This study presents a web-based database application for storing experimental data and related documents at a single location and sharing them among researchers and engineers from all over the world. The database application, accessible from a website was developed for experimental structural engineering researches, and initially tested at Structural and Earthquake Engineering Laboratory of Civil Engineering Department, METU. The application is composed of two parts. The first part is the database that stores information about projects, specimens, experiments, experimental data, documentation, site members, and member groups at the server side. The second part is the website that provides a functional user interface for easy use of application and providing accessibility from everywhere via internet. After the development of the database and the website, these two parts were attached to each other and application functionalities that enabled users to create, modify, search, and delete projects, specimens and experiments / allowed users to upload/download documentation and experimental data / provided abilities to users to plot test data and share their opinions were ensured. ASP.NET framework and C# programming language was utilized for the web application development. Functionality and usability of the database application was then tested by uploading and sharing various experimental results.

As the Internet became widespread all over the world, people started to share great amount of data on the web and almost every people joined different data networks in order to have a quick access to data shared among people and survive against the information overload on the web. Recommender systems are created to provide users more personalized information services and to make data available for people without an extra effort. Most of these systems aim to get or learn user preferences, explicitly or implicitly depending to the system, and guess &ldquo / preferable data&rdquo / that has not already been consumed by the user. Traditional approaches use user/item similarity or item content information to filter items for the active user / however most of the recent approaches also consider the trustworthiness of users. By using trustworthiness, only reliable users according to the target user opinion will be considered during information retrieval. Within this thesis work, a content boosted method of using trust data in recommender systems is proposed. It is aimed to be shown that people who trust the active user and the people, whom the active user trusts, also have correlated opinions with the active user. This results the fact that the rated items by these people can also be used while offering new items to users. For this research, www.epinions.com site is crawled, in order to access user trust relationships, product content information and review ratings which are ratings given by users to product reviews that are written by other users.

In this thesis, some enhancements to an existing automatic web service composition and execution system are described which provide a practical significance to the existing framework with scalability, i.e. the ability to operate on large service sets in reasonable time. In addition, the service storage mechanism utilized in the enhanced system presents an effective method to maintain large service sets. The described enhanced system provides scalability by implementing a pre-processing phase that extracts service chains and problem initial and goal state dependencies from service descriptions. The service storage mechanism is used to store this extracted information and descriptions of available services. The extracted information is used in a forward chaining algorithm which selects the potentially useful services for a given composition problem and eliminates the irrelevant ones according to the given problem initial and goal states. Only the selected services are used during the AI planning and execution phases which generate the composition and execute the services respectively.

Modeling spatiotemporal data, in particular fuzzy and complex spatial objects representing geographic entities and relations, is a topic of great importance in geographic information systems, computer vision, environmental data management systems, etc. Because of complex requirements, it is challenging to design a database for spatiotemporal data and its features and to effectively query them. This thesis presents a new approach for modeling, indexing and querying the spatiotemporal data of fuzzy spatial and complex objects and/or spatial relations. As a case study, we model and implement a meteorological application in an intelligent database architecture, which combines an object-oriented database with a knowledge base.

Traditional hybrid recommender systems typically follow a manually created fixed prediction strategy in their decision making process. Experts usually design these static strategies as fixed combinations of different techniques. However, people&#039 / s tastes and desires are temporary and they gradually evolve. Moreover, each domain has unique characteristics, trends and unique user interests. Recent research has mostly focused on static hybridization schemes which do not change at runtime. In this thesis work, we describe an adaptive hybrid recommender system, called AdaRec that modifies its attached prediction strategy at runtime according to the performance of prediction techniques (user feedbacks). Our approach to this problem is to use adaptive prediction strategies. Experiment results with datasets show that our system outperforms naive hybrid recommender.

Serving geospatial data collected from remote sensing methods (satellite images, areal photos, etc.) have become crutial in many geographic information system (GIS) applications such as disaster management, municipality applications, climatology, environmental observations, military applications, etc. Even in today&rsquo / s highly developed information systems, geospatial image data requies huge amount of physical storage spaces and such characteristics of geospatial image data make its usage limited in above mentioned applications. For this reason, web-based GIS applications can benefit from geospatial image streaming through web-based architectures. Progressive transmission of geospatial image and map data on web-based architectures is implemented with the developed image streaming methodology. The software developed allows user interaction in such a way that the users will visualize the images according to their level of detail. In this way geospatial data is served to the users in an efficient way. The main methods used to transmit geospatial images are serving tiled image pyramids and serving wavelet based compressed bitstreams. Generally, in GIS applications, tiled image pyramids that contain copies of raster datasets at different resolutions are used rather than differences between resolutions. Thus, redundant data is transmitted from GIS server with different resolutions of a region while using tiled image pyramids. Wavelet based methods decreases redundancy. On the other hand methods that use wavelet compressed bitsreams requires to transform the whole dataset before the transmission. A hybrid streaming methodology is developed to decrease the redundancy of tiled image pyramids integrated with wavelets which does not require transforming and encoding whole dataset. Tile parts&rsquo / coefficients produced with the methodlogy are encoded with JPEG 2000, which is an efficient technology to compress images at wavelet domain.

This thesis proposes the design, development and evaluation of a hybrid video recommendation system. The proposed hybrid video recommendation system is based on a graph algorithm called Adsorption. Adsorption is a collaborative filtering algorithm in which relations between users are used to make recommendations. Adsorption is used to generate the base recommendation list. In order to overcome the problems that occur in pure collaborative system, content based filtering is injected. Content based filtering uses the idea of suggesting similar items that matches user preferences. In order to use content based filtering, first, the base recommendation list is updated by removing weak recommendations. Following this, item similarities of the remaining list are calculated and new items are inserted to form the final recommendations. Thus, collaborative recommendations are empowered considering item similarities. Therefore, the developed hybrid system combines both collaborative and content based approaches to produce more effective suggestions.

In this thesis, we developed SemKPSearch which is a tool for searching documents by the keyphrases that are semantically related with the given query phrase. By relating the keyphrases semantically, we aim to provide users an extended search and browsing capability over a document collection and to increase the number of related results returned for a keyphrase query. Keyphrases provide a brief summary of the content of documents. They can be either author assigned or automatically extracted from the documents. SemKPSearch uses SemKPIndexes which are generated with the keyphrases of the documents. SemKPIndex is a keyphrase index extended with a keyphrase to keyphrase index which stores the semantic relation score between the keyphrases in the document collection. Semantic relation score between keyphrases is calculated using a metric which considers the similarity score between words of the keyphrases. The semantic similarity score between two words is determined with the help of two word-to-word semantic similarity metrics, namely the metric of Wu&amp / Palmer and the metric of Li et al. SemKPSearch is evaluated by the human evaluators which are all computer engineers. For the evaluation, in addition to the author assigned keyphrases, the keyphrases automatically extracted by employing the state-of-the-art algorithm KEA are used to create keyphrase indexes.

Generating in-between images from multiple views of a scene is a crucial task for both computer vision and computer graphics fields. Photorealistic rendering, 3DTV and robot navigation are some of many applications which benefit from arbitrary view synthesis, if it is achieved in real-time. Most modern commodity computer architectures include programmable processing chips, called Graphics Processing Units (GPU), which are specialized in rendering computer generated images. These devices excel in achieving high computation power by processing arrays of data in parallel, which make them ideal for real-time computer vision applications. This thesis focuses on an arbitrary view rendering algorithm by using two high resolution color cameras along with a single low resolution time-of-flight depth camera and matching the programming paradigms of the GPUs to achieve real-time processing rates. Proposed method is divided into two stages. Depth estimation through fusion of stereo vision and time-of-flight measurements forms the data acquisition stage and second stage is intermediate view rendering from 3D representations of scenes. Ideas presented are examined in a common experimental framework and practical results attained are put forward. Based on the experimental results, it could be concluded that it is possible to realize content production and display stages of a free-viewpoint system in real-time by using only low cost commodity computing devices.

This thesis presents a robust face recognition method and a combination of methods for gender identification and age group classification for semantic annotation of videos. Local binary pattern histogram which has 256 bins and pixel intensity differences are used as extracted facial features for gender classification. DCT Mod2 features and edge detection results around facial landmarks are used as extracted facial features for age group classification. In gender classification module, a Random Trees classifier is trained with LBP features and an adaboost classifier is trained with pixel intensity differences. DCT Mod2 features are used for training of a Random Trees classifier and LBP features around facial landmark points are used for training another Random Trees classifier in age group classification module. DCT Mod2 features of the detected faces morped by two dimensional face morphing method based on Active Appearance Model and Barycentric Coordinates are used as the inputs of the nearest neighbor classifier with weights obtained from the trained Random Forest classifier in face identification module. Different feature extraction methods are tried and compared and the best achievements in the face recognition module to be used in the method chosen. We compared our classification results with some successful earlier works results in our experiments performed with same datasets and got satisfactory results.