Left behind occupant recognition in parked cars based on acceleration and pressure information using k-Nearest-Neighbor classification

One of the major causes of lethal or serious injuries to children in non-traffic accidents with cars is founded on the unattended left behind of them in parked cars. Therefore, Delphi's safety division is interested in the development of a low cost left behind occupant recognition, so that since 2008 different approaches for a reliable detection system are evaluated. One of them is based on high sensitive analogue accelerometers that monitor vibrations occurring at the car chassis. The investigations show a recognizable signal produced by human beings seated in a parked car which provides enough information to determine the occupancy state of a car. The presented contribution describes the additional use of a second sensor (pressure signal) input to improve the classification reliability by fusing the information of both sensing elements. This is illustrated at the k-Nearest-Neighbor algorithm as preferred classifier.

[1]  K. Lyons,et al.  Handbook of Essential Tremor and Other Tremor Disorders , 2005 .

[2]  A. Kruczek,et al.  A full-car model for active suspension - some practical aspects , 2004, Proceedings of the IEEE International Conference on Mechatronics, 2004. ICM '04..

[3]  A. Prochazka,et al.  Wavelet transform use for feature extraction and EEG signal segments classification , 2008, 2008 3rd International Symposium on Communications, Control and Signal Processing.

[4]  T C Grey,et al.  Fatal car trunk entrapment involving children--United States, 1987-1998. , 1998, MMWR. Morbidity and mortality weekly report.

[5]  Munna Khan,et al.  A Review of Measurement and Analysis of Heart Rate Variability , 2009, 2009 International Conference on Computer and Automation Engineering.

[6]  M Mitschke.  DYNAMIK DER KRAFTFAHRZEUGE - BAND B: SCHWINGUNGEN , 1997 .

[7]  Michel F. Sultan,et al.  Monitoring Driver Physiological Parameters for Improved Safety , 2006 .

[8]  Zhongwei Jiang,et al.  Comparison of envelope extraction algorithms for cardiac sound signal segmentation , 2008, Expert Syst. Appl..

[9]  Bernd Tibken,et al.  Left Behind Occupant Recognition Based on Human Tremor Detection via Accelerometers Mounted at the Car Body , 2009 .

[10]  Michael Spickenreuther.  Funktionsmodell der Karosserie zur Auslegung des Schwingungskomforts im Gesamtfahrzeug , 2006 .

[11]  Patrick Gaydecki,et al.  The use of the Hilbert transform in ECG signal analysis , 2001, Comput. Biol. Medicine.

[12]  Nong Ye,et al.  The Handbook of Data Mining , 2003 .

[13]  Favret Ag,et al.  Fetal electrocardiographic wave forms from abdominal-wall recordings. , 1966 .

[14]  Mehmet Engin,et al.  The classification of human tremor signals using artificial neural network , 2007, Expert Syst. Appl..

[15]  A. Favret,et al.  Fetal Electrocardiographic Wave Forms from Abdominal‐Wall Recordings , 1966, Obstetrics and gynecology.

[16]  Marwa I. Obayya,et al.  Classification of heart rate variability signals using higher order spectra and neural networks , 2009, 2009 International Conference on Networking and Media Convergence.

[17]  Szi-Wen Chen,et al.  A wavelet-based heart rate variability analysis for the study of nonsustained ventricular tachycardia , 2002, IEEE Trans. Biomed. Eng..

[18]  Stanislaw Osowski,et al.  Higher order statistics and neural network for tremor recognition , 2002, IEEE Transactions on Biomedical Engineering.

[19]  Bohn Stafleu van Loghum,et al.  Online … , 2002, LOG IN.

[20]  K Hardie,et al.  DATA COLLECTION STUDY: DEATHS AND INJURIES RESULTING FROM CERTAIN NON-TRAFFIC AND NON-CRASH EVENTS , 2004 .