Sharif Digital Repository

In the last decade, Intrusion Detection Systems has attracted attention due to their importance in network security, but still they've shortcomings. Generating a lot of low level alerts is the main problem. Many of these alerts are actually false positives. One suggested solution is Alert Correlation Analysis. Because of false positives alert correlation techniques are not able to build accurate scenarios, but the accuracy of alerts can be verified with the aid of the information logged in the host systems. In this dissertation after surveying the current alert correlation techniques, a model will be introduced to effectively verify the generated alerts and to apply correlation techniques to... 

Web service plays an important role in software development. Since Web service can be used in small scale and large scale environments, many different entities may participate in each interaction. Regarding situation, a lot of information is available around these entities. This kind of information is called context. In some cases, context information is used to provide outputs which are called context-aware systems.
The main challenging issue in producing a context-aware system is context modeling and sharing. Semantic Web and its ontology languages are the most promising solution to context modeling. In pervasive computing many ontologies are proposed for this purpose, but little... 

Protein multiple sequence alignment is one of important problems in biology which no polynomial time algorithms is known for it yet. Due to importance of this problem, several methods have been developed to find an approximate solution for it. Approximation algorithms, Evolutionary algorithms and Probabilistic methods are some of these methods. According to evolutionary nature of this problem, evolutionary algorithms and specifically genetic algorithms can be a potential good solution method for this problem. In this project we have a survey on using genetic algorithms for this problem and after mentioning benefits and draw backs of existing methods, we develop a method for improving one of... 

Today many applications produce data stream that grow continuously over time. Classification is an important task in mining this data. One of the major challenges in classification of data streams is that the underlying concept of data may change over time; this needs updating the classification model. Many of traditional classification algorithms are adapted for classifying data streams. Evolutionary algorithms are stochastic methods that have been successfully applied to a wide range of optimization problems. Harmony search is a new evolutionary algorithm that convergence to global optimum and can be applied to discrete and continuous data. The evolutionary nature of classifying data... 

Sensor Observation Service (SOS) which is defined by Open Geospatial Consortium (OGC) Sensor Web Enablement group is a Web service specification in order to standardize the way sensors and sensor data are discovered and accessed on the Sensor Web. Multiple instances of this service can be implemented around the world, providing huge amount of data every moment. Each of these services operates in specific domain of knowledge (thematic), spatial and temporal dimensions. One way to reveal the underlying data over all of them is to provide an architecture for data integration to allow the user to query sensor data without the knowledge of the infrastructure components. In this research, a novel... 

Semantic relation extraction is one of the challenging information extraction’s steps. The main task of relation extraction is finding of relationships in text corpus using Machine Learning methods. There are plenty of usage for relation extraction such as providing information for Question Answering systems, protein interaction detection in biomedical corpora and ontology population. There are many research take placed in this area in which relation extraction task is defined as a classification problem and in most of them, this problem is solved by SVM method. Results of recent research imply that current state of relation extraction methods are far from appropriate state that is... 

Recently, data stream has been popular in many contexts like click sequences in web pages, obtained data from sensor networks and satellite data. A data stream is an ordered list of points that should be used once. Clustering of these kinds of data is one of the most difficult issues in data mining. Due to the high amount of data, the traditional clustering algorithms are not suitable for this family of problems. Many data stream clustering algorithms have been proposed in recent years considered the scalability (largeness) of data, but most of them didn’t attend to the following issues. •The quality of clustering can be bad over the time. •Some of the algorithms cannot handle arbitrary... 

Nowadays the importance of ontologies in various domains such as semantic web and NLP is obvious. Manually construction of ontologies is a time-consuming, costly and error prone. The non-manual building of ontologies approaches are divided to the expand approach and the merge approach, each has pros and cons. The expand approach is preferred upon the merge approach for languages with few lingual resources. The most important thing in the expand approach, which is building an ontology from another existing ontology, is making distinction between the different meanings of polysemous words. This activity is called word sense disambiguation(WSD). The existing approaches usually give attention to... 

Gene expression using microarrays technology has special importance in biology studies especially in cancer researches. Using this technology we can assess expression level of several thousand genes simultaneously. One of the major applications of this technology is diseases’ diagnosis which cancers are the most important types of them. The problem in classifying microarray data is its high dimension; although number of samples hardly exceeds a hundred. This severe asymmetry and high dimensionality, results in reduction of accuracy, speed, stability and generalization of classification methods. Thus, one of the most important issues in cancer diagnosis is selection of related and useful... 

An ontology is a formal description of a domain by definition a set of concepts and the relationships between those concepts. Ontologies defined by different applications usually describe their domains in different terminologies,even when they cover the same domain. Thus, we need to resolve the semantic heterogeneities problem and align terms in different ontologies. Ontology alignment plays the central role in these areas to identify correspondences among elements of two or more ontologies. It should be noted that,finding an optimize mapping between two ontologies with respect to search space is an NP-hard [6] problem.
In This thesis we focused on large ontologies and alignment among... 

Due to the application of data streams in various data sources such as Web click streams, Web pages, and data generated by sensors and satellites, data streams have attracted a huge attention recently. A data stream is an ordered sequence of points that must be accessed in order and can be read only once or a small number of times. For mining such data, the ability to process in one pass along with limited memory usage is very important. Data stream clustering also has received a huge attention in recent years and numerous algorithms are developed in this field. None of them has paid attention to the feature selection problem as an effective factor in clustering quality especially when the... 

Ontology alignment is a process for selection of a good mapping between entities of two (or more) ontologies. It can be viewed as a two phase process of: 1) Find the similarity of each pair of entities from two ontologies, and 2) Extraction of an optimal or near optimal mapping. Many researches had been down in the first phase, but researches in the second phase are little. Mapping extraction approaches applied in ontology alignment use similarity matrix to extract mapping, and ontologies have not any role in mapping extraction phase. One of the most important components in ontology is its structure which can help us in alignment extraction.
In this thesis, an approach was proposed that... 

Increasing in social communication via electronic ways has been made social network analysis of these communications more important each day. One of the most important aspects in social network analysis is community detection in such networks. There are many different ways to extract communities from social graph structure which in some of them the content of communication between actors has been noticed in community extraction algorithm. In this thesis after a short survey over advantages and disadvantages of existing methods for community detection, a new method for extracting communities from social networks has been suggested which in addition to streaming property of data it spot the... 

One of the new paradigms in information retrieval is to develop textual Question-Answering systems. Question-Answering (QA) is an advanced IR process at which for a natural language question, the answer is extracted and issued in natural language. The QA systems are divided into two general groups: Open-Domain QA and Restricted-Domain QA.
In this research field, a number of different models and methods are developed in which a document collection is used to retrieve candidate answers and then different methods are deployed to detect and eliminate irrelevant ones from answer set. Most of these methods decide based on expected semantic answer type, which is determined using pre-defined... 

Semi-automated Continuous Speech system deals with collecting corpus speech. It has very different problems in various natural languages because of different types of speech, and collecting speech corpus containing continuous word is very time-and- cost consuming. To overcome this problem, human-based computing techniques are proposed to collect speech corpus. In this thesis, we describe influencing factors in collecting steps of continuous speech and provide a description of human-based techniques to solve problems specially collecting of continuous speech. To collect speech corpus using human-based techniques, a game has been used so that speech corpus of web users are collected during the... 

Trust as a major part of human interactions, lets us take the risk of decision making in uncertain situations. In computer science trust has lots of applications, and is stated as the highest level in the Semantic Web Cake and one of the seven points of W3C consortium. Trust can be embedded into several different networks and Social networks. Regarding to the fact that rust is transitive and value of trust can be compound and different paths in trust graph has different properties; a trust framework can be formed to embed trust into different networks. This framework should define trust and distrust, certainty and uncertainty, context and trust propagation. Architecture of this general... 

We propose a range-free localization framework in which a network of randomly deployed acoustic sensors can passively use natural acoustic phenomena within its environment to localize itself. We introduce a novel approach for registration of sensors observations which takes advantage of a clustering technique on triplets of associated observations. A Bayesian filtering method is employed to incrementally improve system state estimation as more observations become available. To the best of our knowledge this is the first work done on range-free passive acoustic localization. Furthermore, we have proposed a simple but effective and efficient acoustic detection method which can be used to... 

Nowadays, clustering is one of the most common data mining tasks used for data categorization upon their similarities and analysis of these data groups in both industry and academia is of interest. Clustering does not need any supervision. The theme of this thesis is using some prior knowledge to improve clustering algorithms. The prior knowledge is in the form of some constraints determined by supervision to allowing preventing some combination data to be in one cluster or allocate some data in the same cluster. Here, prior knowledge in the form of constraints is used to modify a heuristic optimization algorithm (harmony search) and a novel "semi-supervised harmony clustering" is proposed.... 

With the explosive increase in the amount of information in the today's world, the need for high-speed data transmission is felt more and more. According to Cisco's forecast, the traffic explosion in real wireless networks will continue. According to the forecast, the volume of data traffic on wireless networks will be about one hundred and ninety exabytes in the next two years, and in the next four years will reach over five hundred exabytes per year. On the other hand, the advent of new technologies, such as the Internet of Things and the Tactile Internet, pushes us to make it possible to transmit with very low delays and high reliability in future generation networks. In this project, we...