Current Search: College of Computer Science and Engineering (x)
View All Items
Pages
- Title
- DEEP MAXOUT NETWORKS FOR CLASSIFICATION PROBLEMS ACROSS MULTIPLE DOMAINS.
- Creator
- Castaneda, Gabriel, Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Machine learning techniques such as deep neural networks have become an indispensable tool for a wide range of applications such as image classification, speech recognition, and sentiment analysis in text. An activation function is a mathematical equation that determines the output of each neuron in the neural network. In deep learning architectures the choice of activation functions is very important to the network’s performance. Activation functions determine the output of the model, its...
Show moreMachine learning techniques such as deep neural networks have become an indispensable tool for a wide range of applications such as image classification, speech recognition, and sentiment analysis in text. An activation function is a mathematical equation that determines the output of each neuron in the neural network. In deep learning architectures the choice of activation functions is very important to the network’s performance. Activation functions determine the output of the model, its computational efficiency, and its ability to train and converge after multiple iterations of training epochs. The selection of an activation function is critical to building and training an effective and efficient neural network. In real-world applications of deep neural networks, the activation function is a hyperparameter. We have observed a lack of consensus on how to select a good activation function for a deep neural network, and that a specific function may not be suitable for all domain-specific applications.
Show less - Date Issued
- 2019
- PURL
- http://purl.flvc.org/fau/fd/FA00013362
- Subject Headings
- Classification, Machine learning--Technique, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- Channel Assignment in Cognitive Radio Wireless Networks.
- Creator
- Wu, Yueshi, Cardei, Mihaela, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Cognitive radio technology that enables dynamic spectrum access has been a promising solution for the spectrum scarcity problem. Cognitive radio networks enable the communication on both licensed and unlicensed channels, having the potential to better solve the interference and collision issues. Channel assignment is of great importance in cognitive radio networks. When operating on licensed channels, the objective is to exploit spectrum holes through cognitive communication, giving priority...
Show moreCognitive radio technology that enables dynamic spectrum access has been a promising solution for the spectrum scarcity problem. Cognitive radio networks enable the communication on both licensed and unlicensed channels, having the potential to better solve the interference and collision issues. Channel assignment is of great importance in cognitive radio networks. When operating on licensed channels, the objective is to exploit spectrum holes through cognitive communication, giving priority to the primary users. In this dissertation, we focus on the development of efficient channel assignment algorithms and protocols to improve network performance for cognitive radio wireless networks. The first contribution is on channel assignment for cognitive radio wireless sensor networks aiming to provide robust topology control, as well as to increase network throughput and data delivery rate. The approach is then extended to specific cognitive radio network applications achieving improved performances.
Show less - Date Issued
- 2016
- PURL
- http://purl.flvc.org/fau/fd/FA00004750, http://purl.flvc.org/fau/fd/FA00004750
- Subject Headings
- Cognitive radio networks--Technological innovations., Wireless communication systems--Technological innovations., Ad hoc networks (Computer networks), Routing protocols (Computer network protocols)
- Format
- Document (PDF)
- Title
- Context-based Image Concept Detection and Annotation.
- Creator
- Zolghadr, Esfandiar, Furht, Borko, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Scene understanding attempts to produce a textual description of visible and latent concepts in an image to describe the real meaning of the scene. Concepts are either objects, events or relations depicted in an image. To recognize concepts, the decision of object detection algorithm must be further enhanced from visual similarity to semantical compatibility. Semantically relevant concepts convey the most consistent meaning of the scene. Object detectors analyze visual properties (e.g., pixel...
Show moreScene understanding attempts to produce a textual description of visible and latent concepts in an image to describe the real meaning of the scene. Concepts are either objects, events or relations depicted in an image. To recognize concepts, the decision of object detection algorithm must be further enhanced from visual similarity to semantical compatibility. Semantically relevant concepts convey the most consistent meaning of the scene. Object detectors analyze visual properties (e.g., pixel intensities, texture, color gradient) of sub-regions of an image to identify objects. The initially assigned objects names must be further examined to ensure they are compatible with each other and the scene. By enforcing inter-object dependencies (e.g., co-occurrence, spatial and semantical priors) and object to scene constraints as background information, a concept classifier predicts the most semantically consistent set of names for discovered objects. The additional background information that describes concepts is called context. In this dissertation, a framework for building context-based concept detection is presented that uses a combination of multiple contextual relationships to refine the result of underlying feature-based object detectors to produce most semantically compatible concepts. In addition to the lack of ability to capture semantical dependencies, object detectors suffer from high dimensionality of feature space that impairs them. Variances in the image (i.e., quality, pose, articulation, illumination, and occlusion) can also result in low-quality visual features that impact the accuracy of detected concepts. The object detectors used to build context-based framework experiments in this study are based on the state-of-the-art generative and discriminative graphical models. The relationships between model variables can be easily described using graphical models and the dependencies and precisely characterized using these representations. The generative context-based implementations are extensions of Latent Dirichlet Allocation, a leading topic modeling approach that is very effective in reduction of the dimensionality of the data. The discriminative contextbased approach extends Conditional Random Fields which allows efficient and precise construction of model by specifying and including only cases that are related and influence it. The dataset used for training and evaluation is MIT SUN397. The result of the experiments shows overall 15% increase in accuracy in annotation and 31% improvement in semantical saliency of the annotated concepts.
Show less - Date Issued
- 2016
- PURL
- http://purl.flvc.org/fau/fd/FA00004745, http://purl.flvc.org/fau/fd/FA00004745
- Subject Headings
- Computer vision--Mathematical models., Pattern recognition systems., Information visualization., Natural language processing (Computer science), Multimodal user interfaces (Computer systems), Latent structure analysis., Expert systems (Computer science)
- Format
- Document (PDF)
- Title
- Developing a photovoltaic MPPT system.
- Creator
- Bennett, Thomas, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Many issues related to the design and implementation of a maximum power point tracking (MPPT) converter as part of a photovoltaic (PV) system are addressed. To begin with, variations of the single diode model for a PV module are compared, to determine whether the simplest variation may be used for MPPT PV system modeling and analysis purposes. As part ot this determination, four different DC/DC converters are used in conjunction with these different PV models. This is to verify consistent...
Show moreMany issues related to the design and implementation of a maximum power point tracking (MPPT) converter as part of a photovoltaic (PV) system are addressed. To begin with, variations of the single diode model for a PV module are compared, to determine whether the simplest variation may be used for MPPT PV system modeling and analysis purposes. As part ot this determination, four different DC/DC converters are used in conjunction with these different PV models. This is to verify consistent behavior across the different PV models, as well as across the different converter topologies. Consistent results across the different PV models, will allow a simpler model to be used for simulation ana analysis. Consistent results with the different converters will verify that MPPT algorithms are converter independent. Next, MPPT algorithms are discussed. In particular,the differences between the perturb and observe, and the incremental conductance algorithms are explained and illustrated. A new MPPT algorithm is then proposed based on the deficiencies of the other algorithms. The proposed algorithm's parameters are optimized, and the results for different PV modules obtained. Realistic system losses are then considered, and their effect on the PV system is analyzed ; especially in regards to the MPPT algorithm. Finally, a PV system is implemented and the theoretical results, as well as the behavior of the newly proposed MPPT algorithm, are verified.
Show less - Date Issued
- 2012
- PURL
- http://purl.flvc.org/FAU/3356887
- Subject Headings
- Photovoltaic power systems, Design, Electronic circuits, Electric current converters, Power (Mechanics), Renewable energy sources
- Format
- Document (PDF)
- Title
- Design considerations in high-throughput automation for biotechnology protocols.
- Creator
- Cardona, Aura, Roth, Zvi S., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
In this dissertation a computer-aided automation design methodology for biotechnology applications is proposed that leads to several design guidelines. Because of the biological nature of the samples that propagate in the automation line, a very specific set of environmental and maximum allowed shelf time conditions have to be followed to obtain good yield. In addition all biotechnology protocols require precise sequence of steps, the samples are scarce and the reagents are costly, so no...
Show moreIn this dissertation a computer-aided automation design methodology for biotechnology applications is proposed that leads to several design guidelines. Because of the biological nature of the samples that propagate in the automation line, a very specific set of environmental and maximum allowed shelf time conditions have to be followed to obtain good yield. In addition all biotechnology protocols require precise sequence of steps, the samples are scarce and the reagents are costly, so no waste can be afforded.
Show less - Date Issued
- 2014
- PURL
- http://purl.flvc.org/fau/fd/FA00004272, http://purl.flvc.org/fau/fd/FA00004272
- Subject Headings
- Biotechnological process control, Biotechnological process monitoring, Molecular biology -- Automation, Molecular biology -- Technique, Molecular cloning -- Technique, Pharmacognosy
- Format
- Document (PDF)
- Title
- Development of Smart Phone-based Automated Microfluidic-ELISA For Human Immunodefciency Virus 1.
- Creator
- Coarsey, Chad Thomas, Asghar, Waseem, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
The majority of HIV prevalence is found in Sub-Saharan Africa with 36.9 mil- lion living with HIV/AIDS. The cultural implications such as patient non-compliance or denial of available routine medical care can potentially cause limitations on the ef- fectiveness of detecting such virulent pathogens and manage chronic disease. The lack of access to healthcare and further socioeconomic impacts hinder the ability to ade- quately diagnose and treat infection in resource-limited settings....
Show moreThe majority of HIV prevalence is found in Sub-Saharan Africa with 36.9 mil- lion living with HIV/AIDS. The cultural implications such as patient non-compliance or denial of available routine medical care can potentially cause limitations on the ef- fectiveness of detecting such virulent pathogens and manage chronic disease. The lack of access to healthcare and further socioeconomic impacts hinder the ability to ade- quately diagnose and treat infection in resource-limited settings. Intervention through diagnosis and treatment helps prevent the spread of transmission, where pre-exposure prophylaxis or active disease prevention measures are not readily available. The cur- rent gold standard for HIV detection is by molecular detection; Reverse-Transcription Polymerase Chain Reaction is widely used that employs cycles of temperature condi- tions that require a thermal cycling platform and typically laboratory space for RNA extraction separate from RT-PCR space required. Serological detection can be ad- vantageous for surveillance and screening, Lateral Flow Assays and Enzyme-Linked Immunosorbent Assay (ELISA) can detect a viral protein (antigen) or antibodies. The ELISA can require at least 12 hours of assay preparation and takes a diagnostic laboratory many resources to run. There is need to develop Point-of-Care (POC) testing that can potentially be used for decentralized testing that can leverage ex- isting technologies such as smart phone capability and routine medical or diagnostic tests with cutting edge applications leveraging micro uidics, nanotechnology and in- tegrated circuit design. Such technologies allow for automated, rapid turnaround and cost-e ective diagnosis of HIV, where these assays could potentially be read- ily deployed. It is such technology that can potentially change the way diagnostics are performed, as POC technology can be rapidly disseminated, enable decentralized testing and, is user-friendly. A novel smart phone-enabled automated magnetic bead- based platform was developed for a micro uidic ELISA for HIV-1 detection at the POC to meet this demand.
Show less - Date Issued
- 2017
- PURL
- http://purl.flvc.org/fau/fd/FA00005945
- Subject Headings
- Dissertations, Academic -- Florida Atlantic University
- Format
- Document (PDF)
- Title
- Development of a Wearable Device to Detect Epilepsy.
- Creator
- Khandnor Bakappa, Pradeepkumar, Agarwal, Ankur, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
This paper evaluates the effectiveness of a wearable device, developed by the author, to detect different types of epileptic seizures and monitor epileptic patients. The device uses GSR, Pulse, EMG, body temperature and 3-axis accelerometer sensors to detect epilepsy. The device first learns the signal patterns of the epileptic patient in ideal condition. The signal pattern generated during the epileptic seizure, which are distinct from other signal patterns, are detected and analyzed by the...
Show moreThis paper evaluates the effectiveness of a wearable device, developed by the author, to detect different types of epileptic seizures and monitor epileptic patients. The device uses GSR, Pulse, EMG, body temperature and 3-axis accelerometer sensors to detect epilepsy. The device first learns the signal patterns of the epileptic patient in ideal condition. The signal pattern generated during the epileptic seizure, which are distinct from other signal patterns, are detected and analyzed by the algorithms developed by the author. Based on an analysis, the device successfully detected different types of epileptic seizures. The author conducted an experiment on himself to determine the effectiveness of the device and the algorithms. Based on the simulation results, the algorithms are 100 percent accurate in detecting different types of epileptic seizures.
Show less - Date Issued
- 2017
- PURL
- http://purl.flvc.org/fau/fd/FA00004937, http://purl.flvc.org/fau/fd/FA00004937
- Subject Headings
- Epilepsy--Diagnosis--Technological innovations., Patient monitoring., Signal processing--Digital techniques., Wearable computers--Industrial applications.
- Format
- Document (PDF)
- Title
- Finite safety models for high-assurance systems.
- Creator
- Sloan, John C., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Preventing bad things from happening to engineered systems, demands improvements to how we model their operation with regard to safety. Safety-critical and fiscally-critical systems both demand automated and exhaustive verification, which is only possible if the models of these systems, along with the number of scenarios spawned from these models, are tractably finite. To this end, this dissertation ad dresses problems of a model's tractability and usefulness. It addresses the state space...
Show morePreventing bad things from happening to engineered systems, demands improvements to how we model their operation with regard to safety. Safety-critical and fiscally-critical systems both demand automated and exhaustive verification, which is only possible if the models of these systems, along with the number of scenarios spawned from these models, are tractably finite. To this end, this dissertation ad dresses problems of a model's tractability and usefulness. It addresses the state space minimization problem by initially considering tradeoffs between state space size and level of detail or fidelity. It then considers the problem of human interpretation in model capture from system artifacts, by seeking to automate model capture. It introduces human control over level of detail and hence state space size during model capture. Rendering that model in a manner that can guide human decision making is also addressed, as is an automated assessment of system timeliness. Finally, it addresses state compression and abstraction using logical fault models like fault trees, which enable exhaustive verification of larger systems by subsequent use of transition fault models like Petri nets, timed automata, and process algebraic expressions. To illustrate these ideas, this dissertation considers two very different applications - web service compositions and submerged ocean machinery.
Show less - Date Issued
- 2010
- PURL
- http://purl.flvc.org/FAU/2683206
- Subject Headings
- System failures (Engineering), Prevention, Sustainable engineering, Finite element method, Expert systems (Computer science)
- Format
- Document (PDF)
- Title
- Face Processing Using Mobile Devices.
- Creator
- James, Jhanon, Marques, Oge, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Image Processing and Computer Vision solutions have become commodities for software developers, thanks to the growing availability of Application Program- ming Interfaces (APIs) that encapsulate rich functionality, powered by advanced al- gorithms. To understand and create an e cient method to process faces in images by computers, one must understand how the human visual system processes them. Face processing by computers has been an active research area for about 50 years now. Face detection...
Show moreImage Processing and Computer Vision solutions have become commodities for software developers, thanks to the growing availability of Application Program- ming Interfaces (APIs) that encapsulate rich functionality, powered by advanced al- gorithms. To understand and create an e cient method to process faces in images by computers, one must understand how the human visual system processes them. Face processing by computers has been an active research area for about 50 years now. Face detection has become a commodity and is now incorporated into simple devices such as digital cameras and smartphones. An iOS app was implemented in Objective-C using Microsoft Cognitive Ser- vices APIs, as a tool for human vision and face processing research. Experimental work on image compression, upside-down orientation, the Thatcher e ect, negative inversion, high frequency, facial artifacts, caricatures and image degradation were completed on the Radboud and 10k US Adult Faces Databases along with other images.
Show less - Date Issued
- 2016
- PURL
- http://purl.flvc.org/fau/fd/FA00004770, http://purl.flvc.org/fau/fd/FA00004770
- Subject Headings
- Image processing--Digital techniques., Mobile communication systems., Mobile computing., Artificial intelligence., Human face recognition (Computer science), Computer vision., Optical pattern recognition.
- Format
- Document (PDF)
- Title
- Fuzzycuda: interactive matte extraction on a GPU.
- Creator
- Gibson, Joel, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Natural matte extraction is a difficult and generally unsolved problem. Generating a matte from a nonuniform background traditionally requires a tediously hand drawn matte. This thesis studies recent methods requiring the user to place only modest scribbles identifying the foreground and the background. This research demonstrates a new GPU-based implementation of the recently introduced Fuzzy- Matte algorithm. Interactive matte extraction was achieved on a CUDA enabled G80 graphics processor....
Show moreNatural matte extraction is a difficult and generally unsolved problem. Generating a matte from a nonuniform background traditionally requires a tediously hand drawn matte. This thesis studies recent methods requiring the user to place only modest scribbles identifying the foreground and the background. This research demonstrates a new GPU-based implementation of the recently introduced Fuzzy- Matte algorithm. Interactive matte extraction was achieved on a CUDA enabled G80 graphics processor. Experimental results demonstrate improved performance over the previous CPU based version. In depth analysis of experimental data from the GPU and the CPU implementations are provided. The design challenges of porting a variant of Dijkstra's shortest distance algorithm to a parallel processor are considered.
Show less - Date Issued
- 2008
- PURL
- http://purl.flvc.org/FAU/186288
- Subject Headings
- Computer graphics, Scientific applications, Information visualization, High performance computing, Real-time data processing
- Format
- Document (PDF)
- Title
- GAMIFICATION: A MONITORING SYSTEM FOR DIALYSIS PATIENTS.
- Creator
- Marella, Srivarsha, Agarwal, Ankur, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Dialysis patients are operated to have AV Fistula which is a joint junction of an artery and vein in the arm, operated to increase the blood flow through the dialyzer machine. AV- fistula is a type of vascular access which is a path into the body to connect/disconnect devices, but in this case, it is mainly Dialyzer. To reduce the failure rate during maturation period of AV Fistula, doctors recommend squeezing ball exercise as a necessary precaution for AV Fistula failure. Doing Squeezable...
Show moreDialysis patients are operated to have AV Fistula which is a joint junction of an artery and vein in the arm, operated to increase the blood flow through the dialyzer machine. AV- fistula is a type of vascular access which is a path into the body to connect/disconnect devices, but in this case, it is mainly Dialyzer. To reduce the failure rate during maturation period of AV Fistula, doctors recommend squeezing ball exercise as a necessary precaution for AV Fistula failure. Doing Squeezable interaction for about 3-4 times a day is recommended based on patient’s health condition. Hence, the proposed architecture adopts this squeezable exercise by embedding with sensor and measuring the angle at which the sensor is bent. The framework also proposes a new care coordination system having the hardware layer which has key components such as raspberry Pi, sensor which help in recording the pressure values when user presses the ball and software layer which solely focuses on data sync among the applications used by the user. It has been recorded that 53 % of patients having AV-Fistula fail because of negligence and lack of care. The maturation period is so critical and important which made us to build a gamification platform to monitor the exercise and track the activity through android application to keep users motivated and disciplined. In further chapters of the study will focus on different clinical like procedure around AV-Fistula and technical information such as different technologies used and implemented in the proposed system along with sensor circuit. This project goal is to present a way of monitoring patients and to keep track of the compliance whether the patient is active doing exercise daily. This way we are trying to present a care monitoring system for patients to help prevent AV Fistula failure.
Show less - Date Issued
- 2019
- PURL
- http://purl.flvc.org/fau/fd/FA00013331
- Subject Headings
- Gamification, Dialysis patients, Arteriovenous Fistula, Hemodialysis--Patients--Care, Patient monitoring
- Format
- Document (PDF)
- Title
- Efficient Implementations of Post-quantum Isogeny-based Cryptography.
- Creator
- Jalali, Amir, Azarderakhsh, Reza, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Quantum computers are envisioned to be able to solve mathematical problems which are currently unsolvable for conventional computers, because of their exceptional computational power from quantum mechanics. Therefore, if quantum computers are ever built in large scale, they will certainly be able to solve many classical exponential complexity problems such as the hard problems which the current public key cryptography is constructed upon. To counteract this problem, the design of post-quantum...
Show moreQuantum computers are envisioned to be able to solve mathematical problems which are currently unsolvable for conventional computers, because of their exceptional computational power from quantum mechanics. Therefore, if quantum computers are ever built in large scale, they will certainly be able to solve many classical exponential complexity problems such as the hard problems which the current public key cryptography is constructed upon. To counteract this problem, the design of post-quantum cryptography protocols is necessary to preserve the security in the presence of quantum adversaries. Regardless of whether we can estimate the exact time for the advent of the quantum computing era, security protocols are required to be resistant against potentially-malicious power of quantum computing. In this thesis, the main focus is on the sperformance improvement of one of the potential PQC candidates, isogeny-based cryptography. Several optimized implementations of cryptography applications based on this primitive are presented. From a general viewpoint, the proposed methods, implementation techniques and libraries have a practical impact on the performance evaluation of post-quantum cryptography schemes in a wide range of applications. In particular, the provided benchmarks and optimizations on ARM-powered processors provide a reference for comparison and evaluation of isogeny-based cryptography with other post-quantum candidates during the first round of NIST's PQC standardization process.
Show less - Date Issued
- 2018
- PURL
- http://purl.flvc.org/fau/fd/FA00013125
- Subject Headings
- Cryptography, Quantum computing, ARM microprocessors, Post-quantum cryptography
- Format
- Document (PDF)
- Title
- Ensemble Learning Algorithms for the Analysis of Bioinformatics Data.
- Creator
- Fazelpour, Alireza, Khoshgoftaar, Taghi M., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Developments in advanced technologies, such as DNA microarrays, have generated tremendous amounts of data available to researchers in the field of bioinformatics. These state-of-the-art technologies present not only unprecedented opportunities to study biological phenomena of interest, but significant challenges in terms of processing the data. Furthermore, these datasets inherently exhibit a number of challenging characteristics, such as class imbalance, high dimensionality, small dataset...
Show moreDevelopments in advanced technologies, such as DNA microarrays, have generated tremendous amounts of data available to researchers in the field of bioinformatics. These state-of-the-art technologies present not only unprecedented opportunities to study biological phenomena of interest, but significant challenges in terms of processing the data. Furthermore, these datasets inherently exhibit a number of challenging characteristics, such as class imbalance, high dimensionality, small dataset size, noisy data, and complexity of data in terms of hard to distinguish decision boundaries between classes within the data. In recognition of the aforementioned challenges, this dissertation utilizes a variety of machine-learning and data-mining techniques, such as ensemble classification algorithms in conjunction with data sampling and feature selection techniques to alleviate these problems, while improving the classification results of models built on these datasets. However, in building classification models researchers and practitioners encounter the challenge that there is not a single classifier that performs relatively well in all cases. Thus, numerous classification approaches, such as ensemble learning methods, have been developed to address this problem successfully in a majority of circumstances. Ensemble learning is a promising technique that generates multiple classification models and then combines their decisions into a single final result. Ensemble learning often performs better than single-base classifiers in performing classification tasks. This dissertation conducts thorough empirical research by implementing a series of case studies to evaluate how ensemble learning techniques can be utilized to enhance overall classification performance, as well as improve the generalization ability of ensemble models. This dissertation investigates ensemble learning techniques of the boosting, bagging, and random forest algorithms, and proposes a number of modifications to the existing ensemble techniques in order to improve further the classification results. This dissertation examines the effectiveness of ensemble learning techniques on accounting for challenging characteristics of class imbalance and difficult-to-learn class decision boundaries. Next, it looks into ensemble methods that are relatively tolerant to class noise, and not only can account for the problem of class noise, but improves classification performance. This dissertation also examines the joint effects of data sampling along with ensemble techniques on whether sampling techniques can further improve classification performance of built ensemble models.
Show less - Date Issued
- 2016
- PURL
- http://purl.flvc.org/fau/fd/FA00004588
- Subject Headings
- Bioinformatics., Data mining -- Technological innovations., Machine learning.
- Format
- Document (PDF)
- Title
- Enhancing performance in publish/subscribe systems.
- Creator
- Kamdar, Akshay., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Publish/subscribe is a powerful paradigm for distributed applications based on decoupled clients of information. In pub/sub applications, there exist a large amount of publishers and subscribes ranging from hundreds to millions. Publish/subscribe systems need to disseminate numerous events through a network of brokers. Due to limited resources of brokers, there may be lots of events that cannot be handled in time which in turn causes overload problem. Here arises the need of admission control...
Show morePublish/subscribe is a powerful paradigm for distributed applications based on decoupled clients of information. In pub/sub applications, there exist a large amount of publishers and subscribes ranging from hundreds to millions. Publish/subscribe systems need to disseminate numerous events through a network of brokers. Due to limited resources of brokers, there may be lots of events that cannot be handled in time which in turn causes overload problem. Here arises the need of admission control mechanism to provide guaranteed services in publish/subscribe systems. Our approach gives the solution to this overload problem in the network of brokers by limiting the incoming subscriptions by certain criteria. The criteria are the factors like resources which include bandwidth, CPU, memory (in broker network), resource requirements by the subscription.
Show less - Date Issued
- 2009
- PURL
- http://purl.flvc.org/FAU/329842
- Subject Headings
- Electronic data processing, Distributed processing, Embedded computer systems, Text processing (Computer science)
- Format
- Document (PDF)
- Title
- Enabling access for mobile devices to the web services resource framework.
- Creator
- Mangs, Jan Christian., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
The increasing availability of Web services and grid computing has made easier the access and reuse of different types of services. Web services provide network accessible interfaces to application functionality in a platform-independent manner. Developments in grid computing have led to the efficient distribution of computing resources and power through the use of stateful web services. At the same time, mobile devices as a platform of computing have become a ubiquitous, inexpensive, and...
Show moreThe increasing availability of Web services and grid computing has made easier the access and reuse of different types of services. Web services provide network accessible interfaces to application functionality in a platform-independent manner. Developments in grid computing have led to the efficient distribution of computing resources and power through the use of stateful web services. At the same time, mobile devices as a platform of computing have become a ubiquitous, inexpensive, and powerful computing resource. Concepts such as cloud computing has pushed the trend towards using grid concepts in the internet domain and are ideally suited for internet-supported mobile devices. Currently, there are a few complete implementations that leverage mobile devices as a member of a grid or virtual organization. This thesis presents a framework that enables the use of mobile devices to access stateful Web services on a Globus-based grid. To illustrate the presented framework, a user-friendly mobile application has been created that utilizes the framework libraries do to demonstrate the various functionalities that are accessible from any mobile device that supports Java ME.
Show less - Date Issued
- 2008
- PURL
- http://purl.flvc.org/FAU/186290
- Subject Headings
- User interfaces (Computer systems), Data structures (Computer science), Mobile computing, Security measures, Mobile communication systems, Computational grids (Computer systems)
- Format
- Document (PDF)
- Title
- Effects of gene selection and data sampling on prediction of breast cancer treatments.
- Creator
- Heredia, Brian, Khoshgoftaar, Taghi M., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
In recent years more and more researchers have begun to use data mining and machine learning tools to analyze gene microarray data. In this thesis we have collected a selection of datasets revolving around prediction of patient response in the specific area of breast cancer treatment. The datasets collected in this paper are all obtained from gene chips, which have become the industry standard in measurement of gene expression. In this thesis we will discuss the methods and procedures used in...
Show moreIn recent years more and more researchers have begun to use data mining and machine learning tools to analyze gene microarray data. In this thesis we have collected a selection of datasets revolving around prediction of patient response in the specific area of breast cancer treatment. The datasets collected in this paper are all obtained from gene chips, which have become the industry standard in measurement of gene expression. In this thesis we will discuss the methods and procedures used in the studies to analyze the datasets and their effects on treatment prediction with a particular interest in the selection of genes for predicting patient response. We will also analyze the datasets on our own in a uniform manner to determine the validity of these datasets in terms of learning potential and provide strategies for future work which explore how to best identify gene signatures.
Show less - Date Issued
- 2014
- PURL
- http://purl.flvc.org/fau/fd/FA00004292, http://purl.flvc.org/fau/fd/FA00004292
- Subject Headings
- Antineoplastic agents -- Development, Breast -- Cancer -- Treatment, Cancer -- Genetic aspects, DNA mircroarrays, Estimation theory, Gene expression
- Format
- Document (PDF)
- Title
- Fault tolerance and reliability patterns.
- Creator
- Buckley, Ingrid A., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
The need to achieve dependability in critical infrastructures has become indispensable for government and commercial enterprises. This need has become more necessary with the proliferation of malicious attacks on critical systems, such as healthcare, aerospace and airline applications. Additionally, due to the widespread use of web services in critical systems, the need to ensure their reliability is paramount. We believe that patterns can be used to achieve dependability. We conducted a...
Show moreThe need to achieve dependability in critical infrastructures has become indispensable for government and commercial enterprises. This need has become more necessary with the proliferation of malicious attacks on critical systems, such as healthcare, aerospace and airline applications. Additionally, due to the widespread use of web services in critical systems, the need to ensure their reliability is paramount. We believe that patterns can be used to achieve dependability. We conducted a survey of fault tolerance, reliability and web service products and patterns to better understand them. One objective of our survey is to evaluate the state of these patterns, and to investigate which standards are being used in products and their tool support. Our survey found that these patterns are insufficient, and many web services products do not use them. In light of this, we wrote some fault tolerance and web services reliability patterns and present an analysis of them.
Show less - Date Issued
- 2008
- PURL
- http://purl.flvc.org/FAU/166447
- Subject Headings
- Fault-tolerant computing, Computer software, Reliability, Reliability (Engineering), Computer programs
- Format
- Document (PDF)
- Title
- Design and implementation of driver drowsiness detection system.
- Creator
- Colic, Aleksandar, Marques, Oge, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
There is a substantial amount of evidence that suggests that driver drowsiness plays a significant role in road accidents. Alarming recent statistics are raising the interest in equipping vehicles with driver drowsiness detection systems. This dissertation describes the design and implementation of a driver drowsiness detection system that is based on the analysis of visual input consisting of the driver's face and eyes. The resulting system combines off-the-shelf software components for face...
Show moreThere is a substantial amount of evidence that suggests that driver drowsiness plays a significant role in road accidents. Alarming recent statistics are raising the interest in equipping vehicles with driver drowsiness detection systems. This dissertation describes the design and implementation of a driver drowsiness detection system that is based on the analysis of visual input consisting of the driver's face and eyes. The resulting system combines off-the-shelf software components for face detection, human skin color detection and eye state classification in a novel way. It follows a behavioral methodology by performing a non-invasive monitoring of external cues describing a driver's level of drowsiness. We look at this complex problem from a systems engineering point of view in order to go from a proof-of-concept prototype to a stable software framework. Our system utilizes two detection and analysis methods: (i) face detection with eye region extrapolation and (ii) eye state classification. Additionally, we use two confirmation processes - one based on custom skin color detection, the other based on nod detection - to make the system more robust and resilient while not sacrificing speed significantly. The system was designed to be dynamic and adaptable to conform to the current conditions and hardware capabilities.
Show less - Date Issued
- 2014
- PURL
- http://purl.flvc.org/fau/fd/FA00004275, http://purl.flvc.org/fau/fd/FA00004275
- Subject Headings
- Circadian rhythms, Computer vision, Driver assistance systems, Drowsy driving, Fatigue -- Prevention
- Format
- Document (PDF)
- Title
- Design of a power management model for a solar/fuel cell hybrid energy system.
- Creator
- Melendez, Rosana., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
This thesis proposes a Power Management Model (PMM) for optimization of several green power generation systems. A Photovoltaic/Fuel cell Hybrid Energy System (PFHES) consisting of solar cells, electrolyzer and fuel cell stack is utilized to meet a specific DC load bank for various applications. The Photovoltaic system is the primary power source to take advantage of renewable energy. The electrolyzer-fuel cell integration is used as a backup and as a hydrogen storage system with the different...
Show moreThis thesis proposes a Power Management Model (PMM) for optimization of several green power generation systems. A Photovoltaic/Fuel cell Hybrid Energy System (PFHES) consisting of solar cells, electrolyzer and fuel cell stack is utilized to meet a specific DC load bank for various applications. The Photovoltaic system is the primary power source to take advantage of renewable energy. The electrolyzer-fuel cell integration is used as a backup and as a hydrogen storage system with the different energy sources integrated through a DC link bus. An overall power management strategy is designed for the optimization of the power flows among the different energy sources. Extensive simulation experiments have been carried out to verify the system performance under PMM governing strategy. The simulation results indeed demonstrate the effectiveness of the proposed approach.
Show less - Date Issued
- 2010
- PURL
- http://purl.flvc.org/FAU/2705074
- Subject Headings
- Electric power systems, Building-integrated photovoltaic systems, Renewable energy sources, Hydrogen as fuel, Research
- Format
- Document (PDF)
- Title
- Determining the Effectiveness of Human Interaction in Human-in-the-Loop Systems by Using Mental States.
- Creator
- Lloyd, Eric, Huang, Shihong, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
A self-adaptive software is developed to predict the stock market. It’s Stock Prediction Engine functions autonomously when its skill-set suffices to achieve its goal, and it includes human-in-the-loop when it recognizes conditions benefiting from more complex, expert human intervention. Key to the system is a module that decides of human participation. It works by monitoring three mental states unobtrusively and in real time with Electroencephalography (EEG). The mental states are drawn from...
Show moreA self-adaptive software is developed to predict the stock market. It’s Stock Prediction Engine functions autonomously when its skill-set suffices to achieve its goal, and it includes human-in-the-loop when it recognizes conditions benefiting from more complex, expert human intervention. Key to the system is a module that decides of human participation. It works by monitoring three mental states unobtrusively and in real time with Electroencephalography (EEG). The mental states are drawn from the Opportunity-Willingness-Capability (OWC) model. This research demonstrates that the three mental states are predictive of whether the Human Computer Interaction System functions better autonomously (human with low scores on opportunity and/or willingness, capability) or with the human-in-the-loop, with willingness carrying the largest predictive power. This transdisciplinary software engineering research exemplifies the next step of self-adaptive systems in which human and computer benefit from optimized autonomous and cooperative interactions, and in which neural inputs allow for unobtrusive pre-interactions.
Show less - Date Issued
- 2016
- PURL
- http://purl.flvc.org/fau/fd/FA00004764, http://purl.flvc.org/fau/fd/FA00004764
- Subject Headings
- Cognitive neuroscience., Neural networks (Computer science), Pattern recognition systems., Artificial intelligence., Self-organizing systems., Human-computer interaction., Human information processing.
- Format
- Document (PDF)