Improving the Accuracy of Low-Cost Sensor Measurements for Freezer Automation

In this work, a regression method is implemented on a low-cost digital temperature sensor to improve the sensor’s accuracy; thus, following the EN12830 European standard. This standard defines that the maximum acceptable error regarding temperature monitoring devices should not exceed 1 °C for the refrigeration and freezer areas. The purpose of the proposed method is to improve the accuracy of a low-cost digital temperature sensor by correcting its nonlinear response using simple linear regression (SLR). In the experimental part of this study, the proposed method’s outcome (in a custom created dataset containing values taken from a refrigerator) is compared against the values taken from a sensor complying with the EN12830 standard. The experimental results confirmed that the proposed method reduced the mean absolute error (MAE) by 82% for the refrigeration area and 69% for the freezer area—resulting in the accuracy improvement of the low-cost digital temperature sensor. Moreover, it managed to achieve a lower generalization error on the test set when compared to three other machine learning algorithms (SVM, B-ELM, and OS-ELM).

[1]  Wei Ge,et al.  A Fully Digital Physical Unclonable Function Based Temperature Sensor for Secure Remote Sensing , 2018, 2018 27th International Conference on Computer Communication and Networks (ICCCN).

[2]  Yi Lin,et al.  All-Digital Time-Domain CMOS Smart Temperature Sensor with On-Chip Linearity Enhancement , 2016, Sensors.

[3]  Georgi Nikolov,et al.  Improvement of NDIR carbon dioxide sensor accuracy , 2015, 2015 38th International Spring Seminar on Electronics Technology (ISSE).

[4]  Peter L. Bartlett,et al.  The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network , 1998, IEEE Trans. Inf. Theory.

[5]  Kun Liu,et al.  A De-Noising Algorithm Based on EEMD in Raman-Based Distributed Temperature Sensor , 2017, IEEE Sensors Journal.

[6]  Erick Agrimson,et al.  Calibration of Temperature Sensors in Preparation for the 2017 Total Solar Eclipse , 2017 .

[7]  Mohini P. Barde,et al.  What to use to express the variability of data: Standard deviation or standard error of mean? , 2012, Perspectives in clinical research.

[8]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[9]  Jun Tan,et al.  A fully passive RFID temperature sensor SoC with an accuracy of ±0.4°C (3σ) from 0°C to 125°C , 2018, 2018 IEEE International Conference on RFID (RFID).

[10]  Chun-Chi Chen,et al.  A CMOS Smart Temperature Sensor with One Homogeneous Delay Line and Curvature Compensation , 2016 .

[11]  Harinaldi,et al.  A simple method for calibration of temperature sensor DS18B20 waterproof in oil bath based on Arduino data acquisition system , 2019 .

[12]  Narasimhan Sundararajan,et al.  On-Line Sequential Extreme Learning Machine , 2005, Computational Intelligence.

[13]  Gerard C. M. Meijer,et al.  Design of a temperature sensor with optimized noise-power performance , 2018 .

[14]  Hyoung-Jun Park,et al.  Accuracy improvement in peak positioning of spectrally distorted fiber Bragg grating sensors by Gaussian curve fitting. , 2007, Applied optics.

[15]  Michael B. Miller.  Linear Regression Analysis , 2013 .

[16]  Yingheng Tang,et al.  A low power CMOS temperature sensor frontend for RFID tags , 2018, 2018 IEEE 18th Topical Meeting on Silicon Monolithic Integrated Circuits in RF Systems (SiRF).

[17]  Yaonan Wang,et al.  Bidirectional Extreme Learning Machine for Regression Problem and Its Learning Effectiveness , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[18]  J. S. Dowker,et al.  Fundamentals of Physics , 1970, Nature.

[19]  Hyoung-Jun Park,et al.  Linear FBG Temperature Sensor Interrogation with Fabry-Perot ITU Multi-wavelength Reference , 2008, Sensors.

[20]  David Zhang,et al.  Evolutionary Cost-Sensitive Extreme Learning Machine , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[21]  N. Zahir,et al.  SNOW DEPTH ESTIMATION USING TIME SERIES PASSIVE MICROWAVE IMAGERY VIA GENETICALLY SUPPORT VECTOR REGRESSION (CASE STUDY URMIA LAKE BASIN) , 2015 .

[22]  Pradip Kumar Sahu,et al.  Analysis of Variance and Experimental Designs , 2013 .

[23]  Derek Molloy.  Exploring Raspberry Pi , 2016 .

[24]  Jose M. Lopez-Higuera,et al.  Comparative Experimental Study of a High-Temperature Raman-Based Distributed Optical Fiber Sensor with Different Special Fibers , 2019, Sensors.

[25]  Feng Ning,et al.  Accuracy improvement of distributed optical fiber Raman temperature sensor system based on dynamic calibration , 2012, Other Conferences.

[26]  Nianxiong Tan,et al.  A CMOS Temperature Sensor With Versatile Readout Scheme and High Accuracy for Multi-Sensor Systems , 2018, IEEE Transactions on Circuits and Systems I: Regular Papers.

[27]  S. Turns.  Thermodynamics: Concepts and Applications , 2020 .

[28]  Kambiz Moez,et al.  An RF-Powered Wireless Temperature Sensor for Harsh Environment Monitoring With Non-Intermittent Operation , 2018, IEEE Transactions on Circuits and Systems I: Regular Papers.

[29]  Eckhard Hennig,et al.  A Fully Passive RFID Temperature Sensor SoC With an Accuracy of ±0.4 °C ( $3\sigma$ ) From 0 °C to 125 °C , 2019, IEEE Journal of Radio Frequency Identification.

[30]  F. D. Pasquale,et al.  Enhanced Simultaneous Distributed Strain and Temperature Fiber Sensor Employing Spontaneous Brillouin Scattering and Optical Pulse Coding , 2009, IEEE Photonics Technology Letters.

[31]  Jun Chang,et al.  Accuracy improvement of Raman distributed temperature sensors based on eliminating Rayleigh noise impact , 2013 .

[32]  Chua-Chin Wang,et al.  A High-Precision CMOS Temperature Sensor with Thermistor Linear Calibration in the (−5 °C, 120 °C) Temperature Range , 2018, Sensors.

[33]  Eric Iksoon Im.  A Note On Derivation of the Least Squares Estimator , 1996 .

[34]  David A. Freedman,et al.  Statistical Models: Theory and Practice: References , 2005 .

[35]  Peter R. Kinget,et al.  An Area-Efficient Microprocessor-Based SoC With an Instruction-Cache Transformable to an Ambient Temperature Sensor and a Physically Unclonable Function , 2018, IEEE Journal of Solid-State Circuits.

[36]  Genda Chen,et al.  Measurement accuracy improvement of Brillouin signal using wavelet denoising method , 2009, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[37]  R. Amador,et al.  Technological compensation circuit for accurate temperature sensor , 1998 .

[38]  Kofi A. A. Makinwa,et al.  A Resistor-Based Temperature Sensor With a 0.13 pJ $\cdot$ K2 Resolution FoM , 2017, IEEE Journal of Solid-State Circuits.

[39]  S. Loranger,et al.  Rayleigh scatter based order of magnitude increase in distributed temperature and strain sensing by simple UV exposure of optical fibre , 2015, Scientific Reports.

[40]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[41]  Jianzhong Zhang,et al.  Raman Distributed Temperature Sensor with Optical Dynamic Difference Compensation and Visual Localization Technology for Tunnel Fire Detection , 2019, Sensors.

[42]  K. Zou,et al.  Correlation and simple linear regression. , 2003, Radiology.

[43]  Kofi A. A. Makinwa,et al.  Delft University of Technology A Resistor-Based Temperature Sensor With a 0.13 pJ·K2 Resolution FoM , 2016 .

[44]  Yong Qing Fu,et al.  Performance improvement of BOTDR system using wavelength diversity technique , 2017, 2017 25th Optical Fiber Sensors Conference (OFS).