Monitoring and improving CO2 concentration in classroom based on AIoT technology
Keywords:
AIoT, LR, MLP, predicted CO2 concentration, ThingSpeakAbstract
The paper presents the monitoring and improvement of CO₂ concentration in the classroom through an AIoT system including Raspberry Pi 3 connected to the MH - Z19B CO₂ gas sensor, DHT11 temperature - humidity sensor and Raspberry Pi camera. The collected data including temperature, humidity, current CO₂ gas and the number of people in a 70 m2 classroom are continuously sent to ThingSpeak for analysis and forecasting CO₂ concentration in the classroom using the Multi-Layer Perceptron (MLP) model and linear regression model (LR). The forecasted CO₂ gas concentration results help to give early warnings and control the fan system in the classroom when the predicted CO₂ concentration is greater than 1000 ppm to maintain safe air quality in the classroom, improve concentration and health of learners. The system was tested in real classroom conditions, showing 95.77% accuracy with LR and 98.21% with MLP in predicting CO₂ concentration. This research contributes to improving classroom air quality, contributing to protecting health and improving students' learning efficiency.
References
[1] P. Kadarkarai, P. D. S. Srinivasu, G. C. Ture, R. J. Reddy, and T. R. R. Reddy. IoT based Air Quality Monitoring and Air Purifier System. In: Proceedings of the 5th International Conference on Trends in Material Science and Inventive Materials (ICTMIM); May 12, 2025; IEEE. p.415-420. DOI: 10.1109/ICTMIM65579.2025.10988388.
[2] K. Seth, S. V., M. Manisha, P. Chaudhary, M. Arora, and D. N. Thatoi. Optimizing Indoor Air Quality with IoT and Sensor-Based Solutions: A Case Study of Office Buildings. In: Proceedings of the International Conference on Automation and Computing (AUTOCOM); Apr. 16, 2025; IEEE. p. 701-705. DOI: 10.1109/AUTOCOM64127.2025.10956264.
[3] M. A. Aditya, N. Rokhman, M. R. Effendi, S. Gumilar, P. Alqinsi, and N. Ismail. Smart Greenhouse System for Cultivation of Chili (Capsicum Annum L.) with Raspberry Pi 3B Based on MQTT Protocol. In: Proceedings of the 16th International Conference on Telecommunication Systems, Services, and Applications (TSSA); Mar. 17, 2023; IEEE. p. 233 -238. DOI: 10.1109/TSSA56819.2022.10063907.
[4] MathWorks. Working with Raspberry Pi Camera Board. 2025.
[5] Cyuan-Heng Luo, Hsuan Yang, Li-Pang Huang, Sachit Mahajan and Ling-Jyh Chen. A Fast PM2.5 Forecast Approach Based on Time-Series Data Analysis, Regression and Regularization. In: Conference on Technologies and Applications of Artificial Intelligence (TAAI), 2018, p. 78-81. DOI: 10.1109/TAAI.2018.00026.
[6] Dinesh Komarasamy, Nandhidha G C, Nandhinidevi S, Nanthini P L, Mohanasaranya and Kousalya K. Air Quality Prediction and Classification using Machine Learning. In: the 7th International Conference on Computing Methodologies and Communication (ICCMC), 2023. IEEE. p.187-191. DOI: 10.1109/ICCMC56507.2023.10083760.
[7] Khushi Maheshwari and Sampada Lamba. Air Quality Prediction using Supervised Regression Model. In: International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), 2019; IEEE. p. 1-7. DOI: 10.1109/ICICT46931.2019.8977694.
[8] A. Rosebrock. Implementing the Perception Neural Network with Python. PyImageSearch; 2021.
[9] N. Orouji, M. R. Mosavi, and D. Martín. A Lightweight and Real-Time Hardware Architecture for Interference Detection and Mitigation of Time Synchronization Attacks Based on MLP Neural Networks. IEEE Access. 2021; 9:142938–142949. DOI: 10.1109/ACCESS.2021.3120668.
[10] S. Lawande, V. N. Gavali, I. Sutar, and R. Nehe. Comparative Analysis of Machine Learning Models for Prediction of Air Quality Index. In: Proceedings of the International Conference on Intelligent Systems and Advanced Applications (ICISAA); 2024; IEEE. p.16-21. DOI: 10.1109/ICISAA62385.2024.10829167.
[11] Liang Ge, Aoli Zhou; Hang Li and Junling Liu. Deep Spatial-Temporal Fusion Network for Fine-Grained Air Quality Prediction. In: IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), 2019. IEEE. p.781 - 786. DOI: 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00132.
[12] Chia-Yu Lo, Wen-Hsing Huang, Ming-Feng Ho, Min-Te Sun; Ling-Jyh Chen and Kazuya Sakai. Recurrent Learning on PM2.5 Prediction Based on Clustered Airbox Dataset. In: Transactions on Knowledge and Data Engineering, 2022, IEEE. p. 5440 - 5451. DOI: 10.1109/TKDE.2020.3047634.
[13] B. Kovacs and R. Rusu-Both. IoT and Machine Learning-Based System for Predicting, Monitoring and Controlling Indoor Air Quality. In: Proceedings of the IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR); Jun. 14, 2024; IEEE, p. 1-5. DOI: 10.1109/AQTR61889.2024.10554278.
[14] Jitendra Managre and Navita Khatri. A Review on IoT and ML Enabled Smart Grid for Futurestic and Sustainable Energy Management. In: International Conference for Advancement in Technology (ICONAT);2022, p. 1-8. DOI: 10.1109/ICONAT53423.2022.9725932.
[15] Thuy Thi Tran, Nghia Quoc Phan and Hiep Xuan Huynh. Enhancing CO2 Sequestration Modeling in Mangrove Forests Through Random Forest Hyperparameter Optimization and Remote Sensing Band Analysis. In: 5th Asia Conference on Information Engineering (ACIE); 2025; IEEE. p. 37-43. DOI: 10.1109/ACIE64499.2025.00013.
[16] Snehal Lawande, Vidhya N Gavali, Indrayani Sutar and Reshma Nehe. Comparative Analysis of Machine Learning Models for Prediction of Air Quality Index. In: International Conference on Intelligent Systems and Advanced Applications (ICISAA), 2024. IEEE. p. 1-5. DOI: 10.1109/ICISAA62385.2024.10829167.
[17] Ajiboye S. Osunleke, Kazeem Alli, Ayorinde Bamimore, Adedayo Bamisaye, Mumeenah Mustapha and Hussain Abdullahi. Real-Time Air Quality Monitoring Using Artificial Intelligence (AI) and Internet of Things (IoT). In: 8th International Conference on Electrical, Control and Computer Engineering (InECCE), 2025, p.73-76. DOI: 10.1109/InECCE64959.2025.11151022.
[18] A. Anish Babu and R. Kavitha. Predictive Modeling of Air Pollution Levels using Machine Learning. In: 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), 2025, p. 698-702. DOI: 10.1109/ICSSAS66150.2025.11080698.
[19] D. Yassine, B. Naoua, J. Mustapha, and E. Hamza. Classification of Indoor CO₂ Levels: Exploring the Impact of Humidity, Temperature, and Occupancy on Air Quality Using Machine Learning Model. In: Proceedings of the Mediterranean Smart Cities Conference (MSCC); 2024; IEEE. p. 1-8. DOI: 10.1109/MSCC62288.2024.10697053.
[20] F. Gül and H. Eroǧlu. Sensor Classification for CO₂ Detection in IoT-Enabled Indoor Air Quality Monitoring Systems. In: Proceedings of the IEEE Asia-Pacific Conference on Geoscience, Electronics, and Remote Sensing Technology (AGERS); 2024; IEEE. p. 150-154. DOI: 10.1109/AGERS65212.2024.109328
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Oanh Tran Thi Hoang, Hung Nguyen Xuan, Ngoc Nguyen Quang, Phu Nguyen Ngoc
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
