Application of Sensor Fusion Techniques for Vehicle Condition and Position Analysis

Abstract

Sensor fusion is a method of processing data from raw data to meaningful outputs and getting quality output. Architectures used in sensor fusion are chosen depending on the application. The sensor fusion architecture that is frequently used today was found by the directors of the United States Joint Laboratory (JDL). Sensor fusion has been realized with this architecture. Using the axial data of a car, inertial movements such as acceleration, deceleration and stationary are classified as controlled. At the classification point, low level and high-level methods are used in the sensor fusion application. By pre-processing the received data, joint high-quality data was obtained with complementary sensor modeling, and high-level sensor fusion methods were used after recording the obtained data. Artificial intelligence algorithms are preferred for high-level sensor fusion. Various algorithms such as "Decision Tree", "Gradient Boosting", "Multi-Layer Perceptron", "Regression Algorithm" have been used. Real-time acquired data is stored after preprocessing and raw data fusion. The stored data has created a high-level sensor fusion at the point of decision making with supervised learning artificial intelligence algorithms

Keywords

• Sensor Fusion
• IMU
• Gyroscope
• Accelerometer
• Artificial Intellgence

References

1. [1] S.Birogul, Y. Sonmez, U.guvenc,” Veri Füzyonuna Genel Bir Bakış”, Politeknik Dergisi Vol.10, No.3, pp. 235-240, 2007.
2. [2] W. Elmenreich,” An Introduction to Sensor Fusion”, Research Report 47/2001.
3. [3] Weisstein W., E., “Eric Weissten’s world of science”, www.scienceworld. wolfram.com/physic (2003).
4. [4] Llinas, J.,Waltz, E., “Multisensor data fusion”, Boston, MA: Artech House, (1999).
5. [5] O.Saber, R., J.S Shamma. “Consensus Filters for Sensor Networks and Distributed Sensor Fusion.” Seville, Spain: IEEE, Dec. 2005.
6. [6] M. Kam, X. Zhu, P. Kalata, “Sensor fusion for mobile robot navigation,” 1997, Proceedings of the IEEE(Volume: 85, Issue: 1, Jan. 1997).
7. [7] J.K. Hackett, M. Shah, “Multi-sensor fusion: a perspective,” 1990 IEEE International Conference on Robotics and Automation, Cincinnati, OH, USA.
8. [8] O. Kreibich, J. Neuzil, “Quality-Based Multiple-Sensor Fusion in an Industrial Wireless Sensor Network for MCM,” IEEE Transactions on Industrial Electronics,. 09.2014.

9. [9] Samancı.B, “Accelerometer, Gyroscope, IMU nedir?”, “http://www.barissamanci.net/Makale/26/accelerometer-gyroscope-imu-nedir/”,(05.2020).
10. [10] https://learn.sparkfun.com/tutorials/accelerometer-basics/how-to-select-an-accelerometer,(06.05.2021).
11. [11] https://learn.sparkfun.com/tutorials/gyroscope/all , (06.05.2021).
12. [12] T.C. Akinci. "Applications of big data and AI in electric power systems engineering." AI and Big Data’s Potential for Disruptive Innovation. IGI Global, 2020. 240-260.
13. [13] H.S. Nogay, T.C. Akinci, and M. Yilmaz. "Comparative experimental investigation and application of five classic pre-trained deep convolutional neural networks via transfer learning for diagnosis of breast cancer." Advances in Science and Technology. Research Journal, vol. 15, no. 3, 2021, pp.1-8. https://doi.org/10.12913/22998624/137964
14. [14] O. Akgun, A. Akan, H. Demir, T.C. Akinci, "Analysis of Gait Dynamics of ALS Disease and Classification of Artificial Neural Networks." Tehnički vjesnik 25.Supplement 1 (2018), pp.183-187. https://doi.org/10.17559/TV-20160914144554
15. [15] O. Turk, D. Ozhan, E. Acar, T.C. Akinci, and M. Yilmaz. "Automatic detection of brain tumors with the aid of ensemble deep learning architectures and class activation map indicators by employing magnetic resonance images." Zeitschrift für Medizinische Physik (2022). https://doi.org/10.1016/j.zemedi.2022.11.010
16. [16] https://www.st.com/en/ecosystems/x-nucleo-iks01a2.html, (04.04.2021).