Sharif Digital Repository

Analysis of performance of fetal heart is very important for monitoring its health. In recent years a lot of research is performed on recording electronic signals from mother abdomen which consist of combination of maternal ECG and fetal ECG. Purpose of this thesis is investigating methods. For evaluation of different methods simulated ECG dataset and Dalsy dataset as real data were used. In this thesis Wavelet and EMD denoising as single channel methods and ICA, PiCA and deflation as multichannel methods are used. At last novel combinations of these methods is proposed which outperforms existing methods  

One of the most trivial factors for every service company is to fulfill customer demands and to satisfy them. For this purpose, it is needed to explore the business fundamentals. Transportation companies, however seem to be more important, because in one hand, the demand for their services is too many. In the other hand due to the intense competition between rivals, every business tries to stand in the crowd; thus, it is of high importance to correctly predict the travel time as well as fare. The importance of time is not only because of having a fare pricing system, but also it is important for scheduling, assigning drivers, and covering city or a particular district. Travel time... 

Portfolio optimization in modern markets faces significant challenges stemming from the dynamic environment and the ever-increasing diversity of assets. Addressing the existing gaps in the literature, this research proposes an innovative framework based on Multi-Agent Deep Reinforcement Learning (MADRL) to manage a comprehensive and constrained investment portfolio. The proposed framework features a hierarchical architecture, decomposing the problem into two sub-problems: asset selection (by independent agents) and weight allocation (by a senior agent). By incorporating real-world market constraints and employing a risk-averse reward function based on the Conditional Value at Risk (CVaR)... 

This research develops a multi-objective robust data envelopment analysis framework integrated with advanced deep learning techniques to forecast the future performance of decision-making units within blood supply chains. The model significantly advances traditional performance evaluation by incorporating a sophisticated temporal dimension, enabling the assessment of efficiency across multiple periods rather than at a single point in time. This dynamic approach leverages cutting-edge forecasting methodologies, including attention-based Long Short-Term Memory networks for modelling Generalised Autoregressive Conditional Heteroskedasticity parameters and Segmented Recurrent Neural Networks.... 

This paper presents some approaches based on data mining techniques to solve the prediction task of Computational Intelligence and Learning (CoIL) Challenge 2000. The prediction task of the contest is a direct mailing problem and the goal is to improve its response rate. The main issue in this competition is the incompatibility of the dataset in which the distribution of the classes of the target attribute is highly unbalanced. This in turn causes high error rate in identifying the minority class samples. Three different level methods including data-level, algorithm-level, and hybrid method are used to overcome this issue. The specificity and sensitivity criteria are employed to compare the... 

There are several methods for measuring thin film thickness, however, for the analysis of liquid film motors [1] we need a method which is capable of measuring the thickness using a single image of the film. In this work, we use the colors that appear on thin films, such as soup bubbles, which is a result of light interference to calculate the thickness of the layer  

Thermal relaxation time is the time when maximum temperature of a particle get to 1/e of it’s initial value. The destruction of a tissue depends to this important parameter. This parameter has studied by Monte Carlo simulation of pulsed laser in to environment as healthy and cancerous tissue. The main goal of this method is providing proper temperature in a special area so that minimize thermal destruction around that area. In this thesis, temperature distribution of tissue that is caused by pulsed laser, has solved by new method;in this new method the pulse duration uses for Monte Carlo simulation. Also using the solution of radiation transfer equation by Discretes Ordinate Method, new... 

People in the organization who are influential, opinion leaders, decision-makers and approvers need to be incorporated into the entire Strategic Planning process at some levels .The Management of these Stakeholders involves identifying their organizational roles and their disposition towards and understanding of Strategic Planning, then to work with them throughout the process to improve or maintain their opinion of the value of Strategic Planning through continuous updating and addressing of their issues, concerns and questions. Physical asset practitioners apply the physical asset management framework and policies to ensure the performance and output potential of physical assets through... 

By direct and alternating electric field applied to thin film of liquid suspended in the air we can spin out and control it. Rotation pattern depends on the geometry of the electrodes and the applied magnetic field. This is called a rotating liquid film (Liquid Film Motor). To determine the cause of rotation, different models have been proposed. In this project we have tried to check the accuracy of any of the models. Using particle velocimetry using the photo, we calculate the velocity pattern. Then, using the Navier-Stokes equation calculate the acceleration and viscosity from the velocity. Then, for a special arrangement using a finite diffrent method, electric potential and the electric... 

Ultrasound waves have attracted substantial attention due to their potential for trapping the small particles, which cannot be handled by usual tweezers. The acoustic tweezer is a technology that is able to tarp and control the movement of micrometer to millimeter objects by standing or focused sound waves. Acoustic tweezers are the subject of many researches around the world, due to simplicity, cost-effective, biocompatibility and most important better performance in non-transparent optical environments, compared with optical tweezers.In this project, by using a ring piezoelectric and a power amplifier, an acoustic tweezer was designed and constructed. Moreover, the polystyrene particles... 

In recent years, requirement engineering and goal modeling have gained more attention among different organisations. Therefore, different methods have been designed to discover stakeholders’ requirements and translate them into process and organizational goals. Various goal models have been introduced to represent these goals and their relations towards each other. Still, these methods are manual representations of different process scenarios and do not relate to the actual behavior. In 2014, Map Miner Method (MMM) was introduced to discover intentional process models from event logs. MMM uses Hidden Markov Model (HMM) as a means to represent the process as a map model of strategies and... 

Eyesight is one of the most important tools for humans to communicate with environment and consequently, blindness or poor eyesight results in unsatisfactory effect on life quality. Owing to the importance of the sense and to assist to the patients, this thesis aims to design and assemble cybernetic glasses using ultrasound waves. To this end, firstly, the notion of waves focusing on ultrasound waves is described and reactions of human hearing system to the waves are studied. Then, the transducers as a key device are introduced. Afterward, bat sense system to communicate with environment which is based ultrasound waves is described. Next, attenuation effects on ultrasound wave pressures are... 

Recommending routes to city taxis in order to improve their performance in finding passengers can reduce traffic, pollution and waiting time for passengers, as well as this, increasing the efficiency of taxis can increase their income. In this study, by analyzing trajectory data obtained from 536 taxis in San Francisco over a period of one month, we generated networks of cells, each of which has time-dependent characteristics such as the probability of finding a passenger, the capacity of each cell, or the amount of demand exists is in the cell and the average speed of passing through that cell. also, the connections between these cells in order to make more use of the experiences of taxi... 

The purpose of the present study is to develop neural network estimation method for hybrid or panel data which have a combination of two cross-sectional and time series structures and because of the features of both structures, their use in different sciences offers many advantages; and the analytical methods for this data structure are also different from other one-dimensional structures, so different and specific regression models are presented for this data structure. However, in the artificial neural network method, modeling the development for this data structure is neglected, so in the present study, using the concepts of panel regression methods and their application to the... 

Introduction: Today, backward and forward scattering tomography of dispersive medium is of great interest because of its broad applications, especially in medical imaging, of breast cancer, Distinguishing different tissues of the body from each other is one of the necessities. Increasing the quality of the image by just a few percents has great improvement on the tomography resolution.
Materials and Methods: In this project we made phantom of the tissue and tumor from Intralipid 10% plus Agarose and Indian ink for soft tissue and plastic fibers as tumor having birefringence factor of 0.001.After putting the plastic tumor in soft tissue phantom, the polarized white light and a digital...