Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Bayesian statistical decision theory; Computer algorithms; Data mining; Machine learning (1)
- Biometric identification; Hidden Markov models; Pattern recognition systems; Signal processing--Digital techniques (1)
- Computer recognition (1)
- Dirty bomb detection (1)
- Flying objects (1)
-
- Megavoltage X-ray technology (1)
- Multi-Processor System-on-Chip (1)
- Network-on-Chips (NoCs) (1)
- Nuclear material detection (1)
- Processor architectures (1)
- Radioactive materials (1)
- Real time (1)
- Remote cargo inspection systems (1)
- Three dimensional object recognition (1)
- Topologies (1)
- Tracking objects (1)
- Transistors (1)
- Two dimensional images (1)
Articles 1 - 5 of 5
Full-Text Articles in Computer Engineering
Text Categorization Based On Apriori Algorithm's Frequent Itemsets, Prathima Madadi
Text Categorization Based On Apriori Algorithm's Frequent Itemsets, Prathima Madadi
UNLV Theses, Dissertations, Professional Papers, and Capstones
Automatic Text categorization is the task of assigning an electronic document to one or more categories, based on its contents. There are many known techniques to efficiently solve categorization problems. Typically these techniques fall into two distinct methodologies which are either logic based or probabilistic. In recent years, many researchers have tried approaches which area hybrid of these two methodologies.
In this thesis, we deal with document categorization using Apriori Algorithm. The Apriori algorithm was initially developed for data mining and basket analysis applications in the relational databases. Although the technique is logic based, it also relies on the statistical …
Human Identification Using Pyroelectric Infrared Sensors, Aron E. Suppes
Human Identification Using Pyroelectric Infrared Sensors, Aron E. Suppes
UNLV Theses, Dissertations, Professional Papers, and Capstones
The objective of this thesis is to discuss the viability of using pyroelectric infrared (PIR) sensors as a biometric system for human identification.
The human body emits infrared radiation, the distribution of which varies throughout the body, and depends upon the shape and composition of the particular body part. A PIR sensor utilizing a Fresnel lens will respond to this infrared radiation. When a human walks, the motion of the body's individual components form a characteristic gait that is likely to affect a PIR sensor field in a unique way.
A statistical model, such as a Hidden Markov Model, could …
Extents And Limits Of Radioscopic Detection Of Nuclear Materials In Cargo Containers With Two Megavoltage Energy Barriers, Vijay Kumar Mandava
Extents And Limits Of Radioscopic Detection Of Nuclear Materials In Cargo Containers With Two Megavoltage Energy Barriers, Vijay Kumar Mandava
UNLV Theses, Dissertations, Professional Papers, and Capstones
The megavoltage X-ray technology is utilized for detecting nuclear materials in cargo containers. Interlaced response is obtained by switching rapidly between 6MeV and 9 MeV beams. It is known that the ratio of penetration levels of cargo contents taken at nominal and dual energies provides the information about atomic numbers of materials, and thus can also indicate the threat group. However, the identification is not straightforward if combinations of materials are present. The latter can lead to misdetections. It is imperative to know what are the extent and the limit of the currently employed technology, and how to carry out …
On-Board Three-Dimensional Object Tracking: Software And Hardware Solutions, Ajay Kumar Mandava
On-Board Three-Dimensional Object Tracking: Software And Hardware Solutions, Ajay Kumar Mandava
UNLV Theses, Dissertations, Professional Papers, and Capstones
We describe a real time system for recognition and tracking 3D objects such as UAVs, airplanes, fighters with the optical sensor. Given a 2D image, the system has to perform background subtraction, recognize relative rotation, scale and translation of the object to sustain a prescribed topology of the fleet. In the thesis a comparative study of different algorithms and performance evaluation is carried out based on time and accuracy constraints. For background subtraction task we evaluate frame differencing, approximate median filter, mixture of Gaussians and propose classification based on neural network methods. For object detection we analyze the performance of …
Performance Evaluation Of Network-On-Chip Interconnect Architectures, Xinan Zhou
Performance Evaluation Of Network-On-Chip Interconnect Architectures, Xinan Zhou
UNLV Theses, Dissertations, Professional Papers, and Capstones
With a communication design style, Network-on-Chips (NoCs) have been proposed as a new Multi-Processor System-on-Chip paradigm. Simulation and functional validation are essential to assess the correctness and performance of the NoC design. In this thesis, a cycle-accurate NoC simulation system in Verilog HDL is developed to evaluate the performance of various NoC architectures. First, a library of NoC components is developed based on an existing design. Each NoC architecture to be evaluated is constructed from the library according to the topology description which specifies the network topology, network size, and routing algorithm. The network performance of four NoC architectures under …