Neuro-Fuzzy Transformation with Minimize Entropy Principle to Create New Features for Particulate Matter Prediction

Air pollution is a major global issue. In Thailand, this issue continues to increase every year, similar to other countries, especially during the dry season in the northern region. In this period, particulate matter with aerodynamic diameters smaller than 10 and 2.5 micrometers, known as PM10 and PM2.5, are important pollutants, most of which exceed the national standard levels, the so-called Thailand air quality index (T-AQI). Therefore, this study created a prediction model to classify T-AQI calculated from both types of PM. The neuro-fuzzy model with a minimum entropy principle model is proposed to transform the original data into new informative features. The processes in this model are able to discover appropriate separation points of the trapezoidal membership function by applying the minimum entropy principle. The membership value of the fuzzy section is then passed to the neural section to create a new data feature, the PM level, for each hour of the day. Finally, as an analytical process to obtain new knowledge, predictive models are created using new data features for better classification results. Various experiments were utilized to find an appropriate structure with high prediction accuracy. The results of the proposed model were favorable for predicting both types of PM up to three hours in advance. The proposed model can help people who are planning short-term outdoor activities.

[1]  S. Homhuan,et al.  The development of forest fire monitoring and warning system for agroforestry areas in Uttaradit Province, Thailand , 2020 .

[2]  Anamika Pimpa,et al.  Decision Support System for Dairy Cattle Management Using Computational Intelligence Technique , 2019, INFOCOM 2019.

[3]  Ari Karppinen,et al.  Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki. , 2011, The Science of the total environment.

[4]  Kemal Polat,et al.  Usage of output-dependent data scaling in modeling and prediction of air pollution daily concentration values (PM10) in the city of Konya , 2011, Neural Computing and Applications.

[5]  Narissara Eiamkanitchat,et al.  The Adaptive Dynamic Clustering Neuro-Fuzzy System for Classification , 2015 .

[6]  Aditya Kumar Patra,et al.  Particulate matter pollution in opencast coal mining areas: a threat to human health and environment , 2018 .

[7]  David C. Carslaw,et al.  Random forest meteorological normalisation models for Swiss PM 10 trend analysis , 2018 .

[8]  Ζ. Ceylan.  Forecasting PM10 levels using ANN and MLR: A case study for Sakarya City , 2018 .

[9]  Narissara Eiamkanitchat,et al.  An Ensemble K-Nearest Neighbor with Neuro-Fuzzy Method for Classification , 2014, IC2IT.

[10]  Narissara Eiamkanitchat,et al.  Collective Neural Networks System for PM10 Classification in the North of Thailand , 2018, 2018 22nd International Computer Science and Engineering Conference (ICSEC).

[11]  Timothy J. Ross,et al.  Membership Functions, Fuzzification and Defuzzification , 2000 .

[12]  M. Lovrić,et al.  Pollution Sources and Carcinogenic Risk of PAHs in PM1 Particle Fraction in an Urban Area , 2020, International journal of environmental research and public health.

[13]  Utkan Özdemir,et al.  Impacts of Meteorological Factors on PM10: Artificial Neural Networks (ANN) and Multiple Linear Regression (MLR) Approaches , 2014 .

[14]  D. Chicco,et al.  The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation , 2020, BMC Genomics.

[15]  Sansanee Auephanwiriyakul,et al.  A novel neuro-fuzzy method for linguistic feature selection and rule-based classification , 2010, 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE).

[16]  Carlos González-Figueredo,et al.  Clustering Approach Applied On An Artificial Neural Network Model To Predict Pm10 In Mega Cities Of Mexico , 2016 .

[17]  Kyung-Joong Kim,et al.  PM10 density forecast model using long short term memory , 2017, 2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN).

[18]  Nor Azam Ramli,et al.  Short Term Prediction of PM10 Concentrations Using Seasonal Time Series Analysis , 2016 .

[19]  Yafeng Yin,et al.  Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach , 2009 .

[20]  P. Perez.  Combined model for PM10 forecasting in a large city , 2012 .

[21]  Ora-orn Poocharoen,et al.  The haze problem in Northern Thailand and policies to combat it: A review , 2019, Environmental Science & Policy.

[22]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[23]  Mahmut Bayramoglu,et al.  Adaptive neuro-fuzzy based modelling for prediction of air pollution daily levels in city of Zonguldak. , 2006, Chemosphere.

[24]  Narissara Eiamkanitchat,et al.  Increasing Predictive Accuracy of Neuro-Fuzzy Using Quartiles to Initialize the Membership Function , 2020, ICCCM.

[25]  M. Lovrić,et al.  Applying machine learning methods to better understand, model and estimate mass concentrations of traffic-related pollutants at a typical street canyon , 2020 .

[26]  P. Goyal,et al.  Statistical models for the prediction of respirable suspended particulate matter in urban cities , 2006 .

[27]  Martin Drlík,et al.  Towards Predicting Student’s Dropout in University Courses Using Different Machine Learning Techniques , 2021, Applied Sciences.

[28]  Hooman Farzaneh,et al.  Air Pollution Health Risk Assessment (AP-HRA), Principles and Applications , 2021, International journal of environmental research and public health.

[29]  Marcella Busilacchio,et al.  Recursive neural network model for analysis and forecast of PM10 and PM2.5 , 2017 .

[30]  Ching-Hsue Cheng,et al.  Entropy-based and trapezoid fuzzification-based fuzzy time series approaches for forecasting IT project cost , 2006 .

[31]  Minglei Fu,et al.  Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model , 2015, Neural Computing and Applications.

[32]  N. Pérez,et al.  Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean. , 2013, The Science of the total environment.

[33]  S. Chantara,et al.  Identification of potential sources of PM10 pollution from biomass burning in northern Thailand using statistical analysis of trajectories , 2018, Atmospheric Pollution Research.

[34]  Li Zhisheng,et al.  Sources, health effects and control strategies of indoor fine particulate matter (PM2.5): A review. , 2017 .

[35]  Hiroyuki Sugimori,et al.  Improvement in the Convolutional Neural Network for Computed Tomography Images , 2021, Applied Sciences.

[36]  S. Shamshirband,et al.  Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain. , 2019, The Science of the total environment.

[37]  Sansanee Auephanwiriyakul,et al.  On Feature Selection and Rule Extraction for High Dimensional Data: A Case of Diffuse Large B-Cell Lymphomas Microarrays Classification , 2015 .