Smart Prosthetic Leg with Wrist-Worn Fall Alert and Automatic Emergency E-mail Using ESP32

Author

Swayam Ranjit Wakurde , Aditya Kailas Dafale, Raju Narayan Chopade, Tejas Dilip Anuje, Dr. S. Y. Salunkhe

Abstract

 A person who walks with an artificial lower limb is more likely to stumble, yet an ordinary prosthesis has no way of noticing a fall or asking anyone for help. We built a working prototype that closes this gap at modest cost. An MPU6050 motion sensor fixed to the prosthetic shank is read by an ESP32; the controller raises a fall suspicion when the measured acceleration vector drifts more than 1.15 g away from a stored standing reference for 300 ms, or when its magnitude passes 2 g. The suspicion is forwarded through ESP-NOW to a second ESP32 housed in a wrist unit with an OLED screen and one button. The wearer gets ten seconds to press the button; a press discards the alert, while silence leads to a buzzer and an e-mail to the caretaker, stamped with network time. In 100 bench trials of everyday movements and staged falls, 96 decisions were correct, with 3 false alarms and 1 missed event. Radio delay between the units averaged about 6.4 ms, the wrist display reacted in roughly 120 ms, and the batteries lasted about 9 h (leg) and 13 h (wrist). Total build cost was about ₹8,000. The work suggests that asking the wearer to confirm an alert is a simple and effective way to keep an inertial fall detector from sending needless emergency messages.

Keywords

smart prosthesis, fall detection, ESP32, MPU6050, ESP-NOW, wearable alert, emergency e-mail

Full Text:

Download Paper PDF

References

[1]  W. C. Miller, M. Speechley and B. Deathe, “The prevalence and risk factors of falling and fear of falling among lower extremity amputees,” Archives of Physical Medicine and Rehabilitation, vol. 82, no. 8, pp. 1031–1037, 2001.

[2]  C. Gauthier-Gagnon, M.-C. Grisé and D. Potvin, “Enabling factors related to prosthetic use by people with transtibial and transfemoral amputation,” Archives of Physical Medicine and Rehabilitation, vol. 80, no. 6, pp. 706–713, 1999.

[3]  R. Igual, C. Medrano and I. Plaza, “Challenges, issues and trends in fall detection systems,” BioMedical Engineering OnLine, vol. 12, art. 66, 2013.

[4]  M. Mubashir, L. Shao and L. Seed, “A survey on fall detection: Principles and approaches,” Neurocomputing, vol. 100, pp. 144–152, 2013.

[5]  A. K. Bourke, J. V. O'Brien and G. M. Lyons, “Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm,” Gait & Posture, vol. 26, no. 2, pp. 194–199, 2007.

[6]  Espressif Systems, “ESP-NOW,” ESP-IDF Programming Guide, Espressif Systems. [Online]. Available: https://docs.espressif.com

[7]  InvenSense Inc., “MPU-6000 and MPU-6050 Product Specification, Revision 3.4,” 2013.

Share your valuable work from Social Media Buttons