Selected algorithms of MEMS accelerometers signal processing in burglary detector application

• Autorzy: Fabiański B. , Nowopolski K. , Wicher B.
• Konferencja: Computer Applications in Electrical Engineering (18-19.04.2016 ; Poznań, Polska)
• Języki publikacji: EN

Abstrakty

EN

In the paper, implementations and results of operation of artificial neural network applied as a burglary classifier are presented in comparison to solution with a direct digital signal processing (DSP) approach. The neural network operates in a mobile access control device, that may be easily attached to a door. The device is an integrated system, equipped with several sensors based on microelectromechanical systems (MEMS) technology. Due to limited effectiveness of simple, conditional logic algorithms on acquired signal samples, a more sophisticated approaches are investigated. Data acquisition during imitation of various burglary scenarios and further processing of the recorded signals are described in the paper. Selection of the neural network structure and pre-processing methods of sensor signals are presented as well. The direct DSP algorithm based on the application of the properties of application phenomena is shown in the same way. Finally, results of selected algorithms implementation in a low-power 32-bit microcontroller system are presented. Limitation of the platform responsiveness in the real-time conditions and comparison of used classification methods are discussed in the paper conclusions.

Słowa kluczowe

EN

MEMS; accelerometer sensor; data streaming; DSP; low-power MCU; alarm system; artificial neural network

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Poznan University of Technology Academic Journals. Electrical Engineering
• Rocznik: 2016
• Tom: No. 87
• Strony: 267--278
• Opis fizyczny: Bibliogr. 9 poz., rys., tab.

Twórcy

autor

Fabiański B.

• Poznan University of Technology

autor

Nowopolski K.

• Poznan University of Technology

autor

Wicher B.

• Poznan University of Technology

Bibliografia

• [1] S. Finkbeiner, MEMS for automotive and consumer electronics, in Solid-State Device Research Conference (ESSDERC), 2013 Proceedings of the European, 2013, pp. 9–14.
• [2] M. Perlmutter and L. Robin, High-performance, low cost inertial MEMS: A market in motion!, in Position Location and Navigation Symposium (PLANS), 2012 IEEE/ION, 2012, pp. 225–229.
• [3] STM32L052R8 Ultra-low power ARM Cortex-M0+ MCU with 64 Kbytes Flash, 32 MHz CPU, USB – STMicroelectronics, 09-Feb-2016. [Online]. Available: http://www.st.com/web/catalog/mmc/FM141/SC1169/SS1817/LN184.
• [4] B. Fabiański, K. Nowopolski and B. Wicher, The System of Streaming and Analysis of Signals from MEMS Accelerometers, Poznan University of Technology Academic Journals, 2016.
• [5] S. Awasthi and A. Joshi, MEMS accelerometer based system for motion analysis, in 2015 2nd International Conference on Electronics and Communication Systems (ICECS), 2015, pp. 762–767.
• [6] B. Fabianski, Embedded System of Critical Information Management, Poznan University of Technology Academic Journals, pp. 143–149, 2013.
• [7] Y.Y. Chen, S.-J. Chang, C.-Y. Huang, and C.Y. Hsinag, An Elimination Design for drift rate effects of MEMS-Based Inertial Devices, in Microsystems, Packaging, Assembly Circuits Technology Conference, 2008. IMPACT 2008. 3rd International, 2008, pp. 153–155.
• [8] M.F. Møller, “Moller, M.F., A Scaled Conjugate Gradient Algorithm For Fast Supervised Learning. Neural Networks 6, Neural Networks, vol. 6, no. 4, 1993, pp. 525–533.
• [9] D.E. Rumelhart, G.E. Hinton and R.J. Williams, Learning internal representations by error propagation, DTIC Document, 1985.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.