Engineering Commons^™

Real-Time Supervised Detection Of Pink Areas In Dermoscopic Images Of Melanoma: Importance Of Color Shades, Texture And Location, Ravneet Kaur, P. P. Albano, Justin G. Cole, Jason R. Hagerty, Robert W. Leander, Randy Hays Moss, William V. Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

Background/Purpose: Early detection of malignant melanoma is an important public health challenge. In the USA, dermatologists are seeing more melanomas at an early stage, before classic melanoma features have become apparent. Pink color is a feature of these early melanomas. If rapid and accurate automatic detection of pink color in these melanomas could be accomplished, there could be significant public health benefits.

Methods: Detection of three shades of pink (light pink, dark pink, and orange pink) was accomplished using color analysis techniques in five color planes (red, green, blue, hue, and saturation). Color shade analysis was performed using a logistic …

Vehicle Routing Problem With Stochastic Demand (Vrpsd): Optimisation By Neighbourhood Search Embedded Adaptive Ant Algorithm (Ns-Aaa), M Nagalakshmi, Mukul Tripathi, Nagesh Shukla, Manoj Tiwari

Nagesh Shukla

Taking into account the real world applications, this paper considers a vehicle routing problem with stochastic demand (VRPSD) in which the customer demand has been modelled as a stochastic variable. Considering the computational complexity of the problem and to enhance the algorithm performance, a neighbourhood search embedded adaptive ant algorithm (ns-AAA) is proposed as an improvement to the existing ant colony optimisation. The proposed metaheuristic adapts itself to maintain an adequate balance between exploitation and exploration throughout the run of the algorithm. The performance of the proposed methodology is benchmarked against a set of test instances that were generated using …

Genetic-Algorithms-Based Algorithm Portfolio For Inventory Routing Problem With Stochastic Demand, Nagesh Shukla, M Tiwari, Darek Ceglarek

Nagesh Shukla

This paper presents an algorithm portfolio methodology based on evolutionary algorithms to solve complex dynamic optimization problems. These problems are known to have computationally complex objective functions which make their solutions to be computationally hard to find, when problem instances of large dimensions are considered. This is due to the inability of the algorithms to provide optimal or near optimal solution within allocated time interval. Therefore, this paper employs a bundle of evolutionary algorithms (EAs) tied together with several processors, known as algorithm portfolio, to solve a complex optimization problem such as inventory routing problem (IRP) with stochastic demands. EAs …

The Programmatic Generation Of Discrete-Event Simulation Models From Production Tracking Data, Christopher Rand Smith

Theses and Dissertations

Discrete-event simulation can be a useful tool in analyzing complex system dynamics in various industries. However, it is difficult for entry-level users of discrete-event simulation software to both collect the appropriate data to create a model and to actually generate the base-case simulation model. These difficulties decrease the usefulness of simulation software and limit its application in areas in which it could be potentially useful. This research proposes and evaluates a data collection and analysis methodology that would allow for the programmatic generation of simulation models using production tracking data. It uses data collected from a GPS device that follows …

Affect Classification Using Genetic-Optimized Ensembles Of Fuzzy Artmaps

Faculty of Engineering University of Malaya

Training neural networks in distinguishing different emotions from physiological signals frequently involves fuzzy definitions of each affective state. In addition, manual design of classification tasks often uses sub-optimum classifier parameter settings, leading to average classification performance. In this study, an attempt to create a framework for multi-layered optimization of an ensemble of classifiers to maximize the system's ability to learn and classify affect, and to minimize human involvement in setting optimum parameters for the classification system is proposed. Using fuzzy adaptive resonance theory mapping (ARTMAP) as the classifier template, genetic algorithms (GAs) were employed to perform exhaustive search for the …

An Improved Particle Swarm Optimization Based Maximum Power Point Tracking Strategy With Variable Sampling Time

Faculty of Engineering University of Malaya

This paper presents an improved maximum power point tracking (MPPT) strategy for photovoltaic (PV) systems based on particle swarm optimization (PSO). The capability of the PSO algorithm to cope with partially shaded conditions (PSCs) is the primary motivation of this research. Unlike conventional PSO-based MPPT systems, a variable sampling time strategy (VSTS) based on the investigation of the dynamic behavior of converter current is deployed to increase system tracking time. The performance of the proposed system is evaluated using MATLAB simulation and experimentation, in which a digital signal controller is used to implement the proposed algorithm on a real boost …

Desarrollo E Implementación De Un Algoritmo Para Localización Relativa De Sags De Tensión En Un Sistema De Distribución, Cristian Camilo Díaz Piñeros, Angie Lorena Rivera Gómez

Ingeniería Eléctrica

Este proyecto tiene como propósito el desarrollo e implementación de un algoritmo en Matlab que permita determinar, en un sistema de distribución, la zona donde hay presencia de fuentes de sags. Para obtener este algoritmo, se utilizó el sistema de distribución de prueba IEEE de 37 nodos, modelado en el software ATP, además se simularon fallas de diferente naturaleza en distintos puntos del sistema. A partir de la información obtenida en las simulaciones, se realizó el tratamiento de datos para proceder a desarrollar el algoritmo en Matlab, el cual tuvo en cuenta elementos como la topología del sistema y la …

A Distributed Broadcast Algorithm For Duty-Cycled Networks With Physical Interference Model, Dianbo Zhao, Kwan-Wu Chin

Faculty of Engineering and Information Sciences - Papers: Part A

Broadcast is a fundamental operation in multi-hop wireless networks. Given a source node with a message to broadcast, the objective is to propagate the message to all nodes in an interferencefree manner while incurring minimum latency. This problem, called Minimum-Latency Broadcast Scheduling (MLBS), has been studied extensively in wireless networks whereby nodes remain on all times and has been shown to be NP-hard. However, only a few studies have addressed this problem in the context of duty-cycled wireless networks, which unfortunately, remains NP-hard. In these networks, nodes do not wake up simultaneously, and hence, not all neighbors of a transmitting …

Evaluating Distributed Generations In Utility Operation And Planning Issues Using A Novel Fusion Pso-Sfla Algorithm, Esmaeil Mahboubi-Moghaddam, Jamshid Aghaei, Kashem M. Muttaqi, Behrouz Zoghdar-Moghadam-Shahrekohne, Mohammad Rasoul Narimani

Faculty of Engineering and Information Sciences - Papers: Part A

Increasing demand of electrical energy has leaded to utilization of more and more Distributed generation (DG) sources in distribution systems. Since the locations and capacities of the DG sources connected to the distribution system profoundly impact on reducing system loss and improving system reliability, so placement and sizing indication of DGs is the most substantial process in distribution systems. By adding the reliability objective to this problem, it becomes more complicated than before and it needs to be solved with an accurate algorithm. To this reason, to solve the proposed problem a new approach based on the mixture of two …

Application Of The Largest Lyapunov Exponent Algorithm For Feature Extraction In Low Speed Slew Bearing Condition Monitoring, Wahyu Caesarendra, Prabuono Buyung Kosasih, A Kiet Tieu, Craig A. S Moodie

Faculty of Engineering and Information Sciences - Papers: Part A

This paper presents a new application of the largest Lyapunov exponent (LLE) algorithm for feature extraction method in low speed slew bearing condition monitoring. The LLE algorithm is employed to measure the degree of non-linearity of the vibration signal which is not easily monitored by existing methods. The method is able to detect changes in the condition of the bearing and demonstrates better tracking of the progressive deterioration of the bearing during the 139 measurement days than comparable methods such as the time domain feature methods based on root mean square (RMS), skewness and kurtosis extraction from the raw vibration …

A Distributed Diffusion-Driven Algorithm For Load Balancing In An Electrical Power Grid, Isaac Abhilash Ayyala

LSU Master's Theses

In this thesis we propose a distributed algorithm, based on diffusion, to balance loads on an electrical power grid, while maintaining stable operation (system’s ability to maintain bus voltages within preset bounds). This algorithm, called the Diffusion-driven Distributed Load Balancing (DDLB) algorithm, is implemented on the OMNET++ Discrete Event Simulator and the response of the physical grid is simulated on a load flow program, which together simulate a deployment of the DDLB algorithm on the grid. The electrical grid is represented as a graph whose nodes are buses and whose edges are power lines connecting buses. Each node (except the …

The Optimisation Of The Secondary Cooling Water Distribution With Improved Genetic Algorithm In Continuous Casting Of Steels, Yu-Chun Zhai, Ying Li, Beiyue Ma, C Yan, Zhengyi Jiang

Faculty of Engineering and Information Sciences - Papers: Part A

An improved genetic algorithm is presented for the water consumption of the secondary cooling zone based on the heat transfer model of the off-line bloom caster. This study is to control the existing cooling systems and the steel casting practises in order to produce steel with best possible quality. The fitness function of improved genetic algorithm is founded according to the metallurgical criteria. This algorithm coupled with heat transfer model and metallurgical criteria, added dynamic coding method and self-adapting mutation on the original genetic algorithm can increase water distribution adaptively and improve the process efficiency. The simulation results of T91 …

An Effective Asexual Genetic Algorithm For Solving The Job Shop Scheduling Problem, Mehrdad Amirghasemi, Reza R. Zamani

Faculty of Engineering and Information Sciences - Papers: Part A

All rights reserved. Abstract By using the notion of elite pool, this paper presents an effective asexual genetic algorithm for solving the job shop scheduling problem. Based on mutation operations, the algorithm selectively picks the solution with the highest quality from the pool and after its modification, it can replace the solution with the lowest quality with such a modified solution. The elite pool is initially filled with a number of non-delay schedules, and then, in each iteration, the best solution of the elite pool is removed and mutated in a biased fashion through running a limited tabu search procedure. …

Target Tracking Algorithm Using Angular Point Matching Combined With Compressive Tracking, Jing Luo, Tingting Dong, Chunyuan Zi, Chunbo Xiu, Huixin Tian, Jiangtao Xi

Faculty of Engineering and Information Sciences - Papers: Part A

To solve the problems of tracking errors such as target missing that emerged in compressive tracking (CT) algorithm due to factors such as pose variation, illumination change, and occlusion, a novel tracking algorithm combined angular point matching with compressive tracking (APMCCT) was proposed. A sparse measurement matrix was adopted to extract the Haar-like features. The offset of the predicted target position was integrated into the angular point matching, and the new target position was calculated. Furthermore, the updating mechanism of the template was optimized. Experiments on different video sequences have shown that the proposed APMCCT performs better than CT algorithm …

A Framework For Determining Building Water Cycle Resilience Using A Dynamic Water Resilience Assessment Model (Wram), Caryssa Joustra

USF Tampa Graduate Theses and Dissertations

The aim of this project was to quantitatively measure the resilience of the building water cycle. In order to accomplish this goal, a framework was developed that outlines how building water resilience can be evaluated. The framework presented assumed that resilience describes the fulfillment of system functions; in this case, the system functions considered are those actualized by the building water system. A building water resilience assessment model (WRAM) was developed with the ability to simulate different building water cycles and resilience scenarios. Resilience is dependent on the type and magnitude of a disturbance. Therefore, unique disruption scenarios were developed …

Information Propagation Algorithms For Consensus Formation In Decentralized Multi-Agent Systems, Christopher Hollander

Electronic Theses and Dissertations

Consensus occurs within a multi-agent system when every agent is in agreement about the value of some particular state. For example, the color of an LED, the position or magnitude of a vector, a rendezvous location, the most recent state of data within a database, or the identity of a leader are all states that agents might need to agree on in order to execute their tasking. The task of the decentralized consensus problem for multi-agent systems is to design an algorithm that enables agents to communicate and exchange information such that, in finite time, agents are able to form …

Drive-By Bridge Damage Inspection, Ahmed Ali Elhattab

All ETDs from UAB

Bridge structures are subjected to continuous degradation due to environmental effects and increase in traffic loading. Bridge monitoring is a key element of any maintenance strategy as it can provide early signs of structural deterioration. In recent years, the demand towards sensor-based bridge monitoring in lieu of visual inspection, has increased. However, sensor-based monitoring is costly and requires significant maintenance. Recent studies on bridge damage monitoring have focused on the instrumentation of a passing vehicle instead of the bridge. This approach is referred to ‘drive-by’ bridge inspection (Kim and Kawatani, 2009). Using this approach, the bridge itself is not instrumented, …