 37-41, 2007.
[5] L. H. Xie Tingfeng, Wu Jianjun, "Fault Detection and Diagnosis for
Sensors of LRE Based on PCA," Journal of Astronautics, vol. 28, no.1,
pp. 668-1672, 1703, Jan, 2007.
[6] L. Yu, J.-h. Zhu and L.-j. Chen, "Parametric Study on PCA-based
Algorithm for Structural Health," in 2010 the Prognostics & System
Health Management Conference, pp.1-6.
[7] P. Picton, Neural Networks. New York: Palgrave Houndmills, pp.
215-229, 2000.
[8] J. Liu, H. Chang, T.Y.Hsu, and X. Ruan, "Prediction of the flow stress of
high-speed steel during hot performation using a BP artifical neural
network," Journal of Materials Processing Technology vol. 103, no.2, pp.
200-205, Feb, 2000.
[9] Y. Wang, D. Gu, J. Xu, and J. Li, "Back Propagation Neural Network for
Short-term Electricity Load Forecasting with Weather Features," in 2009
International Conference on Computational Intelligence and Natural
Computing , pp. 58-61.