Particulate matter prediction using ANFIS modelling techniques

Mihalache, Sanda Florentina; Popescu, Marian; Oprea, Mihaela

doi:10.1109/icstcc.2015.7321408

Cited by 14 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptive neuro-fuzzy inference systems (ANFIS) model, proposed by Jang et al (1993), is a hybrid architecture composed of fuzzy inference systems (FIS) enhanced with ANN features [92]. This model compensates for the disadvantages of fuzzy inference systems such as trial–error methods in tuning membership functions parameters, high time-consumption in design, a continuous and complete rule base, and a lack of standard methods for transforming human knowledge into a rule base [93]. On the other hand, the main advantages of the ANFIS model are the lack of any requirement for a mathematical model, its simulation of human thinking, and its simple interpretation of results [93,94].…”

Section: Future Directions For Reduction In Personal Pm Exposurementioning

confidence: 99%

“…The rule base has enough if–then rules for the scope of input variables, while the database determines membership functions applied in fuzzy rules, and the reasoning mechanism is responsible for an inference procedure [96]. Besides, the ANN portion in this architecture can improve membership functions related to the FIS structure based on its training mode, according to a training and checking dataset [93]. The training process is based on a hybrid learning algorithm or a BP algorithm.…”

Section: Future Directions For Reduction In Personal Pm Exposurementioning

confidence: 99%

See 1 more Smart Citation

Particulate Matter Exposure of Passengers at Bus Stations: A Review

Ngoc

Kim

Bui

et al. 2018

IJERPH

View full text Add to dashboard Cite

This review clarifies particulate matter (PM) pollution, including its levels, the factors affecting its distribution, and its health effects on passengers waiting at bus stations. The usual factors affecting the characteristics and composition of PM include industrial emissions and meteorological factors (temperature, humidity, wind speed, rain volume) as well as bus-station-related factors such as fuel combustion in vehicles, wear of vehicle components, cigarette smoking, and vehicle flow. Several studies have proven that bus stops can accumulate high PM levels, thereby elevating passengers’ exposure to PM while waiting at bus stations, and leading to dire health outcomes such as cardiovascular disease (CVD), respiratory effects, and diabetes. In order to accurately predict PM pollution, an artificial neural network (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) have been developed. ANN is a data modeling method of proven effectiveness in solving complex problems in the fields of alignment, prediction, and classification, while the ANFIS model has several advantages including non-requirement of a mathematical model, simulation of human thinking, and simple interpretation of results compared with other predictive methods.

show abstract

Section: Future Directions For Reduction In Personal Pm Exposurementioning

confidence: 99%

Section: Future Directions For Reduction In Personal Pm Exposurementioning

confidence: 99%

Particulate Matter Exposure of Passengers at Bus Stations: A Review

Ngoc

Kim

Bui

et al. 2018

IJERPH

View full text Add to dashboard Cite

show abstract

“…In [7] it is formulated a fuzzy based forecasting model used in Polish Environmental Agency, a model that forecast specific air pollutants based on decades of measurements. Examples of ANFIS based systems for the prediction of air pollutants concentrations are presented in [22], [23], [32] and [33]]. In [23] it is proposed a fuzzy inference system to forecast PM 2.5 concentrations at specific hours using as additional input the medium temperature.…”

Section: An Overview On Pm 25 Computational Intelligence Based Forecmentioning

confidence: 99%

“…For the city of Konya, Turkey the literature present the solution of ANFIS forecasting model for PM 10 trained with large datasets [32]. In [22] there are presented three case studies from three different cities from Romania. Each time the proposed ANFIS forecasting model for PM 10 is tested and there are made recommendations on how to adjust the model parameters to improve forecasting accuracy.…”

Section: An Overview On Pm 25 Computational Intelligence Based Forecmentioning

confidence: 99%

Computational Intelligence-based PM2.5 Air Pollution Forecasting

Oprea¹,

Mihalache²,

Popescu³

2017

INT J COMPUT COMMUN

Self Cite

View full text Add to dashboard Cite

Computational intelligence based forecasting approaches proved to be more efficient in real time air pollution forecasting systems than the deterministic ones that are currently applied. Our research main goal is to identify the computational intelligence model that is more proper to real time PM 2.5 air pollutant forecasting in urban areas. Starting from the study presented in [27] a , in this paper we first perform a comparative study between the most accurate computational intelligence models that were used for particulate matter (fraction PM 2.5 ) air pollution forecasting: artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS). Based on the obtained experimental results, we make a comprehensive analysis of best ANN architecture identification. The experiments were realized on datasets from the AirBase databases with PM 2.5 concentration hourly measurements. The statistical parameters that were computed are mean absolute error, root mean square error, index of agreement and correlation coefficient.

show abstract

“…In ROkidAIR AI model, forecasting knowledge is extracted by using ANFIS (generating the fuzzy rules set), and other methods (e.g., a combination between some machine learning techniques) on the specific datasets (continuous monitoring data, historical data, meteorological data, and medical data). All the extracted forecasting rules and knowledge are included in a forecasting knowledge base that provide expert knowledge (heuristics) for a faster and optimal air pollution forecasting in a critical polluted area [21].…”

Section: A Cyberinfrastructure For the Protection Of Children's Respimentioning

confidence: 99%

Analyzing the Impact of Airborne Particulate Matter on Urban Contamination with the Help of Hybrid Neural Networks

Dunea¹,

Iordache²

2016

Artificial Neural Networks - Models and Applications

View full text Add to dashboard Cite

In this study, particulate matter (PM), total suspended particulate (TSP), PM 10 , and PM 2.5 fractions) concentrations were recorded in various cities from south of Romania to build the corresponding time series for various intervals. First, the time series of each pollutant were used as inputs in various configurations of feed-forward neural networks (FANN) to find the most suitable network architecture to the PM specificity. The outputs were evaluated using mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and Pearson correlation coefficient (r) between observed series and output series. Second, each time series was decomposed using Daubechies wavelets of third order into its corresponding components. Each decomposed component of a PM time series was used as input in the optimal feed-forward neural networks (FANN) architecture established in the first step. The output of each component was re-included to form the modeled series of the original pollutant time series.The final step was the comparison of FANN outputs with wavelet-FANN results to retrieve the wavelet utilization outcomes. The last section of the study describes the ROkidAIR cyberinfrastructure that integrates a decision support system (DSS). The DSS system uses artificial intelligence techniques and hybrid algorithms for assessing children's exposure to the pollution with particulate matter, in order to elaborate PM forecasted values and early warnings.

show abstract

Particulate matter prediction using ANFIS modelling techniques

Cited by 14 publications

References 29 publications

Particulate Matter Exposure of Passengers at Bus Stations: A Review

Particulate Matter Exposure of Passengers at Bus Stations: A Review

Computational Intelligence-based PM2.5 Air Pollution Forecasting

Analyzing the Impact of Airborne Particulate Matter on Urban Contamination with the Help of Hybrid Neural Networks

Contact Info

Product

Resources

About