Abstract




 
   

IJE TRANSACTIONS B: Applications Vol. 30, No. 11 (November 2017) 1568-1577    Article in Press

PDF URL: http://www.ije.ir/Vol30/No11/B/29.pdf  
downloaded Downloaded: 0   viewed Viewed: 84

  A NOVEL TYPE-2 ANFIS CLASSIFIER FOR MODELLING UNCERTAINTY IN PREDICTION OF AIR POLLUTION DISASTER (RESEARCH NOTE)
 
R. Hosseini, M. Mazinani and A. Safari
 
( Received: July 27, 2017 – Accepted: September 08, 2017 )
 
 

Abstract    The type-2 fuzzy set theory is one of the most powerful tools for dealing with uncertainty and imperfection in a dynamic and complex environment. The applications of type-2 fuzzy sets and soft computing methods are rapidly emerging in the ecological fields such as air pollution and weather prediction. The air pollution problem is a major public health problem in many cities of the world. Prediction of natural phenomena always suffers from uncertainty in the environment and incompleteness of data. There are many studies reported for air quality index prediction but all of them suffers from uncertainty and imprecision associated to the incompleteness of knowledge and imprecise input measures. This work takes advantages of learning and adoption of adaptive neural networks alongside in new environment. Furthermore, it presents an adaptive neuro-type-2 fuzzy inference system (ANT2FIS) to address the uncertainty and imprecision in air quality prediction. The dataset of this study was collected from Tehran municipality official website for last five years (2012-2017). The result reveals that the ANT2FIS method prediction is more reliable and is capable of handling uncertainty compared to the other counterpart methods. The performance results on real dataset shows advantage of the type2- ANFIS system in the prediction process with an average accuracy of 94% (AUC 99%) compared to other related works.

 

Keywords    Fuzzy Logic, Type-2 Fuzzy Set, ANFIS, Air Pollution Disaster

 

چکیده    تئوری مجموعه فازی نوع 2 یکی از قوی ترین ابزارها برای مقابله با عدم قطعیت و ناقص بودن در یک محیط پویا و پیچیده است.در سال های اخیر کاربردهای مجموعه های فازی نوع 2 و روش های محاسبات نرم به سرعت در زمینه های زیست محیطی مانند آلودگی هوا و پیش بینی آب و هوا مورد استفاده قرار گرفته است. مشکل آلودگی هوا یک مشکل عمده بهداشت عمومی در بسیاری از شهرهای جهان است. پیش بینی پدیده های طبیعی همیشه از عدم اطمینان در محیط و ناقص بودن داده ها رنج می برند. در این زمینه مطالعات زیادی برای پیش بینی شاخص های کیفیت هوا گزارش شده است، اما همه آنها از عدم اطمینان و ابهام در ارتباط با ناقص بودن دانش و اندازه گیری های نامناسب رنج برده اند. این مطالعه مزایای یادگیری و قدرت سازگاری شبکه های عصبی تطبیقی فازی ​​را در محیط های جدید نشان میدهد. علاوه بر این، این پژوهش ارائه یک سیستم استنتاج فازی تطبیقی ​​عصبی نوع 2 (ANT2FIS) برای رفع عدم اطمینان و عدم ابهام در پیش بینی کیفیت هوا را ارئه داده است. مجموعه داده های این مطالعه از وب سایت رسمی شهرداری تهران طی پنج سال گذشته (2012-2017) جمع آوری شده است. نتایج نشان می دهد که پیش بینی بر اساس روش ANT2FIS قابل اعتماد تر است و قابلیت بیشتری در مدیریت عدم قطعیت در مقایسه با سایر روش های مرتبط را داراست. نتایج عملکرد مدل ارائه شده در این پژوهش بر روی داده های واقعی نشان دهنده قدرت سیستم ANT2FIS در فرآیند پیش بینی شاخص وضعیت هوا با دقت میانگین ​​94٪ در مقایسه با سایر کارهای مرتبط است.

References     Sher, E., “Handbook of Air Pollution”, Academic Press, University of Shanghai, (2002)Douglas H. K. L, “Air Pollution and its effect”, Academic Press, London, Vol. 1, (1968).Ram, M, and Chandna, R, “Reliability Measures Measurement under Rule-Based Fuzzy Logic Technique”, International. Journal of Engineering (IJE), TRANSACTIONS A: Basics Vol. 28, No. 10, (2015) 1486-1492Zadeh, L.A, “Fuzzy logic and soft computing”, Advances in fuzzy Systems-Application and theory, Vol. 4, (1995).Hosseini, R, Ellis, T, Mazinani, M, Qandali, S and Dehmeshki, J, “A Genetic Fuzzy Approach for Rule Extraction for Rule- Based Classification with Application to Medical Diagnosis”, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), (2011), 05-09.Mendel J. M. and Sadeghian, A. R, “Advances in Type-2 Fuzzy Sets and Systems Theory and Applications”, Studies in Fuzziness and Soft Computing Springer, Vol. 301, (2014).Hosseini, R et al, “An automatic approach for learning and tuning Gaussian interval type-2 fuzzy membership functions applied to lung CAD classification system”. IEEE Transactions on Fuzzy Systems, Vol. 20 (2), (2012), 224-234.Mendel, J. M, et al, “Introduction to type-2 fuzzy logic control Theory and application”, IEEE Press in computational intelligence, (2014).Sowlat, M. H., et al, "A novel, fuzzy-based air quality index (FAQI) for air quality assessment, “Atmospheric Environment”, 45(12), (2011), 2050-2059.Yildirim, Y and Bayramoglu, M., “Adaptive neuro-fuzzy based modelling for prediction of air pollution daily levels in city of Zonguldak”, chemosphere Elsevier, Vol. 63 (2006), 1575–1582.Singh, K. P., et al, “Linear and nonlinear modeling approaches for urban air quality prediction”, The science of The Total Environment Vol. 426, (2012), 244-255.Ababneh, M.F., et al, “PM10 Forecasting Using Soft Computing Techniques”, Research Journal of Applied Sciences, Engineering and Technology, Vol. 7(16), (2014), 3253-3265.Shahraiyni, H. T., et al, “A new structure identification scheme for ANFIS and its application for the simulation of virtual air pollution monitoring stations in urban areas”, Engineering Applications of Artificial Intelligence, Vol. 41, (2015), 175–182Elangasinghe, M.A., et al, “Complex time series analysis of PM10 and PM2.5 for a coastal site using”, Atmospheric Environment, Vol. 94, (2014), 106-116.Shad, R., at al., “Predicting air pollution using fuzzy genetic linear membership kriging in GIS”, Computers, Environment and Urban Systems, Vol. 33 (2009) 472–481.Moghadam-Fard, H. and Samadi F., “Active Suspension System Control Using Adaptive Neuro Fuzzy (ANFIS) Controller”, International Journal of Engineering (IJE), TRANSACTIONS C: Aspects, Vol. 28, No. 3, (2015), 396-401.Mendez, G. M. and Hernandez, M., “Interval Type-2 ANFIS”, Innovations in Hybrid Intelligent Systems, Vol. 44 (2001), 64-71.Khezri, R., Hosseini, R., Mazinani, M., “a Fuzzy Rule-based Expert System for the Prognosis of the Risk of Development of the Breast Cancer”, International Journal of Engineering (IJE), TRANSACTIONS A: Basics, Vol. 27, No. 10, (2014) 1557-1564.U.S. Environmental Protection Agency (EPA), “Air Quality Index”, Office of Air Quality Planning and Standards Outreach and Information Division Research Triangle Park, NC, (2014).Bernard, S, et al, “The Multiclass ROC Front method for cost-sensitive classification”, Journal of Pattern Recognition, Vol 52, (2016), 46-60. Lashkar Ara, A, Bagheri Tolabi, H. and Hosseini, R, “Dynamic Modeling and Controller Design of Distribution Static Compensator in a Microgrid Based on Combination of Fuzzy Set and Galaxy-based Search Algorithm”, International Journal of Engineering (IJE), TRANSACTIONS A: Basics Vol. 29, No. 10, (2016), 1392-1400.


Download PDF 



International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir