View All Items

Title: A fuzzy logic material selection methodology for renewable ocean energy applications.
Creator: Welling, Donald Anthony., College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
Abstract/Description: The purpose of this thesis is to develop a renewable ocean energy material selection methodology for use in FAU's Ocean Energy Projects. A detailed and comprehensive literature review has been performed concerning all relevant material publications and forms the basis of the developed method. A database of candidate alloys has been organized and is used to perform case study material selections to validate the developed fuzzy logic approach. The ultimate goal of this thesis is to aid in the...
Show moreThe purpose of this thesis is to develop a renewable ocean energy material selection methodology for use in FAU's Ocean Energy Projects. A detailed and comprehensive literature review has been performed concerning all relevant material publications and forms the basis of the developed method. A database of candidate alloys has been organized and is used to perform case study material selections to validate the developed fuzzy logic approach. The ultimate goal of this thesis is to aid in the selection of materials that will ensure the successful performance of renewable ocean energy projects so that clean and renewable energy becomes a reality for all.
Show less
Date Issued: 2009
PURL: http://purl.flvc.org/FAU/227980
Subject Headings: Oceanic submersibles, Control systems, Acoustical engineering, Fuzzy algorithms, Renewable energy sources
Format: Document (PDF)

Title: A utility-based routing scheme in multi-hop wireless networks.
Creator: Lu, Mingming., College of Engineering and Computer Science, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Multi-hop wireless networks are infrastructure-less networks consisting of mobile or stationary wireless devices, which include multi-hop wireless mesh networks and multi-hop wireless sensor networks. These networks are characterized by limited bandwidth and energy resources, unreliable communication, and a lack of central control. These characteristics lead to the research challenges of multi-hop wireless networks. Building up routing schemes with good balance among the routing QoS (such as...
Show moreMulti-hop wireless networks are infrastructure-less networks consisting of mobile or stationary wireless devices, which include multi-hop wireless mesh networks and multi-hop wireless sensor networks. These networks are characterized by limited bandwidth and energy resources, unreliable communication, and a lack of central control. These characteristics lead to the research challenges of multi-hop wireless networks. Building up routing schemes with good balance among the routing QoS (such as reliability, cost, and delay) is a paramount concern to achieve high performance wireless networks. These QoS metrics are internally correlated. Most existing works did not fully utilize this correlation. We design a metric to balance the trade-off between reliability and cost, and build up a framework of utility-based routing model in multi-hop wireless networks. This dissertation focuses on the variations with applications of utility-based routing models, designing new concepts, and developing new algorithms for them. A review of existing routing algorithms and the basic utility-based routing model for multi-hop wireless networks has been provided at the beginning. An efficient algorithm, called MaxUtility, has been proposed for the basic utility-based routing model. MaxUtility is an optimal algorithm that can find the best routing path with the maximum expected utility., Various utility-based routing models are extended to further enhance the routing reliability while reducing the routing overhead. Besides computing the optimal path for a given benefit value and a given source-destination pair, the utility-based routing can be further extended to compute all optimal paths for all possible benefit values and/or all source-destination pairs. Our utility-based routing can also adapt to different applications and various environments. In the self-organized environment, where network users are selfish, we design a truthful routing, where selfish users have to tell the truth in order to maximize their utilities. We apply our utility-based routing scheme to the data-gathering wireless sensor networks, where a routing scheme is required to transmit data sensed by multiple sensor nodes to a common sink node.
Show less
Date Issued: 2008
PURL: http://purl.flvc.org/FAU/77647
Subject Headings: Wireless communication systems, Security measures, Computer network protocols, Computer algorithms, Computer networks, Security measures
Format: Document (PDF)

Title: Real-Time Localization of a Magnetic Anomaly: A Study of the Effectiveness of a Genetic Algorithm for Implementation on an Autonomous Underwater Vehicle.
Creator: Philippeaux, Harryel Arsene, Dhanak, Manhar R., Florida Atlantic University, College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
Abstract/Description: The primary objective of this research is to investigate the viability of magnetic anomaly localization with an autonomous underwater vehicle, using a genetic algorithm (GA). The localization method, first proposed by Sheinker. et al. 2008, is optimized here for the case of a moving platform. Extensive magnetic field modeling and algorithm simulation has been conducted and yields promising results. Field testing of the method is conducted with the use of the Ocean Floor Geophysics Self...
Show moreThe primary objective of this research is to investigate the viability of magnetic anomaly localization with an autonomous underwater vehicle, using a genetic algorithm (GA). The localization method, first proposed by Sheinker. et al. 2008, is optimized here for the case of a moving platform. Extensive magnetic field modeling and algorithm simulation has been conducted and yields promising results. Field testing of the method is conducted with the use of the Ocean Floor Geophysics Self-Compensating Magnetometer (SCM). Extensive out-of-water field testing is conducted to validate the ability to measure a target signal in a uniform NED frame as well as to validate the effectiveness of the GA. The outcome of the simulation closely matches the results of the conducted field tests. Additionally, the SCM is fully integrated with FAU’s Remus 100 AUV and preliminary in-water testing of the system has been conducted.
Show less
Date Issued: 2017
PURL: http://purl.flvc.org/fau/fd/FA00005948
Subject Headings: Dissertations, Academic -- Florida Atlantic University, Autonomous underwater vehicles, Genetic algorithms., Geomagnetic field, Geomagnetism.
Format: Document (PDF)

Title: Probabilistic predictor-based routing in disruption-tolerant networks.
Creator: Yuan, Quan., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Disruption-Tolerant Networks (DTNs) are the networks comprised of a set of wireless nodes, and they experience unstable connectivity and frequent connection disruption because of the limitations of radio range, power, network density, device failure, and noise. DTNs are characterized by their lack of infrastructure, device limitation, and intermittent connectivity. Such characteristics make conventional wireless network routing protocols fail, as they are designed with the assumption the...
Show moreDisruption-Tolerant Networks (DTNs) are the networks comprised of a set of wireless nodes, and they experience unstable connectivity and frequent connection disruption because of the limitations of radio range, power, network density, device failure, and noise. DTNs are characterized by their lack of infrastructure, device limitation, and intermittent connectivity. Such characteristics make conventional wireless network routing protocols fail, as they are designed with the assumption the network stays connected. Thus, routing in DTNs becomes a challenging problem, due to the temporal scheduling element in a dynamic topology. One of the solutions is prediction-based, where nodes mobility is estimated with a history of observations. Then, the decision of forwarding messages during data delivery can be made with that predicted information. Current prediction-based routing protocols can be divided into two sub-categories in terms of that whether they are probability related: probabilistic and non-probabilistic. This dissertation focuses on the probabilistic prediction-based (PPB) routing schemes in DTNs. We find that most of these protocols are designed for a specified topology or scenario. So almost every protocol has some drawbacks when applied to a different scenario. Because every scenario has its own particular features, there could hardly exist a universal protocol which can suit all of the DTN scenarios. Based on the above motivation, we investigate and divide the current DTNs scenarios into three categories: Voronoi-based, landmark-based, and random moving DTNs. For each category, we design and implement a corresponding PPB routing protocol for either basic routing or a specified application with considering its unique features., Specifically, we introduce a Predict and Relay routing protocol for Voronoi-based DTNs, present a single-copy and a multi-copy PPB routing protocol for landmark-based DTNs, and propose DRIP, a dynamic Voronoi region-based publish/subscribe protocol, to adapt publish/subscribe systems to random moving DTNs. New concepts, approaches, and algorithms are introduced during our work.
Show less
Date Issued: 2009
PURL: http://purl.flvc.org/FAU/359928
Subject Headings: Routers (Computer networks), Computer network protocols, Computer networks, Reliability, Computer algorithms, Wireless communication systems, Technological innovations
Format: Document (PDF)

Title: SUSTAINING CHAOS USING DEEP REINFORCEMENT LEARNING.
Creator: Vashishtha, Sumit, Verma, Siddhartha, Florida Atlantic University, Department of Ocean and Mechanical Engineering, College of Engineering and Computer Science
Abstract/Description: Numerous examples arise in fields ranging from mechanics to biology where disappearance of Chaos can be detrimental. Preventing such transient nature of chaos has been proven to be quite challenging. The utility of Reinforcement Learning (RL), which is a specific class of machine learning techniques, in discovering effective control mechanisms in this regard is shown. The autonomous control algorithm is able to prevent the disappearance of chaos in the Lorenz system exhibiting meta-stable...
Show moreNumerous examples arise in fields ranging from mechanics to biology where disappearance of Chaos can be detrimental. Preventing such transient nature of chaos has been proven to be quite challenging. The utility of Reinforcement Learning (RL), which is a specific class of machine learning techniques, in discovering effective control mechanisms in this regard is shown. The autonomous control algorithm is able to prevent the disappearance of chaos in the Lorenz system exhibiting meta-stable chaos, without requiring any a-priori knowledge about the underlying dynamics. The autonomous decisions taken by the RL algorithm are analyzed to understand how the system’s dynamics are impacted. Learning from this analysis, a simple control-law capable of restoring chaotic behavior is formulated. The reverse-engineering approach adopted in this work underlines the immense potential of the techniques used here to discover effective control strategies in complex dynamical systems. The autonomous nature of the learning algorithm makes it applicable to a diverse variety of non-linear systems, and highlights the potential of RLenabled control for regulating other transient-chaos like catastrophic events.
Show less
Date Issued: 2020
PURL: http://purl.flvc.org/fau/fd/FA00013498
Subject Headings: Machine learning--Technique, Reinforcement learning, Algorithms, Chaotic behavior in systems, Nonlinear systems
Format: Document (PDF)

Title: Application level intrusion detection using a sequence learning algorithm.
Creator: Dong, Yuhong., Florida Atlantic University, Hsu, Sam, Rajput, Saeed, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: An un-supervised learning algorithm on application level intrusion detection, named Graph Sequence Learning Algorithm (GSLA), is proposed in this dissertation. Experiments prove its effectiveness. Similar to most intrusion detection algorithms, in GSLA, the normal profile needs to be learned first. The normal profile is built using a session learning method, which is combined with the one-way Analysis of Variance method (ANOVA) to determine the value of an anomaly threshold. In the proposed...
Show moreAn un-supervised learning algorithm on application level intrusion detection, named Graph Sequence Learning Algorithm (GSLA), is proposed in this dissertation. Experiments prove its effectiveness. Similar to most intrusion detection algorithms, in GSLA, the normal profile needs to be learned first. The normal profile is built using a session learning method, which is combined with the one-way Analysis of Variance method (ANOVA) to determine the value of an anomaly threshold. In the proposed approach, a hash table is used to store a sparse data matrix in triple data format that is collected from a web transition log instead of an n-by-n dimension matrix. Furthermore, in GSLA, the sequence learning matrix can be dynamically changed according to a different volume of data sets. Therefore, this approach is more efficient, easy to manipulate, and saves memory space. To validate the effectiveness of the algorithm, extensive simulations have been conducted by applying the GSLA algorithm to the homework submission system at our computer science and engineering department. The performance of GSLA is evaluated and compared with traditional Markov Model (MM) and K-means algorithms. Specifically, three major experiments have been done: (1) A small data set is collected as a sample data, and is applied to GSLA, MM, and K-means algorithms to illustrate the operation of the proposed algorithm and demonstrate the detection of abnormal behaviors. (2) The Random Walk-Through sampling method is used to generate a larger sample data set, and the resultant anomaly score is classified into several clusters in order to visualize and demonstrate the normal and abnormal behaviors with K-means and GSLA algorithms. (3) Multiple professors' data sets are collected and used to build the normal profiles, and the ANOVA method is used to test the significant difference among professors' normal profiles. The GSLA algorithm can be made as a module and plugged into the IDS as an anomaly detection system.
Show less
Date Issued: 2006
PURL: http://purl.flvc.org/fcla/dt/12220
Subject Headings: Data mining, Parallel processing (Electronic computers), Computer algorithms, Computer security, Pattern recognition systems
Format: Document (PDF)

Title: Efficient localized broadcast algorithms in mobile ad hoc networks.
Creator: Lou, Wei., Florida Atlantic University, Wu, Jie, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: The broadcast operation has a most fundamental role in mobile ad hoc networks because of the broadcasting nature of radio transmission, i.e., when a sender transmits a packet, all nodes within the sender's transmission range will be affected by this transmission. The benefit of this property is that one packet can be received by all neighbors while the negative effect is that it interferes with other transmissions. Flooding ensures that the entire network receives the packet but generates...
Show moreThe broadcast operation has a most fundamental role in mobile ad hoc networks because of the broadcasting nature of radio transmission, i.e., when a sender transmits a packet, all nodes within the sender's transmission range will be affected by this transmission. The benefit of this property is that one packet can be received by all neighbors while the negative effect is that it interferes with other transmissions. Flooding ensures that the entire network receives the packet but generates many redundant transmissions which may trigger a serious broadcast storm problem that may collapse the entire network. The broadcast storm problem can be avoided by providing efficient broadcast algorithms that aim to reduce the number of nodes that retransmit the broadcast packet while still guaranteeing that all nodes receive the packet. This dissertation focuses on providing several efficient localized broadcast algorithms to reduce the broadcast redundancy in mobile ad hoc networks. In my dissertation, the efficiency of a broadcast algorithm is measured by the number of forward nodes for relaying a broadcast packet. A classification of broadcast algorithms for mobile ad hoc networks has been provided at the beginning. Two neighbor-designating broadcast algorithms, called total dominant pruning and partial dominant pruning, have been proposed to reduce the number of the forward nodes. Several extensions based on the neighbor-designating approach have also been investigated. The cluster-based broadcast algorithm shows good performance in dense networks, and it also provides a constant upper bound approximation ratio to the optimum solution for the number of forward nodes in the worst case. A generic broadcast framework with K hop neighbor information has a trade-off between the number of the forward nodes and the size of the K-hop zone. A reliable broadcast algorithm, called double-covered broadcast, is proposed to improve the delivery ratio of a broadcast package when the transmission error rate of the network is high. The effectiveness of all these algorithms has been confirmed by simulations.
Show less
Date Issued: 2004
PURL: http://purl.flvc.org/fau/fd/FADT12103
Subject Headings: Wireless LANS, Mobile communication systems, Wireless communication systems--Mathematics, Algorithms
Format: Document (PDF)

Title: Damage detection for autonomous underwater vehicles.
Creator: Rae, Graeme John Stuart., Florida Atlantic University, Dunn, Stanley E., College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
Abstract/Description: A method of on-line monitoring AUV onboard systems is described. This algorithm determines deviations from normal operating conditions based on a damage level calculated from recursive least squares system identification performed on the system under consideration, followed by a gradient detection technique which extracts significant changes in identified model parameters System damage types are characterized together with likely system responses to such failures. Extensive testing of the...
Show moreA method of on-line monitoring AUV onboard systems is described. This algorithm determines deviations from normal operating conditions based on a damage level calculated from recursive least squares system identification performed on the system under consideration, followed by a gradient detection technique which extracts significant changes in identified model parameters System damage types are characterized together with likely system responses to such failures. Extensive testing of the algorithm is performed using several simulated AUV on-board systems undergoing different types of failures while carrying out different mission scenarios.
Show less
Date Issued: 1993
PURL: http://purl.flvc.org/fcla/dt/12331
Subject Headings: Submersibles--Automatic control, Fault-tolerant computing, Algorithms--Data procedssing
Format: Document (PDF)

Title: Determination of receptive fields in neural networks using Alopex.
Creator: Shah, Gaurang G., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: This research aims at proposing a model for visual pattern recognition inspired by the neural circuitry in the brain. Our attempt is to propose few modifications in the Alopex algorithm and try to use it for the calculations of the receptive fields of neurons in the trained network. We have developed a small-scale, four-layered neural network model for simple character recognition as well as complex image patterns, which can recognize the patterns transformed by affine conversion. Here Alopex...
Show moreThis research aims at proposing a model for visual pattern recognition inspired by the neural circuitry in the brain. Our attempt is to propose few modifications in the Alopex algorithm and try to use it for the calculations of the receptive fields of neurons in the trained network. We have developed a small-scale, four-layered neural network model for simple character recognition as well as complex image patterns, which can recognize the patterns transformed by affine conversion. Here Alopex algorithm is presented as an iterative and stochastic processing method, which was proposed for optimization of a given cost function over hundreds or thousands of iterations. In this case the receptive fields of the neurons in the output layers are obtained using the Alopex algorithm.
Show less
Date Issued: 2005
PURL: http://purl.flvc.org/fcla/dt/13298
Subject Headings: Pattern recognition systems, Neural networks (Computer science), Computer algorithms, Neuroanatomy, Image processing
Format: Document (PDF)

Title: Connected Dominating Set in Wireless Ad Hoc Networks: Variations with Applications.
Creator: Yang, Shuhui, Wu, Jie, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Wireless ad hoc networks (or simply ad hoc networks) are infrastructureless multihop networks consisting of mobile or stationary wireless devices, which include mobile ad hoc networks (MANETs) and wireless sensor networks (WSNs). These networks are characterized by limited bandwidth and energy resources, frequent topology changes, and a lack of central control. These characteristics lead to the research challenges of ad hoc networks. The algorithms designed for ad hoc networks should be...
Show moreWireless ad hoc networks (or simply ad hoc networks) are infrastructureless multihop networks consisting of mobile or stationary wireless devices, which include mobile ad hoc networks (MANETs) and wireless sensor networks (WSNs). These networks are characterized by limited bandwidth and energy resources, frequent topology changes, and a lack of central control. These characteristics lead to the research challenges of ad hoc networks. The algorithms designed for ad hoc networks should be localized, selforganizing, and energy efficient. A connected dominating set (CDS) is frequently used in ad hoc networks as a virtual backbone to support efficient routing, service discovery, and area monitoring. In addition, efficient broadcasting (i.e., finding a small set of forward nodes to ensure full delivery) can be viewed as forming a CDS on-the-fly. The periodically maintained virtual backbone is called a static CDS, and the temporarily formed forward node set is called a dynamk CDS. For efficiency and robustness, the ideal CDS construction algorithm is lightweight, has fast convergence, and minimizes the CDS size. Recently, due to some specific applications and new techniques, the concept of a connected dominating set can be modified or further extended for more efficient usage. This dissertation focuses on the variations with applications of the connected dominating set, designing new concepts, and developing new algorithms for them. A review of CDS construction algorithms for ad hoc networks has been provided at the beginning. An efficient scheme, called Rule K, has been proposed for static CDS construction. Rule K achieves a probabilistic constant upper bound on the expected CDS size, which is currently the best known performance guarantee for localized CDS algorithms. Several CDS algorithms are extended to generate the extended CDS, which exploits the cooperative communication technique to further reduce the size of CDS. A k-coverage set is developed for higher robustness. With the equipment of directional antennas , the transmission can be restricted to some certain directions to reduce interference and energy consumption. The corresponding directional CDS is discussed. Finally, a wireless sensor and actor network (WSAN) is introduced and localized algorithms are designed for it.
Show less
Date Issued: 2007
PURL: http://purl.flvc.org/fau/fd/FA00012580
Subject Headings: Computer network protocols, Wireless communication systems--Design and construction, Mobile computing, Computer algorithms
Format: Document (PDF)

Title: Methods and Algorithms for Human Detection in Video Sequences.
Creator: Pertuz, Carlos, Marques, Oge, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Lower prices of video sensors, security concerns and the need for better and faster algorithms to extract high level information from video sequences are all factors which have stimulated research in the area of automated video surveillance systems. In the context of security the analysis of human interrelations and their environment provides hints to proactively identify anomalous behavior. However, human detection is a necessary component in systems where the automatic extraction of higher...
Show moreLower prices of video sensors, security concerns and the need for better and faster algorithms to extract high level information from video sequences are all factors which have stimulated research in the area of automated video surveillance systems. In the context of security the analysis of human interrelations and their environment provides hints to proactively identify anomalous behavior. However, human detection is a necessary component in systems where the automatic extraction of higher level information, such as recognizing individuals' activities, is required. The human detection problem is one of classification. In general, motion, appearance and shape are the classification approaches a system can employ to perform human detection. Techniques representative of these approaches, such us periodic motion detection, skin color detection and MPEG-7 shape descriptors are implemented in this work. An infrastructure that allows data collection for such techniques was also implemented.
Show less
Date Issued: 2007
PURL: http://purl.flvc.org/fau/fd/FA00012538
Subject Headings: MPEG (Video coding standard), Image processing--Digital techniques, Form perception, Computer algorithms, Video compression
Format: Document (PDF)

Title: Multi-Path Intelligent Virtual Mobile Nodes for Ad Hoc Networks.
Creator: Qian, Binbin, Wu, Jie, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: In mobile ad hoc networks, it is challenging to solve the standard problems encountered in fixed network because of the unpredictable motion of mobile nodes. Due to the lack of a fixed infrastructure to serve as the backbone of the network, it is difficult to manage nodes' locations and ensure the stable node performance. The virtual mobile node (VMN) abstraction that has been applied implements an virtual mobile node that consists of a set of real nodes traveling on one predetermined virtual...
Show moreIn mobile ad hoc networks, it is challenging to solve the standard problems encountered in fixed network because of the unpredictable motion of mobile nodes. Due to the lack of a fixed infrastructure to serve as the backbone of the network, it is difficult to manage nodes' locations and ensure the stable node performance. The virtual mobile node (VMN) abstraction that has been applied implements an virtual mobile node that consists of a set of real nodes traveling on one predetermined virtual path to collect messages and deliver them to the destinations when they meet. It conquers the unpredictable motion with virtual nodes' predictable motion. But it encounters unavoidable failure when all the nodes leave the VMN region and stop emulating the VMN. We extend the idea of the VMN abstraction to the Multi-path Intelligent Virtual Mobile Node (MIVMN) abstraction, which allows the messages to switch between multiple Hamiltonian paths to increase the message delivery ratio and decrease the failure rate of the virtual nodes. Through simulation results we show that the MIVMN abstraction successfully meets our goals.
Show less
Date Issued: 2007
PURL: http://purl.flvc.org/fau/fd/FA00012542
Subject Headings: Routers (Computer networks), Computer network architectures, Wireless communication systems, Computer algorithms
Format: Document (PDF)

Title: Performance analysis of K-means algorithm and Kohonen networks.
Creator: Syed, Afzal A., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: K-means algorithm and Kohonen network possess self-organizing characteristics and are widely used in different fields currently. The factors that influence the behavior of K-means are the choice of initial cluster centers, number of cluster centers and the geometric properties of the input data. Kohonen networks have the ability of self-organization without any prior input about the number of clusters to be formed. This thesis looks into the performances of these algorithms and provides a...
Show moreK-means algorithm and Kohonen network possess self-organizing characteristics and are widely used in different fields currently. The factors that influence the behavior of K-means are the choice of initial cluster centers, number of cluster centers and the geometric properties of the input data. Kohonen networks have the ability of self-organization without any prior input about the number of clusters to be formed. This thesis looks into the performances of these algorithms and provides a unique way of combining them for better clustering. A series of benchmark problem sets are developed and run to obtain the performance analysis of the K-means algorithm and Kohonen networks. We have attempted to obtain the better of these two self-organizing algorithms by providing the same problem sets and extract the best results based on the users needs. A toolbox, which is user-friendly and written in C++ and VC++ is developed for applications on both images and feature data sets. The tool contains K-means algorithm and Kohonen networks code for clustering and pattern classification.
Show less
Date Issued: 2004
PURL: http://purl.flvc.org/fcla/dt/13112
Subject Headings: Self-organizing maps, Neural networks (Computer science), Cluster analysis--Computer programs, Computer algorithms
Format: Document (PDF)

Title: Object recognition by genetic algorithm.
Creator: Li, Jianhua., Florida Atlantic University, Han, Chingping (Jim), Zhuang, Hanqi, College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
Abstract/Description: Vision systems have been widely used for parts inspection in electronics assembly lines. In order to improve the overall performance of a visual inspection system, it is important to employ an efficient object recognition algorithm. In this thesis work, a genetic algorithm based correlation algorithm is designed for the task of visual electronic parts inspection. The proposed procedure is composed of two stages. In the first stage, a genetic algorithm is devised to find a sufficient number of...
Show moreVision systems have been widely used for parts inspection in electronics assembly lines. In order to improve the overall performance of a visual inspection system, it is important to employ an efficient object recognition algorithm. In this thesis work, a genetic algorithm based correlation algorithm is designed for the task of visual electronic parts inspection. The proposed procedure is composed of two stages. In the first stage, a genetic algorithm is devised to find a sufficient number of candidate image windows. For each candidate window, the correlation is performed between the sampled template and the image pattern inside the window. In the second stage, local searches are conducted in the neighborhood of these candidate windows. Among all the searched locations, the one that has a highest correlation value with the given template is selected as the best matched location. To apply the genetic algorithm technique, a number of important issues, such as selection of a fitness function, design of a coding scheme, and tuning of genetic parameters are addressed in the thesis. Experimental studies have confirmed that the proposed GA-based correlation method is much more effective in terms of accuracy and speed in locating the desired object, compared with the existing Monte-Carlo random search method.
Show less
Date Issued: 1995
PURL: http://purl.flvc.org/fcla/dt/15225
Subject Headings: Genetic algorithms, Robots--Control systems, Computer vision, Quality control--Optical methods
Format: Document (PDF)

Title: Quality of service support in TDMA-based mobile ad hoc networks.
Creator: Jawhar, Imad., Florida Atlantic University, Wu, Jie, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: With the continuing advances in computing and wireless technologies, mobile ad hoc networks (MANETs) are expected to become an indispensable part of the computing environment in the near future. Wireless devices are constantly growing in computing speed, memory, communication capabilities and features, while shrinking in weight and size. With this growth and the proliferation of these devices in every aspect of society, the need for such devices to communicate in a seamless manner is becoming...
Show moreWith the continuing advances in computing and wireless technologies, mobile ad hoc networks (MANETs) are expected to become an indispensable part of the computing environment in the near future. Wireless devices are constantly growing in computing speed, memory, communication capabilities and features, while shrinking in weight and size. With this growth and the proliferation of these devices in every aspect of society, the need for such devices to communicate in a seamless manner is becoming increasingly essential. Multiple routing protocols have been developed for MANETs [51]. As MANETs gain popularity, their need to support real time and multimedia applications is growing as well. Such applications have stringent quality of service (QoS) requirements such as bandwidth, delay, and delay fitter. Design and development of routing algorithms with QoS support is experiencing increased research interest. Several approaches which propose various routing algorithms with QoS support for MANETs have been presented in research. This dissertation addresses the issues and challenges of QoS routing in MANETS and presents three new protocols which provide QoS support for this environment. First, a brief classification of existing QoS routing algorithms is provided. Then, the three new protocols for QoS routing support in MANETs are presented. These protocols focus on resource reservation for QoS provisioning in TDMA-based MANETs. The first protocol improves QoS support by eliminating racing conditions during multiple reservations of QoS paths. The second protocol is a new protocol for resource reservation for QoS support in TDMA-based MANETs using directional antennas. The last protocol provides dynamic range resource reservation for QoS support in MANETs and represents an extension of the previous protocols.
Show less
Date Issued: 2005
PURL: http://purl.flvc.org/fcla/dt/12158
Subject Headings: Digital communications, Time division multiple access, Computer algorithms, Computer network protocols, Wireless communication systems
Format: Document (PDF)

Title: A general pressure based Navier-Stokes solver in arbitrary configurations.
Creator: Ke, Zhao Ping., Florida Atlantic University, Chow, Wen L., College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
Abstract/Description: A pressure-based computer program for a general Navier-Stokes equations has been developed. Body-fitted coordinate system is employed to handle flows with complex geometry. Non-staggered grid is used while the pressure oscillation is eliminated by a special pressure interpolation scheme. The hybrid algorithm is adopted to discretize the equations and the finite-difference equations are solved by TDMA, while the whole solution is obtained through an under-relaxed iterative process. The...
Show moreA pressure-based computer program for a general Navier-Stokes equations has been developed. Body-fitted coordinate system is employed to handle flows with complex geometry. Non-staggered grid is used while the pressure oscillation is eliminated by a special pressure interpolation scheme. The hybrid algorithm is adopted to discretize the equations and the finite-difference equations are solved by TDMA, while the whole solution is obtained through an under-relaxed iterative process. The pressure field is evaluated using the compressible from of the SIMPLE algorithm., To test the accuracy and efficiency of the computer program, problems of incompressible and compressible flows are calculated. As examples of inviscid compressible flow problems, flows over a bump with 10% and 4% thickness are computed with the incoming Mach numbers of M[infinity] = 0.5 (subsonic flow), M[infinity] = 0.675 (transonic flow and M[infinity] = 1.65 (supersonic flow). One laminar subsonic flow over a bump with 5% thickness at M[infinity] = 0.5 is also calculated with the consideration of the full energy equation. With the help of the k-epsilon model incorporating the wall function, the computations of two turbulent incompressible flows are carried out. One is the flow past a flat plate and the other over a flame holder. As an application to the three-dimensional flow, a laminar flow in a driven cubic cavity is calculated. All the numerical results obtained here are compared with experimental data or other numerical results available in the literature.
Show less
Date Issued: 1993
PURL: http://purl.flvc.org/fcla/dt/12330
Subject Headings: Navier-Stokes equations--Numerical solutions--Data processing, Algorithms, Flows (Differential dynamical systems)
Format: Document (PDF)

Title: A VLSI implementable thinning algorithm.
Creator: Zhang, Wei, Florida Atlantic University, Shankar, Ravi, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Thinning is a very important step in a Character Recognition System. This thesis evolves a thinning algorithm that can be hardware implemented to improve the speed of the process. The software thinning algorithm features a simple set of rules that can be applied on both hexagonal and orthogonal character images. The hardware architecture features the SIMD structure, simple processing elements and near neighbor communications. The algorithm was simulated against the U.S. Postal Service...
Show moreThinning is a very important step in a Character Recognition System. This thesis evolves a thinning algorithm that can be hardware implemented to improve the speed of the process. The software thinning algorithm features a simple set of rules that can be applied on both hexagonal and orthogonal character images. The hardware architecture features the SIMD structure, simple processing elements and near neighbor communications. The algorithm was simulated against the U.S. Postal Service Character Database. The architecture, evolved with consideration of both the software constraints and the physical layout limitations, was simulated using VHDL hardware description language. Subsequent to VLSI design and simulations the chip was fabricated. The project provides for a feasibility study in utilizing the parallel processor architecture for the implementation of a parallel image thinning algorithm. It is hoped that such a hardware implementation will speed up the processing and lead eventually to a real time system.
Show less
Date Issued: 1992
PURL: http://purl.flvc.org/fcla/dt/14837
Subject Headings: Optical character recognition devices--Computer simulation, Algorithms, Integrated circuits--Very large scale integration
Format: Document (PDF)

Title: Visualization as a Qualitative Method for Analysis of Data from Location Tracking Technologies.
Creator: Mani, Mohan, VanHilst, Michael, Pandya, Abhijit S., Hsu, Sam, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: One of the biggest factors in the quest to better wireless communication is cellular call handoff, which in tum, is a function of geographic location. In this thesis, our fundamental goal was to demonstrate the value addition brought forth by spatial data visualization techniques for the analysis of geo-referenced data from two different location tracking technologies: GPS and cellular systems. Through our efforts, we unearthed some valuable and surprising insights from the data being...
Show moreOne of the biggest factors in the quest to better wireless communication is cellular call handoff, which in tum, is a function of geographic location. In this thesis, our fundamental goal was to demonstrate the value addition brought forth by spatial data visualization techniques for the analysis of geo-referenced data from two different location tracking technologies: GPS and cellular systems. Through our efforts, we unearthed some valuable and surprising insights from the data being analyzed that led to interesting observations about the data itself as opposed to the entity, or entities, that the data is supposed to describe. In doing so, we underscored the value addition brought forth by spatial data visualization techniques even in the incipient stages of analysis of georeferenced data from cellular networks. We also demonstrated the value of visualization techniques as a verification tool to verify the results of analysis done through other methods, such as statistical analysis.
Show less
Date Issued: 2008
PURL: http://purl.flvc.org/fau/fd/FA00012536
Subject Headings: Mobile communication systems, Algorithms--Data analysis, Radio--Transmitters and transmissions, Code division multiple access
Format: Document (PDF)

Title: An intelligent GMDH forecaster for forecasting certain variables in financial markets.
Creator: Mehta, Sandeep., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: In this thesis, application of GMDH Algorithm to real life problems is studied. A particular type of GMDH Algorithm namely TMNN is chosen for this purpose. An effort is made to forecast S&P Index Closing Value with the help of the forecaster. The performance of the TMNN Algorithm is simulated by implementing a tool in C++ for developing forecast models. The validation of this simulation tool is carried out with Sine Wave Values and performance analysis is done in a noisy environment. The...
Show moreIn this thesis, application of GMDH Algorithm to real life problems is studied. A particular type of GMDH Algorithm namely TMNN is chosen for this purpose. An effort is made to forecast S&P Index Closing Value with the help of the forecaster. The performance of the TMNN Algorithm is simulated by implementing a tool in C++ for developing forecast models. The validation of this simulation tool is carried out with Sine Wave Values and performance analysis is done in a noisy environment. The noisy environment tests the TMNN forecaster for its robustness. The primary goal of this research is to develop a simulation software based on TMNN Algorithm for forecasting stock market index values. The main inputs are previous day's closing values and the output is predicted closing index.
Show less
Date Issued: 2002
PURL: http://purl.flvc.org/fcla/dt/12996
Subject Headings: GMDH algorithms, Neural networks (Computer science), Time-series analysis, Pattern recognition systems
Format: Document (PDF)

Title: Fuzzy identification of processes on finite training sets with known features.
Creator: Diaz-Robainas, Regino R., Florida Atlantic University, Huang, Ming Z., Zilouchian, Ali, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: A methodology is presented to construct an approximate fuzzy-mapping algorithm that maps multiple inputs to single outputs given a finite training set of argument vectors functionally linked to corresponding scalar outputs. Its scope is limited to problems where the features are known in advance, or equivalently, where the expected functional representation is known to depend exclusively on the known selected variables. Programming and simulations to implement the methodology make use of...
Show moreA methodology is presented to construct an approximate fuzzy-mapping algorithm that maps multiple inputs to single outputs given a finite training set of argument vectors functionally linked to corresponding scalar outputs. Its scope is limited to problems where the features are known in advance, or equivalently, where the expected functional representation is known to depend exclusively on the known selected variables. Programming and simulations to implement the methodology make use of Matlab Fuzzy and Neural toolboxes and a PC application of Prolog, and applications range from approximate representations of the direct kinematics of parallel manipulators to fuzzy controllers.
Show less
Date Issued: 1996
PURL: http://purl.flvc.org/fcla/dt/12487
Subject Headings: Fuzzy algorithms, Set theory, Logic, Symbolic and mathematical, Finite groups, Representations of groups
Format: Document (PDF)

FAU Theses and Dissertations (119)	+ -
FAU Graduate Student Research (2)	+ -
HBOI Faculty Contributions (2)	+ -
FAU College Collections (1)	+ -

Algorithms (44)	+ -
Computer algorithms (35)	+ -
Genetic algorithms (16)	+ -
Machine learning (12)	+ -
Neural networks (Computer science) (11)	+ -

Wireless communication systems (9)	+ -
Computer network protocols (8)	+ -
Pattern recognition systems (8)	+ -
Cryptography (7)	+ -
Algorithms. (6)	+ -
Computer networks (6)	+ -
Parallel processing (Electronic computers) (6)	+ -
Fault-tolerant computing (5)	+ -
GMDH algorithms (5)	+ -
Mobile computing (5)	+ -
Computer algorithms. (4)	+ -
Data encryption (Computer science) (4)	+ -
Fuzzy algorithms (4)	+ -
Image processing (4)	+ -
Integrated circuits--Very large scale integration (4)	+ -
Mobile communication systems (4)	+ -
Big data (3)	+ -
Combinatorial optimization (3)	+ -
Dissertations, Academic -- Florida Atlantic University (3)	+ -
Machine learning. (3)	+ -
Quantum computing (3)	+ -
Robots--Control systems (3)	+ -
Routing protocols (Computer network protocols) (3)	+ -
Technological innovations (3)	+ -
Acoustical engineering (2)	+ -

Electronic Thesis or Dissertation (119)	+ -
article (3)	+ -
abstract (2)	+ -

Florida Atlantic University (108)	+ -
College of Engineering and Computer Science (85)	+ -
Department of Computer and Electrical Engineering and Computer Science (69)	+ -
Charles E. Schmidt College of Science (17)	+ -
Department of Ocean and Mechanical Engineering (15)	+ -

Search In

Pages

Pages

Sort Results By:

Narrow results by:

Collection

Topical Subject

Geographic Subject

Genre

Type of Resource

Language

Creator

Format

Owner