REDUCING PREDICTION ERROR BY TRANSFORMING INPUT DATA FOR NEURAL NETWORKS

The application of neural networks (NNs) in construction cover a large range of topics, including estimating construction costs and markup estimation, predicting construction productivity, predicting settlements during tunneling, and predicting the outcome of construction litigation. The primary purpose of data transformation is to modify the distribution of input variables so that they can better match outputs. The performance of a NN is often improved through data transformations. There are three existing data transformation methods: linear transformation, statistical standardization, and mathematical functions. This paper presents another data transformation method using cumulative distribution functions, simply addressed as distribution transformation. This method can transform a stream of random data distributed in any range to data points uniformly distributed on the interval [0,1]. Therefore, all neural input variables can be transformed to the same ground-uniform distributions on [0,1]. The transformation can also serve the specific need of neural computation that requires all input data to be scaled to the range [1,1] or [0,1]. The paper applies distribution transformation to two examples. Example 1 fits a cowboy hat surface because it provides a controlled environment for generating accurate input and output data patterns. The results show that distribution transformation improves the network performance by 50% over linear transformation. Example 2 is a real tunneling project, the Brasilia Tunnel, in which distribution transformation has reduced the prediction error by more than 13% compared with linear transformation.

[1]  John W. Tukey,et al.  Exploratory Data Analysis. , 1979 .

[2]  Linus Schrage,et al.  A guide to simulation , 1983 .

[3]  Paul Bratley,et al.  A guide to simulation (2nd ed.) , 1986 .

[4]  D. Ruppert,et al.  Transformation and Weighting in Regression , 1988 .

[5]  N. Logothetis.  The role of data transformation in taguchi analysis , 1988 .

[6]  Ian Flood,et al.  A Neural Network Approach to the Sequencing of Construction Tasks , 1989 .

[7]  Tarek Hegazy,et al.  Neural networks as tools in construction , 1991 .

[8]  Ian Flood,et al.  Neural Networks in Civil Engineering. I: Principles and Understanding , 1994 .

[9]  Miroslaw J. Skibniewski,et al.  Estimating construction productivity: neural-network-based approach , 1994 .

[10]  Ian Flood,et al.  Neural networks in civil engineering. II: Systems and application , 1994 .

[11]  Tarek Hegazy,et al.  Analogy‐Based Solution to Markup Estimation Problem , 1994 .

[12]  Satoshi Chiba,et al.  Impacts of Data Transformations on Least-Squares Solutions and Their Significance in Data Analysis and Evaluation , 1994 .

[13]  Michael Y. Hu,et al.  Effect of data standardization on neural network training , 1996 .

[14]  Tunnelling in Brasília porous clay , 1996 .

[15]  A. Alan B. Pritsker,et al.  Simulation with Visual SLAM and AweSim , 1997 .

[16]  Jingsheng Shi,et al.  MODULAR NEURAL NETWORKS FOR PREDICTING SETTLEMENTS DURING TUNNELING , 1998 .

[17]  Onur Behzat Tokdemir,et al.  Predicting the Outcome of Construction Litigation Using Neural Networks , 1998 .

[18]  M. H. Choueiki,et al.  Training data development with the D-optimality criterion , 1999, IEEE Trans. Neural Networks.