Forecasting Method For Air Pollution Using Machine Learning

This chapter aims to explore the application of Internet of Things (IoT) and machine learning (ML) in assessing the planning and management of smart cities and new towns. Additionally, we have discussed the possible solutions that combine IoT and ML opportunities in this field. Similarly, our results support that ML and IoT optimize resources, address environmental challenges and enhance citizen well-being by using real-time data and predictive models. However, challenges such as interoperability, cybersecurity, data protection, algorithmic bias and high costs must be addressed. Finally, we support that by adopting transparent governance and innovation, smart cities and new towns can build resilient urban ecosystems that prioritize the needs of their residents and ensure equitable development.

Air quality, both indoors and outdoors, is crucial for public health as it affects respiratory conditions and overall well-being. Machine learning (ML) techniques offer innovative solutions for monitoring and predicting air quality. However, choosing the right ML algorithms and evaluation metrics is essential for creating accurate air quality prediction models, as these choices directly impact the accuracy and reliability of the results. This study aims to explore and summarize the literature on the use of ML techniques in predicting and optimizing air quality, addressing the urgent issue of air pollution. The review analyzed papers from two electronic databases, namely Scopus and Science Direct. Information on ML techniques for predicting air quality and identifying the main sources of pollution was extracted from 26 studies. The study focuses on common ML techniques employed in air quality prediction, including classification, deep learning, regression, ensemble learning, and combinations of regression and deep learning. It also identifies the evaluation metrics used to assess the performance of these models, such as recall, root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). By synthesizing existing knowledge, this study provides a comprehensive understanding of the metrics researchers use to measure the overall effectiveness of ML algorithms. It serves as a benchmark for future research and guides the selection of appropriate evaluation metrics in the field of air quality prediction.

Background The Internet of Things (IoT) is a swiftly advancing technology with wide-ranging applications in smart cities, where substantial data exchange and real-time services necessitate high standards of security, privacy, and operational efficiency. Current IoT frameworks frequently face difficulties in delivering strong protection against emerging post-quantum threats while also preserving system performance, especially in decentralized and data-heavy smart city settings. Methods To tackle these issues, this article introduces a Post-Quantum Ring Signature and ABC-based Effective IoT (PQRAEI) framework. This model combines blockchain technology, post-quantum cryptography, and hybrid swarm optimization methods. Initially, data preprocessing is conducted using the K-Nearest Neighbour (KNN) algorithm for data imputation and min–max scaling for normalization. Secure and privacy-preserving decentralized transactions are guaranteed through a Post-Quantum Linkable Ring Signature (PQLRS) scheme, which functions through a three-phase cryptographic process. Additionally, air quality forecasting is improved using an Artificial Bee Colony (ABC) optimization algorithm enhanced with Q-learning, facilitating efficient exploration and identification of optimal environmental parameters that affect the Air Quality Index (AQI). Results The effectiveness of the proposed PQRAEI framework is assessed against existing models, specifically FHPCC, ELDSE, and PQBFR, utilizing metrics such as signing time, verification time, Peak Signal-to-Noise Ratio (PSNR), latency, and throughput. Experimental findings indicate that PQRAEI achieves significantly reduced latency and increased throughput, while ensuring strong cryptographic efficiency and data integrity in comparison to the benchmark models. Conclusions The proposed PQRAEI framework significantly improves security, privacy, and performance in IoT-based smart city environments. By utilizing post-quantum cryptography, blockchain, and intelligent swarm optimization, the model offers a scalable and future-ready solution.

This chapter explores how smart cities can enhance building management through technologies like the Internet of Things (IoT) and advanced predictive models, focusing on energy efficiency and air quality. The escalating reliance on technology as the primary solution to contemporary and future challenges has highlighted Internet of Things (IoT), digitalization, and machine learning, among others, as new methodologies for assessing management in smart cities. Moreover, in the realm of defining innovative building management systems, pressing issues such as climate change and pandemic episodes like COVID-19 underscore the need to prioritize energy efficiency and air quality. This imperative has led to the emergence of digital twins, a technology integrating 3D models with real-time data, enabling a comprehensive understanding of building dynamics. In addition, automated prediction models leveraging advanced statistical and machine learning techniques contribute significantly to enhancing climatization control, energy efficiency, and air quality management. These predictive models analyze historical data, enabling accurate forecasts to assess future behavior, which is crucial for effective maintenance planning. The application of linear and non-linear regression models, alongside techniques like Support Vector Machines and neural networks, further refines predictions. Additionally, real-time monitoring and decision algorithms optimize information transmission during incidents, ensuring a rapid response to environmental factors or anomalies, thereby mitigating risks and maximizing operational efficiency.

In smart cities, air pollution has harmful impacts on human physical health and the quality of living environment. correctly predicting air quality is important for developing effective strategies to reduce air pollution and promote healthier, more sustainable environments. Tracking and predicting air pollution is essential for enabling individuals to make wellinformed choices that safeguard their health. Predicting air quality is vital for public health, environmental management, and the development of effective policies. This research focuses on predicting the Air Quality Index (AQI) using machine learning techniques, with an emphasis on improving model efficiency and prediction accuracy. This study compares the performance of two regression algorithms: Linear Regression and Principal Component Regression (PCR) with Decision Tree Regression, across several key evaluation metrics. The performance is assessed using measures such as Mean Squared Error (MSE), Mean Percentage Error (MPE), Mean Absolute Percentage Error (MAPE), Median Absolute Error (MedAE), Explained Variance, Adjusted R². The analysis reveals that the PCR with Decision Tree Regression model outperforms Linear Regression in terms of accuracy, as indicated by lower error values and higher explained variance. The superior model also demonstrates better generalization, with more robust metrics like MedAE, which reduces sensitivity to outliers. Overall, the study highlights the advantages of combining principal component regression with decision tree regression for enhanced predictive accuracy.

Ambient air pollution is the most harmful environmental risk to health. As urban air quality improves, health costs from air pollution-related diseases diminish. This is why air pollution is a major challenge for the public and government around the world. Deployment of the Internet of Things-based sensors has considerably changed the dynamics of predicting air quality. Air pollution can be predicted using machine learning algorithms Data-based sensors in the context of smart cities. In this paper, we performed pollution forecasting using machine learning techniques while presenting a comparative study to determine the best model to accurately predict air quality. Random Forest is an efficient algorithm capable of detecting air quality.

Air pollution has significant and severe impacts on human health, the environment, materials, and the economy, emerging as a key issue for microclimate and air quality regulation. Hence, the spatial and temporal characterization of air pollutants and their relationship with meteorological constraining factors is of utmost importance, particularly under a climate change perspective. Air pollutants’ spatial and temporal characterization over the Iberian Peninsula is performed, focusing particularly on the emissions of Particulate Matter (PM) and Carbon Monoxide (CM) during wildfire events in 2012-2023. This will be performed based on the Copernicus Atmosphere Monitoring (CAMS) data, to profit from the added value of having reliable and gridded information on the atmosphere composition and its related processes, anywhere in the world. After a preliminary analysis, air quality (AQ) forecasts are produced to model AQ environmental emergencies. The rationale is to develop a methodology to forecast air pollutants' exceedances, without being limited to areas closer to monitoring AQ stations. To achieve this goal, Machine Learning (ML) methods are applied to find the most efficient model architecture predicting pollutants’ concentration a few days ahead.Space-time patterns reveal a good agreement between CAMS data and extreme fire events, with this agreement being clearer for maximum concentrations measured by CAMS pollutants such as CO, PM10, and PM2.5, as well as the exceedances of pollutant thresholds during fire activity periods, over affected regions. ML models reveal coefficient of determination (R) values ranging from 0.76 to 0.85 for their forecasts, revealing high accuracy in predicting PM10 exceedances, with precision levels up to 0.91.Model results reveal the potential to develop an air quality tool over regions less covered by the national air quality monitoring network.Acknowledgements: This study is partially supported by the Portuguese Fundação para a Ciência e a Tecnologia (FCT) I.P./MCTES on behalf of DHEFEUS -2022.09185.PTDC and the project FAIR- 2022.01660.PTDC).

This research navigates the confluence of data analytics, machine learning, and artificial intelligence to revolutionize the management of urban services in smart cities. The study thoroughly investigated with advanced tools to scrutinize key performance indicators integral to the functioning of smart cities, thereby enhancing leadership and decision-making strategies. Our work involves the implementation of various machine learning models such as Logistic Regression, Support Vector Machine, Decision Tree, Naive Bayes, and Artificial Neural Networks (ANN), to the data. Notably, the Support Vector Machine and Bernoulli Naive Bayes models exhibit robust performance with an accuracy rate of 70% precision score. In particular, the study underscores the employment of an ANN model on our existing dataset, optimized using the Adam optimizer. Although the model yields an overall accuracy of 61% and a precision score of 58%, implying correct predictions for the positive class 58% of the time, a comprehensive performance assessment using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metrics was necessary. This evaluation results in a score of 0.475 at a threshold of 0.5, indicating that there's room for model enhancement. These models and their performance metrics serve as a key cog in our data analytics pipeline, providing decision-makers and city leaders with actionable insights that can steer urban service management decisions. Through real-time data availability and intuitive visualization dashboards, these leaders can promptly comprehend the current state of their services, pinpoint areas requiring improvement, and make informed decisions to bolster these services. This research illuminates the potential for data analytics, machine learning, and AI to significantly upgrade urban service management in smart cities, fostering sustainable and livable communities. Moreover, our findings contribute valuable knowledge to other cities aiming to adopt similar strategies, thus aiding the continued development of smart cities globally.

It was analyzed the information of databases, encryption algorithms, and information security that are the main components of a Smart City. The problem is the lack of security of public or secret data that is stored in a repository, where there is access to the citizen, local government, and central government. The objective is to define a security prototype and adopt a cryptographic algorithm to mitigate the risks of the database in the management of a Smart City. It was used the deductive method and exploratory research to analyze the information of the reference articles. It turned out a general prototype of security; an algorithm to implement a database for Smart City; an algorithm of data protection expressed in flowcharts. It was concluded that information protected with an encryption algorithm, is a support to be more efficient, reduce costs, reduce the environmental footprint and improve the management of a Smart City.

The application of Machine Learning (ML) in Electronic Design Automation (EDA) for Very Large-Scale Integration (VLSI) design has garnered significant research attention. Despite the requirement for extensive datasets to build effective ML models, most studies are limited to smaller, internally generated datasets due to the lack of comprehensive public resources. In response, we introduce EDALearn, the first holistic, open-source benchmark suite specifically for ML tasks in EDA. This benchmark suite presents an end-to-end flow from synthesis to physical implementation, enriching data collection across various stages. It fosters reproducibility and promotes research into ML transferability across different technology nodes. Accommodating a wide range of VLSI design instances and sizes, our benchmark aptly represents the complexity of contemporary VLSI designs. Additionally, we provide an in-depth data analysis, enabling users to fully comprehend the attributes and distribution of our data, which is essential for creating efficient ML models. Our contributions aim to encourage further advances in the ML-EDA domain.

For the past several years, urbanization and industrialization have been on increase in developed nations, resulting in a huge rise in contaminated air. Citizens and governments have become increasingly worried about the detrimental effects of Air Pollution (AP). Predicting Air Quality (AQ) is a critical step that the government should take because it becoming a major public health concern. The AQ index is a metric for measuring AQ. When fossil fuels such as natural gas, coal, and wood are burned, as well as factories and motor cars, carbon dioxide, nitrogen dioxide, carbon monoxide, and other noxious gases are emitted which leads to AP. This can cause health issues such as cancer, brain impairment, and even death. The forecast of AP allows the government to take preventive actions such as restricting driving hours, partially closing factories, and issuing public service messages. So, the prediction of AP is essential and there is a lot of research being done in this field. This research article reviewed the recent works on AP prediction and present the research using five important sections. In the first section of this review, we will discuss the available methods that can be used to acquire AP data. Second, the processes that can be carried out to pre-process the raw data. Third, the prediction of pollution made use of developing technologies such as Machine Learning (ML) and Deep Learning (DL), and lastly, the evaluation of the model was discussed. The research gap and future steps on the prediction of AP also elaborated. This review will help researchers for a better understanding of the automatic prediction of AP.

Air quality monitoring and prediction in many industrial and urban areas, it has become one of the most important activities. Owing to different types of pollution, air quality is heavily affected. With increasing air pollution, efficient air quality monitoring models is to be implemented; these models gather data on the concentration of air pollutants. In a proposed approach, to solve three problems- prediction, interpolation and feature analysis, previously these problems were solved using three different models but now in the proposed system can solve these three problems in one model i.e Air Pollutant Prediction. This approach relates to unlabeled spatiotemporal data to enhance interpolation efficiency and air quality prediction. Experiments to test the proposed solution based on the real-time data sources collected by the Karnataka State Pollution Control Board (KSPCB), India. The goal of this research paper is to explore various strategies based on machine learning techniques for monitoring and predicating the air quality.

Abstract. As air pollution is regarded as the single largest environmental health risk in Europe it is important that communication to the public is up to date and accurate and provides means to avoid exposure to high air pollution levels. Long- and short-term exposure to outdoor air pollution is associated with increased risks of mortality and morbidity. Up-to-date information on present and coming days' air quality helps people avoid exposure during episodes with high levels of air pollution. Air quality forecasts can be based on deterministic dispersion modelling, but to be accurate this requires detailed information on future emissions, meteorological conditions and process-oriented dispersion modelling. In this paper, we apply different machine learning (ML) algorithms – random forest (RF), extreme gradient boosting (XGB), and long short-term memory (LSTM) – to improve 1, 2, and 3 d deterministic forecasts of PM10, NOx, and O3 at different sites in Greater Stockholm, Sweden. It is shown that the deterministic forecasts can be significantly improved using the ML models but that the degree of improvement of the deterministic forecasts depends more on pollutant and site than on what ML algorithm is applied. Also, four feature importance methods, namely the mean decrease in impurity (MDI) method, permutation method, gradient-based method, and Shapley additive explanations (SHAP) method, are utilized to identify significant features that are common and robust across all models and methods for a pollutant. Deterministic forecasts of PM10 are improved by the ML models through the input of lagged measurements and Julian day partly reflecting seasonal variations not properly parameterized in the deterministic forecasts. A systematic discrepancy by the deterministic forecasts in the diurnal cycle of NOx is removed by the ML models considering lagged measurements and calendar data like hour and weekday, reflecting the influence of local traffic emissions. For O3 at the urban background site, the local photochemistry is not properly accounted for by the relatively coarse Copernicus Atmosphere Monitoring Service ensemble model (CAMS) used here for forecasting O3 but is compensated for using the ML models by taking lagged measurements into account. Through multiple repetitions of the training process, the resulting ML models achieved improvements for all sites and pollutants. For NOx at street canyon sites, mean squared error (MSE) decreased by up to 60 %, and seven metrics, such as R2 and mean absolute percentage error (MAPE), exhibited consistent results. The prediction of PM10 is improved significantly at the urban background site, whereas the ML models at street sites have difficulty capturing more information. The prediction accuracy of O3 also modestly increased, with differences between metrics. Further work is needed to reduce deviations between model results and measurements for short periods with relatively high concentrations (peaks) at the street canyon sites. Such peaks can be due to a combination of non-typical emissions and unfavourable meteorological conditions, which are rather difficult to forecast. Furthermore, we show that general models trained using data from selected street sites can improve the deterministic forecasts of NOx at the station not involved in model training. For PM10 this was only possible using more complex LSTM models. An important aspect to consider when choosing ML algorithms is the computational requirements for training the models in the deployment of the system. Tree-based models (RF and XGB) require fewer computational resources and yield comparable performance in comparison to LSTM. Therefore, tree-based models are now implemented operationally in the forecasts of air pollution and health risks in Stockholm. Nevertheless, there is big potential to develop generic models using advanced ML to take into account not only local temporal variation but also spatial variation at different stations.

24 - Current trends and future challenges in smart waste management in smart cities

The burgeoning field of Machine Learning (ML) has revolutionized various aspects of our lives. However, the reliance on vast amounts of data, often containing personal information, raises concerns about individual privacy. Striking a balance between effective ML model training and protecting sensitive data is crucial for responsible development and ethical implementation. This paper explores the challenges and potential solutions for preserving privacy in ML training, focusing on differential privacy (DP). The advantages of implementing DP in ML training include robust protection of individual data, enabling meaningful insights from large datasets while maintaining privacy. This is essential for ethical and responsible data usage in machine learning applications. However, DP in ML training presents challenges including scalability issues and trade-offs between utility and privacy. The paper also covers the mathematical mechanisms of Laplace and Gaussian and their noise addition, followed by a comparative analysis of their efficiency within the dataset.