Evaluating the performance of combining neural networks and genetic algorithms to forecast construction demand: the case of the Singapore residential sector

In recent years, forecasting demand for residential construction in Singapore has become more vital, since it is widely perceived that the next trough of the real estate cycle is approaching. This paper evaluates the use of a combination of neural networks (NNs) and genetic algorithms (GAs) to forecast residential construction demand in Singapore. Successful applications of NNs, especially in solving complex non-linear problems, have since stimulated interest in exploring the capabilities of other biological-based methods such as GAs, and in exploiting the synergy of these two techniques to create more problem-solving power. In the study, a basic NN model is used as a benchmark to gauge the performance of the combined NN-GA model. A relative measure of forecasting accuracy, known as the mean absolute percentage error (MAPE), is used for the comparison. The models are checked also for internal validity by allowing each to be trained twice and having a set of forecasts generated after each training. Both models are found to produce accurate forecasts, because their MAPE values consistently fall within the acceptable limit of 10%. However, the combined model out-performs the basis model remarkably by reducing the average MAPE from about 6% to a mere 1%. For each model, the marginal difference in the MAPE values (i.e., 0.5% for the NN model and 0.06% for the NN-GA model) of its two forecasts indicates consistency in performance, hence establishing internal validity as well. The findings reinforce the reliability of using NNs to model construction demand and reveal the benefit of combining NNs and GAs to produce more accurate models.     

A Wavelet Support Vector Machine‐Based Neural Network Metamodel for Structural Reliability Assessment

Wavelet neural network (WNN) has been widely used in the field of civil engineering. However, WNN can only effectively handle problems of small dimensions as the computational cost for constructing wavelets of large dimensions is prohibitive. To expand the application of WNN to higher dimensions, this article develops a new wavelet support vector machine (SVM)‐based neural network metamodel for reliability analysis. The method first develops an autocorrelation wavelet kernel SVM and then uses a set of wavelet SVMs with different resolution as the activation function of WNN. The output of network is obtained through aggregating outputs of different wavelet SVMs. The method takes advantage of the excellent capacities of SVM to handle high‐dimensional problems and of the attractive properties of wavelet to represent complex functions. Four examples are given to demonstrate the application and effectiveness of the proposed method.     

Large metropolitan water demand forecasting using DAN2, FTDNN,and KNN models: A case study of the city of Tehran,Iran

Efficient operation of urban water systems necessitates accurate water demand forecasting. We present daily, weekly, and monthly water demand forecasting using dynamic artificial neural network (DAN2), focused time-delay neural network (FTDNN), and K-nearest neighbor (KNN) models for the city of Tehran. The daily model investigates whether partitioning weekdays into weekends and non-weekends can improve forecast results; it did not. The weekly model yielded good results by using the summation of the daily forecast values into their corresponding weeks. The monthly results showed that partitioning the year into high and low seasons can improve forecast accuracy. All three models offer very good results for water demand forecasting. DAN2, the best model, yielded forecasting accuracies of 96%, 99%, and 98%, for daily, weekly, and monthly models respectively.     

Using extreme learning machines for short-term urban water demand forecasting

This study explores the ability of various machine learning methods to improve the accuracy of urban water demand forecasting for the city of Montreal (Canada). Artificial Neural Network (ANN), Support Vector Regression (SVR) and Extreme Learning Machine (ELM) models, in addition to a traditional model (Multiple linear regression, MLR) were developed to forecast urban water demand at lead times of 1 and 3 days. The use of models based on ELM in water demand forecasting has not previously been explored in much detail. Models were based on different combinations of the main input variables (e.g., daily maximum temperature, daily total precipitation and daily water demand), for which data were available for Montreal, Canada between 1999 and 2010. Based on the squared coefficient of determination, the root mean square error and an examination of the residuals, ELM models provided greater accuracy than MLR, ANN or SVR models in forecasting Montreal urban water demand for 1 day and 3 days ahead, and can be considered a promising method for short-term urban water demand forecasting.     

Assessment of predictive uncertainty within the framework of water demand forecasting using the Model Conditional Processor (MCP)

This paper presents an application of the Model Conditional Processor (MCP), originally proposed by Todini (2008) within the hydrological framework, to assess the predictive uncertainty in water demand forecasting related to water distribution systems. The MCP enables us to assess the probability distribution of the future water demand conditional on the forecasts provided by two or more deterministic forecasting models. In the numerical application described here, where two years of hourly water demand data for a town in northern Italy are considered, two forecasting models are applied in order to forecast hourly water demands from 1 to 24 hours ahead: the first model has a modular structure comprising a periodic component which reflects the long-term effects and a persistence component which represents the short-term memory of the process; the latter is based on neural networks. The results highlight the effectiveness of the approach, provided that the data set used for the MCP parameterization is properly selected so as to be actually representative of the accuracy of the real-time water demand forecasting models.     

太阳散射辐射逐日预测模型研究

针对于传统的确定性太阳辐射模型不能反映气象变化的弊端,提出了基于回归BP神经网络和小波分析理论的太阳散射辐射逐日预测模型。神经网络具有非线性函数逼近及自组织自学习的能力,基于小波分析在信号处理方面的时频域多分辨特性,本文利用小波变换将太阳散射辐射数据序列进行时频域分解后作为神经网络预测模型的输入样本,实例表明该方法与传统模型相比预测精度高,具有可行性。     

位移反分析的APSO-WNN模型研究及应用

用改进粒子群优化算法对小波神经网络进行优化，从而提出改进粒子群算法优化小波神经网络模型（APSO-WNN）。该模型具有小波变换的良好时频局域化性质、良好时域和频域分辨能力及传统神经网络的自学习功能；同时用改进的粒子群优化法进行全局最优搜索，快速收敛到全局最优解，使其具有良好的逼近能力、容错能力和较强的鲁棒性。因此，该计算模型适合解决具有复杂非线性和模糊性特点的岩土工程问题。为证明该模型的优越性，同时将该计算模型与传统遗传算法神经网络用于三峡船闸高边坡4种介质弹性模量的位移反分析计算，结果表明不论是优化精度还是收敛时间，该算法都较遗传算法有明显提高。最后利用APSO-WNN反演的弹性模量参数进行测点位移预测，预测表明各个测点的计算位移值与监测值吻合较好，说明该模型在岩土工程位移反分析中具有良好的实际应用价值。     

Nonparametric Identification of a Building Structure from Experimental Data Using Wavelet Neural Network

Abstract:   This study presents a wavelet neural network-based approach to dynamically identifying and modeling a building structure. By combining wavelet decomposition and artificial neural networks (ANN), wavelet neural networks (WNN) are used for solving chaotic signal processing. The basic operations and training method of wavelet neural networks are briefly introduced, since these networks can approximate universal functions. The feasibility of structural behavior modeling and the possibility of structural health monitoring using wavelet neural networks are investigated. The practical application of a wavelet neural network to the structural dynamic modeling of a building frame in shaking tests is considered in an example. Structural acceleration responses under various levels of the strength of the Kobe earthquake were used to train and then test the WNNs. The results reveal that the WNNs not only identify the structural dynamic model, but also can be applied to monitor the health condition of a building structure under strong external excitation.     

An ARIMA-NARX hybrid model for forecasting urban water consumption (case study: Tehran metropolis)

ABSTRACT

In this research, an ARIMA-NARX (Autoregressive Integrated Moving Average-Nonlinear Auto-Regressive eXogenous) hybrid model is proposed to forecast daily Urban Water Consumption (UWC) for Tehran Metropolis. The linear and nonlinear component of the UWC was forecast by ARIMA as a linear forecasting model and the artificial neural network as a nonlinear forecasting model, respectively. An alternative hybrid model including sunshine hour in addition to the previous studies’ predictors (the minimum, maximum and average temperature, relative humidity and precipitation) was selected as the superior alternative model. Then, the performance of proposed model was compared with ARIMA and NARX models. The results showed that the hybrid model, which benefits from capability of both linear and nonlinear models, has a higher accuracy than the other two models in forecasting UWC. Therefore, the proposed hybrid model has better results in UWC forecasting and, as a consequence, better urban water reservoir management will be provided.     

Evaluating subcontractor performance using evolutionary fuzzy hybrid neural network

This paper developed an evolutionary fuzzy hybrid neural network (EFHNN) to enhance the effectiveness of assessing subcontractor performance in the construction industry. The developed EFHNN combines neural networks (NN) and high order neural networks (HONN) into 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 is employed to sandwich the HNN between a fuzzification and defuzzification layer. The authors developed and applied the EFHNN to assess subcontractors performance by fusing HNN, FL and GA. Enhancing subcontractor performance assessments are crucial in terms of providing to general contractors information on historical contractor performance essential to guiding a selection of appropriate subcontractors for a specific current or future subcontracting need. Results show that the proposed EFHNN may be deployed effectively to achieve optimal mapping of input factors and subcontractor performance output. Moreover, the performance of linear and non-linear (high order) neuron layer connectors in the EFHNN was significantly better than performances achieved by previous models that used singular linear NN.     

Dynamic Wavelet Neural Network for Nonlinear Identification of Highrise Buildings

Abstract:   Recently, the authors presented a multiparadigm dynamic time-delay fuzzy wavelet neural network (WNN) model for nonparametric identification of structures using the nonlinear autoregressive moving average with exogenous inputs. Compared with conventional neural networks, training of a dynamic neural network for system identification of large-scale structures is substantially more complicated and time consuming because both input and output of the network are not single valued but involve thousands of time steps. In this article, an adaptive Levenberg–Marquardt least-squares algorithm with a backtracking inexact linear search scheme is presented for training of the dynamic fuzzy WNN model. The approach avoids the second-order differentiation required in the Gauss–Newton algorithm and overcomes the numerical instabilities encountered in the steepest descent algorithm with improved learning convergence rate and high computational efficiency. The model is applied to two highrise moment-resisting building structures, taking into account their geometric nonlinearities. Validation results demonstrate that the new methodology provides an efficient and accurate tool for nonlinear system identification of high-rising buildings.     

Wavelet and ANN combination model for prediction of daily suspended sediment load in rivers

In this research, a new wavelet artificial neural network (WANN) model was proposed for daily suspended sediment load (SSL) prediction in rivers. In the developed model, wavelet analysis was linked to an artificial neural network (ANN). For this purpose, daily observed time series of river discharge (Q) and SSL in Yadkin River at Yadkin College, NC station in the USA were decomposed to some sub-time series at different levels by wavelet analysis. Then, these sub-time series were imposed to the ANN technique for SSL time series modeling. To evaluate the model accuracy, the proposed model was compared with ANN, multi linear regression (MLR), and conventional sediment rating curve (SRC) models. The comparison of prediction accuracy of the models illustrated that the WANN was the most accurate model in SSL prediction. Results presented that the WANN model could satisfactorily simulate hysteresis phenomenon, acceptably estimate cumulative SSL, and reasonably predict high SSL values.     

A hybrid FDD strategy for local system of AHU based on artificial neural network and wavelet analysis

This paper presents a self-adaptive sensor fault detection and diagnosis (FDD) strategy for local system of air handing unit (AHU). This hybrid strategy consists of two stages. In the first stage, a fault detection model for the AHU control loop including two back-propagation neural network (BPNN) models is developed. BPNN models are trained by the normal operating data of system. Based on sensitive analysis for the first BPNN model, the second BPNN model is constructed in the same control loop. In the second stage, a fault diagnosis model is developed which combines wavelet analysis method with Elman neural network. The wavelet analysis is employed to process the measurement data by extracting the approximation coefficients of sensor measurement data. The Elman neural network is used to identify sensor faults. A new approach for increasing adaptability of sensor fault diagnosis is presented. This approach gains clustering information of the approximations coefficients by fuzzy c-means (FCM) algorithm. Based on cluster information of the approximation coefficients, the unknown sensor fault can be identified in the control loop. Simulation results in this paper show that this strategy can successfully detect and diagnose fixed biases and drifting fault of sensors for the local system of AHU.     

Monthly water demand prediction using wavelet transform,first-order differencing and linear detrending techniques based on multilayer perceptron models

In this study, combined Discrete Wavelet Transform-Multilayer Perceptron (DWT-MP), combined First-Order Differencing-Multilayer Perceptron (FOD-MP) and combined Linear Detrending-Multilayer Perceptron (LD-MP) were developed and compared with stand-alone Multilayer Perceptron (MP) model for predicting monthly water consumption of Istanbul. The performance of these models were assessed by using coefficient of determination (R²), root mean square error (RMSE) and the Nash-Sutcliffe coefficient of efficiency (CE) as evaluation criteria. The study showed that DWT-MP could be used for forecasting the monthly water demand of Istanbul for only up to prediction lead-time of 3 months. However, FOD-MP was found to perform very well up to 12 months. It can be concluded from the results of the study that First-Order Differencing (FOD) is a reliable pre-processing technique for monthly water demand prediction.     

Comparison of construction cost estimating models based on regression analysis,neural networks,and case-based reasoning

Adequate estimation of construction costs is a key factor in construction projects. This paper examines the performance of three cost estimation models. The examinations are based on multiple regression analysis (MRA), neural networks (NNs), and case-based reasoning (CBR) of the data of 530 historical costs. Although the best NN estimating model gave more accurate estimating results than either the MRA or the CBR estimating models, the CBR estimating model performed better than the NN estimating model with respect to long-term use, available information from result, and time versus accuracy tradeoffs.     

A new method of ozone forecasting using fuzzy expert and neural network systems

This study describes the method of forecasting daily maximum ozone concentrations at four monitoring sites in Seoul, Korea. The forecasting tools developed are fuzzy expert and neural network systems. The hourly data for air pollutants and meteorological variables, obtained both at the surface and at the high elevation (500 hPa) stations of Seoul City for the period of 1989-1999, were analyzed. Two types of forecast models are developed. The first model, Part I, uses a fuzzy expert system and forecasts the possibility of high ozone levels (equal to or above 80 ppb) occurring on the next day. The second model, Part II, uses a neural network system to forecast the daily maximum concentration of ozone on the following day. The forecasting system includes a correction function so that the existing model can be updated whenever a new ozone episode appears. The accuracy of the forecasting system has been improved continuously through verification and augmentation.     

Neural Network-Based Long-Term Hydropower Forecasting System

Artificial neural networks are alternatives to stochastic models even if the optimization of their architectures remains a tricky problem. Two different approaches in long-term forecasting of potential energy inflows using a feedforward neural network (FNN) and a recurrent neural network (RNN) are proposed. The problem of overfitting, particularly critical for limited hydrologic data records, is addressed using a new approach entitled optimal weight estimate procedure (OWEP). The efficiency of the two models using OWEP is assessed through multistep forecasts. The experiment results show that, in general, OWEP improves the models' performance and significantly reduces the training time on the order of 60 percent. The RNN outperforms the FNN but costs about a factor of 2 longer in training time. Furthermore, the neural network-based models provide more accurate forecasts than traditional stochastic models. Overall, the RNN appears to be the best suited for potential energy inflows forecasting and therefore for hydropower systems management and planning.     

Analytical prediction of available rotation capacity of cold-formed rectangular and square hollow section beams

In this paper, a soft-computing based study aimed to estimate the available rotation capacity of cold-formed rectangular and square hollow section (RHS-SHS) steel beams is described and novel mathematical models based on neural network (NN) and genetic expression programming (GEP) are proposed. In order to develop the proposed formulations, a wide experimental database obtained from available studies in the literature has been considered. The data used in the NN and GEP models are arranged in a format of eight input parameters covering both geometrical and mechanical properties such as width, depth and wall thickness of cross section, inside corner radius, yield stress, ratio of modulus of elasticity to hardening modulus, ratio of the strain under initial hardening to yield strain and shear length. The accuracy of the proposed formulations is verified against the experimental data and the rates of efficiency and performance are compared with those provided by analytical semi-empirical formulation developed by some of the Authors in a previous study. The proposed prediction models proved that the NN and GEP methods have strong potential for predicting available rotation capacity of cold-formed RHS-SHS steel beams.     

Neural network modeling of strength enhancement for CFRP confined concrete cylinders

This study presents the application of neural networks (NN) for the modeling of strength enhancement of CFRP (carbon fiber-reinforced plastic) confined concrete cylinders. The proposed NN model is based on experimental results collected from literature. It represents the ultimate strength of concrete cylinders after CFRP confinement which is also given in explicit form in terms of diameter, unconfined concrete strength, tensile strength CFRP laminate and total thickness of CFRP layer used. The accuracy of the proposed NN model is quite satisfactory as compared to experimental results. Moreover the results of proposed NN model are compared with 10 different theoretical models proposed by researchers so far and are found to be by far more accurate.     

基于小波分解的城市供水管网短期水量负荷预测

利用小波分解和人工神经网络相结合的方法建立了城市供水管网短期水量负荷的组合预测模型。该方法首先利用小波分解技术将时负荷水量分解为相对简单的带通分量信号，然后根据各分量信号的特点分别建立独立的神经网络预测模型，最后将预报结果集成。由于小波分解后各分量的频率相对单一，因而可有效缩短网络训练时间，提高计算速度。仿真计算结果表明，该方法建模合理、计算量适中，可准确预测管网水量。