Sharif Digital Repository

Trying both to understand the brain and to emulate some of its strengths has been one of the greatest human desires since ancient times. One of these amazing abilities is recognizing via vision. As a result, image recognition has been turned into one of the most attractive areas of research in Computer Vision field since recently. The challenging problem begins to rise where occlusion, scale, rotation and various light conditions contribute and manipulate the paradigm of image recognition. Although recognitions with these challenging problems are some of the capabilities that the brain has, but these are not all. One of the remarkable abilities of the brain is to recognize concepts through... 

Abnormality detection and prognosis of epileptic patients with artificial intelligence and machine learning techniques is still in its early experimental stages. Surgical candidacy determination for epilepsy depends on the clinical actions which involve an intracranial electrode implantation followed by prolonged electrographic monitoring (EEG phase II) .This invasive test is very costly, painful and time consuming. Here the goal is integration of the two following paradigms: 1-Non invasive multimodality data of epilepsy. 2- Artificial intelligence and machine learning techniques. We have used human brain multi-modality database system that includes patient’s demographics, clinical and EEG... 

Learning disability (LD) is a neurological condition that interferes with an individual’s ability to store, process, or produce information. There are different types of learning disabilities affecting reading, writing, speaking, spelling, etc. Based on a study conducted by National Center for Learning Disabilities, 2.4 million American public school students are diagnosed with learning disability. They attend school in order to learn and be successful while they do not know their learning process is different from their peers. LD diagnosis in children is especially important as such cases must be identified early enough in order to provide them with proper education.This project targets LD... 

Content-based image retrieval (CBIR) is becoming an important field with the advance of multimedia and imaging technology everincreasingly. It makes use of image features, such as color, shape and texture, to index images with minimal human intervention. Among many retrieval features associated with CBIR, texture retrieval is one of the most powerful. Content-based image retrieval can also be utilized to locate medical images in large databases. In this research, we introduce a content-based approach to medical image retrieval. A case study, which describes the methodology of a CBIR system for retrieving digital human brain MRI database based on textural features retrieval, is then... 

Today, with the development of technology, cyberattacks are on the rise. Personal and corporate computer systems can be exposed to various threats and dangers of hackers and malware, including information theft, forgery, and denial of service, which can cause great material and moral damage to individuals and organizations. So, it is necessary to take security measures in this regard. Many security mechanisms are available to prevent security vulnerabilities against various threats. In this study, first, after carefully studying network attacks, we identify the criteria for identifying attacks that can be executed in network traffic and explain how to calculate them. The current research... 

Classification of Traffic Internet obtained early interest in the computer science community. Various methods have been presented for classifying the traffic of Internet to manage both security and Quality of Service (QoS). Nonetheless, traditional methods of classification including scheme of Transmission Control Protocol/Internet Protocol (TCP/IP) have not been accepted because of their complicated management. Classification method of network through learning algorithms of machine is the most popular classification method of traffic at this time. ELM was proposed as a modern algorithm of learning for the Single-hidden Layer Feed Forward Neural Networks (SLFNs). Meanwhile, learning process... 

Nowadays, the world is based on the interaction between individuals, groups and different systems. The actual networks that have a complex structure and behavior are called complex networks. Complex networks are one of the new knowledge that studies the connections. The complex systems represented as graph, with non-trivial topological features—features that do not occur in simple networks.With the vast development of computer networks, complex networks appear in different categories such as social networks, citation networks, collaboration networks and communication networks. Data mining is the process of exploring hidden knowledge in data bases and it has applications in complex networks.... 

In this thesis we propose a two-layer hybrid fuzzy genetic algorithm for designing anomaly based an Intrusion Detection System. Our proposed algorithm is based on two basic Genetic Based Machine Learning Styles (i.e. Pittsburgh and Michigan). The Algorithm supports multiple attack classifications; it means that the algorithm is able to detect five classes of network patterns consisting of Denial of Service, Remote to Local, User to Root, Probing and Normal class.
Our proposed algorithm has two approaches. In the first approach we choose Pittsburgh style as the base of the algorithm that provides a global search. Then combine it with Michigan style to support local search. In this... 

Web services are some kind of software applications which are available on the Web. Growing the popularity of Web services, led to increasing number of providers and as a result a great deal of Web services. This huge number of services made the searching and discovery tasks hard and effort-full jobs. In order to have a better discovery it is better to first classify Web services into some categories and then search in the relevant class. Although this classification can be done based on matching key words through the service registration information, such syntax-level service facilities can’t achieve the satisfaction results both in the precision and the recall sides. Human experience shows... 

Structural Health Monitoring (SHM) of civil infrastructures is of paramount importance in ensuring the safety and reliability of these structures. SHM involves the use of sensors and data analysis techniques to continuously monitor the structural condition of infrastructure, detect damage or degradation, and provide insights for maintenance and repair. Concrete cracks are one of the most common and critical types of damage in civil infrastructure, which can compromise the structural integrity and safety of the infrastructure if left undetected and untreated. Therefore, the development of effective and efficient crack detection techniques using computer vision and machine learning can... 

I investigate methods of integrating prior hierarchical structure into hierarchical portfolio optimization methods. My contributions to the literature are forming a prior hierarchical structure based on investors' priorities and generating a unique representative distance matrix, which can be used as an input to other portfolio optimization methods too. In addition, I use SIC and GICs industry classifications as priory information for S&P500 companies and use them as a complementary input to the Hierarchical Risk Parity model and Hierarchical Equal Risk Contribution and compare the resultant portfolios' performance with (López de Prado, 2019)’s method of integrating prior information and... 

One way for businesses to grow and compete, in any age (especially the digital age), is to create a Brand Relevance through creating or finding, and then owning new categories or subcategories. In this way, instead of beating competitors; they become irrelevant by enticing customers to buy a new category or subcategory for which other alternative brands are not considered relevant. Firms traditionally rely on interviews and focus groups to identify these subcategories and customer needs. Nowadays, with the growth of social media, user-generated content (UGC) is also a good alternative source. However, Due to the large size of UGC and the non-informative or repetitive data it contains,... 

Exchange-rate has always been one of the critical macroeconomic factors influencing Iran’s economy. As a representative of the whole economy, the stock market is also affected by exchange rate fluctuations. However, the direction and the delay of this impact is not similar for all firms. This study aims to find the time and direction of the reactions to dollar fluctuations in the two most recent jumps, during 1390 and 1397, for all firms listed on Tehran Securities Exchange. It also seeks to determine why among stocks with a positive reaction, some react sooner, and some react later, based on their specific characteristics. Using a distributed lag model, we found that about one-half of the... 

Institution covers wide range of rules, laws and policies. Two bodies of literature around institutions and resource curse have evaluated institutional quality by limited indices. In addition, although different institutions have different effects on economy, the literature hasn’t classified different kinds of institution. Furthermore, resources can affect institutions in different ways. This research has been surveyed the impact of resource dependence on institutional quality. Institutions that regulate relation between governors and citizens were named governmental institutions. Institutions that regulate the relation of citizens were named nongovernmental institutions. Governmental... 

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... 

Question answering systems are systems which get a question in natural language as input and present an explicit, appropriate answer to the question. One of the major components of automatic question answering systems is question processing component in which the input question is analyzed. The main goal of question processing phase is to determine the answer type through question classification. Rule-based, machine learning-based and hybrid approaches have been used in order to develop question classifiers among which machine learning-based ones have outperformed the others. This study’s main goal is to develop a question classifier for Persian open domain question answering systems.... 

Spoken Language Understanding (SLU) is aimed at extracting meaning from natural spoken language. Meaning extraction ranges from "extracting specific phrases" to "extracting users' intentions from their speech" and goes as far as "extracting the entities and details of their intentions". Extracting the exact intended meaning of the user is a sophisticated process. In this research, considering the lack of standard data in Persian, an SLU system for this language has been implemented using Markov Logic Networks (MLNs), in order to reduce the need for extra datasets. MLNs combine the explanatory power and orderliness of First-Order Logic with the uncertainty of probabilities. Therefore, these... 

Text classification accompanied by high precision has become a challenging issue in computational linguistics and natural language processing science. Proper data set accessibility, utilizing the best method and prominent linguistics features has been always regarded as the basic concern of this process. The following study relying on Bijan Khan Corpus is tried to represent keywords vectors of different documents using tf_idf. These vectors are regarded as an input for latent topic models algorithms including probabilistic latent semantic analysis. The output of this algorithm will be the documents feature vectors which will be later used in order to train different classifiers like K... 

The main focus of this research is to resolve the semantic ambiguity in Persian. In this study, a semi-supervised machine learning method is proposed to choose the most proper meaning of a target word in the context. Several statistical methods are compared, and the most accurate one is chosen for developing a sense tagger. An initial seed data is built by searching collocation lists for each sense. After developing the sense tagger and initial seed set, a bootstrapping method is used to sense tag all occurences of a target word in corpus with 90% accuracy  

Few-shot learning methods have achieved notable performance in recent years. However, fewshot learning in large-scale settings with hundreds of classes is still challenging. In this dissertation, we tackle the problems of large-scale few-shot learning by taking advantage of pre-trained foundation models. We recast the original problem in two levels with different granularity. At the coarse-grained level, we introduce a novel object recognition approach with robustness to sub-population shifts. At the fine-grained level, generative experts are designed for few-shot learning, specialized for different superclasses. A Bayesian schema is considered to combine coarse-grained information with...