Intelligent forecaster of concentrations (PM2.5, PM10, NO2, CO, O3, SO2) caused air pollution (IFCsAP)

Application of the Lasso regularisation technique in mitigating overfitting in air quality prediction models

As a significant global concern, air pollution triggers enormous challenges in public health and ecological sustainability, necessitating the development of precise algorithms to forecast and mitigate its impacts, which has led to the development of many machine learning (ML)-based models for predicting air quality. Meanwhile, overfitting is a prevalent issue with ML algorithms that decreases their efficacy and generalizability. The present investigation, using an extensive collection of data from 16 sensors in Tehran, Iran, from 2013 to 2023, focuses on applying the Least Absolute Shrinkage and Selection Operator (Lasso) regularisation technique to enhance the forecasting precision of ambient air pollutants concentration models, including particulate matter (PM2.5 and PM10), CO, NO2, SO2, and O3 while decreasing overfitting. The outputs were compared using the R-squared (R2), mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and normalised mean square error (NMSE) indices. Despite the preliminary findings revealing that Lasso dramatically enhances model reliability by decreasing overfitting and determining key attributes, the model's performance in predicting gaseous pollutants against PM remained unsatisfactory (R2PM2.5 = 0.80, R2PM10 = 0.75, R2CO = 0.45, R2NO2 = 0.55, R2SO2 = 0.65, and R2O3 = 0.35). The minimal degree of missing data presumably explained the strong performance of the PM model, while the high dynamism of gases and their chemical interactions, in conjunction with the inherent characteristics of the model, were the primary factors contributing to the poor performance of the model. Simultaneously, the successful implementation of the Lasso regularisation approach in mitigating overfitting and selecting more important features makes it highly suggested for application in air quality forecasting models.

Long term analysis of air quality parameters for Ludhiana, India: sources, trends and health impact

Ludhiana, a pollution hot spot in North India, has seen a rapid deterioration in air quality over the years due to urbanization and industrialization. This study interprets the variations of particulate matter (PM) and gaseous pollutants (Nitrogen oxide, Nitrogen dioxide, NOX, Sulphur dioxide, Carbon monoxide, Benzene, Toluene, Ozone, and Ammonia) for the data observed from 2017 to 2023 in Ludhiana. This also covers the analysis focused on capturing the changes that occurred at the times of lockdown imposed during the Coronavirus Disease (COVID-19). The maximum 24-h averaged mass concentration values exceeded the National Ambient Air Quality Standards (NAAQS) of 100 µg/m3 for PM10 concentration and 60 µg/m3 for PM2.5 concentration in 2018 by the factor of 5 and 8. With the onset of the COVID-19 lockdown in 2020 year, PM10 and PM2.5 reached the minimum level while CO, T, O3, and NO2 increased by the factor of 3.9, 1.9, 1.4, and 1.3 from their previous year. This NO2 is a precursor of ozone formation, a higher NO2 to NO ratio observed during the lockdown, confirms the role of nitrogen compounds in the higher ozone formation rate. Based on the NO2/NO ratio, the probability rate of ozone formation determined using survival analysis is observed to be 94% from 2017 to 2023. The local sources' contribution to these air pollutants during Pre-Lockdown, Lockdown, and Post-Lockdown are analyzed using principal component analysis. The impact of the lockdown on ozone concentration sources has been observed. During the Pre- and Post-Lockdown phases, three sources (PC1, PC2, and PC3) were positively identified. Ozone levels are linked to PC3 in these phases, but during the lockdown, a negative loading in PC3 and positive loadings in PC1 and PC2 indicate a decrease in ozone from reduced emissions and an increase from secondary reactions involving nitrogen compounds. Moreover, the Toluene to Benzene concentration ratio is > 2, indicating the source of their origin from industrial emission or other non-traffic sources. Health assessment for the years 2017-2019 reveals a significant decrease in the number of cases of all-cause mortality, ischemic heart disease, stroke, and chronic obstructive pulmonary disease associated with reducing PM2.5 concentrations to national and international standards.

Airborne particulate matter measurement and prediction with machine learning techniques

Air quality is a fundamental component of a healthy environment for human beings. Monitoring networks for air pollution have been established in numerous industrial zones. The data collected by the pervasive monitoring devices can be utilized not only for determining the current environmental condition, but also for forecasting it in the near future. This paper considers the applications of different machine learning methods for the prediction of the two most widely used quantities. Particulate matter (PM) with a diameter of 2.5 and 10 µm, respectively. The data are collected via a proprietary monitoring station, designated as the Ecolumn. The Ecolumn monitors a number of key parameters, including temperature, pressure, humidity, PM 1.0, PM 2.5, and PM 10, in a timely manner. The data were employed in the development of multiple models based on selected machine learning methods. The decision tree, random forest, recurrent neural network, and long short-term memory models were employed. Experiments were conducted with varying hyperparameters and network architectures. Different time scales (10 min, 1 h, and 24 h) were examined. The most optimal results were observed for the Long Short-Term Memory algorithm when utilizing the shortest available time spans (shortest averaging times). The decision tree and random forest algorithms demonstrated unexpectedly high performance for long averaging times, exhibiting only a slight decline in accuracy compared to neural networks for shorter averaging times. Recommendations for the potential applicability of the tested methods were formulated.

Design and Enhancement of a Fog-Enabled Air Quality Monitoring and Prediction System: An Optimized Lightweight Deep Learning Model for a Smart Fog Environmental Gateway

Effective air quality monitoring and forecasting are essential for safeguarding public health, protecting the environment, and promoting sustainable development in smart cities. Conventional systems are cloud-based, incur high costs, lack accurate Deep Learning (DL)models for multi-step forecasting, and fail to optimize DL models for fog nodes. To address these challenges, this paper proposes a Fog-enabled Air Quality Monitoring and Prediction (FAQMP) system by integrating the Internet of Things (IoT), Fog Computing (FC), Low-Power Wide-Area Networks (LPWANs), and Deep Learning (DL) for improved accuracy and efficiency in monitoring and forecasting air quality levels. The three-layered FAQMP system includes a low-cost Air Quality Monitoring (AQM) node transmitting data via LoRa to the Fog Computing layer and then the cloud layer for complex processing. The Smart Fog Environmental Gateway (SFEG) in the FC layer introduces efficient Fog Intelligence by employing an optimized lightweight DL-based Sequence-to-Sequence (Seq2Seq) Gated Recurrent Unit (GRU) attention model, enabling real-time processing, accurate forecasting, and timely warnings of dangerous AQI levels while optimizing fog resource usage. Initially, the Seq2Seq GRU Attention model, validated for multi-step forecasting, outperformed the state-of-the-art DL methods with an average RMSE of 5.5576, MAE of 3.4975, MAPE of 19.1991%, R2 of 0.6926, and Theil's U1 of 0.1325. This model is then made lightweight and optimized using post-training quantization (PTQ), specifically dynamic range quantization, which reduced the model size to less than a quarter of the original, improved execution time by 81.53% while maintaining forecast accuracy. This optimization enables efficient deployment on resource-constrained fog nodes like SFEG by balancing performance and computational efficiency, thereby enhancing the effectiveness of the FAQMP system through efficient Fog Intelligence. The FAQMP system, supported by the EnviroWeb application, provides real-time AQI updates, forecasts, and alerts, aiding the government in proactively addressing pollution concerns, maintaining air quality standards, and fostering a healthier and more sustainable environment.

AI-Enabled Portable E-Nose Regression Predicting Harmful Molecules in a Gas Mixture

The biomimetic electronic nose (e-nose) technology is a novel technology used for the identification and monitoring of complex gas molecules, and it is gaining significance in this field. However, due to the complexity and multiplicity of gas mixtures, the accuracy of electronic noses in predicting gas concentrations using traditional regression algorithms is not ideal. This paper presents a solution to the difficulty by introducing a fusion network model that utilizes a transformer-based multikernel feature fusion (TMKFF) module combined with a 1DCNN_LSTM network to enhance the accuracy of regression prediction for gas mixture concentrations using a portable electronic nose. The experimental findings demonstrate that the regression prediction performance of the fusion network is significantly superior to that of single models such as convolutional neural network (CNN) and long short-term memory (LSTM). The present study demonstrates the efficacy of our fusion network model in accurately predicting the concentrations of multiple target gases, such as SO2, NO2, and CO, in a gas mixture. Specifically, our algorithm exhibits substantial benefits in enhancing the prediction performance of low-concentration SO2 gas, which is a noteworthy achievement. The determination coefficient (R2) values of 93, 98, and 99% correspondingly demonstrate that the model is very capable of explaining the variation in the concentration of the target gases. The root-mean-square errors (RMSE) are 0.0760, 0.0711, and 3.3825, respectively, while the mean absolute errors (MAE) are 0.0507, 0.0549, and 2.5874, respectively. These results indicate that the model has relatively small prediction errors. The method we have developed holds significant potential for practical applications in detecting atmospheric pollution detection and other molecular detection areas in complex environments.

PM2.5 concentration prediction based on EEMD-ALSTM

The concentration prediction of PM2.5 plays a vital role in controlling the air and improving the environment. This paper proposes a prediction model (namely EEMD-ALSTM) based on Ensemble Empirical Mode Decomposition (EEMD), Attention Mechanism and Long Short-Term Memory network (LSTM). Through the combination of decomposition and LSTM, attention mechanism is introduced to realize the prediction of PM2.5 concentration. The advantage of EEMD-ALSTM model is that it decomposes and combines the original data using the method of ensemble empirical mode decomposition, reduces the high nonlinearity of the original data, and Specially reintroduction the attention mechanism, which enhances the extraction and retention of data features by the model. Through experimental comparison, it was found that the EEMD-ALSTM model reduced its MAE and RMSE by about 15% while maintaining the same R2 correlation coefficient, and the stability of the model in the prediction process was also improved significantly.

An idiosyncratic MIMBO-NBRF based automated system for child birth mode prediction

Predicting the mode of child birth is still remains one of the most complex and challenging tasks in ancient times. Also, there is no such strong methodologies are developed in the conventional works for birth mode prediction. Therefore, the proposed work objects to develop a novel and distinct optimization based machine learning technique for creating the child birth mode prediction system. This framework includes the modules of data imputation, feature selection, classification, and prediction. Initially, the data imputation process is performed to improve the quality of dataset by normalizing the attributes and filling the missed fields. Then, the Multivariate Intensified Mine Blast Optimization (MIMBO) technique is implemented to choose the best set of features by estimating the optimal function. After that, an integrated Naïve Bayes - Random Forest (NBRF) technique is developed by incorporating the functions of conventional NB and RF techniques. The novel contribution of this technique, a Bird Mating (BM) optimization technique is used in NBRF classifier for estimating the likelihood parameter to generate the Bayesian rules. The main idea of this paper is to develop a simple as well as efficient automated system with the use of hybrid machine learning model for predicting the mode of child birth. For this purpose, advanced algorithms such as MIMBO based feature selection, and NBRF based classification are implemented in this work. Due to the inclusion of MIMBO and BM optimization techniques, the performance of classifier is greatly improved with low computational burden and increased prediction accuracy. Moreover, the combination of proposed MIMBO-NBRF technique outperforms the existing child birth prediction methods with superior results in terms of average accuracy up to 99 %. In addition, some other parameters are also estimated and compared with the existing techniques for proving the overall superiority of the proposed framework.

Research on the Prediction of the Inauguration Development Direction of College Students’ Entrepreneurship Education Based on Educational Data Mining

In many related studies, educational data mining technology has been proven to play an important role in predicting the development direction of entrepreneurship education for college students. To further improve the accuracy of the prediction, we chose the grey prediction model as the basic prediction model and automatically optimized the weighting method to improve the model. To solve the problem of predicting the development direction of students’ employment in the guidance of entrepreneurship and employment in colleges and universities, the study selects the grey prediction model as the basic prediction model and chooses the automatic optimization and weighting method to improve the model. Meanwhile, the study establishes a variable system containing six dimensions: academic achievement; physical and mental development; cultural, physical, and artistic quantified status; ideological and political quantified status; scientific and technological innovation quantified status; social work quantified status. The final study used the actual prediction test to analyze the prediction effect. We have selected a variable system consisting of six dimensions, which are the results of extensive research. These dimensions include academic achievement, physical and mental development, cultural/sports/art quantitative status, ideological and political quantitative status, technological innovation quantitative status, and social work quantitative status. Each dimension provides us with important predictions about student entrepreneurship and employment. The results show that the model designed by the survey has only two cases of error in the prediction of 20 actual samples. At the same time, there is no prediction error in the two prediction directions of entrepreneurship and social employment. This shows that the model designed by the study is stable and accurate, and the prediction results are more reliable in the prediction directions of entrepreneurship and social employment. Compared with other relevant research results, our model performs well in predicting accuracy, especially in predicting entrepreneurial and social employment directions, without any prediction errors, indicating that our model has superior performance in predicting stability and accuracy compared to other studies.

New horizon in fuzzy distributions: statistical distributions in continuous domains generated by Choquet integral

In this paper, some statistical properties of the Choquet integral are discussed. As an interesting application of Choquet integral and fuzzy measures, we introduce a new class of exponential-like distributions related to monotone set functions, called Choquet exponential distributions, by combining the properties of Choquet integral with the exponential distribution. We show some famous statistical distributions such as gamma, logistic, exponential, Rayleigh and other distributions are a special class of Choquet distributions. Then, we show that this new proposed Choquet exponential distribution is better on daily gold price data analysis. Also, a real dataset of the daily number of new infected people to coronavirus in the USA in the period of 2020/02/29 to 2020/10/19 is analyzed. The method presented in this article opens a new horizon for future research.

Unveiling air pollution patterns in Yemen: a spatial-temporal functional data analysis

The application of spatiotemporal functional analysis techniques in environmental pollution research remains limited. As a result, this paper suggests spatiotemporal functional data clustering and visualization tools for identifying temporal dynamic patterns and spatial dependence of multiple air pollutants. The study uses concentrations of four major pollutants, named particulate matter (PM2.5), ground-level ozone (O3), carbon monoxide (CO), and sulfur oxides (SO2), measured over 37 cities in Yemen from 1980 to 2022. The proposed tools include Fourier transformation, B-spline functions, and generalized-cross validation for data smoothing, as well as static and dynamic visualization methods. Innovatively, a functional mixture model was used to capture/identify the underlying/hidden dynamic patterns of spatiotemporal air pollutants concentration. According to the results, CO levels increased 25% from 1990 to 1996, peaking in the cities of Taiz, Sana'a, and Ibb before decreasing. Also, PM2.5 pollution reached a peak in 2018, increasing 30% with severe concentrations in Hodeidah, Marib, and Mocha. Moreover, O3 pollution fluctuated with peaks in 2014-2015, 2% increase and pollution rate of 265 Dobson. Besides, SO2 pollution rose from 1997 to 2010, reaching a peak before stabilizing. Thus, these findings provide insights into the structure of the spatiotemporal air pollutants cycle and can assist policymakers in identifying sources and suggesting measures to reduce them. As a result, the study's findings are promising and may guide future research on predicting multivariate air pollution statistics over the analyzed area.

Assessment of urban air quality from Twitter communication using self-attention network and a multilayer classification model

Social media platforms are one of the prominent new-age methods used by public for spreading awareness or drawing attention on an issue or concern. This study demonstrates how the twitter responses of public can be used for qualitative monitoring of air pollution in an urban area. Tweets discussing about air quality in Delhi, India, were extracted during 2019-2020 using a machine learning technique based on self-attention network. These tweets were cleaned, sorted, and classified into 3-class quality viz. poor air quality, good air quality, and noise or neutral tweets. The present study used a multilayer classification model with first layer as an embedding layer and second layer as bi-directional long-short term memory (BiLSTM) layer. A method was then devised for estimating PM_2.5 concentration from the tweets using 'spaCy' similarity analysis of classified tweets and data extracted from Continuous Ambient Air Quality Monitoring Stations (CAAQMS) in Delhi for the study period. The accuracy of this estimation was found to be high (80-99%) for extreme air quality conditions (extremely good or severe) and lower during moderate variations in air quality. Application of this methodology depended on perceivable changes in air quality, twitter engagement, and environmental consciousness among public.

Public health events emergency management supervision strategy considering citizens’ and new media’s different ways of participation

Public health events have done great harm. Emergency management requires the joint participation of multiple parties including government department, pharmaceutical enterprises, citizens and new media. Then, what are the effects of different strategy choices in participation of citizens and new media on emergency management? To answer the question, we construct a four-party evolutionary game model, considering the citizens' two participation ways consisted of true evaluation and false evaluation, and the new media's two participation ways consisted of report after verification and report without verification. This is of more practical significance than simply studying whether citizens and new media participate in emergency management or not because citizen and new media participation does not represent the completely positive behavior. Then, we conduct the evolutionary stability analysis, solve the stable equilibrium points using the Lyapunov first method and conduct the simulation analysis with MATLAB 2020b. The results show that, firstly, the greater the probability of citizens making true evaluation, the more inclined the government department is to strictly implement the emergency management system; secondly, when the probability of citizens making true evaluation decreases, new media are more inclined to report after verification, and when new media lose more pageview value or should be punished more for reporting without verification, the probability that they report without verification is smaller; thirdly, the greater the probability of citizens making false evaluation, the less enthusiasm of pharmaceutical enterprises to participate in emergency management, which indicates that false evaluation is detrimental to prompt pharmaceutical enterprises to participate; what's more, the greater the probability of new media reporting after verification, the greater the probability of pharmaceutical enterprises actively participating, which shows that new media's verification to citizens' evaluation is beneficial to emergency management.

Full-convolution Siamese network algorithm under deep learning used in tracking of facial video image in newborns

This study was carried out with the aim of exploring the full-convolution Siamese network (SiamFC) in the application of neonatal facial video image tracking, achieving accurate recognition of neonatal pain and helping doctors evaluate neonatal emotions in an automatic manner. The current technology shows low accuracy on facial image recognition of newborns, so the SiamFC algorithm under the deep learning was optimized in this study. Besides, a newborn facial video image tracking model (FVIT model) was constructed based on the SiamFC algorithm in combination with the attention mechanism with face tracking algorithm, and the facial features of newborns were tracked and recognized. In addition, a newborn face database was constructed based on the adult face database to evaluate performance of the FVIT model. It was found that the accuracy of the improved algorithm is 0.889, higher by 0.036 in contrast to other models; the area under the curve (AUC) of success rate reaches 0.748, higher by 0.075 compared with other algorithms. What's more, the improved algorithm shows good performance in tracking the facial occlusion, facial expression changes, and scale conversion of newborns. Therefore, the improved algorithm shows higher accuracy and success rate and has good effect in capturing and tracking the facial images of newborns, thereby providing an experimental basis for facial recognition and pain assessment of newborns in the later stage.

Air quality prediction using CNN+LSTM-based hybrid deep learning architecture

Air pollution prediction based on variables in environmental monitoring data gains further importance with increasing concerns about climate change and the sustainability of cities. Modeling of the complex relationships between these variables by sophisticated methods in machine learning is a promising field. The objectives of this work are to develop a supervised model for the prediction of air pollution by using real sensor data and to transfer the model between cities. The combination of a convolutional neural network and a long short-term memory deep neural network model was proposed to predict the concentration of air pollutants in multiple locations of a city by using spatial-temporal relationships. Two approaches have been adopted: the univariate model contains the information of one pollutant whereas the multivariate model contains the information of all pollutants and meteorology data for prediction. The study was carried out for different pollutants which are in the publicly available data of the cities of Barcelona, Kocaeli, and İstanbul. The hyperparameters of the model (filter, frame, and batch sizes; number of convolutional/LSTM layers and hidden units; learning rate; and parameters for sample selection, pooling, and validation) were tuned to determine the architecture that achieved the lowest test error. The proposed model improved the prediction performance (measured by the root mean square error) by 11-53% for particulate matter, 20-31% for ozone, 9-47% for nitrogenoxides, and 18-46% for sulfurdioxide with respect to the 1-hidden layer long short-term memory networks utilized in the literature. The multivariate model without using meteorological data revealed the best results. Regarding transfer learning, the network weights were transferred from the source city to the target city. The model has more accurate prediction performance with the transfer of the network from Kocaeli to İstanbul as those neighbor cities have similar air pollution and meteorological characteristics.