Anđela Đorđević, Miroslav Milovanović, Marko Milojković, Miodrag Spasić

DOI Number
First page
Last page


Environmental conditions can have a crucial impact on the functioning of laboratory equipment. Electric components are sensitive to the influence of certain environmental factors such as temperature, humidity, vibrations, etc. Environmental factors should, therefore, be monitored to avoid their negative influence on the system and potential faults and failures they could cause. Unlike the traditional approaches which required the presence of special staff to monitor environmental factors and react if they are poor, the rise of the Internet of Things enhanced the application of intelligent solutions where human factor is not necessary. In this paper, research on data analysis, preprocessing and intelligent classification of environmental conditions has been conducted. The data was collected by sensors connected to Raspberry Pi. The applied monitoring system setup enabled long-distance monitoring of laboratory conditions through the internet and full applicability of fundamental IoT concepts. Since data preparation is an important step in the process of designing machine learning models, the collected data was analyzed and preprocessed in Python. Intelligent classification of environmental conditions was performed using machine learning models k-Nearest Neighbors and Random Forest. Grid search was used for model selection, and the performances of k-Nearest Neighbors and Random Forest machine learning models were compared. Experimental results show that these machine learning models can be successfully used for intelligent classification of environmental conditions.


Environmental conditions, Raspberry Pi, Internet of things, Data analysis, Machine learning

Full Text:



N. Driendl, F. Pauli and K. Hameyer, "Influence of Ambient Conditions on the Qualification Tests of the Interturn Insulation in Low-Voltage Electrical Machines," in IEEE Transactions on Industrial Electronics, vol. 69, no. 8, pp. 7807-7816, Aug. 2022, doi: 10.1109/TIE.2021.3108721.

F. A. L. Souza, P. C. T. Pereira, H. de Paula, B. J. C. Filho and A. V. Rocha, "Motor drive systems reliability: Impact of the environment conditions on the electronic component failure rates," 2014 IEEE Industry Application Society Annual Meeting, 2014, pp. 1-8, doi: 10.1109/IAS.2014.6978463.

M. S. S. Chani, K. S. Karimov, A. M. Asiri, M. M. Rahman and T. Kamal, “Effect of Vibrations, Displacement, Pressure, Temperature and Humidity on the Resistance and Impedance of the Shockproof Resistors Based on Rubber and Jelly (NiPc-CNT-Oil) Composites,” in Gels, vol. 8, no. 4, 226, Apr. 2022, doi: 10.3390/gels8040226.

M. Shooshtari, A. Salehi and S. Vollebregt, "Effect of Humidity on Gas Sensing Performance of Carbon Nanotube Gas Sensors Operated at Room Temperature," in IEEE Sensors Journal, vol. 21, no. 5, pp. 5763-5770, 1 March1, 2021, doi: 10.1109/JSEN.2020.3038647.

R. A. Amy, G. S. Aglietti and G. Richardson, “Reliability Analysis of Electronic Equipment Subjected to Shock and Vibration – A Review,” Shock and Vibration, vol. 16, no. 1, 2009, pp. 45-59, doi: 10.3233/SAV-2009-0453.

A. M. Veprik, “Vibration protection of critical components of electronic equipment in harsh environmental conditions,” Journal of Sound and Vibration, vol. 259, no. 1, 2003, pp. 161-175, doi: 10.1006/jsvi.2002.5164.

R. Usamentiaga, M. A. Fernandez, A. F. Villan and J. L. Carus, "Temperature Monitoring for Electrical Substations Using Infrared Thermography: Architecture for Industrial Internet of Things," in IEEE Transactions on Industrial Informatics, vol. 14, no. 12, pp. 5667-5677, Dec. 2018, doi: 10.1109/TII.2018.2868452.

Z. -x. Tu, C. -c. Hong and H. Feng, "EMACS: Design and implementation of indoor environment monitoring and control system," 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS), 2017, pp. 305-309, doi: 10.1109/ICIS.2017.7960010.

A. A. Jaber, F. K. I. Al-Mousawi and H. B. Jasem, “Internet of things based industrial environment monitoring and control: a design approach,” in International Journal of Electrical & Computer Engineering (2088-8708), pp. 4657-4667, vol. 9. no. 6, Dec. 2019, doi: 10.11591/ijece.v9i6.pp4657-4667.

A. D. Đorđević, M. B. Milovanović, M. T. Milojković, M. D. Spasić, “Intelligent Classification of Environmental Conditions Influencing the Work of Laboratory Equipment”, Proceedings of the XVI International Conference on Systems, Automatic Control and Measurements, SAUM 2022, Niš, Serbia, November 17.-18., 2022., Publisher: Faculty of Electronic Engineering, Niš, Faculty of Mechanical Engineering, Niš, Serbia (Accepted for publication)

S. Garcia, J. Luengo and F. Herrera, “Data preprocessing in data mining”, vol. 72, Cham, Switzerland: Springer International Publishing, 2015.

Raspberry Pi 3 Model B+, [Online]. Available:, visited in June 2022.

D. L. Whaley III, “The interquartile range: Theory and estimation”, PhD Thesis, East Tennessee State University, 2005.

H. M. Kaltenbach, “A concise guide to statistics”, Springer Science & Business Media, 2011.

L. Jiang, Z. Cai, D. Wang and S. Jiang, "Survey of Improving K-Nearest-Neighbor for Classification," Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007), 2007, pp. 679-683, doi: 10.1109/FSKD.2007.552.

O. Kramer, “Dimensionality reduction with unsupervised nearest neighbors.”, vol. 51. Berlin: Springer, 2013.

S. Sathe and C. C. Aggarwal, "Nearest Neighbor Classifiers Versus Random Forests and Support Vector Machines," 2019 IEEE International Conference on Data Mining (ICDM), 2019, pp. 1300-1305, doi: 10.1109/ICDM.2019.00164.

R. Primartha and B. A. Tama, "Anomaly detection using random forest: A performance revisited," 2017 International Conference on Data and Software Engineering (ICoDSE), 2017, pp. 1-6, doi: 10.1109/ICODSE.2017.8285847.



  • There are currently no refbacks.

Print ISSN: 1820-6417
Online ISSN: 1820-6425