Evolutionary fuzzy hybrid neural network for dynamic project success assessment in construction industry

This paper developed an evolutionary fuzzy hybrid neural network (EFHNN) to enhance project cash flow management. Neural networks (NN) and high order neural networks (HONN) are combined in the developed EFHNN to form a hybrid neural network (HNN), which acts as the major inference engine and operates with alternating linear and non-linear NN layer connections. Fuzzy logic (FL) is employed to sandwich the HNN between a fuzzification and defuzzification layer. The authors developed and applied this EFHNN to assess construction industry project success by fusing HNN, FL and GA. CAPP (Continuous Assessment of Project Performance) software was used to study in a dynamic manner the significant factors that influence project performance. Results showed that the proposed EFHNN can be deployed effectively to achieve optimal mapping of input factors and project success output. Moreover, the performance of linear and non-linear (high order) neuron layer connectors in the EFHNN was significantly better than the performance achieved by previous models that used singular linear NN.

► This paper fused a hybrid neural network, fuzzy logic, and genetic algorithms for developing an inference model. ► The hybrid neural network is composed of linear neural networks and high order neural networks. ► The proposed evolutionary fuzzy hybrid neural network can achieve optimal mapping of project success. ► CAPP software was used in a dynamic manner the significant factors that influence project performance.