Edge-to-Cloud Long Short-Term Memory Model for Ambient Carbon Monoxide Level Prediction
Article Sidebar
Main Article Content
Abstract
Carbon monoxide (CO) is a harmful gas from incomplete fuel combustion, often found in motor vehicle emissions. Prolonged exposure can cause serious health issues or death. While existing Internet-of-Things (IoT) systems monitor CO levels, most lack predictive capability. One prior study used an Artificial Neural Network with limited accuracy (79%). To address this, a new IoT-based CO prediction model is proposed using a Long Short-Term Memory (LSTM) algorithm. The model predicts future CO concentrations based on seasonal patterns, empowering users to anticipate and proactively respond to potential exposure. By leveraging Edge-to-Cloud architecture, this approach enables low-power edge devices to send data to the cloud for accurate forecasting without local model deployment. Based on the evaluation, the model achieved 98.42% accuracy, outperforming previous approaches by 19.42%. It also showed superior performance against other algorithms, with the lowest MAE (0.026305), MSE (0.016004), RMSE (0.126506), and the highest R² (0.997647). Evaluation with AIC and BIC confirmed its reliability, scoring zero after MinMax scaling. The model demonstrates a substantial advancement in predictive CO monitoring, giving users actionable insights to protect health and safety.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
H. Kinoshita et al., “Carbon monoxide poisoning,” Toxicology Reports, vol. 7, pp. 169–173, 2020.
L. K. Weaver, “Carbon monoxide poisoning,” Undersea & amp; hyperbaric medicine : journal of the Undersea and Hyperbaric Medical Society, Inc, vol. 47, no. 1, p. 151—169, 2020.
L. M. Chu, S. Shaefi, J. D. Byrne, R. W. Alves de Souza, and L. E. Otterbein, “Carbon monoxide and a change of heart,” Redox Biology, vol. 48, p. 102183, Dec. 2021.
M. Yang et al., “A systematic review and metaanalysis of air pollution and angina pectoris attacks: identification of hazardous pollutant, short-term effect, and vulnerable population,” Environmental Science and Pollution Research, vol. 30, no. 12, pp. 32246–32254, Mar. 2023.
“Carbon monoxide,” World Health Organisation; obtainable from WHO Publications Centre USA, Geneva : Albany, N.Y, 13, 1979.
G. Reumuth et al., “Carbon monoxide intoxication: What we know,” Burns, vol. 45, no. 3, pp. 526–530, 2019.
G. D. Astudillo, L. E. Garza-Casta¯non and L. I. Minchala Avila, “Design and Evaluation of a Reliable Low-Cost Atmospheric Pollution Station in Urban Environment,” in IEEE Access, vol. 8, pp. 51129-51144, 2020
T. Joseph et al., “Portable gas detection and warning system for olfactory disabled people,” in 2020 International Conference for Emerging Technology, INCET 2020, 2020.
Y. A. Koedoes, S. Jie, M. N. A. Nur, Bunyamin and A. Astari, “Design of Prototype System for Monitoring Air Quality for Smart City Implementation,” IOP Conference Series: Materials Science and Engineering, vol. 797, no. 1, p. 012023, Mar. 2020.
T. Porselvi, S. G. CS, J. B, P. K and S. B. S, “IoT-Based Coal Mine Safety and Health Monitoring System using LoRaWAN,” in 2021 3rd International Conference on Signal Processing and Communication (ICPSC), pp. 49–53, May 2021.
H. Etemadfard, V. Sadeghi, F. Hassan Ali and R. Shad, “CO Emissions Modelling and Prediction using ANN and GIS,” Pollution, vol. 7, no. 3, Jul. 2021.
A. N. Hikmah and C. B. Dwi Kuncoro, “Carbon Monoxide Monitoring System based on IoT with Low Power Sensor Node for Indoor Applications,” in 2022 9th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), pp. 316–320, Oct. 2022.
Karuna, G., Kumar, R.P. Ram, Gopaldas, Steven, Parvathaneni, Vasista and Lokesh, Teddu, “Air Quality and Hazardous Gas Detection using IoT for Household and Industrial Areas,” E3S Web Conf., vol. 391, p. 01146, 2023.
D. M. B. Sidan, H. Hartono and S. Suyatmo, “Design And Development Of Diesel Power Plant Exhaust Gas Emission Monitoring Based on IoT,” Int. Conf. Adv. Transp. Eng. Appl. Soc. Sci., vol. 3, no. 1, pp. 35–40, Dec. 2024.
A. Rerkratn, V. Riewruja, W. Petchmaneelumka and S. Tammaruckwattana, “Wireless Carbon Monoxide Level Control and Monitoring System,” in 2025 11th International Conference on Control, Automation and Robotics (ICCAR), pp. 537–541, Apr. 2025.
V. N. Saputri, F. A. Alifteria, A. I. Agusty, M. Anggaryani and M. N. R. Jauhariyah, “The use of DHT11 for making green ecosystem model,” AIP Conference Proceedings, vol. 2858, no. 1, p. 040007, Aug. 2023.
A. Sudaryanto, Yohanes Aditya Wisnu W, and Agung Kridoyono, “Accuracy of DHT11 Temperature and Humidity Sensor In Egg Incubator,” INFOTRON, vol. 4, no. 1, pp. 1–6, May 2024.
K. Han and Y. Wang, “A review of artificial neural network techniques for environmental issues prediction,” Journal of Thermal Analysis and Calorimetry, vol. 145, no. 4, pp. 2191–2207, Aug. 2021.
R. Maya, B. Hassan and A. Hassan, “Develop an artificial neural network (ANN) model to predict construction projects’ performance in Syria,” Journal of King Saud University Engineering Sciences, vol. 35, no. 6, pp. 366–371, Sep. 2023.
S. C. Agustinur, K. I. Khalifa, M. Yantidewi and U. A. Deta, “Literature Review: Air Oxygen Level Monitoring System,” Int. J. Res. Community Empower., vol. 1, no. 2, pp. 62–70, Jul. 2023.
L. M. Easterline, A. A.-Z. R. Putri, P. S. Atmaja, A. L. Dewi and A. Prasetyo, “Smart Air Monitoring with IoT-based MQ-2, MQ-7, MQ-8, and MQ-135 Sensors using NodeMCU ESP32,” Procedia Computer Science, vol. 245, pp. 815–824, Jan. 2024.
E. Evcin and Y. M. Erten, “Comparison of Different Weather Data Acquisition Methods,” in 2024 9th International Conference on Computer Science and Engineering (UBMK), Oct. 2024, pp. 1–6.
D. Milojicic, “The Edge-to-Cloud Continuum,” Computer, vol. 53, no. 11, pp. 16–25, Nov. 2020.
M. N. Jamil, O. Schel´en, A. Afif Monrat and K. Andersson, “Enabling Industrial Internet of Things by Leveraging Distributed Edge-to-Cloud Computing: Challenges and Opportunities,” IEEE Access, vol. 12, pp. 127294–127308, 2024.
D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Computer Science, vol. 7, p. e623, Jul. 2021.
T. O. Hodson, “Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not,” Geoscientific Model Development, vol. 15, no. 14, pp. 5481–5487, 2022.
S. I. Vrieze, “Model selection and psychological theory: A discussion of the differences between the Akaike information criterion (AIC) and the Bayesian information criterion (BIC),” Psychological Methods, vol. 17, no. 2, pp. 228–243, 2012.
S. Portet, “A primer on model selection using the Akaike Information Criterion,” Infectious Disease Modelling, vol. 5, pp. 111–128, Jan. 2020.
H. Akaike, “Akaike’s Information Criterion,” in International Encyclopedia of Statistical Science, M. Lovric, Ed., Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 41–42, 2025.
