Current Search: classification (x)
View All Items
Pages
- Title
- Classifying and Predicting Walking Speed From Electroencephalography Data.
- Creator
-
Rahrooh, Allen, Huang, Helen, Huang, Hsin-Hsiung, Samsam, Mohtashem, University of Central Florida
- Abstract / Description
-
Electroencephalography (EEG) non-invasively records electrocortical activity and can be used to understand how the brain functions to control movements and walking. Studies have shown that electrocortical dynamics are coupled with the gait cycle and change when walking at different speeds. Thus, EEG signals likely contain information regarding walking speed that could potentially be used to predict walking speed using just EEG signals recorded during walking. The purpose of this study was to...
Show moreElectroencephalography (EEG) non-invasively records electrocortical activity and can be used to understand how the brain functions to control movements and walking. Studies have shown that electrocortical dynamics are coupled with the gait cycle and change when walking at different speeds. Thus, EEG signals likely contain information regarding walking speed that could potentially be used to predict walking speed using just EEG signals recorded during walking. The purpose of this study was to determine whether walking speed could be predicted from EEG recorded as subjects walked on a treadmill with a range of speeds (0.5 m/s, 0.75 m/s, 1.0 m/s, 1.25 m/s, and self-paced). We first applied spatial Independent Component Analysis (sICA) to reduce temporal dimensionality and then used current popular classification methods: Bagging, Boosting, Random Forest, Na(&)#239;ve Bayes, Logistic Regression, and Support Vector Machines with a linear and radial basis function kernel. We evaluated the precision, sensitivity, and specificity of each classifier. Logistic regression had the highest overall performance (76.6 +/- 13.9%), and had the highest precision (86.3 +/- 11.7%) and sensitivity (88.7 +/- 8.7%). The Support Vector Machine with a radial basis function kernel had the highest specificity (60.7 +/- 39.1%). These overall performance values are relatively good since the EEG data had only been high-pass filtered with a 1 Hz cutoff frequency and no extensive cleaning methods were performed. All of the classifiers had an overall performance of at least 68% except for the Support Vector Machine with a linear kernel, which had an overall performance of 55.4%. These results suggest that applying spatial Independent Component Analysis to reduce temporal dimensionality of EEG signals does not significantly impair the classification of walking speed using EEG and that walking speeds can be predicted from EEG data.
Show less - Date Issued
- 2019
- Identifier
- CFE0007517, ucf:52642
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007517
- Title
- Bayesian Model Selection for Classification with Possibly Large Number of Groups.
- Creator
-
Davis, Justin, Pensky, Marianna, Swanson, Jason, Richardson, Gary, Crampton, William, Ni, Liqiang, University of Central Florida
- Abstract / Description
-
The purpose of the present dissertation is to study model selection techniques which are specifically designed for classification of high-dimensional data with a large number of classes. To the best of our knowledge, this problem has never been studied in depth previously. We assume that the number of components p is much larger than the number of samples n, and that only few of those p components are useful for subsequent classification. In what follows, we introduce two Bayesian models...
Show moreThe purpose of the present dissertation is to study model selection techniques which are specifically designed for classification of high-dimensional data with a large number of classes. To the best of our knowledge, this problem has never been studied in depth previously. We assume that the number of components p is much larger than the number of samples n, and that only few of those p components are useful for subsequent classification. In what follows, we introduce two Bayesian models which use two different approaches to the problem: one which discards components which have "almost constant" values (Model 1) and another which retains the components for which between-group variations are larger than within-group variation (Model 2). We show that particular cases of the above two models recover familiar variance or ANOVA-based component selection. When one has only two classes and features are a priori independent, Model 2 reduces to the Feature Annealed Independence Rule (FAIR) introduced by Fan and Fan (2008) and can be viewed as a natural generalization to the case of L (>) 2 classes. A nontrivial result of the dissertation is that the precision of feature selection using Model 2 improves when the number of classes grows. Subsequently, we examine the rate of misclassification with and without feature selection on the basis of Model 2.
Show less - Date Issued
- 2011
- Identifier
- CFE0004097, ucf:49091
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004097
- Title
- SELF DESIGNING PATTERN RECOGNITION SYSTEM EMPLOYING MULTISTAGE CLASSIFICATION.
- Creator
-
ABDELWAHAB, MANAL MAHMOUD, Mikhael, Wasfy, University of Central Florida
- Abstract / Description
-
Recently, pattern recognition/classification has received a considerable attention in diverse engineering fields such as biomedical imaging, speaker identification, fingerprint recognition, etc. In most of these applications, it is desirable to maintain the classification accuracy in the presence of corrupted and/or incomplete data. The quality of a given classification technique is measured by the computational complexity, execution time of algorithms, and the number of patterns that can be...
Show moreRecently, pattern recognition/classification has received a considerable attention in diverse engineering fields such as biomedical imaging, speaker identification, fingerprint recognition, etc. In most of these applications, it is desirable to maintain the classification accuracy in the presence of corrupted and/or incomplete data. The quality of a given classification technique is measured by the computational complexity, execution time of algorithms, and the number of patterns that can be classified correctly despite any distortion. Some classification techniques that are introduced in the literature are described in Chapter one.In this dissertation, a pattern recognition approach that can be designed to have evolutionary learning by developing the features and selecting the criteria that are best suited for the recognition problem under consideration is proposed. Chapter two presents some of the features used in developing the set of criteria employed by the system to recognize different types of signals. It also presents some of the preprocessing techniques used by the system. The system operates in two modes, namely, the learning (training) mode, and the running mode. In the learning mode, the original and preprocessed signals are projected into different transform domains. The technique automatically tests many criteria over the range of parameters for each criterion. A large number of criteria are developed from the features extracted from these domains. The optimum set of criteria, satisfying specific conditions, is selected. This set of criteria is employed by the system to recognize the original or noisy signals in the running mode. The modes of operation and the classification structures employed by the system are described in details in Chapter three.The proposed pattern recognition system is capable of recognizing an enormously large number of patterns by virtue of the fact that it analyzes the signal in different domains and explores the distinguishing characteristics in each of these domains. In other words, this approach uses available information and extracts more characteristics from the signals, for classification purposes, by projecting the signal in different domains. Some experimental results are given in Chapter four showing the effect of using mathematical transforms in conjunction with preprocessing techniques on the classification accuracy. A comparison between some of the classification approaches, in terms of classification rate in case of distortion, is also given.A sample of experimental implementations is presented in chapter 5 and chapter 6 to illustrate the performance of the proposed pattern recognition system. Preliminary results given confirm the superior performance of the proposed technique relative to the single transform neural network and multi-input neural network approaches for image classification in the presence of additive noise.
Show less - Date Issued
- 2004
- Identifier
- CFE0000020, ucf:46077
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000020
- Title
- Methods for online feature selection for classification problems.
- Creator
-
Razmjoo, Alaleh, Zheng, Qipeng, Rabelo, Luis, Boginski, Vladimir, Xanthopoulos, Petros, University of Central Florida
- Abstract / Description
-
Online learning is a growing branch of machine learning which allows all traditional data miningtechniques to be applied on an online stream of data in real-time. In this dissertation, we presentthree efficient algorithms for feature ranking in online classification problems. Each of the methodsare tailored to work well with different types of classification tasks and have different advantages.The reason for this variety of algorithms is that like other machine learning solutions, there is...
Show moreOnline learning is a growing branch of machine learning which allows all traditional data miningtechniques to be applied on an online stream of data in real-time. In this dissertation, we presentthree efficient algorithms for feature ranking in online classification problems. Each of the methodsare tailored to work well with different types of classification tasks and have different advantages.The reason for this variety of algorithms is that like other machine learning solutions, there is usuallyno algorithm which works well for all types of tasks. The first method, is an online sensitivitybased feature ranking (SFR) which is updated incrementally, and is designed for classificationtasks with continuous features. We take advantage of the concept of global sensitivity and rankfeatures based on their impact on the outcome of the classification model. In the feature selectionpart, we use a two-stage filtering method in order to first eliminate highly correlated and redundantfeatures and then eliminate irrelevant features in the second stage. One important advantage of ouralgorithm is its generality, which means the method works for correlated feature spaces withoutpreprocessing. It can be implemented along with any single-pass online classification method withseparating hyperplane such as SVMs. In the second method, with help of probability theory wepropose an algorithm which measures the importance of the features by observing the changes inlabel prediction in case of feature substitution. A non-parametric version of the proposed methodis presented to eliminate the distribution type assumptions. These methods are application to alldata types including mixed feature spaces. At last, we present a class-based feature importanceranking method which evaluates the importance of each feature for each class, these sub-rankingsare further exploited to train an ensemble of classifiers. The proposed methods will be thoroughlytested using benchmark datasets and the results will be discussed in the last chapter.
Show less - Date Issued
- 2018
- Identifier
- CFE0007584, ucf:52567
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007584
- Title
- Vehicle Tracking and Classification via 3D Geometries for Intelligent Transportation Systems.
- Creator
-
Mcdowell, William, Mikhael, Wasfy, Jones, W Linwood, Haralambous, Michael, Atia, George, Mahalanobis, Abhijit, Muise, Robert, University of Central Florida
- Abstract / Description
-
In this dissertation, we present generalized techniques which allow for the tracking and classification of vehicles by tracking various Point(s) of Interest (PoI) on a vehicle. Tracking the various PoI allows for the composition of those points into 3D geometries which are unique to a given vehicle type. We demonstrate this technique using passive, simulated image based sensor measurements and three separate inertial track formulations. We demonstrate the capability to classify the 3D...
Show moreIn this dissertation, we present generalized techniques which allow for the tracking and classification of vehicles by tracking various Point(s) of Interest (PoI) on a vehicle. Tracking the various PoI allows for the composition of those points into 3D geometries which are unique to a given vehicle type. We demonstrate this technique using passive, simulated image based sensor measurements and three separate inertial track formulations. We demonstrate the capability to classify the 3D geometries in multiple transform domains (PCA (&) LDA) using Minimum Euclidean Distance, Maximum Likelihood and Artificial Neural Networks. Additionally, we demonstrate the ability to fuse separate classifiers from multiple domains via Bayesian Networks to achieve ensemble classification.
Show less - Date Issued
- 2015
- Identifier
- CFE0005976, ucf:50790
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005976
- Title
- a priori synthetic sampling for increasing classification sensitivity in imbalanced data sets.
- Creator
-
Rivera, William, Xanthopoulos, Petros, Wiegand, Rudolf, Karwowski, Waldemar, Kincaid, John, University of Central Florida
- Abstract / Description
-
Building accurate classifiers for predicting group membership is made difficult when data is skewedor imbalanced which is typical of real world data sets. The classifier has the tendency to be biased towards the over represented group as a result. This imbalance is considered a class imbalance problem which will induce bias into the classifier particularly when the imbalance is high.Class imbalance data usually suffers from data intrinsic properties beyond that of imbalance alone.The problem...
Show moreBuilding accurate classifiers for predicting group membership is made difficult when data is skewedor imbalanced which is typical of real world data sets. The classifier has the tendency to be biased towards the over represented group as a result. This imbalance is considered a class imbalance problem which will induce bias into the classifier particularly when the imbalance is high.Class imbalance data usually suffers from data intrinsic properties beyond that of imbalance alone.The problem is intensified with larger levels of imbalance most commonly found in observationalstudies. Extreme cases of class imbalance are commonly found in many domains including frauddetection, mammography of cancer and post term births. These rare events are usually the mostcostly or have the highest level of risk associated with them and are therefore of most interest.To combat class imbalance the machine learning community has relied upon embedded, data preprocessing and ensemble learning approaches. Exploratory research has linked several factorsthat perpetuate the issue of misclassification in class imbalanced data. However, there remainsa lack of understanding between the relationship of the learner and imbalanced data among thecompeting approaches. The current landscape of data preprocessing approaches have appeal dueto the ability to divide the problem space in two which allows for simpler models. However, mostof these approaches have little theoretical bases although in some cases there is empirical evidence supporting the improvement.The main goals of this research is to introduce newly proposed a priori based re-sampling methodsthat improve concept learning within class imbalanced data. The results in this work highlightthe robustness of these techniques performance within publicly available data sets from differentdomains containing various levels of imbalance. In this research the theoretical and empiricalreasons are explored and discussed.
Show less - Date Issued
- 2015
- Identifier
- CFE0006169, ucf:51129
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006169
- Title
- A MACHINE LEARNING APPROACH TO ASSESS THE SEPARATION OF SEISMOCARDIOGRAPHIC SIGNALS BY RESPIRATION.
- Creator
-
Solar, Brian, Mansy, Hansen, University of Central Florida
- Abstract / Description
-
The clinical usage of Seismocardiography (SCG) is increasing as it is being shown to be an effective non-invasive measurement for heart monitoring. SCG measures the vibrational activity at the chest surface and applications include non-invasive assessment of myocardial contractility and systolic time intervals. Respiratory activity can also affect the SCG signal by changing the hemodynamic characteristics of cardiac activity and displacing the position of the heart. Other clinically...
Show moreThe clinical usage of Seismocardiography (SCG) is increasing as it is being shown to be an effective non-invasive measurement for heart monitoring. SCG measures the vibrational activity at the chest surface and applications include non-invasive assessment of myocardial contractility and systolic time intervals. Respiratory activity can also affect the SCG signal by changing the hemodynamic characteristics of cardiac activity and displacing the position of the heart. Other clinically significant information, such as systolic time intervals, can thus manifest themselves differently in an SCG signal during inspiration and expiration. Grouping SCG signals into their respective respiratory cycle can mitigate this issue. Prior research has focused on developing machine learning classification methods to classify SCG events as according to their respiration cycle. However, recent research at the Biomedical Acoustics Research Laboratory (BARL) at UCF suggests grouping SCG signals into high and low lung volume may be more effective. This research aimed at com- paring the efficiency of grouping SCG signals according to their respiration and lung volume phase and also developing a method to automatically identify the respiration and lung volume phase of SCG events.
Show less - Date Issued
- 2018
- Identifier
- CFH2000310, ucf:45877
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH2000310
- Title
- AN ADAPTIVE MULTIOBJECTIVE EVOLUTIONARY APPROACH TO OPTIMIZE ARTMAP NEURAL NETWORKS.
- Creator
-
Kaylani, Assem, Georgiopoulos, Michael, University of Central Florida
- Abstract / Description
-
This dissertation deals with the evolutionary optimization of ART neural network architectures. ART (adaptive resonance theory) was introduced by a Grossberg in 1976. In the last 20 years (1987-2007) a number of ART neural network architectures were introduced into the literature (Fuzzy ARTMAP (1992), Gaussian ARTMAP (1996 and 1997) and Ellipsoidal ARTMAP (2001)). In this dissertation, we focus on the evolutionary optimization of ART neural network architectures with the intent of optimizing...
Show moreThis dissertation deals with the evolutionary optimization of ART neural network architectures. ART (adaptive resonance theory) was introduced by a Grossberg in 1976. In the last 20 years (1987-2007) a number of ART neural network architectures were introduced into the literature (Fuzzy ARTMAP (1992), Gaussian ARTMAP (1996 and 1997) and Ellipsoidal ARTMAP (2001)). In this dissertation, we focus on the evolutionary optimization of ART neural network architectures with the intent of optimizing the size and the generalization performance of the ART neural network. A number of researchers have focused on the evolutionary optimization of neural networks, but no research has been performed on the evolutionary optimization of ART neural networks, prior to 2006, when Daraiseh has used evolutionary techniques for the optimization of ART structures. This dissertation extends in many ways and expands in different directions the evolution of ART architectures, such as: (a) uses a multi-objective optimization of ART structures, thus providing to the user multiple solutions (ART networks) with varying degrees of merit, instead of a single solution (b) uses GA parameters that are adaptively determined throughout the ART evolution, (c) identifies a proper size of the validation set used to calculate the fitness function needed for ART's evolution, thus speeding up the evolutionary process, (d) produces experimental results that demonstrate the evolved ART's effectiveness (good accuracy and small size) and efficiency (speed) compared with other competitive ART structures, as well as other classifiers (CART (Classification and Regression Trees) and SVM (Support Vector Machines)). The overall methodology to evolve ART using a multi-objective approach, the chromosome representation of an ART neural network, the genetic operators used in ART's evolution, and the automatic adaptation of some of the GA parameters in ART's evolution could also be applied in the evolution of other exemplar based neural network classifiers such as the probabilistic neural network and the radial basis function neural network.
Show less - Date Issued
- 2008
- Identifier
- CFE0002212, ucf:47907
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002212
- Title
- The Perceptual and Decisional Basis of Emotion Identification in Creative Writing.
- Creator
-
Williams, Sarah, Bohil, Corey, Hancock, Peter, Smither, Janan, Johnson, Dan, University of Central Florida
- Abstract / Description
-
The goal of this research was to assess the ability of readers to determine the emotion of a passage of text, be it fictional or non-fictional. The research includes examining how genre (fiction and non-fiction) and emotion (positive emotion, such as happiness, and negative emotion, such as anger) interact to form a reading experience. Reading is an activity that many, if not most, humans undertake in either a professional or leisure capacity. Researchers are thus interested in the effect...
Show moreThe goal of this research was to assess the ability of readers to determine the emotion of a passage of text, be it fictional or non-fictional. The research includes examining how genre (fiction and non-fiction) and emotion (positive emotion, such as happiness, and negative emotion, such as anger) interact to form a reading experience. Reading is an activity that many, if not most, humans undertake in either a professional or leisure capacity. Researchers are thus interested in the effect reading has on the individual, particularly with regards to empathy. Some researchers believe reading fosters empathy; others think empathy might already be present in those who enjoy reading. A greater understanding of this dispute could be provided by general recognition theory (GRT). GRT allows researchers to investigate how stimulus dimensions interact in an observer's mind: on a perceptual or decisional level. In the context of reading, this allows researchers to look at how emotion is tied in with (or inseparable from) genre, or if the ability to determine the emotion of a passage is independent from the genre of the passage. In the reported studies, participants read passages and responded to questions on the passages and their content. Empathy scores significantly predicted discriminability of passage categories, as did reported hours spent reading per week. Non-fiction passages were easier to identify than fiction, and positive emotion classification was affiliated with non-fiction classification.
Show less - Date Issued
- 2019
- Identifier
- CFE0007877, ucf:52760
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007877
- Title
- Characterization, Classification, and Genesis of Seismocardiographic Signals.
- Creator
-
Taebi, Amirtaha, Mansy, Hansen, Kassab, Alain, Huang, Helen, Vosoughi, Azadeh, University of Central Florida
- Abstract / Description
-
Seismocardiographic (SCG) signals are the acoustic and vibration induced by cardiac activity measured non-invasively at the chest surface. These signals may offer a method for diagnosing and monitoring heart function. Successful classification of SCG signals in health and disease depends on accurate signal characterization and feature extraction.In this study, SCG signal features were extracted in the time, frequency, and time-frequency domains. Different methods for estimating time-frequency...
Show moreSeismocardiographic (SCG) signals are the acoustic and vibration induced by cardiac activity measured non-invasively at the chest surface. These signals may offer a method for diagnosing and monitoring heart function. Successful classification of SCG signals in health and disease depends on accurate signal characterization and feature extraction.In this study, SCG signal features were extracted in the time, frequency, and time-frequency domains. Different methods for estimating time-frequency features of SCG were investigated. Results suggested that the polynomial chirplet transform outperformed wavelet and short time Fourier transforms.Many factors may contribute to increasing intrasubject SCG variability including subject posture and respiratory phase. In this study, the effect of respiration on SCG signal variability was investigated. Results suggested that SCG waveforms can vary with lung volume, respiratory flow direction, or a combination of these criteria. SCG events were classified into groups belonging to these different respiration phases using classifiers, including artificial neural networks, support vector machines, and random forest. Categorizing SCG events into different groups containing similar events allows more accurate estimation of SCG features.SCG feature points were also identified from simultaneous measurements of SCG and other well-known physiologic signals including electrocardiography, phonocardiography, and echocardiography. Future work may use this information to get more insights into the genesis of SCG.
Show less - Date Issued
- 2018
- Identifier
- CFE0007106, ucf:51944
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007106
- Title
- Motor imagery classification using sparse representation of EEG signals.
- Creator
-
Saidi, Pouria, Atia, George, Vosoughi, Azadeh, Berman, Steven, University of Central Florida
- Abstract / Description
-
The human brain is unquestionably the most complex organ of the body as it controls and processes its movement and senses. A healthy brain is able to generate responses to the signals it receives, and transmit messages to the body. Some neural disorders can impair the communication between the brain and the body preventing the transmission of these messages. Brain Computer Interfaces (BCIs) are devices that hold immense potential to assist patients with such disorders by analyzing brain...
Show moreThe human brain is unquestionably the most complex organ of the body as it controls and processes its movement and senses. A healthy brain is able to generate responses to the signals it receives, and transmit messages to the body. Some neural disorders can impair the communication between the brain and the body preventing the transmission of these messages. Brain Computer Interfaces (BCIs) are devices that hold immense potential to assist patients with such disorders by analyzing brain signals, translating and classifying various brain responses, and relaying them to external devices and potentially back to the body. Classifying motor imagery brain signals where the signals are obtained based on imagined movement of the limbs is a major, yet very challenging, step in developing Brain Computer Interfaces (BCIs). Of primary importance is to use less data and computationally efficient algorithms to support real-time BCI. To this end, in this thesis we explore and develop algorithms that exploit the sparse characteristics of EEGs to classify these signals. Different feature vectors are extracted from EEG trials recorded by electrodes placed on the scalp.In this thesis, features from a small spatial region are approximated by a sparse linear combination of few atoms from a multi-class dictionary constructed from the features of the EEG training signals for each class. This is used to classify the signals based on the pattern of their sparse representation using a minimum-residual decision rule.We first attempt to use all the available electrodes to verify the effectiveness of the proposed methods. To support real time BCI, the electrodes are reduced to those near the sensorimotor cortex which are believed to be crucial for motor preparation and imagination.In a second approach, we try to incorporate the effect of spatial correlation across the neighboring electrodes near the sensorimotor cortex. To this end, instead of considering one feature vector at a time, we use a collection of feature vectors simultaneously to find the joint sparse representation of these vectors. Although we were not able to see much improvement with respect to the first approach, we envision that such improvements could be achieved using more refined models that can be subject of future works. The performance of the proposed approaches is evaluated using different features, including wavelet coefficients, energy of the signals in different frequency sub-bands, and also entropy of the signals. The results obtained from real data demonstrate that the combination of energy and entropy features enable efficient classification of motor imagery EEG trials related to hand and foot movements. This underscores the relevance of the energies and their distribution in different frequency sub-bands for classifying movement-specific EEG patterns in agreement with the existence of different levels within the alpha band. The proposed approach is also shown to outperform the state-of-the-art algorithm that uses feature vectors obtained from energies of multiple spatial projections.
Show less - Date Issued
- 2015
- Identifier
- CFE0005882, ucf:50884
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005882
- Title
- Classification of Silicone-Based Personal and Condom Lubricants Using DART-TOFMS.
- Creator
-
Harvey, Lauren, Bridge, Candice, Sigman, Michael, Campiglia, Andres, Yestrebsky, Cherie, University of Central Florida
- Abstract / Description
-
Sexual lubricants are used to enable sexual encounters. There are different types of sexual lubricants such as water-based, oil-based, and silicone-based. They come pre-applied to condoms and separately in bottles as personal lubricants. Although sexual lubricants are intended for consensual use, they are also unfortunately used during the commission of sexual assaults. The analysis of sexual lubricants facilitates sexual assault investigations. With the increased usage of condoms in sexual...
Show moreSexual lubricants are used to enable sexual encounters. There are different types of sexual lubricants such as water-based, oil-based, and silicone-based. They come pre-applied to condoms and separately in bottles as personal lubricants. Although sexual lubricants are intended for consensual use, they are also unfortunately used during the commission of sexual assaults. The analysis of sexual lubricants facilitates sexual assault investigations. With the increased usage of condoms in sexual assault cases, the potential of collected DNA evidence in each case is reduced. In the absence of biological evidence, the presence of sexual lubricants after a sexual assault can provide an additional link between a suspect and the crime scene and/or victim. Having the ability to compare known and unknown sexual lubricants may be the only actionable information available for investigators. Current lubricant analysis only classifies samples into lubricant types based on the major component such as glycerol, petrolatum, and polydimethylsiloxane for water-based, oil-based, and silicone-based lubricants respectively. Differentiation within major types has not been explored. Previously, protocols have been developed to detect and categorize personal lubricants using Fourier transform infrared (FTIR) spectroscopy, gas chromatography-mass spectrometry (GC-MS), liquid chromatography mass spectrometry (LC-MS), and pyrolysis GC-MS. FTIR is routinely used as a screening tool to detect peaks of the major lubricant components and the mass spectrometry (MS) techniques are commonly used to confirm the presence of some of the major components, excluding PDMS.This thesis focused on the differentiation of silicone-based personal and condom lubricants because it is a common type of lubricant due to its ability to reduce friction for a longer period of time. Fifty-six (56) silicone personal and condom lubricants were analyzed to identify unique characteristics that can be used to determine individual sub-classes and test those sub-classes. Direct analysis in real time-time of flight mass spectrometry (DART-TOFMS) was utilized because minor and unique molecular ions that could be attributed to different sub-groups can easily be distinguished from the major sample peaks. This is primarily based on the direct mass spectrometry design of the instrumentation that can differentiate minor components from major components that might not be observed using traditional chromatographic separation. The DART source creates molecular ions for individual components in mixed samples under atmospheric conditions in either positive or negative mode. The TOF-MS, which is capable of high resolution and accurate mass analysis, allows more accurate and precise detection of molecular component ions. Additionally, no sample preparation is required to analyze neat samples, which minimizes potential contamination issues. Attenuated total reflectance-FTIR (ATR-FIR) was used to analyze the training set personal lubricants to compare previous methods of analysis to the newly developed DART-TOFMS method of analysis.Principle component analysis (PCA) and cluster analysis were used to identify potential sub-groups and subsequently a classification scheme. Linear discriminant analysis was utilized to conduct leave one out cross validation and to categorize test samples. Eight sub-groups were developed based on the presence and/or absence of PDMS and minor component peaks observed.A classification scheme was developed using the eight sub-groups identified through PCA and cluster analysis. This classification scheme was tested using LDA to classify blind samples. One group includes a scented personal lubricant. Another group includes flavored condom lubricants. The other groups were developed based on the relative intensity of PDMS peaks and minor component peaks. Variation of the intensity of PDMS peaks between and within samples of different lot numbers causes some misclassification of samples. This classification scheme also doesn't take into account real-world factors such as dilution and biodegradation. Although further research is required to create a more stable classification scheme, the identified sub-groups are a good foundation for the creation of a lubricant database and finalized classification scheme.
Show less - Date Issued
- 2016
- Identifier
- CFE0006459, ucf:51415
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006459
- Title
- A PREDICTIVE MODEL FOR BENCHMARKING ACADEMIC PROGRAMS (PBAP)USING U.S. NEWS RANKING DATA FOR ENGINEERING COLLEGES OFFERING GRADUATE PROGRAMS.
- Creator
-
Chuck, Lisa, Tubbs, LeVester, University of Central Florida
- Abstract / Description
-
Improving national ranking is an increasingly important issue for university administrators. While research has been conducted on performance measures in higher education, research designs have lacked a predictive quality. Studies on the U.S. News college rankings have provided insight into the methodology; however, none of them have provided a model to predict what change in variable values would likely cause an institution to improve its standing in the rankings. The purpose of this study...
Show moreImproving national ranking is an increasingly important issue for university administrators. While research has been conducted on performance measures in higher education, research designs have lacked a predictive quality. Studies on the U.S. News college rankings have provided insight into the methodology; however, none of them have provided a model to predict what change in variable values would likely cause an institution to improve its standing in the rankings. The purpose of this study was to develop a predictive model for benchmarking academic programs (pBAP) for engineering colleges. The 2005 U.S. News ranking data for graduate engineering programs were used to create a four-tier predictive model (pBAP). The pBAP model correctly classified 81.9% of the cases in their respective tier. To test the predictive accuracy of the pBAP model, the 2005 U.S .News data were entered into the pBAP variate developed using the 2004 U.S. News data. The model predicted that 88.9% of the institutions would remain in the same ranking tier in the 2005 U.S. News rankings (compared with 87.7% in the actual data), and 11.1% of the institutions would demonstrate tier movement (compared with an actual 12.3% movement in the actual data). The likelihood of improving an institution's standing in the rankings was greater when increasing the values of 3 of the 11 variables in the U.S. News model: peer assessment score, recruiter assessment score, and research expenditures.
Show less - Date Issued
- 2005
- Identifier
- CFE0000431, ucf:46377
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000431
- Title
- A PREDICTIVE MODEL FOR BENCHMARKING ACADEMIC PROGRAMS (PBAP) USING U.S. NEWS RANKING DATA FOR ENGINEERING COLLEGES OFFERING GRADUATE PROGRAMS.
- Creator
-
Chuck, Lisa, Tubbs, LeVester, University of Central Florida
- Abstract / Description
-
Improving national ranking is an increasingly important issue for university administrators. While research has been conducted on performance measures in higher education, research designs have lacked a predictive quality. Studies on the U.S. News college rankings have provided insight into the methodology; however, none of them have provided a model to predict what change in variable values would likely cause an institution to improve its standing in the rankings. The purpose of this study...
Show moreImproving national ranking is an increasingly important issue for university administrators. While research has been conducted on performance measures in higher education, research designs have lacked a predictive quality. Studies on the U.S. News college rankings have provided insight into the methodology; however, none of them have provided a model to predict what change in variable values would likely cause an institution to improve its standing in the rankings. The purpose of this study was to develop a predictive model for benchmarking academic programs (pBAP) for engineering colleges. The 2005 U.S. News ranking data for graduate engineering programs were used to create a four-tier predictive model (pBAP). The pBAP model correctly classified 81.9% of the cases in their respective tier. To test the predictive accuracy of the pBAP model, the 2005 U.S .News data were entered into the pBAP variate developed using the 2004 U.S. News data. The model predicted that 88.9% of the institutions would remain in the same ranking tier in the 2005 U.S. News rankings (compared with 87.7% in the actual data), and 11.1% of the institutions would demonstrate tier movement (compared with an actual 12.3% movement in the actual data). The likelihood of improving an institution's standing in the rankings was greater when increasing the values of 3 of the 11 variables in the U.S. News model: peer assessment score, recruiter assessment score, and research expenditures.
Show less - Date Issued
- 2005
- Identifier
- CFE0000576, ucf:46422
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000576
- Title
- THE EFFECT OF MISMATCH PRIMERS ON THE EFFICIENCY OF AMPLIFICATION IN QUANTITATIVE POLYMERASE CHAIN REACTIONS.
- Creator
-
Dawkins, Molly C, Moore, Sean, University of Central Florida
- Abstract / Description
-
Polymerase chain reaction (PCR) is a method used in many research protocols to amplify a small amount of a short segment of DNA to millions of copies. PCR is used for many taxonomic studies, as well as for some medical diagnostic procedures. Through PCR, short DNA primers bind to the template DNA to allow the thermostable DNA polymerase to copy the DNA. Often, researchers create universal primers to target a conserved region of DNA in multiple species, for example, the 16S rRNA gene in...
Show morePolymerase chain reaction (PCR) is a method used in many research protocols to amplify a small amount of a short segment of DNA to millions of copies. PCR is used for many taxonomic studies, as well as for some medical diagnostic procedures. Through PCR, short DNA primers bind to the template DNA to allow the thermostable DNA polymerase to copy the DNA. Often, researchers create universal primers to target a conserved region of DNA in multiple species, for example, the 16S rRNA gene in bacteria. The problem with these universal primers is that they do not always perfectly match the target DNA. The mismatch primers can still bind to the template, but could affect the efficiency of the PCR amplification. The effect of mismatch primers on the efficiency of the amplification in PCR is the focus of this thesis. Four forward primers with various mismatch overhangs were generated and incorporated into a DNA template through an initial PCR. These primers contained the binding region complementary to the V3/V4 region of the 16S rRNA bacterial gene. Further quantitative PCR (qPCR) reactions were run on these newly-made templates using two sets of primers complementary to the 16S rRNA gene region – one with ambiguous base pairs, one with unambiguous base pairs. The qPCR amplification curves, the Cq values, and the initial concentrations of DNA products (seed values) were analyzed and compared. The results showed differences in the Cq values and seed values between the reactions containing mismatches and those not containing mismatches. Other variables including annealing temperature, addition of Illumina sequencing tails to the primers, and initial primer concentration were also tested to determine if these variables had an effect on the amplification. The results from these reactions using different variables were inconclusive.
Show less - Date Issued
- 2018
- Identifier
- CFH2000361, ucf:45761
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH2000361
- Title
- DEVELOPMENT OF A WEIGH-IN-MOTION SYSTEM USING ACOUSTIC EMISSION SENSORS.
- Creator
-
Bowie, Jeanne, Radwan, Essam, University of Central Florida
- Abstract / Description
-
This dissertation proposes a system for weighing commercial vehicles in motion using acoustic emission sensors attached to a metal bar placed across the roadway. The signal from the sensors is analyzed by a computer and the vehicle weight is determined by a statistical model which correlates the acoustic emission parameters to the vehicle weight. Such a system would be portable and low-cost, allowing for the measurement of vehicle weights in much the same way commercial tube and radar...
Show moreThis dissertation proposes a system for weighing commercial vehicles in motion using acoustic emission sensors attached to a metal bar placed across the roadway. The signal from the sensors is analyzed by a computer and the vehicle weight is determined by a statistical model which correlates the acoustic emission parameters to the vehicle weight. Such a system would be portable and low-cost, allowing for the measurement of vehicle weights in much the same way commercial tube and radar counters routinely collect vehicle speed and count. The system could be used to collect vehicle speed and count data as well as weight information. Acoustic emissions are naturally occurring elastic waves produced by the rapid release of energy within a material. They are caused by deformation or fracturing of a solid due to thermal or mechanical stress. Acoustic emission sensors have been developed to detect these waves and computer software and hardware have been developed to analyze and provide information about the waveforms. Acoustic emission testing is a common form of nondestructive testing and is used for pressure vessel testing, leak detection, machinery monitoring, structural integrity monitoring, and weld monitoring, among other things (Miller, 1987). For this dissertation, acoustic emission parameters were correlated to the load placed on the metal test bar to determine the feasibility of using a metal test bar to measure the weight of a vehicle in motion. Several experiments were done. First, the concept was tested in a laboratory setting using an experimental apparatus. A concrete cylinder was mounted on a frame and rotated using a motor. The metal test bar was applied directly to the surface of the cylinder and acoustic emission sensors were attached to each end of the bar. As the cylinder rotated, a motorcycle tire was pushed up against the cylinder using a scissor jack to simulate different loads. The acoustic emission response in the metal test strip to the motorcycle tire rolling over it was detected by the acoustic emission sensors and analyzed by the computer. Initial examinations of the data showed a correlation between the force of the tire against the cylinder and the energy and count of the acoustic emissions. Subsequent field experiments were performed at a weigh station on I-95 in Flagler County, Florida. The proposed weigh-in-motion system (the metal test bar with attached acoustic emission sensors) was installed just downstream of the existing weigh-in-motion scale at the weigh station. Commercial vehicles were weighed on the weigh station weigh-in-motion scale and acoustic emission data was collected by the experimental system. Test data was collected over several hours on two different days, one in July 2008 and the other in April 2009. Initial examination of the data did not show direct correlation between any acoustic emission parameter and vehicle weight. As a result, a more sophisticated model was developed. Dimensional analysis was used to examine possible relationships between the acoustic emission parameters and the vehicle weight. In dimensional analysis, a dimensionally correct equation is formed using measurable parameters of a system. The dimensionally correct equation can then be tested using experimental data. Dimensional analysis revealed the possible relationships between the acoustic emission parameters and the vehicle weight. Statistical models for weight using the laboratory data and using the field data were developed. Dimensional analysis variables as well as other relevant measurable parameters were used in the development of the statistical models. The model created for the April 2009 dataset was validated, with only 27 lbs average error in the weight calculation as compared with the weight measurement made with the weigh station weigh-in-motion scale. The maximum percent error for the weight calculation was 204%, with about 65% of the data falling within 30% error. Additional research will be needed to develop an acoustic emission weigh-in-motion system with adequate accuracy for a commercial product. Nevertheless, this dissertation presents a valuable contribution to the effort of developing a low-cost acoustic emission weigh-in-motion scale. Future research needs that were identified as part of this dissertation include: Examination of the effects of pavement type (flexible or rigid), vehicle speeds greater than 50 mph, and temperature Determination of the best acoustic emission sensor for this system Exploration of the best method to separate the data from axles which pass over the equipment close together in time (such as tandem axles) Exploration of the effect of repeated measures on improving the accuracy of the system.
Show less - Date Issued
- 2011
- Identifier
- CFE0003581, ucf:48903
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0003581
- Title
- Taming Wild Faces: Web-Scale, Open-Universe Face Identification in Still and Video Imagery.
- Creator
-
Ortiz, Enrique, Shah, Mubarak, Sukthankar, Rahul, Da Vitoria Lobo, Niels, Wang, Jun, Li, Xin, University of Central Florida
- Abstract / Description
-
With the increasing pervasiveness of digital cameras, the Internet, and social networking, there is a growing need to catalog and analyze large collections of photos and videos. In this dissertation, we explore unconstrained still-image and video-based face recognition in real-world scenarios, e.g. social photo sharing and movie trailers, where people of interest are recognized and all others are ignored. In such a scenario, we must obtain high precision in recognizing the known identities,...
Show moreWith the increasing pervasiveness of digital cameras, the Internet, and social networking, there is a growing need to catalog and analyze large collections of photos and videos. In this dissertation, we explore unconstrained still-image and video-based face recognition in real-world scenarios, e.g. social photo sharing and movie trailers, where people of interest are recognized and all others are ignored. In such a scenario, we must obtain high precision in recognizing the known identities, while accurately rejecting those of no interest.Recent advancements in face recognition research has seen Sparse Representation-based Classification (SRC) advance to the forefront of competing methods. However, its drawbacks, slow speed and sensitivity to variations in pose, illumination, and occlusion, have hindered its wide-spread applicability. The contributions of this dissertation are three-fold: 1. For still-image data, we propose a novel Linearly Approximated Sparse Representation-based Classification (LASRC) algorithm that uses linear regression to perform sample selection for l1-minimization, thus harnessing the speed of least-squares and the robustness of SRC. On our large dataset collected from Facebook, LASRC performs equally to standard SRC with a speedup of 100-250x.2. For video, applying the popular l1-minimization for face recognition on a frame-by-frame basis is prohibitively expensive computationally, so we propose a new algorithm Mean Sequence SRC (MSSRC) that performs video face recognition using a joint optimization leveraging all of the available video data and employing the knowledge that the face track frames belong to the same individual. Employing MSSRC results in a speedup of 5x on average over SRC on a frame-by-frame basis.3. Finally, we make the observation that MSSRC sometimes assigns inconsistent identities to the same individual in a scene that could be corrected based on their visual similarity. Therefore, we construct a probabilistic affinity graph combining appearance and co-occurrence similarities to model the relationship between face tracks in a video. Using this relationship graph, we employ random walk analysis to propagate strong class predictions among similar face tracks, while dampening weak predictions. Our method results in a performance gain of 15.8% in average precision over using MSSRC alone.
Show less - Date Issued
- 2014
- Identifier
- CFE0005536, ucf:50313
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005536
- Title
- ANALYSES OF CRASH OCCURENCE AND INURY SEVERITIES ON MULTI LANE HIGHWAYS USING MACHINE LEARNING ALGORITHMS.
- Creator
-
Das, Abhishek, Abdel-Aty, Mohamed A., University of Central Florida
- Abstract / Description
-
Reduction of crash occurrence on the various roadway locations (mid-block segments; signalized intersections; un-signalized intersections) and the mitigation of injury severity in the event of a crash are the major concerns of transportation safety engineers. Multi lane arterial roadways (excluding freeways and expressways) account for forty-three percent of fatal crashes in the state of Florida. Significant contributing causes fall under the broad categories of aggressive driver behavior;...
Show moreReduction of crash occurrence on the various roadway locations (mid-block segments; signalized intersections; un-signalized intersections) and the mitigation of injury severity in the event of a crash are the major concerns of transportation safety engineers. Multi lane arterial roadways (excluding freeways and expressways) account for forty-three percent of fatal crashes in the state of Florida. Significant contributing causes fall under the broad categories of aggressive driver behavior; adverse weather and environmental conditions; and roadway geometric and traffic factors. The objective of this research was the implementation of innovative, state-of-the-art analytical methods to identify the contributing factors for crashes and injury severity. Advances in computational methods render the use of modern statistical and machine learning algorithms. Even though most of the contributing factors are known a-priori, advanced methods unearth changing trends. Heuristic evolutionary processes such as genetic programming; sophisticated data mining methods like conditional inference tree; and mathematical treatments in the form of sensitivity analyses outline the major contributions in this research. Application of traditional statistical methods like simultaneous ordered probit models, identification and resolution of crash data problems are also key aspects of this study. In order to eliminate the use of unrealistic uniform intersection influence radius of 250 ft, heuristic rules were developed for assigning crashes to roadway segments, signalized intersection and access points using parameters, such as 'site location', 'traffic control' and node information. Use of Conditional Inference Forest instead of Classification and Regression Tree to identify variables of significance for injury severity analysis removed the bias towards the selection of continuous variable or variables with large number of categories. For the injury severity analysis of crashes on highways, the corridors were clustered into four optimum groups. The optimum number of clusters was found using Partitioning around Medoids algorithm. Concepts of evolutionary biology like crossover and mutation were implemented to develop models for classification and regression analyses based on the highest hit rate and minimum error rate, respectively. Low crossover rate and higher mutation reduces the chances of genetic drift and brings in novelty to the model development process. Annual daily traffic; friction coefficient of pavements; on-street parking; curbed medians; surface and shoulder widths; alcohol / drug usage are some of the significant factors that played a role in both crash occurrence and injury severities. Relative sensitivity analyses were used to identify the effect of continuous variables on the variation of crash counts. This study improved the understanding of the significant factors that could play an important role in designing better safety countermeasures on multi lane highways, and hence enhance their safety by reducing the frequency of crashes and severity of injuries. Educating young people about the abuses of alcohol and drugs specifically at high schools and colleges could potentially lead to lower driver aggression. Removal of on-street parking from high speed arterials unilaterally could result in likely drop in the number of crashes. Widening of shoulders could give greater maneuvering space for the drivers. Improving pavement conditions for better friction coefficient will lead to improved crash recovery. Addition of lanes to alleviate problems arising out of increased ADT and restriction of trucks to the slower right lanes on the highways would not only reduce the crash occurrences but also resulted in lower injury severity levels.
Show less - Date Issued
- 2009
- Identifier
- CFE0002928, ucf:48007
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002928
- Title
- Cost-Sensitive Learning-based Methods for Imbalanced Classification Problems with Applications.
- Creator
-
Razzaghi, Talayeh, Xanthopoulos, Petros, Karwowski, Waldemar, Pazour, Jennifer, Mikusinski, Piotr, University of Central Florida
- Abstract / Description
-
Analysis and predictive modeling of massive datasets is an extremely significant problem that arises in many practical applications. The task of predictive modeling becomes even more challenging when data are imperfect or uncertain. The real data are frequently affected by outliers, uncertain labels, and uneven distribution of classes (imbalanced data). Such uncertainties createbias and make predictive modeling an even more difficult task. In the present work, we introduce a cost-sensitive...
Show moreAnalysis and predictive modeling of massive datasets is an extremely significant problem that arises in many practical applications. The task of predictive modeling becomes even more challenging when data are imperfect or uncertain. The real data are frequently affected by outliers, uncertain labels, and uneven distribution of classes (imbalanced data). Such uncertainties createbias and make predictive modeling an even more difficult task. In the present work, we introduce a cost-sensitive learning method (CSL) to deal with the classification of imperfect data. Typically, most traditional approaches for classification demonstrate poor performance in an environment with imperfect data. We propose the use of CSL with Support Vector Machine, which is a well-known data mining algorithm. The results reveal that the proposed algorithm produces more accurate classifiers and is more robust with respect to imperfect data. Furthermore, we explore the best performance measures to tackle imperfect data along with addressing real problems in quality control and business analytics.
Show less - Date Issued
- 2014
- Identifier
- CFE0005542, ucf:50298
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005542
- Title
- DATA MINING METHODS FOR MALWARE DETECTION.
- Creator
-
Siddiqui, Muazzam, Wang, Morgan, University of Central Florida
- Abstract / Description
-
This research investigates the use of data mining methods for malware (malicious programs) detection and proposed a framework as an alternative to the traditional signature detection methods. The traditional approaches using signatures to detect malicious programs fails for the new and unknown malwares case, where signatures are not available. We present a data mining framework to detect malicious programs. We collected, analyzed and processed several thousand malicious and clean programs to...
Show moreThis research investigates the use of data mining methods for malware (malicious programs) detection and proposed a framework as an alternative to the traditional signature detection methods. The traditional approaches using signatures to detect malicious programs fails for the new and unknown malwares case, where signatures are not available. We present a data mining framework to detect malicious programs. We collected, analyzed and processed several thousand malicious and clean programs to find out the best features and build models that can classify a given program into a malware or a clean class. Our research is closely related to information retrieval and classification techniques and borrows a number of ideas from the field. We used a vector space model to represent the programs in our collection. Our data mining framework includes two separate and distinct classes of experiments. The first are the supervised learning experiments that used a dataset, consisting of several thousand malicious and clean program samples to train, validate and test, an array of classifiers. In the second class of experiments, we proposed using sequential association analysis for feature selection and automatic signature extraction. With our experiments, we were able to achieve as high as 98.4% detection rate and as low as 1.9% false positive rate on novel malwares.
Show less - Date Issued
- 2008
- Identifier
- CFE0002303, ucf:47870
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002303