"JOURNAL OF RADIO ELECTRONICS" (Zhurnal Radioelektroniki ISSN 1684-1719, N 12, 2017

contents             full textpdf   

UDC 618.19-006-07:616.073.756.8-027.552

Software development for the multiprocessor architecture of the personal electrical impedance mammograph PEM


I. K. Lakeev, A. V. Korjenevsky, T. S. Tuikin

Kotelnikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences, Mokhovaya 11-7, Moscow 125009, Russia


The paper is received on December 8, 2017


Abstract. Optimized software development for symmetric multiprocessing systems, especially the low-level ones, has always been hard in terms of achieving sustainable operational level with reasonable effort and in acceptable time. Through the process of personal electrical impedance mammograph software development and debugging it was shown that major drawback of Harvard-type architecture, implemented in modern AVR microprocessors, may be an issue in terms of precise interrupt-driven synchronization between several elements of the multiprocessor architecture because of the different length of commands and therefore often unpredictable execution timing before finishing the very last command and entering the particular interruption, that can be successfully mitigated in two steps: initial configuration of the job that needs to be done with respect to timing which should be followed by light sleep state and further synchronization interruption that will be able to wake up the modules and provide exact timing. It was also shown that during parallel usage of one UART of the micro controller unit to serve two dependent units one may experience frame errors unless UART reconfigured on demand.  Utilization of any python-based computational environments that support special kernels with enhanced introspection and parallel computing clusters management with the help of asynchronous status callbacks can significantly improve the development process speeding up the debugging routine. It is shown in the example of personal electrical impedance mammograph software development and debugging, especially on the late stages of development when the level of abstraction gets higher, particularly on the examples of experiment data results assessment on multiple levels from raw data to reconstructed images.

Keywords: hardware and software system, multiprocessing system, synchronization problem solving, debugging and development, python.


1.     O.V. Trokhanova, M.B. Okhapkin and A.V. Korjenevsky. Dual-frequency electrical impedance mammography for the diagnosis of non-malignant breast disease. Physiol. Meas., 2008, Vol. 29, pp. S331-S344

2.  V. Cherepenin, A. Karpov, A. Korjenevsky, V. Kornienko, Y. Kultiasov, M. Ochapkin, O. Trochanova and D. Meister. Three-dimensional EIT imaging of breast tissues: system design and clinical testing. IEEE Trans. Medical Imaging, 2002, Vol. 21(6), pp. 662-667

3.  Barber D. C., Brown B. H., Freeston I. L. Imaging spatial distribution of resistivity using applied potential tomography. Electronics Letters, 1983, Vol.19(22), pp.933-935

4.  Brown B. H., Barber D. C., Segar A. D. Applied potential tomography: possible clinical applications. Clin. Phys. Physiol. Meas., 1985, Vol.6(2), pp.109-121

5.  IDE NetBeans features [electronic resource]. Available at https://netbeans.org/features/java/index_ru.html

6.  Anaconda cloud [electronic resource]. Available at https://anaconda.org/anaconda/python

For citation:
I. K. Lakeev, A. V. Korjenevsky, T. S. Tuikin. Software development for the multiprocessor architecture of the personal electrical impedance mammograph PEM. Zhurnal Radioelektroniki - Journal of Radio Electronics. 2017. No. 12. Available at http://jre.cplire.ru/jre/dec17/9/text.pdf.