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

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

- The refrigeration area must operate between 1 °C and 7 °C
- The freezer must operate between −22 °C and −10 °C [2].

_{2}detection. This research aimed to examine and evaluate the impact of these approaches regarding the accuracy improvement of NDIR CO

_{2}sensors. This investigation focused on NDIR sensors without taking into consideration non-NDIR sensors.

## 2. Simple Linear Regression

## 3. The SLR-DS18B20 System Architecture

## 4. Sensors Calibration Procedure

## 5. Experimental Measurements and Simulation Results

- 1st part. The refrigeration area. It contains temperatures over −10 °C and below or equal to 30 °C.
- 2nd part. The freezer area. It contains temperatures between −22 °C and −10 °C.

## 6. Comparative Study

## 7. Discussion

## 8. Conclusions

## 9. Future Work

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Commission Regulation (EC) No 37/2005 of 12 January 2005. The Monitoring of Temperatures in the Means of Transport, Warehousing and Storage of Quick-Frozen Foodstuffs Intended for Human Consumption; Official Journal of the European Union: Brussels, Belgium, 2005. [Google Scholar]
- Regulation (EC) No 852/2004 of the European Parliament and of the Council of 29 April 2004. The Hygiene of Foodstuffs; Official Journal of the European Communities: Brussels, Belgium, 2004.
- Maxim, R. Writing 1-Wire
^{®}Devices Through Serial Interfaces. AN74. 2009. Available online: https://pdfserv.maximintegrated.com/en/an/AN74.pdf (accessed on 2 September 2020). - Maxim Integrated, D.B. Programmable Resolution 1-Wire Digital Thermometer, Datasheet. 1999. Available online: https://datasheets.maximintegrated.com/en/ds/DS18B20.pdf (accessed on 2 September 2020).
- Agrimson, E.P.; Smith, K.; DuBose, R.; Onyango-Robshaw, V.; Taylor, A.; Walter, A.; Sinyigaya, P.; Maki, G.; Lang, R.; Craig, B.; et al. Calibration of Temperature Sensors in Preparation for the 2017 Total Solar Eclipse. In Academic High Altitude Conference; Iowa State University Digital Press: Ames, IA, USA, 2017. [Google Scholar]
- Hafiz, M.; Renjani, R.A.; Haryanto, A.; Araswati, N.; Subrata, I.D. Design of Temperature and Volume Control System at Crude Palm Oil (CPO) Storage Tank. In Proceedings of the AESAP 2016, Bogor, Indonesia, 13–14 December 2016. [Google Scholar]
- Koestoer, R.A.; Saleh, Y.A.; Roihan, I.; Harinaldi. A simple method for calibration of temperature sensor DS18B20 waterproof in oil bath based on Arduino data acquisition system. In Proceedings of the AIP Conference Proceedings, Kuta, Indonesia, 25 January 2019. [Google Scholar]
- Chamberlin, R. Temperature Measurements on the Leighton Telescope: Surface Memo No. 2; Caltech Sub-Millimeter Observatory: Hilo, HI, USA, 2003. [Google Scholar]
- Sun, B.N.; Chang, J.; Lian, J.; Wang, Z.L.; Lv, G.P.; Liu, X.Z.; Wang, W.J.; Zhou, S.; Wei, W.; Jiang, S.; et al. Accuracy improvement of Raman distributed temperature sensors based on eliminating Rayleigh noise impact. Opt. Commun.
**2013**, 306, 117–120. [Google Scholar] [CrossRef] - Lee, H.W.; Park, H.J.; Lee, J.H.; Song, M. Accuracy improvement in peak positioning of spectrally distorted fiber Bragg grating sensors by Gaussian curve fitting. Appl. Opt.
**2007**, 46, 2205–2208. [Google Scholar] [CrossRef] [PubMed] - He, J.; Zhou, Z.; Chen, G.; Ou, J. Measurement accuracy improvement of Brillouin signal using wavelet denoising method. In Proceedings of the Smart Sensor Phenomena, Technology, Networks, and Systems, International Society for Optics and Photonics, San Diego, CA, USA, 8 April 2009. [Google Scholar]
- Lalam, N.; Ng, W.P.; Dai, X.; Wu, Q.; Fu, Y.Q. Performance improvement of BOTDR system using wavelength diversity technique. In Proceedings of the 2017 25th Optical Fiber Sensors Conference (OFS), Jeju, Korea, 24–28 April 2017. [Google Scholar]
- Soto, M.A.; Bolognini, G.; di Pasquale, F. Enhanced simultaneous distributed strain and temperature fiber sensor employing spontaneous Brillouin scattering and optical pulse coding. IEEE Photonics Technol. Lett.
**2009**, 21, 450–452. [Google Scholar] [CrossRef] [Green Version] - Park, H.-J.; Song, M. Linear FBG temperature sensor interrogation with Fabry-Perot ITU multi-wavelength reference. Sensors
**2008**, 8, 6769–6776. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Loranger, S.; Gagné, M.; Lambin-Iezzi, V.; Kashyap, R. Rayleigh scatter based order of magnitude increase in distributed temperature and strain sensing by simple UV exposure of optical fibre. Sci. Rep.
**2015**, 5, 11177. [Google Scholar] [CrossRef] [PubMed] - Jin, Z.-X.; Cui, H.-J.; Ning, F. Accuracy improvement of distributed optical fiber Raman temperature sensor system based on dynamic calibration. In Proceedings of the Third International Conference on Smart Materials and Nanotechnology in Engineering, International Society for Optics and Photonics, Shenzhen, China, 12 April 2012. [Google Scholar]
- Yan, B.; Li, J.; Zhang, M.; Zhang, J.; Qiao, L.; Wang, T. Raman distributed temperature sensor with optical dynamic difference compensation and visual localization technology for tunnel fire detection. Sensors
**2019**, 19, 2320. [Google Scholar] [CrossRef] [Green Version] - Laarossi, I.; Quintela-Incera, M.Á.; López-Higuera, J.M. Comparative experimental study of a high-temperature raman-based distributed optical fiber sensor with different special fibers. Sensors
**2019**, 19, 574. [Google Scholar] [CrossRef] [Green Version] - Pan, L.; Liu, K.; Jiang, J.; Ma, C.; Tian, M.; Liu, T. A de-noising algorithm based on EEMD in Raman-based distributed temperature sensor. IEEE Sens. J.
**2016**, 17, 134–138. [Google Scholar] [CrossRef] - Marinov, M.; Nikolov, G.; Gieva, E.; Ganev, B. Improvement of NDIR carbon dioxide sensor accuracy. In Proceedings of the 2015 38th International Spring Seminar on Electronics Technology (ISSE), Eger, Hungary, 6–10 May 2015. [Google Scholar]
- Tang, Z.; Fang, Y.; Yu, X.P.; Shi, Z.; Tan, N. A CMOS temperature sensor with versatile readout scheme and high accuracy for multi-sensor systems. IEEE Trans. Circuits Syst. I Regul. Pap.
**2018**, 65, 3821–3829. [Google Scholar] [CrossRef] - Amador, R.; Polanco, A.; Hernández, H.; González, E.; Nagy, A. Technological compensation circuit for accurate temperature sensor. Sens. Actuators A Phys.
**1998**, 69, 172–177. [Google Scholar] [CrossRef] - Chen, C.-C.; Chen, C.-L.; Lin, Y. All-digital time-domain CMOS smart temperature sensor with on-chip linearity enhancement. Sensors
**2016**, 16, 176. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Chen, C.-C.; Guo, Z.-Y. A CMOS Smart Temperature Sensor with One Homogeneous Delay Line and Curvature Compensation. Procedia Eng.
**2016**, 168, 1755–1758. [Google Scholar] [CrossRef] - Tan, J.; Sathyamurthy, M.; Rolapp, A.; Gamez, J.; Hennig, E.; Schäfer, E.; Sommer, R. A Fully Passive RFID Temperature Sensor SoC With an Accuracy of ±0.4 °C (3σ) From 0 °C to 125 °C. IEEE J. Radio Freq. Identif.
**2019**, 3, 35–45. [Google Scholar] [CrossRef] - Heidari, A.; Wang, G.; Abdollahpour, M.; Meijer, G.C. Design of a temperature sensor with optimized noise-power performance. Sens. Actuators A Phys.
**2018**, 282, 79–89. [Google Scholar] [CrossRef] - Wang, C.-C.; Hou, Z.-Y.; You, J.-C. A high-precision CMOS temperature sensor with thermistor linear calibration in the (−5 °C, 120 °C) temperature range. Sensors
**2018**, 18, 2165. [Google Scholar] [CrossRef] [Green Version] - Shan, H.; Peterson, J.; Tsai, M.S.; Tang, Y.; Conrad, N.J.; Mohammadi, S. A low power CMOS temperature sensor frontend for RFID tags. In Proceedings of the 2018 IEEE 18th Topical Meeting on Silicon Monolithic Integrated Circuits in RF Systems (SiRF), Anaheim, CA, USA, 14–17 January 2018. [Google Scholar]
- Pan, S.; Luo, Y.; Shalmany, S.H.; Makinwa, K.A. A Resistor-Based Temperature Sensor With a 0.13 pJ·K2 Resolution FoM. IEEE J. Solid-State Circuits
**2017**, 53, 164–173. [Google Scholar] [CrossRef] [Green Version] - Saffari, P.; Basaligheh, A.; Sieben, V.J.; Moez, K. An RF-powered wireless temperature sensor for harsh environment monitoring with non-intermittent operation. IEEE Trans. Circuits Syst. I Regul. Pap.
**2017**, 65, 1529–1542. [Google Scholar] [CrossRef] - Cao, Y.; Guo, Y.; Liu, B.; Ge, W.; Zhu, M.; Chang, C.H. A fully digital physical unclonable function based temperature sensor for secure remote sensing. In Proceedings of the 2018 27th International Conference on Computer Communication and Networks (ICCCN), Hangzhou, China, 30 July–2 August 2018. [Google Scholar]
- Li, J.; Yang, T.; Yang, M.; Kinget, P.R.; Seok, M. An area-efficient microprocessor-based SoC with an instruction-cache transformable to an ambient temperature sensor and a physically unclonable function. IEEE J. Solid-State Circuits
**2018**, 53, 728–737. [Google Scholar] [CrossRef] - Freedman, D.A. Statistical Models: Theory and Practice; Cambridge University Press: Cambridge, UK, 2009. [Google Scholar]
- Zou, K.H.; Tuncali, K.; Silverman, S.G. Correlation and simple linear regression. Radiology
**2003**, 227, 617–628. [Google Scholar] [CrossRef] - Seber, G.A.; Lee, A.J. Linear Regression Analysis; John Wiley & Sons: Hoboken, NJ, USA, 2012; Volume 329. [Google Scholar]
- Neter, J.; Wasserman, W.; Kutner, M.H. Applied Linear Models, Regression, Analysis of Variance and Experimental Designs; RD Irwin: Boston, CA, USA, 1990. [Google Scholar]
- Im, E.I. A Note on Derivation of the Least Squares Estimator; Working Papers; Department of Economics, University of Hawaii at Manoa: Honolulu, HI, USA, 1996; p. 199611. [Google Scholar]
- Tzivaras, V. Raspberry Pi Zero W Wireless Projects; Packt Publishing Ltd.: Birmingham, UK, 2017. [Google Scholar]
- Molloy, D. Exploring Raspberry PI; Wiley Online Library: Hoboken, NJ, USA, 2016. [Google Scholar]
- Arduino. Arduino Nano Every. 2020. Available online: https://store.arduino.cc/arduino-nano-every (accessed on 2 September 2020).
- Raspberry Pi Foundation. Raspberry Pi. Available online: https://www.raspberrypi.org/ (accessed on 2 September 2020).
- Laurila, H. How to Calibrate Temperature Sensors. 2020. Available online: https://blog.beamex.com/how-to-calibrate-temperature-sensors (accessed on 2 September 2020).
- Turns, S.R.; Pauley, L.L. Thermodynamics: Concepts and Applications; Cambridge University Press: Cambridge, UK, 2020. [Google Scholar]
- Halliday, D.; Resnick, R.; Walker, J. Fundamentals of Physics; John Wiley & Sons: Hoboken, NJ, USA, 2013. [Google Scholar]
- Beamex. Calibration World. In Beamex Corporate Magzine; Beamex: Pietarsaari, Finland, 2017. [Google Scholar]
- Barde, M.P.; Barde, P.J. What to use to express the variability of data: Standard deviation or standard error of mean? Perspect. Clin. Res.
**2012**, 3, 113. [Google Scholar] [CrossRef] - Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn.
**1995**, 20, 273–297. [Google Scholar] [CrossRef] - Zahir, N.; Mahdi, H. Snow Depth Estimation Using Time Series Passive Microwave Imagery via Genetically Support Vector Regression (case Study Urmia Lake Basin). Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.
**2015**, 40, 555. [Google Scholar] [CrossRef] [Green Version] - Huang, G.-B.; Zhu, Q.-Y.; Siew, C.-K. Extreme learning machine: Theory and applications. Neurocomputing
**2006**, 70, 489–501. [Google Scholar] [CrossRef] - Bartlett, P.L. The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network. IEEE Trans. Inf. Theory
**1998**, 44, 525–536. [Google Scholar] [CrossRef] [Green Version] - Zhang, L.; Zhang, D. Evolutionary cost-sensitive extreme learning machine. IEEE Trans. Neural Netw. Learn. Syst.
**2016**, 28, 3045–3060. [Google Scholar] [CrossRef] [PubMed] - Yang, Y.; Wang, Y.; Yuan, X. Bidirectional extreme learning machine for regression problem and its learning effectiveness. IEEE Trans. Neural Netw. Learn. Syst.
**2012**, 23, 1498–1505. [Google Scholar] [CrossRef] - Huang, G.B.; Liang, N.Y.; Rong, H.J.; Saratchandran, P.; Sundararajan, N. On-line sequential extreme learning machine. Comput. Intell.
**2005**, 2005, 232–237. [Google Scholar]

**Figure 1.**The SLR-DS18B20 System Architecture. This diagram depicts the proposed system’s architecture. The Raspberry Pi Zero W (Device

**1**) is connected to the series of DS18B20 sensors (the sensors are given the number

**2**) using pins 7, 17, and 25. Pin 7 is responsible for the communication, pin 17 provides 3.3 voltage to the device, while pin 25 is responsible for grounding the circuit. Then, these sensors are inserted into a commercial fridge (device

**3**).

**Figure 2.**Submerge procedure of the reference sensor and the sensor that is going to be calibrated. Initially, we gently stir and submerge the reference sensor, as seen in the left image. Then, we stir and submerge the sensor that is going to be calibrated (right image).

**Figure 3.**The AE regarding sampled values for both temperature areas. The AE for each sampled value is depicted with blue dots. The x-axis shows the temperatures, while on the y-axis, the AE calculated using Formula (7). The left diagram shows the 1st temperature zone’s measurement results where the AE ranged from 0 °C to 2.07 °C. The right graph shows the 2nd temperature zone’s measurement results, where the AE went from 0 °C to 2.07 °C.

**Figure 4.**The AE regarding predicted values for both temperature areas. The AE for each sampled value is depicted with blue dots. The x-axis shows the temperatures, while on the y-axis, the AE, which was calculated using Formula (7). The left diagram shows the 1st temperature zone’s measurement results where the AE ranged from 0 °C to 0.75 °C. The right diagram shows the 2nd temperature zone’s measurement results, where the AE went from 0 °C to 0.4 °C.

**Figure 5.**Comparison between actual and predicted values for the 1st temperature zone. This diagram compares the $\overline{{R}^{2}}$ for the actual and predicted values. The 95% CI for each category can be seen with a red vertical line. Each CI’s limits are depicted with magenta (actual values), and blue (predicted values) dashed lines. The two Cis do not overlap, which is a strong indication that the error reduction achieved after the application of linear regression is statistically significant.

**Figure 6.**Comparison between actual and predicted values for the 2nd temperature zone. This diagram compares the $\overline{{R}^{2}}$ for the actual and predicted values. The 95% CI for each category can be seen with a red vertical line. The limits for each CI are depicted with magenta (actual values), and blue (predicted values) dashed lines. The two Cis do not overlap, which is a strong indication that the error reduction achieved after the application of linear regression is statistically significant.

Sampled Measurements | Predicted Measurements | |
---|---|---|

1st Temperature Zone | 0.64 | 0.41 |

2nd Temperature Zone | 0.19 | 0.007 |

Method | Parameter Name | Symbol | Values/Types |
---|---|---|---|

SVM | Kernel | $ker$ | $ker=\left\{Linear,RBF\right\}$ |

B-ELM | Output Function | $g$ | ${g}_{B-ELM}=\left\{Sigmoid,Sinusoid\right\}$ |

OS-ELM | Output Function | $g$ | ${g}_{OS-ELM}=\left\{Sigmoid,Sinusoid,RBF\right\}$ |

B-ELM and OS-ELM | Input Weights Matrix | $w$ | $w\in \left[-1,1\right]$ |

Input Thresholds Matrix | $\theta $ | $\theta \in \left[-1,1\right]$ | |

Hidden Layer Units No | n | $n\in 100$ | |

Experiments No | $expNo$ | $expNo=10$ |

Method | MSE |
---|---|

SVM (Linear) | 0.0006991 |

SVM (RBF) | 0.0003568 |

B-ELM (Sigmoid) | 0.0020735 |

B-ELM (Sinusoid) | 0.0119922 |

OS-ELM (Sigmoid) | 0.0018569 |

OS-ELM (Sinusoid) | 0.0010747 |

OS-ELM (RBF) | 0.0010636 |

SLR-DS18B20 | 0.0003505 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Koritsoglou, K.; Christou, V.; Ntritsos, G.; Tsoumanis, G.; Tsipouras, M.G.; Giannakeas, N.; Tzallas, A.T.
Improving the Accuracy of Low-Cost Sensor Measurements for Freezer Automation. *Sensors* **2020**, *20*, 6389.
https://doi.org/10.3390/s20216389

**AMA Style**

Koritsoglou K, Christou V, Ntritsos G, Tsoumanis G, Tsipouras MG, Giannakeas N, Tzallas AT.
Improving the Accuracy of Low-Cost Sensor Measurements for Freezer Automation. *Sensors*. 2020; 20(21):6389.
https://doi.org/10.3390/s20216389

**Chicago/Turabian Style**

Koritsoglou, Kyriakos, Vasileios Christou, Georgios Ntritsos, Georgios Tsoumanis, Markos G. Tsipouras, Nikolaos Giannakeas, and Alexandros T. Tzallas.
2020. "Improving the Accuracy of Low-Cost Sensor Measurements for Freezer Automation" *Sensors* 20, no. 21: 6389.
https://doi.org/10.3390/s20216389