Dynamic Cost Estimation of Reconstruction Project Based on Particle Swarm Optimization Algorithm

Abstract

This paper proposes the research on dynamic cost estimation of reconstruction project in accordance with the particle swarm optimization procedure in order to predict the value of dynamic cost estimation of reconstruction project. To accomplish the task initially the applicability of example swarm optimization procedure is introduced. The basic principle of particle swarm optimization procedure is described, and PSO (particle swarm optimization) procedure is used to optimize the super factors of LS-SVM. The spss20.0 statistics is used to cluster the sample data to obtain similar engineering classes. BP-NN (Back Propagation Neural Network), LS -SVM, and PSO-LSSVM are implemented to anticipate and simulate the development price for the authentication of request effect of the optimized design in that area. The results show that the relative errors of the three designs are controlled within + 10%, this may be used in the early stages of building to anticipate construction costs accurately. The range of the relative error dissemination interval predicted using the BP-NN design is 13.12% and is between [-7.46%, 5.74%]. The range of the relative error dissemination interval predicted by the LS SVM design is 14.22% and is between [-8.12%, 6.17%]. According to the PSO-LSSVM design, the relative error dissemination interval is [-2.56%, 2.49%], and its range is 5.21%. In terms of prediction stability and robustness, the prediction design optimized using PSO procedure outperforms the LS SVM design. In conclusion, the predictions design on the basis of PSO optimized LS SVM is better appropriate for predicting construction costs early in the building process and has strong guiding importance for the cost of construction.Povzetek: Raziskava predlaga dinamično ocenjevanje stroškov obnove projektov z uporabo postopka optimizacije delcev za natančnejše napovedi.

Recognition and Prediction of Nonlinear Dynamic States of Microelectronic Devices Based on Machine Learning Algorithms

“…Firstly, ELM can recognize input data by adjusting the weights of the input and output layers, thereby achieving high recognition accuracy under different parameters [19]. Secondly, by using feature selection methods such as filtering, wrapping, and embedding, ELM can find the optimal subset of features, further improving the predictive performance and interpretability of the model [20]. In addition, the running speed and data volume requirements of ELM are relatively low, making it more efficient in practical applications.…”

Construction Project Cost Prediction Method Based on Improved BiLSTM

“…However, the ARIMA model is unsuitable for capturing the nonlinearities of time series in engineering costs [2], which negatively affects prediction accuracy. To solve this problem, the support vector machine (SVM) [3][4][5], backpropagation (BP) neural network [6][7][8], and other machine learning models have been applied to cost prediction. Although such methods can effectively handle nonlinear problems, the SVM has limitations regarding data correlation processing and slow processing speed, and the BP neural network can quickly lose time series data and fall into local minimal values.…”