Sharif Digital Repository

The use of machine learning and deep learning tools to predict the future behavior of trends in massive data requires the extraction and creation of the eigenvector for the chosen model in the problem. It should be noted that simply by increasing the number of features, it cannot be expected that the learning model will have a higher efficiency. Rather, the quality and importance of the features in the field under study should be carefully considered. Topics such as data redundancy, data correlation, the amount of information in the data, distorted data, outliers, etc. are important steps in improving the dataset and creating a feature vector for training the learning model. In the realm of... 

Road accidents are unfortunate events that cause more thanl16000 deaths each year in Iran. Intercity accidents require a comprehensive plan to reduce casualties because the number of roads users are increasing and the accidents account for nearlyl65% of fatalities. In this study, we first tried to identify the status of Iran through a study of traffic accidents in the world, and then the research and activities carried out in Iran were analyzed to find new and effective solutions. Using the daily fatalities data froml2008 tol2014, and using the new methodology presented in this research based on the Discrete Fourier Transformation (DFT), the Box-Jenkins models and the Secant method, the... 

This research has dedicated to study the control of chaos when the system dynamics is unknown and there are some limitations on measuring states. There are many chaotic systems with these features occurring in many biological, economical and mechanical systems. The usual chaos control methods do not have the ability to present a systematic control method for these kinds of systems. To fulfill these strict conditions we have employed Takens embedding theory which guarantees the preservation of topological characteristics of the chaotic attractor under an embedding named "Takens transformation". Takens transformation just needs time series of one of the measurable states. This transformation... 

Over the past few decades, with the exponential increase in data volume, scientists and researchers have tried to discover relationships and algorithms for productivity and find useful information from this amount of data in various fields. Their efforts in data analysis have led to the development of algorithms in the big data field. The result of researchers' working in multiple fields has come to aid the people of science and technology. Among the most important of these areas, we can mention the health and medical sectors, financial sectors, services, manufacturing sectors, etc. The purpose of this study is to enter the financial industry and use data mining tools. One of the newest and... 

Human as an important part of the natural environment and can exert their positive or negative effects in the form of long-term and short-term on a natural environment. Human impacts on the natural system are very complex and consist of various components. The most considerable among them from past to now are maybe land use and land cover change, although, the impact of dam construction, water pollution, air pollution and etc, can not be neglected. To quantify the impact of these changes, many researchers have studied meteorological and climatic parameters using statistical relationships, but one major problem always existed, the low spatial accuracy of meteorological data. In recent years,... 

Water shortages resulting from macro-environmental climate changes as well as local inefficient agricultural practices and dam constructions activities have resulted in the gradual reduction of water level in Urmia Lake, located in the northwest of Iran. As such, restoration efforts were initiated to prevent further adverse impacts exacerbating the conditions and creating secondary problems such as regional salt dust generation and dispersion, resulting in health issues for the greater area population in the neighboring vicinities. The utilization of advanced forecast modeling based on deep learning algorithms can assist the authorities to manage better multi-dimensional issues affecting the... 

An important class of applications which have been rapidly growing recently is the one that create and use time series data. These types of data sets are ordered based on the timestamps associated to their data items. In practice, traditional relational databases are unable to satisfy the requirements of these data sets; however, NoSQL databases with column-wide data structure are appropriate infrastructure for them. These databases are very efficient in read and write operations (especially for time series data, which are ordered) and are able to store unstructured data. Time series data may contain valuable and sensitive information; hence, they should be protected from the information... 

Implying non-model based approach and using seasonal data, we determined cyclical component of housing market and discussed about its lagging or leading behavior to overall economic business cycles in Iran. To extract cyclical component we applied band pass filters, including Hodrick-Prescot, Baxter- King, Butterworth and Christiano-Fitzjerald, and Bry-Boschan’s algorithm on any time series which is able to explain housing market’s behavior in aggregate level. After examining many criteria we found that real residential investment in urban cycles depict cyclical behavior of housing investment. Real residential investment’ cycles in urban lag monetary base rate cycles and m1 rate cycles which... 

Performing analysis and forecasting is crucial. Better forecasting will lead to better decisions. One method for predicting the future is time series analysis. In reality, it is common for an intervention to occur and alter the characteristics of a time series. In recent years, interrupted time series analysis has been receiving a lot of attention. A new forecasting method for interrupted time series has been developed in this study. This is a system dynamics-based approach. At every stage of the approach, system thinking is incorporated. In order to model the effects of a given intervention, common modes of behavior in dynamic systems are used. Furthermore, control theory has been used to... 

Electricity consumption has increased dramatically in recent decades, and this increase has severely affected electricity distribution. Therefore, forecasting electricity demand can provide a precondition for distributors. Predicting power consumption requires many parameters to be considered.In this research, machine learning, and deep learning methods such as recursive neural networks, long short-term memory networks, etc., as well as the ARIMA model will be used. These models have been tested on the London Smart Measurement Database. In order to evaluate the capability of the models in forecasting electricity consumption, each has been used to predict the electricity consumption of a... 

P/E ratio is studied in four levels in this study:
1)Macroeconomics level
2)Capital market level
3)Industry level
4)Company level
The first level studies effects of macroeconomics variables on P/E ratio. At this level we use variables such as economic growth, inflation, exchange rate, and etc.The next level uses capital market variables such as market volume, and IPO information.The third level that we study in this research is industry level. Stocks of an industry generally behave similar, because they have common advantages and disadvantages, thus industry is an effective factor on P/E ratio.The last level studies financial statements and internal features of a... 

Support vector regression (SVR) in the field of machine learning attracted much attention because of its attractive features and high efficiency for high-dimensional and nonlinear data. Although support vector regression has shown to be very effective for prediction problems, it is necessary to adjust the parameters contained therein to obtain the desired output with error rates. In the past, this was done manually, by trial and error. Over time and by development of optimization algorithms, one of the newest methods to solve such problems is the meta-heuristic optimization algorithms. Therefore, in this thesis, we use the firefly optimization algorithm, which is a population-based... 

Crop classification is one of the most important applications of remote sensing in agriculture. Knowing what crops are on the farm is invaluable both on a micro and macro scale. For example, this information can be used to design and imple- ment agricultural policies, product management and ensure food security. Also, this information can be used as a prerequisite for implementing other programs at the farm scale, such as monitoring and detecting anomalies during the crop growth cycle. Most of the studies in this field are focused on the optical data of the Sentinel-2 satel- lite, but the optical data are vulnerable to atmospheric conditions, and on the other hand, there is valuable... 

Predicting oil prices, especially in exporting countries, will help governments in the policy-making process by obtaining a reliable estimate of oil revenues. The existence of a complex mechanism governing the process of oil price formation has reduced the efficiency of linear models in forecasting and led researchers to use nonlinear intelligent systems to predict oil prices. In this study, after a detailed study of the structure of artificial neural network, two models of neural network GMDH and MLP and ARIMA method have been used to predict oil price. There are important factors in the prediction process with neural networks, and if all these factors are selected correctly; One can expect... 

In today’s competitive world, using an efficient forecast method is necessity for companies. To now, many forecast methods have been developed, but many of them have not an expected efficiency. In this research, we develop a new hybrid forecast method with application of forecasting retails demand. The hybrid method is the combination of ARIMA method and neural networks. To test the efficiency of the method we use the 96 weeks data of plastic containers demand. We also comprise the hybrid method with other forecast methods including naïve method, ARIMA method and neural network method by applying root mean square error and mean absolute percentage error indexes. In the case of plastic... 

In this thesis we are going to forecast the hourly consumption of the electricity over the country with two models and then, combine them. The first model decomposes the consumption to a deterministic trend and a stochastic residual. The second one assumes that the trend part is also stochastic.Once the consumption is being predicted separately by the models, in the second part of the thesis, we will combine the results to get a final prediction. This prediction is going to be compared with the load forecast of the Dispatching Unit of the electricity network as a base model. We are going to answer two important questions: firstly, does combining the models give a better prediction or not,... 

Using revenue management in any industry can increase the profit. In aviation industries, due to the huge number of requests and travels for each airline, a revenue management system can lead to a good profit for the airlines. The first step in revenue management system is predicting the demand.In this article two models are developed using time series techniques, based on the information taken from one of the Iranian airlines in Tehran-Mashhad fly route.The first model is developed using ARIMA and seasonal-ARIMA models and the second one is based on the demand and price history, price in the day of prediction and the ARIMA model. The second model which is a combination of price, prior price... 

The seasonal fluctuations in economics variables relate to the different behavior of economic agents across different seasons. In past, seasonality has been viewed as a redundant feature that needs to be removed from data before economic analysis. From 1988, modeling seasonality has become the major concern of many economists; moreover, it was seen that many economic analysis and forecasts could be flawed if seasonality is ignored. In the present research, periodic times series approach is used for the first time in modeling the seasonality feature of the housing market. Regarding the importance of the housing sector in economy from micro and macroeconomic points of view, using a more... 

Failure of mechanical parts in the industry lead to a larger system downtime and even imposing economic losses to the factory. For this Purpose, for many years, researchers have been trying to find ways to predict early failure and to prevent losses from occurring. Creation of new sciences like artificial intelligence, helped researchers in this field.In the current study, using experimental data of a set of bearings that have been tested and recorded in the Intelligent Systems Research Center, A new approach with sufficient accuracy is presented for the prediction algorithm. Among the features extracted, three features of entropy, root mean square and maximum are the most appropriate... 

The importance of transfer learning in image-related problems comes from its many advantages that are sometimes undeniable. Previous researches have well shown the success of transfer learning in this area using deep neural networks. However, transfer learning for time series data has not yet been done in a conventional and automated manner. The main reason for avoiding transfer learning in this domain relates to the dynamic and stochastic nature of the time series, where they show a time-varying behavior. Previous experiments have shown that transfer learning between two heterogeneous time series could harm the forecasting accuracy of a model. Therefore, in this thesis, we aim to explore...