Sharif Digital Repository

Predicting groundwater level fluctuations is essential for effective water resource management and environmental preservation. This study examines and compares two modeling techniques, namely Wavelet Neural Networks (WNN) and Artificial Neural Networks (ANN), for predicting fluctuations in the aquifer levels in the Varamin plain. Traditional hydrological models often struggle to detect nonlinear relationships present in hydrological data, which may lead to inconsistencies in predictions. The research focuses on groundwater level fluctuations in the Varamin plain over a 30-year period, from October 1989 to September 2018. Statistical methods such as mean, median, and variance calculations are... 

Chlorophyll-a, as an important component in evaluating water resources, has a significant impact on the status of water resources. This component is dependent on various quality parameters, such as phosphorus concentration, nitrogen concentration, turbidity, suspended solid concentration, temperature, pH, and dissolved oxygen concentration in water. To evaluate the quality status of surface water, it is necessary to estimate the exact concentration of chlorophyll-a in different temporal and spatial ranges. The objective of this study is to simulate and predict the concentration of chlorophyll-a in different temporal and spatial ranges using a combined application of machine learning models,... 

The water crisis in Iran is not only caused by climatic changes, in other words, human factors have also influenced the increase in water consumption. The intertwining of various economic, political, and social factors has caused a direct and dynamic impact on water resources. Undoubtedly, one of the most important processes in policy-making and in the continuation of planning the country's water resources is the approval of useful laws from the point of view of implementation, monitoring and finally having a positive impact on the subject under discussion. From this point of view, the main research question is the role of laws on the current state of water resources management. The first... 

In recent years, Machine Learning models have been developed in Signal Processing, Computer Vision and Neuroscience areas. There are two categories of Machine Learning models which are supervised and unsupervised learning models. Regression and classification problems are two popular problems examples of supervised learning models. From unsupervised learning problems, we can mention the clustering problem. Support Vector Regression (SVR), Decision Tree Regression and Bagging Ensemble Regression models are some important models of the regression problem. For classification problems, we can also mention to Support Vector Classification, Decision Tree Classification, and Bagging Ensemble... 

Knee arthritis is a painful disease from which millions of people around the world are suffering. One of the main causes of osteoarthritis and joint damage that starts from a young age, is that bones around the knee are not in a straight line. As a result, this situation causes additional pressure to the knee. This should be corrected with surgery. There are two procedures for this operation, a conventional method and a customized method. In conventional method, surgical planning is based on 2d X-ray images and plates are formed and fixed approximately at the desired location. This method is not precise enough and may cause problems for the patient. A new developing method, is that all the... 

Briefly, the accomplishment of movies is based on their sales at the box office or gaining an achievement at the film festivals. Utilizing AI calculations and machine learning algorithms, various models have been proposed for the prediction of these achievements in the literature such as predicting the success of movies using regression models or the success of movies using discrete decision models is anticipated, and in another study the effect of social media data on sales investigated. The methods which are used to tackle these problems can be referred to as machine learning algorithms including neural networks, regression models, discrete decision-making models, public and experts... 

Control of complex networks is the main topic in this study. In this thesis, we consider the methods to steer the dynamics of a network from an initial state to the desired final state. To achieve this goal, one needs to inject appropriate control signals from some of the network nodes, known as driver nodes. We consider the quadratic sum of control signals as a cost function, to control the dynamics of the network. By minimising the cost function, we obtain the control signals as well as driver nodes for a linear time-invariant system. As an example, we provide the results of an energy minimization strategy to control the second order Kuramoto and Rössler dynamics in Erdos-Renyi and...