| Title | IoT based smart framework to predict air quality in congested traffic areas using SV-CNN ensemble and KNN imputation model |
|---|---|
| ID_Doc | 42557 |
| Authors | Alnowaiser, K; Alarfaj, AA; Alabdulqader, EA; Umer, M; Cascone, L; Alankar, B |
| Title | IoT based smart framework to predict air quality in congested traffic areas using SV-CNN ensemble and KNN imputation model |
| Year | 2024 |
| Published | |
| Abstract | Addressing air pollution presents a significant environmental challenge in the context of smart city environments. Real-time monitoring of pollution data empowers local authorities to assess current traffic conditions and make informed decisions accordingly. The integration of Internet of Things (IoT) sensors has revolutionized air quality prediction, with human activities being the primary contributors to air pollution, posing threats to all forms of life. Gases such as SO2, PM10, O3, CO, NO2, among others, are key pollutants. Exposure to air pollution can lead to severe health issues and fatalities, underscoring the criticality of air quality monitoring. Distinguishing between breathable and non -breathable air quality further enhances the value of air quality monitoring. However, existing techniques face challenges in achieving high accuracy, exacerbated by missing values in datasets, which can significantly impact machine learning model performance. In response to these challenges, this research introduces an IoT-based automated system designed to classify air quality. This system is adept at managing missing data and attaining high accuracy levels. Central to this approach is a stacked ensemble voting classifier model, which combines two machine learning models. Additionally, the system incorporates the KNN Imputer to address missing values effectively. The work assesses the system's performance against seven alternative machine learning algorithms across two scenarios: one with missing values removed and another with KNN imputation applied. Notably, the proposed strategy achieves remarkable metrics, including 99.17% accuracy, 97.75% precision, 95.24% recall, and a 96.52% F1 score, when leveraging the KNN Imputer. These results underscore the effectiveness of the proposed model compared to current state-of-the-art methodologies. |
| https://doi.org/10.1016/j.compeleceng.2024.109311 |
Similar Articles
| ID | Score | Article |
|---|---|---|
43070
|
Popa, CL; Dobrescu, TG; Silvestru, CI; Firulescu, AC; Popescu, CA; Cotet, CE Pollution and Weather Reports: Using Machine Learning for Combating Pollution in Big Cities(2021)Sensors, 21, 21 | |
| 42305
|
Kataria, A; Puri, V AI- and IoT-based hybrid model for air quality prediction in a smart city with network assistance(2022)Iet Networks, 11, 6 | |
| 39260
|
Khan, MA; Kim, HC; Park, H Leveraging Machine Learning for Fault-Tolerant Air Pollutants Monitoring for a Smart City Design(2022)Electronics, 11, 19 | |
| 42444
|
Song, SG; Li, VOK; Lam, JCK; Wang, Y Personalized Ambient Pollution Estimation Based on Stationary-Camera-Taken Images Under Cross-Camera Information Sharing in Smart City(2023)Ieee Internet Of Things Journal, 10, 17 | |
| 38552
|
Neo, EX; Hasikin, K; Lai, KW; Mokhtar, MI; Azizan, MM; Hizaddin, HF; Razak, SA; Yanto Artificial intelligence-assisted air quality monitoring for smart city management(2023) | |
| 42972
|
Chatterjee, K; Raju, M; Thara, MN; Reddy, MS; Priyadharshini, M; Selvamuthukumaran, N; Mallik, S; Alshahrani, HM; Abbas, M; Soufiene, B Toward Cleaner Industries: Smart Cities' Impact on Predictive Air Quality Management(2024) | |
| 41627
|
Ameer, S; Shah, MA; Khan, A; Song, HB; Maple, C; Ul Islam, S; Asghar, MN Comparative Analysis of Machine Learning Techniques for Predicting Air Quality in Smart Cities(2019) |