Information for Paper ID 1812
Paper Information:
Paper Title: Ultra-Tiny Neural Network for Compensation of Post-Soldering Thermal Drift in MEMS Pressure Sensors 
Student Contest: Yes 
Affiliation Type: Academia 
Keywords: Neural network, pressure sensor, self-compensation, thermal drift 
Abstract: MEMS pressure sensors are widely used in several application fields, such as industrial, medical, automotive, etc, where they are required to be increasingly accurate and reliable. However, these sensors are very sensitive to mechanical and temperature variations. For example, the soldering process, which involves a significant thermal stress, causes drift in the sensor accuracy. This article introduces a digital circuit implementing a very tiny neural network able to compensate for the drift measurement in real time. The circuit is capable of correcting for drift accuracy up to 1.6 hPa, restoring the accuracy to ±0.5 hPa. Synthesis results on TSMC 130 nm CMOS technology show an area occupation of 0.0373 mm2 and a dynamic power of 1.07 µW, which enable its easy integration in the digital circuit which is available into MEMS sensor package for pressure measures conditioning. 
Track ID: 7.5 
Track Name: Environmental sensors (temperature, gas, humidity, ionizing radiation) 
Secondary Track ID: 10.8 
Secondary Track Name: Machine Learning For Signal Processing 
Final Decision: Accept as Poster 
Session Name: Sensory Systems for AIoT (Poster) 
Author Questions:
TCAS-II: No
WiCAS: No
Theme Information:
Selected Theme(s):
Artificial Intelligence & Deep Learning