Sharif Digital Repository

This is the first attempt at process modeling in terms of predictive control using a hierachical method based on regression analysis and artificial neural networks(ANNs).This hierachical use leads to the reliability improvement of neural model of process in prediction (extrapolation and interpolation) of process output. such an outlook makes it possible to predict the proper input settings which achieved a desired process output by designing various senarios for process set up. This approach was applied in Tile industry for spray dring process and in order to indicate the achieved improvement,three models:(i) regression model of process using multiple linear regression,(ii)Neural model of... 

In many fields of science, we observe a response variable together with a large number of potential explanatory variables, and would like to be able to discover which variables are truly associated with the response. At the same time, we need to know that the false discovery rate (FDR)—the expected fraction of false discoveries among all discoveries—is not too high, in order to assure the scientist that most of the discoveries are indeed true and replicable. This paper introduces the knockoff filter, a new variable selection procedure controlling the FDR in the statistical linear model whenever there are at least as many observations as variables. This method achieves exact FDR control in... 

Fatigue is one of the most common failure modes that reduce the structural integrity of asphalt pavements. Dynamic tests are used as fatigue performance indicators for asphalt mixture. However, these tests are expensive and require special equipment and set up. At this research, the main goal is to develop a fuzzy model which is more efficient than the existing regression model for prediction of the fatigue life. A database from the available data from various research was compiled. For each model, a comparison between Fuzzy and regression output by actual outputs was done and it was seen that the fuzzy modeling can predict fatigue life very closely. Finally, the required software for this... 

Forecasting model of water consumption amounts could be used in order to manage water resources for future condition of city. In this thesis, a model for forecasting water demand for Tehran has been presented by evaluating regression models and intelligent models. In this study, uncertainties which are connected to climate and population changes are taken into account. The considered variables include minimum, maximum and medium temperature, precipitation and solar radiation. Considering objectives of this thesis and various forecasting methods and their advantages and regional conditions of Tehran, in addition to regression analysis, perceptron neural network, probabilistic neural network... 

This research conducted to achieve a pragmatic approach for the demand forecasting of ICU beds which is the one of most important services are provided by hospitals and medical centers and always has been challenging associated with capacity planning in many countries. Attaining such a method, ICU patients identified and categorized according to patients age and duration of hospitalization period. Then, as a case study, demanded ICU beds in Iran's hospitals predicted for three time horizons in 2021, 2031 and 2041 by use of regression model to forecast the population of identified patient categories which was extracted from Iran's demographic data in a 30-year period. The results indicated... 

Due to water resources restriction and increase in water demand, optimum use of existing available resources is more essential. This needs accurate prediction of streamflow with lag time from one to several months. In recent decades identification of long term climate variables as predictors of hydrological process has made considerable evolution in climatic predictions and several studies have been made in this field. In this research streamflow volume of Dez Dam in dry season (April to August) has been predicted by using multiple regression models and considering seasonal rainfall data, climate indices and ocean-atmospheric variables including surface temperature of adjacent seas and... 

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... 

Image Registration is spatially alignment of two images in a wide range of applications such as remote sensing, computer assisted surgery, and medical image analysis and processing. In general, registration algorithms can be categorized as either intensity based or feature based. The feature based methods use the alignment between the extracted features in two images. The simplest feature is images intensity which is directly used in the intensity based method via similarity measure. This similarity measure quantifies the matching of two images.Similarity measure is main core of image registration algorithms. Spatially varying intensity dis-tortion is an important challenge in a wide range... 

The derivatives of 5-Hydroxy-3(2H)-pyridazinone show inhibitory effects on hepatitis C virus. The aim of the present work was modeling and prediction of inhibitory effects of these derivatives (Log(1/EC50)) on this disease. In this research, a data set of 119 molecules of 5-Hydroxy-3(2H)-pyridazinone derivatives that have inhibitory effect on hepatitis C virus was selected. The MLR model was generated using SPSS package. Five important descriptors were selected applying stepwise variable selection technique. These descriptors selected through 1207 descriptors that were calculated for all molecules in data set. Best model with high R2 and F values and low RMSE was selected for the... 

Air pollution caused by industrialization is the problem which adversely affects human life. Among air pollutants suspended particles, especially particles smaller than 10 microns (PM10), for their high concentration in air in large cities are the major index as air pollutant. Due to their small size, PM10 can penetrate into the aspiration organs causing harmful effects. The objective of this work is to develop an Artificial Neural Network (ANN) model for prediction of short-term concentration of PM10 in the city of Tehran. Complex mechanism of reactions, numerous types of pollutant materials produced from transportation and industrial activities, variety of sources, difficulties in data... 

Prevalence of Multiple Drug Resistant Tuberculosis and use of Yersinia-Pestis in bioterrorism warrants synthesis of new antimicrobial agents. Although Pyrazoline derivatives were first synthesized as antimicrobial drugs, but they also had Mono Amine Oxidase inhibitory effects. In this Quantitative Structure – Activity Relationship (QSAR) study, MAO-I activity of pyrazoline derivatives were evaluated. By applying semi-empirical quantum calculations at AM1 level, optimum 3D geometry of 32 molecules were obtained.After descriptor generation, Principal Component Analysis (PCA) was performed to fiind out 5 outliers. After omitting outliers and sorting molecules according to IC50 values, Stepwise... 

An event must be modeled in a way that either reflects a comprehensive perspective for the event or acts in an especial part of that event, roperly. The main aim of this thesis is to control. Therefore the models will be accepted whenever the suggested mathematical models can move towards controller final target, desirably.This thesis proposes a linear mathematical model, five nonlinear models and a simple model based upon Convolution, Fuzzy Regression and Neural Networks techniques for Acquired Immune Deficiency Syndrome (AIDS), respectively. The proposed models were achieved through studying 300 HIV+ Patients who were under Highly Active Antiretroviral Therapy (HAART) approach in Iranian... 

Self-driving car can move like an experienced driver without human intervention. For this purpuse, she must be able to fully understand and feel her surroundings like a human being. Accurate understanding of the surrounding environment in real time is one of the important factors that affect the performance of self-driving vehicles. Perception refers to the ability of an autonomous vehicle to collect sensor data, extract relevant knowledge, and develop contextual understanding of the environment, for example, identifying obstacles and the drivable area ahead the car. For this purpose, we use the Kitti dataset. This dataset is the largest dataset for machine vision algorithms for self driving... 

The exitance of a certain amount of halide ions including Chloride (Cl-), Bromide (Br-) and Iodide (I-) in human body is crucial for ensuring health. However, exposure to high levels of these ions can cause diseases, such as goiter and neurological disfunction. As a result, the development of a simple and efficient analytical method for determining the aforesaid halide ions is so important. Triangular silver nanoparticles (TSNPs) display wide color variations due to their tunable plasmonic properties dependent on the aspect ratio of the nanoparticles. Hence, designing a colorimetric sensor array using the optical properties of TSNPs for determination and discrimination of halide ions is of... 

The main goal of the current building design codes is to protect life safety, and generally, they do not directly address other societal, economic, etc., concerns regarding earthquakes. However, recent earthquakes around the world have shown that the effects of earthquakes' damages and losses can go beyond life-safety concerns. This observation has led many renowned scholars, organizations, and agencies to state the need to change the current design codes. In this regard, this thesis investigates the basis of setting the seismic design requirements and suggests a method in this respect. The study consists of two main parts. Part I (theory and design methodology) discusses some theoretical... 

At each stages of oil and gas production, from the time of drilling of the wells to the state of production and development of the reservoirs, formation damage would hinders the oil/gas rate and causes high pressure drop in the drainage area. To eliminate the damage caused by the formation blockage, several remediation techniques are used, which are called well stimulation methods. The most common method for the past tens of years is matrix acidizing which lead to the improvement of the performance of the well. To optimize this operation, optimal acidizing design is needed, otherwise the acidizing process face failure and lead to blocking of the well through acid-induced damage. One of the... 

The present study was aimed at investigating the relationship between reading comprehension ability as probably the most vital language skill especially in academic contexts (Farrell, 2009) and critical thinking as one of the most debated issues among scholars in modern education (Ku, 2009; Rudd, 2006). To this end, 200 male and female university students studying English Translation and Literature were chosen as the participants who sat for two tests. The first was a reading section of a retired TOEFL test provided by educational testing service in which the participants' scores were regarded as their reading comprehension ability. The second was the California Critical Thinking Skills... 

Hybrid engines are one of a variety of chemical propulsion systems that have been given special attention in recent years by various industries such as space and defense. The most important reasons for considering this type of system are its high safety, its affordable price compared with liquid fuel propulsion systems, the possibility of switching on and off and changing thrust. This system has a lot of disadvantages as well. This system cannot meet all the needs of different industries due to the low regression rate and, consequently, the limitation of the operating range, thrusts and special impulse. As a result, increasing the fuel regression rate in these engines can greatly expand... 

today's financial markets such as stock market are more attractive and important position and wealth are considered income and therefore attracts many people have. But the other hand, activity in these markets requires a high risk of admission. The point that is important is that the risk of investing in these markets can be predicted to some extent with the trend of stocks and securities can be controlled. Time series trend of stock prices and non-static characters is excited. But analysis of such behavior is impossible, i.e., reliance on sophisticated tools and of course accept the possibility of an error can be predicted price to pay. Synthetic models of artificial intelligence today, due... 

In some statistical process control applications, quality of a process or product 1s characterized by a relationship between a response variable and one or more explanatory variables which is referred to as profile by researchers. In some applications such as calibration, this relationship is characterized by a simple linear regression. However, in some situations, more complicated models are needed. It seems that there is a little attention to monitoring of profiles with binary response variables. Furthermore, the extensive applications of binary response variables in real industrial worlds make it necessary to concentrate on this kind of profiles. In this ...