To manage large image databases, Content-Based Image Retrieval (CBIR) emerged as a new research subject. CBIR involves the development of automated methods to use visual features in searching and retrieving. Unfortunately, the performance of most...
Images, Photographic--Databases; Image processing--Digital techniques; Data mining; Cluster analysis
The performance of content-based image retrieval systems has proved to be inherently constrained by the used low level features, and cannot give satisfactory results when the user's high level concepts cannot be expressed by low level features. In...
Computer music; Sound--Recording and reproducing--Digital techniques; Music and technology; Computer sound processing
This thesis proposes a concept called low-time-resolution (LTR) structure in music, and investigates its potential significance and application in music-related computing tasks.
The contributions of the thesis are manifold. First, it proposes a...
In this dissertation, we study the performance evaluation of two automated warehouse material handling (MH) technologies - automated storage/retrieval system (AS/RS) and autonomous vehicle storage/retrieval system (AVS/RS). AS/RS is a traditional...
Parking garages--Automation; Parking garages--Design and construction
Automated vehicle storage/retrieval system (AVS/RS) technology is relatively new. It has been applied successfully in several European facilities in 1990s. AVS/RS is a flexible system that is a viable alternative to automated storage/retrieval...
Digital images have primarily been viewed using desktop applications. These types of programs attempt to load all of an image's graphical data into memory in order to display the image in its entirety. The method is effective for images that are...
The advent of larger storage spaces, affordable digital capturing devices, and an ever growing online community dedicated to sharing images has created a great need for efficient analysis methods. In fact, analyzing images for the purpose of...
Recently, social multimedia-sharing websites, which allow users to upload, annotate, and share online photo or video collections, have become increasingly popular. The user tags or annotations constitute the new multimedia "meta-data". We...
This dissertation addresses two different problems: 1) coronal loop detection from solar images: and 2) salient contour group extraction from cluttered images. In the first part, we propose two different solutions to the coronal loop detection...
Sensory neurons; Spinal cord--Wounds and injuries--Research; Pain--Research
This study examined the effects of tissue damage and inflammation on the expression in sensory neurons of P2X3, a gene that has a role in nociception and sensing bladder distension, which is regulated by nerve injury. Tissue damage induces...
Medical records--Data processing; Data mining; Databases--Design
A major problem with integrating information from multiple databases is that the same data objects can exist in inconsistent data formats across databases and a variety of attribute variations, making it difficult to identify matching objects using...
Swarm Intelligence (SI) techniques were inspired by bee swarms, ant colonies, and most
recently, bird flocks. Flock-based Swarm Intelligence (FSI) has several unique features, namely
decentralized control, collaborative learning, high exploration...
Web search engines; Automatic abstracting; Graph theory--Data processing
After a user types in a search query on a major search engine, they are presented with a number of search results. Each search result is made up of a title, brief text summary and a URL. It is then the user's job to select documents for...
Optimizing queries in a distributed database is quite difficult. This work proposes defining new generalized quantifiers which operate on sets rather than tuples. These quantifiers would allow for easier optimization in a horizontally distributed...
Pattern recognition systems; Cluster analysis; Data mining
Despite the large number of existing clustering methods, clustering remains a challenging task especially when the structure of the data does not correspond to easily separable categories, and when clusters vary in size, density and shape. Existing...
Computer-assisted instruction; Three-dimensional imaging; Neuroanatomy--Study and teaching (Higher)
Visualizations in the form of computer-based learning environments are highly
encouraged in science education, especially for teaching spatial material. Some spatial
material, such as sectional neuroanatomy, is very challenging to learn. It...
Spinal cord injury (SCI) can be divided into two distinct stages, an initial mechanical impact and a later "secondary injury" resulting from a cascade of cytokines triggering a spreading demyelination and apoptosis of neurons and glia...
Due to the complex nature of interactions at the genomic level as well as the large number of proteins present in an organism, understanding the functions of various genes that are expressed is essential. Creating an analysis pipeline for Expressed...
Electronic surveillance; Computer networks--Design and construction; Computer crimes
Peer-to-peer networks have been growing in popularity over the past decade. There have been many new innovations that greatly improve access to a wide variety of content. This expanded capability combined with a strong sense of anonymity has given...
Data mining; Lungs--Cancer; Outcome assessment (Medical care)
Lung cancer is the leading cause of cancer death in the United States and the world, with more than 1.3 million deaths worldwide per year. However, because of a lack of effective tools to diagnose Lung Cancer, more than half of all cases are...
