Sharif Digital Repository

The present research proposes a new method to establish a practical framework for extension of gas turbine life time. This method is based on an nine-step operational algorithm which is capable for different types of gas turbine. The essential inputs for this algorithm includes documents of inspection and knowledge of repair and maitenance experts. In this algorithm is used the Bayesian network probabilistic method. Therefore, based on the observations and the knowledge of experts, gas turbine Bayesian network is produced. According to this Bayesian network consequenses are created. Furthermore, making the steps of the algorithem more explicit, FTA and FMEA methods are used to creat the... 

Risk management is one of the important phases of a project life cycle. There are several quantitative and qualitative methods to determine and plan the proper reaction risks in a project. These methods aim to prevent additional and unnecessary costs. Project managers, stake holders and beneficiaries always believe that risk management of project engineering as one of the importance parts. Although there are multiple methods that can evaluate risk, but there is still research problems especially for risk qualitative and quantitative prediction. This gets more serious after evaluating and minimizing risks effects considering the other risks’ damaging effects which have not been considered. In... 

This thesis proposes a probabilistic framework to increase situational awareness about serviceability of infrastructure systems, and extend and distribution of losses in the posthazard state of communities. Maintaining situational awareness is the first and foremost step in prioritizing search and rescue operations and organizing resources. This is a challenging task due to the uncertainties that exist in infrastructure systems’ performance after occurrence of a hazardous event. These uncertainties gradually diminish as further information is received. Therefore, a probabilistic framework is the necessary element for disaster management. This framework must be able to update initial beliefs... 

Evolutionary algorithms are a type of stochastic optimization techniques influenced by genetics and natural evolution. Once the set of candidate solutions has been selected, a new generation is sampled by using recombination (crossover) and mutation operators to the candidate solutions. Public, fixed, problem independent mutation and recombination operators frequently lead to missing building blocks, knowledge of the relationship between variables and result in converging to a local optimum. A method to prevent disruption of building blocks is using the estimation of distribution algorithms (EDAs). The experimental results show that EDAs is capable to identify correct linkage between the... 

This research proposes a probabilistic framework for decision support in emergency response. Currently, decision-making is traditionally based on data from reconnaissance teams, while there are other information sources that assist decision-making. These sources of information include social sensors, physical sensors, aerial imaging, and crowdsourcing. The information obtained from these sources is heterogeneous and uncertain, requires a probabilistic data fusion framework to be used in decision making. This research employs Bayesian Networks for this purpose. The outstanding feature of the Bayesian Network is its real-time nature, which set apart it from other methods. This feature makes... 

Infertility is an important problem to deal in medicine. In every four couples, on average, one couple is affected by infertility in developing countries. In the majority of cases, the infertility of men has a relationship with spermatozoa and semen, and can be measured by semen and spermatozoa analysis for more advanced diagnosis and treatments. Analysis of the movement patterns of spermatozoa were performed by expert screeners earlier, but nowadays, many of these analyzes are performed using computer-based systems called computer assisted sperm analysis (CASA). The benefits of using CASA instead of expert screeners are achieving system-independency and numerical results at the end of the... 

The development of effective models for classification problems, such as the problem of selecting which credit applicants to accept, has been the subject of intense research for decades. Many static and dynamic methods, ranging from statistical classifiers to decision trees, nearest-neighbor methods, and neural networks, have already been proposed to tackle this problem and to assist decision making in the area of consumer and commercial credit. Given the profusion of modeling and data management techniques, it is often the case that which model has the more appropriate outputs in classification of the same problem. Among the stated methods although the latter, Neural Networks, is powerful... 

The growing number of disasters in recent years has become a significant threat to hospital buildings' resilience and preparedness. Besides, the stochastic nature of these disasters and the complexity of the hospital building systems exacerbate the difficulty of making appropriate decisions during and after disasters. To address the issue, this research proposes a novel model that utilizes the capabilities of Bayesian Networks (BNs) and Building Information Modeling (BIM). This model helps decision-makers in hospitals and medical centers measure various effects of disasters on utility systems and analyze the consequences of their decisions. The capabilities of the proposed model are tested... 

Road casualty is the fifth leading cause of death in Iran. To adopt proper countermeasures there is a need to evaluate the consequences of the implemented policies. Despite the development of crash time series models, these methods have not been in accordance with the multivariate, seasonal, and non-linear nature of crash data. On the other hand, the interpretable crash causal analysis frameworks are descriptive and they lack predictive power. Moreover, the unobserved homogeneity between observations has been widely overlooked in the crash causal analysis literature. This thesis introduces a novel causal analysis methodology by combining the interpretability and prediction power of the... 

The purpose of the current study is developing an evaluation model for the electrical grid. Resilience is an approach toward risk management against disorders and protecting the system during critical conditions. The importance of resilience assessment, especially in crucial infrastructures, has always been at the center of attention. Nonetheless, previous studies in this field were mostly limited to micro-scales, meaning that only a limited part of the system was evaluated. Therefore, such studies rely on technical data and system details. This issue renders macro-scale assessments challenging. Some of the models, which are based on analytical-statistical methods, examine the systems at... 

Environmental flows supply critical contributions to wetland health and economic development, while wetlands are one of the richest ecosystems due to diversity of the ecological species. The Shadegan Wetland is the located in the south-west of Iran, at the top of the Persian Gulf. It is the largest wetland of the country with an area of almost 400,000 hectares. The wetland plays a significant role, both hydrological and ecological in the natural functioning of the northern coast of the Gulf. Moreover, Shadegan Protected Zone is of high economic and social importance, as its vegetation is assumed the main source of feeding the wildlife species. On the other hand, the wetland has the potential... 

In this thesis the usage of probabilistic reasoning in collaborative filtering is investigated. The problem of predicting users' rating is formulated as a Bayesian decision problem and a generative probabilistic model is used in order to find the optimal decision. Two different probabilistic models are considered: user based model and rating based model. In user based model prediction of ratings is based on structural learning of Bayesian networks. In rating based model, we assume a predefined Bayesian network represents the joint distribution over model variables and rating prediction is carried out using McMc inference method. MovieLens dataset is chosen to evaluate and compare the results... 

Gene regulatory network consists of a set of genes; interacting with each other via their protein products. Such interations lead to the regulation of the genes’ production rate. A breakdown in the regulatory process, may lead to some kinds of diseases. Therefore, understanding the gene regulatory process, is beneficial for both diagnosis and treatment. In this thesis, gene regulatory networks are modeled by the means of dynamic Bayesian networks. We have used sampling based methods, in order to learn the network structure. As these methos have a very high computational cost; we have used a correlation test to prune the search space. This way, an undirected network skeleton is obtained; for... 

Ambient Intelligence (AmI) is an environment in which devices are embedded and connected to each other with a communication network, working in concert to predict users’ wishes according to the context of the environment (devices and people) to help them with their everyday activities. An ambient intelligent environment should be context-aware. One of the most complicated problems in context-aware computations is recognition of the activities in which users of the environment are engaged. These activities could be recognized by means of the information hidden in communication networks of the devices, especially different sensors embedded in the environment to ease up the process. Most of... 

In this thesis, bayesian network has been used in analyzing the failure of a structural component. The design life of a structural component of a system can be limited or unlimited depending on the working conditions considered by the designers. However, usually during the operation of an industrial system or device, a structural component of it fails prematurely, in other words, its actual life is less than the design life. In this case, the failure must be analyzed to find the causes and factors. The method of work is such that first, according to the problem and the type of failure, the required analyzes and studies are considered. Then, a number of samples of the components, whose... 

Semantic video analysis and automatic concept extraction play an important role in several application including designing content-based search engines, video indexing, and video summarization. Since constructing an appropriate summarized video requires extraction of internal video concepts, video summarization is considered as an application of semantic analysis. The proposed system contains three main stages. In the first stage, the shot boundaries are detected, then using the hidden Markov model (HMM), the video is segmented into larger semantic units, called “play-break” sequences. In the next stage, several features are extracted from each of these units. Finally, in the last stage, in...