Genetic Algorithm Calibration Method and PnP Platform for Multimodal Sensor Systems

멀티모달 센서 시스템용 유전자 알고리즘 보정기 및 PnP 플랫폼

  • Received : 2018.11.22
  • Accepted : 2019.02.15
  • Published : 2019.02.28


This paper proposes a multimodal sensor platform which supports plug and play (PnP) technology. PnP technology automatically recognizes a connected sensor module and an application program easily controls a sensor. To verify a multimodal platform for PnP technology, we build up a firmware and have the experiment on a sensor system. When a sensor module is connected to the platform, a firmware recognizes the sensor module and reads sensor data. As a result, it provides PnP technology to simply plug sensors without any software configuration. Measured sensor raw data suffer from various distortions such as gain, offset, and non-linearity errors. Therefore, we introduce a polynomial calculation to compensate for sensor distortions. To find the optimal coefficients for sensor calibration, we apply a genetic algorithm which reduces the calibration time. It achieves reasonable performance using only a few data points with reducing 97% error in the worst case. The platform supports various protocols for multimodal sensors, i.e., UART, I2C, I2S, SPI, and GPIO.

KCTSAD_2019_v14n1_69_f0001.png 이미지

Fig. 1 Block diagram of genetic algorithm processor

KCTSAD_2019_v14n1_69_f0002.png 이미지

Fig. 2 LFSR-12

KCTSAD_2019_v14n1_69_f0003.png 이미지

Fig. 3 LFSR-16

KCTSAD_2019_v14n1_69_f0004.png 이미지

Fig. 4 Two parents (P0, P1)

KCTSAD_2019_v14n1_69_f0005.png 이미지

Fig. 5 Two children (C0,C1) using 1-point crossover with the 5th point

KCTSAD_2019_v14n1_69_f0006.png 이미지

Fig. 6 Two children (C0,C1) using 2-point crossover with the 3rd and 6th points

KCTSAD_2019_v14n1_69_f0007.png 이미지

Fig. 7 Two children (C0,C1) using uniform crossover

KCTSAD_2019_v14n1_69_f0008.png 이미지

Fig. 8 Block diagram of fitness and selection

KCTSAD_2019_v14n1_69_f0009.png 이미지

Fig. 9 Sensor module for PnP platform

KCTSAD_2019_v14n1_69_f0010.png 이미지

Fig. 10 Sensor identification

KCTSAD_2019_v14n1_69_f0011.png 이미지

Fig. 11 Recognition process

KCTSAD_2019_v14n1_69_f0012.png 이미지

Fig. 12 Timing diagram for I2C interface

KCTSAD_2019_v14n1_69_f0013.png 이미지

Fig. 13 Block diagram for multimodal sensor platform

KCTSAD_2019_v14n1_69_f0014.png 이미지

Fig. 14 Sensor board for the multimodal sensor platform

KCTSAD_2019_v14n1_69_f0015.png 이미지

Fig. 15 Compensated Results for Ambient Light Sensor (TEMT6000)

KCTSAD_2019_v14n1_69_f0016.png 이미지

Fig. 16 Firmware for multimodal sensor platform

Table 1. Simulation Results using Genetic Algorithm

KCTSAD_2019_v14n1_69_t0001.png 이미지


Supported by : 중소벤처기업부


  1. Y. Qu, G. Zhang, Z. Zou, Z. Liu, and J. Mao, "Active Multimodal Sensor System for Target Recognition and Tracking," Sensors, vol. 17, no. 7, June 2017, pp. 1-22.
  2. T. Korthals, M. Kragh, P. Christiansen, H. Karstoft, R. N. Jorgensen, and U. Ruckert, "Multi-Modal Detection and Mapping of Static and Dynamic Obstacles in Agriculture for Process Evaluation," Front. Robot. AI, vol. 5, no. 28, Mar. 2018, p.1.
  3. J. Jeonga, T. S. Yoonb, and J. B. Parka, "Multimodal Sensor-Based Semantic 3D Mapping for a Large-Scale Environment," Expert Systems with Applications, Elsevier, vol. 105, no. 1, Sept. 2018, pp. 1-10.
  4. J. H. Lee, B. Kim, and D. Kim, "Calibration Using Genetic Algorithm and PnP Platform Development for Multimodal Sensors," Proc. of the 7th Int. Conf. on Next Generation Computer and Information Technology (NGCIT), Sapporo, Japan, Aug. 2018, pp. 23-25.
  5. S. Park, S. Oh, S. Lee, J. Maeng, and Y. Ko, "A Study on the Temperature and Humidity Control Methodology of Smart Farm ased on Wireless Communication Network," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 4, 2018, pp. 851-857.
  6. B. Kim, J. Lee, T. Hwang, and D. Kim, "Design of Lightweight Artificial Intelligence System for Multimodal Signal Processing," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 5, 2018, pp. 1037-1042.
  7. W. Oh, "A Fault Detection Scheme in Acoustic Sensor Systems Using Multiple Acoustic Sensors," J. of the Korea Institute of Electronic Communication Sciences, vol. 11, no. 2, 2016, pp. 203-208.
  8. J. Rivera, G. Herrera, and M. Chacon, "Improved progressive polynomial algorithm for self-calibration and optimal response in smart sensors," Measurement, Elsevier, vol. 42, no. 9, Nov. 2009, pp. 1395-1401.
  9. S. Rahili, J. Ghaisari, and A. Golfar, "Intelligent selection of calibration points using a modified progressive polynomial method," IEEE Trans. Instrum. Meas., vol. 61, no. 9, Apr. 2012, pp. 2519-2523.
  10. H. Shah, "Internet of Things (IoT) Rollouts in the Telehealth Industry," Telehealth and Medicine Today, vol. 2, no. 3, 2017, pp. 1-15.
  11. G. Horn and J. L. Huijsing, "Calibration using Digital Signal Processing," Springer International Series in Engineering and Computer Science book series, 1998, pp. 173-192.
  12. TTAK.KO-06.0290, Plug&Play based USN Sensor Access Interface, 2012.
  13. B. Sklar, Digital Communications: Fundamentals and Application., New Jersey: Prentice Hall, New Jersey, 2001.
  14. Z. Michalewicz, Genetic algorithms + data structures = evolution programs (3rd ed.). Berlin: Springer, 1996.
  15. A. Zalzala and P.J. Fleming, Genetic Algorithms in Engineering Systems. The Institution of Engineering and Technology, 1997.