Sharif Digital Repository

Despite complex fluctuations, missing data, and maintenance costs of detectors, traffic volume forecasting at intersections is still a challenge. Moreover, most existing forecasting methods consider an isolated intersection instead of multiple adjacent ones. By accurately forecasting the volume of short-term traffic, a low-cost method can be provided to solve the problems of congestion, delay, and breakdown of detectors in the road transport system. This paper outlines a novel hybrid method based on deep learning to estimate short-term traffic volume at three adjacent intersections. The gated recurrent unit (GRU) and long short-term memory (LSTM) bilayer network with wavelet transform (WL)... 

This paper is a counterfactual analysis investigating the consequences of the formation of a currency union for Canada and the USA: whether outputs increase and prices decrease if these countries form a currency union. We use a two-country cointegrated model to conduct the counterfactual analysis, where the conditional forecasts are generated based on the Gaussian assumption. To deal with structural breaks and model uncertainty, conditional forecasts are generated from different models/estimation windows and the model-averaging technique is used to combine the forecasts. We also examine the robustness of our results to parameter uncertainty using the wild bootstrap method. The results show... 

Accurate forecasts of tourist arrivals and study of the tourist arrival patterns are essential for the tourism-related industries to formulate efficient and effective strategies on maintaining and boosting tourism industry in a country. Forecasting accuracy is one of the most important factors involved in selecting a forecasting method. This study presents a hybrid artificial intelligence (AI) model to develop a Mamdani-type fuzzy rule-based system to forecast tourist arrivals with high accuracy. The hybrid model uses genetic algorithm for learning rule base and tuning data base of fuzzy system. Actually it extracts useful information patterns with a descriptive rule induction approach based... 

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... 

This paper proposes a multi-unit building model, in which the parameters are obtained via an online identification process. The identification process is carried out on-the-fly so it can update the best model of the building units. A model predictive controller (MPC) is also employed that uses the prediction of the building model, as well as the weather forecast data and acts on the heating boiler in an optimal fashion. In addition, since the controller is designed for a multi-unit building, it is crucial to estimate the amount of the delay that takes the hot flow to reach the units. This paper presents a very simple method for the delay identification based on unscented kalman filter. For... 

In the restructured power markets, price of electricity has been the key of all activities in the power market. Accurately and efficiently forecasting electricity price becomes more and more important. Therefore in this paper, an Artificial Neural Network (ANN) model is designed for short term price forecasting of electricity in the environment of restructured power market. The proposed ANN model is a four-layered perceptron neural network, which consists of, input layer, two hidden layers and output layer. Instead of conventional back propagation (BP) method, Levenberg- Marquardt BP (LMBP) method has been used for the ANN training to increase the speed of convergence. Matlab is used for... 

Accurate monthly electricity consumption forecasting (ECF) can help retailers enhance the profitability in deregulated electricity markets. Most current methods use monthly load data to perform monthly ECF, which usually produces large errors due to insufficient training samples. A few methods try to use fine-grained smart-meter data (e.g., hourly data) to increase training samples. However, such methods still exhibit low accuracy due to the increase in forecasting steps. © 1975-2012 IEEE  

Electricity generation in vicinity of the load centers seems rather imperative since the costs associated with the reinforcement of new transmission lines are hugely intolerable or maybe this process cannot be practically applicable. There are many means of power generation in addition to the conventional ones among them are solar cells, wind turbines, and thermal units. In this paper, these sources of power generation are involved to manage a power system of an island region. As a consequence, the possibility of exploiting the constructive effects of such green energy resources would be approved. In respect with a reliable system adequacy management, short-term load forecasting (STLF) is... 

In this paper we develop a hybrid forecasting model which combines artificial intelligence and technical analysis to predict short-term stock price index. The results show that using technical indices as neural network's inputs yields good performance in forecasting short-term prices, but this model cannot predict long-term prices well. To overcome this shortcoming we have exploited a fuzzy inference system based on analyzing the historical effects of macro economic variables on the stock markets' indices. Our forecasting models differ from the other ones in two main aspects: the first one is analyzing previous macroeconomics trends in order to build a Mamdani FIS and the second one is... 

PM10 prediction has attracted special legislative and scientific attention due to its harmful effects on human health. Statistical techniques have the potential for high-accuracy PM10 prediction and accordingly, previous studies on statistical methods for temporal, spatial and spatio-temporal prediction of PM10 are reviewed and discussed in this paper. A review of previous studies demonstrates that Support Vector Machines, Artificial Neural Networks and hybrid techniques show promise for suitable temporal PM10 prediction. A review of the spatial predictions of PM10 shows that the LUR (Land Use Regression) approach has been successfully utilized for spatial prediction of PM10 in urban areas.... 

Electricity load forecasting plays an important role for optimal power system operation. Accordingly, short term load forecast (STLF) is also becoming an important task by researchers to tackle the mentioned problem. As a consequence of the highly non-smooth and volatile trend of the load time series specially in building levels, its STLF is even a more complex procedure than that of a power system. For this purpose, in this paper we proposed a new prediction model based on a new feature selection algorithm and hybrid forecast engine of enhanced version of empirical mode decomposition named sliding window EMD bundled with an intelligent algorithm. The proposed forecast engine is combined... 

The primary objective of this research is to obtain an accurate forecasting model for the US presidential election. To identify a reliable model, artificial neural networks (ANN) and support vector regression (SVR) models are compared based on some specified performance measures. Moreover, six independent variables such as GDP, unemployment rate, the president’s approval rate, and others are considered in a stepwise regression to identify significant variables. The president’s approval rate is identified as the most significant variable, based on which eight other variables are identified and considered in the model development. Preprocessing methods are applied to prepare the data for the... 

The primary objective of this research is to obtain an accurate forecasting model for the US presidential election. To identify a reliable model, artificial neural networks (ANN) and support vector regression (SVR) models are compared based on some specified performance measures. Moreover, six independent variables such as GDP, unemployment rate, the president’s approval rate, and others are considered in a stepwise regression to identify significant variables. The president’s approval rate is identified as the most significant variable, based on which eight other variables are identified and considered in the model development. Preprocessing methods are applied to prepare the data for the...