A fuzzy clustering algorithm for developing predictive models in construction applications

Abstract Fuzzy inference systems (FISs) are a predictive modeling technique based on fuzzy sets that utilize approximate reasoning to mimic the decision-making process of human experts. There are several expert- and data-driven methods for developing FISs, among which fuzzy clustering algorithms are the most frequently used data-driven methods. This paper introduces a new fuzzy clustering algorithm for developing FISs in construction applications that addresses two limitations of existing fuzzy clustering algorithms: the lack of capacity to determine the number of clusters automatically from the characteristics of the data, and the poor performance in predictive modeling of highly dimensional problems. Existing fuzzy clustering algorithms are limited in construction applications since determining the number of clusters based on subjective expert judgment reduces the accuracy of the resulting FIS, and construction systems are often highly dimensional with a large number of inputs affecting the system outputs. The fuzzy clustering algorithm proposed in this paper determines the number of clusters automatically based on the characteristics of the data, specifically the non-linearity observed within clusters, and assigns weights to the rules of FISs to improve their accuracy in highly dimensional problems. This paper advances the state-of-the-art of fuzzy clustering and contributes to construction modeling by providing a new data-driven technique for developing FISs that suits the characteristics of construction problems.

[1]  Donald Gustafson,et al.  Fuzzy clustering with a fuzzy covariance matrix , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[2]  Aminah Robinson Fayek,et al.  Development and Optimization of Artificial Intelligence-Based Concrete Compressive Strength Predictive Models , 2016 .

[3]  Lotfi A. Zadeh,et al.  The concept of a linguistic variable and its application to approximate reasoning-III , 1975, Inf. Sci..

[4]  S. M. Fakhrahmad,et al.  A New Rule-weight Learning Method based on Gradient Descent , 2009 .

[5]  Siamak Haji Yakhchali,et al.  Risk ranking of tunnel construction projects by using the ELECTRE technique under a fuzzy environment , 2013 .

[6]  Ebrahim H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Hum. Comput. Stud..

[7]  Khaled Mahmoud El-Gohary,et al.  Engineering Approach Using ANN to Improve and Predict Construction Labor Productivity under Different Influences , 2017 .

[8]  Amoussou Coffi Adoko,et al.  Fuzzy Inference System-Based for TBM Field Penetration Index Estimation in Rock Mass , 2018, Geotechnical and Geological Engineering.

[9]  E. H. Mamdani,et al.  Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis , 1976, IEEE Transactions on Computers.

[10]  S. Askari,et al.  A novel and fast MIMO fuzzy inference system based on a class of fuzzy clustering algorithms with interpretability and complexity analysis , 2017, Expert Syst. Appl..

[11]  Claudia-Adina Dragos,et al.  Online identification of evolving Takagi-Sugeno-Kang fuzzy models for crane systems , 2014, Appl. Soft Comput..

[12]  Amir Hossein Davaie Markazi,et al.  A new evolving compact optimised Takagi–Sugeno fuzzy model and its application to nonlinear system identification , 2012, Int. J. Syst. Sci..

[13]  Mohammad Hossein Fazel Zarandi,et al.  Generalized Possibilistic Fuzzy C-Means with novel cluster validity indices for clustering noisy data , 2017, Appl. Soft Comput..

[14]  Indrajit Chakrabarti,et al.  Time-frequency masking based supervised speech enhancement framework using fuzzy deep belief network , 2019, Appl. Soft Comput..

[15]  Aminah Robinson Fayek,et al.  Dynamic Modeling of Multifactor Construction Productivity for Equipment-Intensive Activities , 2018, Journal of Construction Engineering and Management.

[16]  Yadong Wang,et al.  Improving fuzzy c-means clustering based on feature-weight learning , 2004, Pattern Recognit. Lett..

[17]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[18]  Kazuyuki Murase,et al.  Adaptive weighted fuzzy rule-based system for the risk level assessment of heart disease , 2018, Applied Intelligence.

[19]  Saeid Rastegar,et al.  Online identification of Takagi–Sugeno fuzzy models based on self-adaptive hierarchical particle swarm optimization algorithm , 2017 .

[20]  Anjana Gosain,et al.  Performance Analysis of Various Fuzzy Clustering Algorithms: A Review , 2016 .

[21]  Aminah Robinson Fayek,et al.  Overview of Fuzzy Hybrid Techniques in Construction Engineering and Management , 2018, Fuzzy Hybrid Computing in Construction Engineering and Management.

[22]  James M. Keller,et al.  A possibilistic approach to clustering , 1993, IEEE Trans. Fuzzy Syst..

[23]  G. N. Pillai,et al.  Recent advances in neuro-fuzzy system: A survey , 2018, Knowl. Based Syst..

[24]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[25]  Himansu Sekhar Behera,et al.  Fuzzy C-Means (FCM) Clustering Algorithm: A Decade Review from 2000 to 2014 , 2015 .

[26]  Shun-Hung Tsai,et al.  A novel identification method for Takagi-Sugeno fuzzy model , 2017, Fuzzy Sets Syst..

[27]  Amit Kumar Das,et al.  A Short Review on Different Clustering Techniques and Their Applications , 2019, Advances in Intelligent Systems and Computing.

[28]  Abdulaziz M. Jarkas.  Critical Investigation into the Applicability of the Learning Curve Theory to Rebar Fixing Labor Productivity , 2010 .

[29]  Min Tang,et al.  Generation of a probabilistic fuzzy rule base by learning from examples , 2012, Inf. Sci..

[30]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[31]  Albert P.C. Chan,et al.  Critical Review of Labor Productivity Research in Construction Journals , 2014 .

[32]  Aminah Robinson Fayek,et al.  System model for analysing construction labour productivity , 2016 .

[33]  James M. Keller,et al.  A possibilistic fuzzy c-means clustering algorithm , 2005, IEEE Transactions on Fuzzy Systems.

[34]  Pei-Chann Chang,et al.  A Takagi-Sugeno fuzzy model combined with a support vector regression for stock trading forecasting , 2016, Appl. Soft Comput..

[35]  Jie Li,et al.  An extended Takagi–Sugeno–Kang inference system (TSK+) with fuzzy interpolation and its rule base generation , 2018, Soft Comput..

[36]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[37]  Gholamreza Heravi,et al.  Applying Artificial Neural Networks for Measuring and Predicting Construction-Labor Productivity , 2015 .

[38]  Witold Pedrycz,et al.  Data and Feature Reduction in Fuzzy Modeling through Particle Swarm Optimization , 2012, Appl. Comput. Intell. Soft Comput..

[39]  Petr Husek,et al.  Aircraft longitudinal motion control based on Takagi-Sugeno fuzzy model , 2016, Appl. Soft Comput..

[40]  Kheireddine Chafaa,et al.  Fuzzy modelling using Kalman filter , 2007 .

[41]  Robinson FayekAminah,et al.  Identification and comparative analysis of key parameters influencing construction labour productivity in building and industrial projects , 2014 .

[42]  Marek Reformat,et al.  Hierarchical FCM in a stepwise discovery of structure in data , 2006, Soft Comput..

[43]  Alireza Rahai,et al.  A fast and efficient clustering based fuzzy time series algorithm (FEFTS) for regression and classification , 2017, Appl. Soft Comput..

[44]  James C. Bezdek,et al.  A mixed c-means clustering model , 1997, Proceedings of 6th International Fuzzy Systems Conference.

[45]  Boris Polyak.  Some methods of speeding up the convergence of iteration methods , 1964 .

[46]  Andrey V. Savchenko,et al.  Compression of Recurrent Neural Networks for Efficient Language Modeling , 2019, Appl. Soft Comput..

[47]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.

[48]  Witold Pedrycz,et al.  Fuzzy Systems Engineering - Toward Human-Centric Computing , 2007 .

[49]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[50]  Mohammad Mehdi Arefi,et al.  Nonlinear system identification based on Takagi-Sugeno fuzzy modeling and unscented Kalman filter. , 2018, ISA transactions.

[51]  Youyi Wang,et al.  Robust Fuzzy Model Predictive Control of Discrete-Time Takagi–Sugeno Systems With Nonlinear Local Models , 2018, IEEE Transactions on Fuzzy Systems.

[52]  Hisao Ishibuchi,et al.  Rule weight specification in fuzzy rule-based classification systems , 2005, IEEE Transactions on Fuzzy Systems.

[53]  R. Menaka,et al.  A deep supervised approach for ischemic lesion segmentation from multimodal MRI using Fully Convolutional Network , 2019, Appl. Soft Comput..

[54]  Aminah Robinson Fayek,et al.  Developing and Optimizing Context-Specific Fuzzy Inference System-Based Construction Labor Productivity Models , 2016 .

[55]  Aminah Robinson Fayek,et al.  Neuro-fuzzy system dynamics technique for modeling construction systems , 2020, Appl. Soft Comput..

[56]  George W. Irwin,et al.  Robust fuzzy Gustafson–Kessel clustering for nonlinear system identification , 2003, Int. J. Syst. Sci..

[57]  Witold Pedrycz,et al.  Granular Computing: Analysis and Design of Intelligent Systems , 2013 .

[58]  Biao Huang,et al.  Gaussian process modelling with Gaussian mixture likelihood , 2019, Journal of Process Control.

[59]  Aminah Robinson Fayek,et al.  Computational method for fuzzy arithmetic operations on triangular fuzzy numbers by extension principle , 2019, Int. J. Approx. Reason..

[60]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .