Physical Sciences and Mathematics Commons^™

Computer Aided Diagnosis System For Breast Cancer Using Deep Learning., Asma Baccouche

Electronic Theses and Dissertations

The recent rise of big data technology surrounding the electronic systems and developed toolkits gave birth to new promises for Artificial Intelligence (AI). With the continuous use of data-centric systems and machines in our lives, such as social media, surveys, emails, reports, etc., there is no doubt that data has gained the center of attention by scientists and motivated them to provide more decision-making and operational support systems across multiple domains. With the recent breakthroughs in artificial intelligence, the use of machine learning and deep learning models have achieved remarkable advances in computer vision, ecommerce, cybersecurity, and healthcare. Particularly, numerous …

Tokamak 3d Heat Load Investigations Using An Integrated Simulation Framework, Thomas Looby

Doctoral Dissertations

Reactor class nuclear fusion tokamaks will be inherently complex. Thousands of interconnected systems that span orders of magnitude in physical scale must operate cohesively for the machine to function. Because these reactor class tokamaks are all in an early design stage, it is difficult to quantify exactly how each subsystem will act within the context of the greater systems. Therefore, to predict the engineering parameters necessary to design the machine, simulation frameworks that can model individual systems as well as the interfaced systems are necessary. This dissertation outlines a novel framework developed to couple otherwise disparate computational domains together into …

Synthetic Aperture Ladar Automatic Target Recognizer Design And Performance Prediction Via Geometric Properties Of Targets, Jacob W. Ross

Browse all Theses and Dissertations

Synthetic Aperture LADAR (SAL) has several phenomenology differences from Synthetic Aperture RADAR (SAR) making it a promising candidate for automatic target recognition (ATR) purposes. The diffuse nature of SAL results in more pixels on target. Optical wavelengths offers centimeter class resolution with an aperture baseline that is 10,000 times smaller than an SAR baseline. While diffuse scattering and optical wavelengths have several advantages, there are also a number of challenges. The diffuse nature of SAL leads to a more pronounced speckle effect than in the SAR case. Optical wavelengths are more susceptible to atmospheric noise, leading to distortions in formed …

A Novel Computer-Aided Diagnosis System For The Early Detection Of Hypertension Based On Cerebrovascular Alterations, Heba Kandil, Ahmed Soliman, Fatma Taher, Mohammed Ghazal, Ashraf Khalil, Guruprasad Giridharan, Robert Keynton, J. Richard Jennings, Ayman El-Baz

All Works

© 2019 The Authors Hypertension is a leading cause of mortality in the USA. While simple tools such as the sphygmomanometer are widely used to diagnose hypertension, they could not predict the disease before its onset. Clinical studies suggest that alterations in the structure of human brains’ cerebrovasculature start to develop years before the onset of hypertension. In this research, we present a novel computer-aided diagnosis (CAD) system for the early detection of hypertension. The proposed CAD system analyzes magnetic resonance angiography (MRA) data of human brains to detect and track the cerebral vascular alterations and this is achieved using …

An Efficient Reliability Simulation Tool For Lifetime-Aware Analog Circuit Synthesis, Engi̇n Afacan

Turkish Journal of Electrical Engineering and Computer Sciences

Time-dependent degradation (aging) has become more severe in modern CMOS technologies. Therefore, it is highly critical to capture the variation effects and design reliable circuits against aging. Simulation of time-dependent variations is quite complicated since the degradation is a function of time, where the step count of simulation directly affects the accuracy and the efficiency of the analysis. Commercial simulator tools use a constant step count during reliability simulations, in which choosing a large step count degrades the efficiency whereas keeping it small may result in accuracy problems. To overcome this bottleneck, a couple of different approaches have been proposed …

A Modified Relay-Race Algorithm For Floorplanning In Pcb And Ic Design, Mert Vatansever, İsmai̇l Fai̇k Başkaya

Turkish Journal of Electrical Engineering and Computer Sciences

Floorplanning is a fundamental design step in the physical design of printed circuit boards (PCBs) and integrated circuits (ICs), as it handles the complexity of layout design. From a computational point of view, the floorplanning problem is an NP hard problem, and the size of the search space grows exponentially with increasing numbers of modules. Thus, the algorithm used is an essential factor for speed and quality of the floorplanning process. Although polynomial-time floorplanning algorithms can be implemented when solution space is limited to slicing floorplans, optimal solutions often exist only in the nonslicing floorplan search space. Various stochastic algorithms …

Framework To Implement Authentication, Authorization And Secure Communications In A Multiuser Collaborative Cax Environment, Francis Mensah

Theses and Dissertations

Computer Aided Design (CAD) applications have historically been based on a single user per application architecture. Although this architecture is still popular to date, it does have several drawbacks. First of all the single user CAD architecture inhibits a concurrent engineering design process where several designers can work on the same model simultaneously. This limitation introduces time inefficiency especially when a project involves geographically dispersed designers. A solution to these drawbacks could be a transition from the traditional single user CAD architecture to a multiuser collaborative architecture. Advances in computer networking technologies, especially relating to the Internet, have provided the …

Interpolating Beach Profile Data Using Linear And Non-Linear Functions, Lance Calloway Croft

USF Tampa Graduate Theses and Dissertations

ABSTRACT

Beach and nearshore surveys are conducted in a variety of ways, the most commonly used being the level-and-transit method; because it is inexpensive, time conducive and highly accurate. Specifically, beach surveys are conducted to better understand cross-shore, long-shore sediment transport processes, as well as to quantify volume changes, which are used to evaluate beach performance. In this study, a section of the beach on Sand Key, FL was surveyed using rod-and-transit. In addition to the commonly used linear data analysis, a non-linear analysis was conducted using NURBS (Non-Uniform Rational B-Splines).

Survey data was collected within a short time window …

Using Pareto Fronts To Evaluate Polyp Detection Algorithms For Ct Colonography, Adam Huang, Jiang Li, Ronald M. Summers, Nicholas Petrick, Amy K. Hara

Electrical & Computer Engineering Faculty Publications

We evaluate and improve an existing curvature-based region growing algorithm for colonic polyp detection for our CT colonography (CTC) computer-aided detection (CAD) system by using Pareto fronts. The performance of a polyp detection algorithm involves two conflicting objectives, minimizing both false negative (FN) and false positive (FP) detection rates. This problem does not produce a single optimal solution but a set of solutions known as a Pareto front. Any solution in a Pareto front can only outperform other solutions in one of the two competing objectives. Using evolutionary algorithms to find the Pareto fronts for multi-objective optimization problems has been …

Computer-Aided Diagnostic Systems For Digital Mammograms, Nicholas Jabari Lee

LSU Master's Theses

A computer-aided diagnostic (CAD) system that uses a unique shape-based classification scheme, the Ellipse-Closed Curve Fitting (ECCF) algorithm, is developed for digital mammogram image analysis. The system is developed to work as a post-processing extension to a previously developed CAD system that locates and segments mass lesions, or tumors, found in digital mammograms into separate images. The ECCF system is implemented in the MATLAB mathematical scripting language and is thus capable of running on multiple platforms. The ECCF algorithm detects edges in tumor images and casts them into closed curve functions. Parameters for an ellipse of best fit for a …

Interactive Dna Sequence And Structure Design For Dna Nanotechnology And Dna Computation, Mingjun Zhang, Chaman Sabharwal, Weimin Tao, Tzyh-Jong Tarn, Ning Xi, Guangyong Li

Computer Science Faculty Research & Creative Works

DNA sequence and structure design are very important for DNA nanotechnology and DNA computation. A computer aided design tool is needed for exploring DNA sequence and structure of interests before experimental synthesis, which is a very time and labor consuming process. In this paper, an interactive DNA sequence and structure design software tool called DNA shop is proposed and implemented.

The Single Row Routing Problem Revisited: A Solution Based On Genetic Algorithms, Albert Y. Zomaya, Roger Karpin, Stephan Olariu

Computer Science Faculty Publications

With the advent of VLSI technology, circuits with more than one million transistors have been integrated onto a single chip. As the complexity of ICs grows, the time and money spent on designing the circuits become more important. A large, often dominant, part of the cost and time required to design an IC is consumed in the routing operation. The routing of carriers, such as in IC chips and printed circuit boards, is a classical problem in Computer Aided Design. With the complexity inherent in VLSI circuits, high performance routers are necessary. In this paper, a crucial step in the …

A Concurrency Control Algorithm For An Open And Safe Nested Transaction Model, Sanjay Kumar Madria

Computer Science Faculty Research & Creative Works

We present a concurrency control algorithm for an open and safe nested transaction model. We use prewrite operations in our model to increase the concurrency. Prewrite operations are modeled as subtransactions in the nested transaction tree. The subtransaction which initiates prewrite subtransactions are modelled as recovery point subtransaction. The recovery point subtransaction can release their locks before its ancestors commit. Thus, our model increases the concurrency in comparison to other nested transaction models. Our model is useful an environment of long-running transactions common in object oriented databases, computer aided design and in the software development process

Time- And Cost-Optimal Parallel Algorithms For The Dominance And Visibility Graphs, D. Bhagavathi, H. Gurla, S. Olariu, J. L. Schwing, J. Zhang

Computer Science Faculty Publications

The compaction step of integrated circuit design motivates associating several kinds of graphs with a collection of non-overlapping rectangles in the plane. These graphs are intended to capture various visibility relations amongst the rectangles in the collection. The contribution of this paper is to propose time- and cost-optimal algorithms to construct two such graphs, namely, the dominance graph (DG, for short) and the visibility graph (VG, for short). Specifically, we show that with a collection of n non-overlapping rectangles as input, both these structures can be constructed in θ (log n) time using n processors in the CREW model.