Sharif Digital Repository

Nowadays, methods based on deep learning networks are the most effective artificial in­ telligence methods. Although they have achieved success in various fields (such as machine vision and object recognition), practical and experimental cases show the fragility of deep learning networks against perturbations and unwanted changes of the input pattern. All these perturbations must be in a way that the main class of the perturbed input pattern can be rec­ ognized by human, but the network makes a mistake in recognizing its correct class. This thesis seeks a more accurate evaluation by designing adversarial attacks such that the main class of the adversarial pattern is detectable by human... 

In this thesis, a multi-stage project portfolio selection and scheduling problem in an uncertain environment is modeled, analyzed and solved. Moreover, we investigate the situations in which a project manager is confronted to a large number of projects to be selected and scheduled while the required resources of the projects are limited and renewable. The aim is to maximize objective function which is the net present value of the profit of the projects. To solve the mentioned problem, we introduce a multi-stage stochastic programming. For the reason that, in real problems, optimization problems that included all restraints are large scale and have computational complexity, these problems are... 

Profile Monitoring is a new research topics in the field of statistical process control. In many applications of statistical quality control, sometimes quality of a process or product described by a relationship between a response variable and one or more independent variables.The researchers call this relationship profile. The study seeks to demonstrate that monitoring profiles In addition, the industry can be effective in medical field and improves control of the patient's condition by a doctor. Profiles are usually modeled with a linear regression equation, non-linear or polynomial. finally, the results of this study, using actual data, models and methods to predict and control... 

At the present, End-stage renal disease(ESRD) is the ninth-leading cause of death in the USA.according methods of medical treatment for End-stage renal disease (ESRD), transplantation is the most viable renal replacement therapy for ESRD patients, there is a disparity between the demand for kidneys for transplantion and the supply. Incompatible inblood-type and antigen matching between patient-donor pairs is cause of shortage in disparity between the demand and the supply.paired kidney exchange of kidney among incompatible patient-donor pairs.PKE can be solve many difficulties in matching patient with incompatible donors. Kidney transplant surgeries in PKE must take place simultaneously... 

As a method of cancer treatment or improvement of cancer-related complications, external radiation therapy is prescribed by physicians, in case of detection of a tumor in a region of patient’s body. Over time, various techniques have been developed for external beam radiation therapy. Among which, Intensity Modulated Radiation Therapy (IMRT), due to its ability to adjust the intensity of radiation beams, has a higher capacity to generate appropriate dose distribution based on tumor size and volume and it is one of the most widely used techniques in cancer treatment centers.The core process in treatment planning is using appropriate computer algorithms which results in posing enough damage to... 

The aim of Emergency Medical Services (EMS) is to provide fast medical care and to transport patients to hospitals at the earliest possible time, so as to reduce injury and fatality rate. Healthcare managers try to improve healthcare systems by reducing the response time to demands. In this thesis, we present mathematical models for the problem of location and relocation of emergency vehicles after the end of their service time or after they have returned to a hospital. We believe that implementing these models can help managers improve the performance of emergency medical services. In the first part of this study, we present a two-level deterministic optimization model considering demand... 

Operating rooms have always been the most expensive and also the most profitable section in hospitals which include approximately one third of cost and two third of income. The management always wants to decrease the cost of hospitals. On the other hand, usually this goal stands against other goals such as patient’s satisfaction. So the manager should make a balance between these goals. In this research, we will propose an integer programming model for operating room scheduling problem without uncertainty for elective patients. In order to make the model more realistic, we want to make connection between operating room theatre and intensive care units. Also, we will consider desirable... 

Cancer is one of the main causes of death among all people around the world. This shows that more and more attention should be paid to cure cancer. One of the most common cancer treatments is radiation therapy. Among all radiation therapy treatments, Intensity-Modulated Radiation Therapy is a very effective and flexible ways to treat cancer. There are numerous mathematical problems to find the perfect treatment plan. One of these mathematical problems is Fluence Map Optimization in which we try to find the best dose intensity for each tumor and surrounding organs. The main purpose in this problem is to minimize the number of cancerous cells which are being destroyed while minimizing the... 

Knowing different groups of customers and building effective communication with them in such a way as to guarantee the future economic interests of the organization is a very important issue in today's businesses. The attraction of profitable customers, as well as the preservation of valuable old customers, are both important, except for the precise identification of their features. The value of customer longevity plays an important role in customer segmentation, and there are numerous researches that focuses on customer value with the aim of making more profit for the organization, most of which have life-cycle customer value models as the main inputs for segmentation cCustomers have been... 

Large amounts of relief resources such as water, tents, medical equipment and fuel after a major disaster need to reach the affected people. Satisfying the needs of victims is crucial to the success of crisis relief operations, as a lack of relief resources can lead to the suffering and loss of lives of victims. According to studies, large-scale catastrophes have occurred frequently in recent years. Therefore, it is necessary to pay more attention to the management of post-crisis resources. Since the distribution of emergency resources depends largely on the efficiency and effectiveness of logistics operations, the primary objectives include minimizing logistics time and cost, minimizing... 

in this study we intend to build a recommender system, more specifically We try to build a multi-criteria collaborative filtering. Collaborative filtering is one of the methods used in building of recommender systems. In this study, we use technical attributes to build a recommender system. Technical attributes refer to the attributes which focus on the writing style of the texts. After building the recommender system based on technical attributes, we also build a recommender system based on the conventional criteria in order to make a comparison between these two criteria. Collaborative filtering consists two major categories, namely memory-based and model-based that both of them have been... 

In recent years, the attention of marketing researchers has shifted from numerical product rating to user-generated content. Because of this, customers' online reviews now play a very important role in the destiny of Internet businesses. Today, huge and comprehensive platforms have been developed to record and analyze online customer reviews. This type of unstructured data that users and Internet shoppers create based on their experiences of using products and services, has a significant impact on gaining and losing the trust of other users. After reading each review, each user can express their opinion about the usefulness of that comment, which can be seen by others. Large Internet... 

Recently, data scientists have been paying much attention to sports. Many researches have been done in this field, using data mining and machine learning techniques. The following research aims to predict the results of football matches, which consists of two general approaches. For the first and second approaches, we used video game data and match statistics, respectively. In both approaches, it was tried to predict not only the final result (win, draw, or loss) but also the final goal difference. In the first approach, the home team victory was predicted by 73% accuracy, the draw by 75.4%, and the home team defeat by 73.7%. Nevertheless, in the second approach, the home team victory was... 

Markets are becoming more saturated every day and competition between different businesses is increasing. The importance of managing Customer churn in various businesses has become increasingly important because the cost of attracting a new customer is many times greater than retaining an existing customer. With the development of data mining and its increasing expansion and the other side, the increase of stored information related to various organizations and businesses has accelerated the operations of extracting knowledge from data. Today, businesses are moving towards the use of intelligent knowledge extraction systems, of which Customer churn prediction systems are one of the most... 

In today's world, decision-making has become one of the main problems and challenges for managers, despite the conflicting goals and the different scenarios. On the other hand, most existing decision-making methods are not applicable to all issues in different decision-making environments. Therefore, in this study, by presenting a new algorithm, these concerns have been reduced and a new method has been proposed using the concept of stratification recently introduced by Lotfi Zadeh. In the present study, a single system multi stratification and multi-system multi stratification are presented, which provide managers with an easier understanding and analysis of each system so that they can... 

People's lives have been affected by the spread of the Covid-19 virus. Due to the high infectivity, governments have screened people, imposed curfews, mandated the use of masks, and so on to reduce the rate of transmission of the disease among people. Meanwhile, infected people are getting treatments: people who are slightly affected are quarantined at home, and those who are heavily affected are treated in hospitals. Hence there is an excessive increase in the hospital workload. On the one hand, this increased workload leads to physical fatigue and, on the other hand, to psychological problems, stress, etc. for the healthcare professionals. Therefore, it is very important to take care of...