Matching Items (15)
Filtering by
- All Subjects: Bioinformatics
- All Subjects: Ecology
- Creators: Li, Baoxin
Description
In many classication problems data samples cannot be collected easily, example in drug trials, biological experiments and study on cancer patients. In many situations the data set size is small and there are many outliers. When classifying such data, example cancer vs normal patients the consequences of mis-classication are probably more important than any other data type, because the data point could be a cancer patient or the classication decision could help determine what gene might be over expressed and perhaps a cause of cancer. These mis-classications are typically higher in the presence of outlier data points. The aim of this thesis is to develop a maximum margin classier that is suited to address the lack of robustness of discriminant based classiers (like the Support Vector Machine (SVM)) to noise and outliers. The underlying notion is to adopt and develop a natural loss function that is more robust to outliers and more representative of the true loss function of the data. It is demonstrated experimentally that SVM's are indeed susceptible to outliers and that the new classier developed, here coined as Robust-SVM (RSVM), is superior to all studied classier on the synthetic datasets. It is superior to the SVM in both the synthetic and experimental data from biomedical studies and is competent to a classier derived on similar lines when real life data examples are considered.
ContributorsGupta, Sidharth (Author) / Kim, Seungchan (Thesis advisor) / Welfert, Bruno (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2011
Description
Surgery as a profession requires significant training to improve both clinical decision making and psychomotor proficiency. In the medical knowledge domain, tools have been developed, validated, and accepted for evaluation of surgeons' competencies. However, assessment of the psychomotor skills still relies on the Halstedian model of apprenticeship, wherein surgeons are observed during residency for judgment of their skills. Although the value of this method of skills assessment cannot be ignored, novel methodologies of objective skills assessment need to be designed, developed, and evaluated that augment the traditional approach. Several sensor-based systems have been developed to measure a user's skill quantitatively, but use of sensors could interfere with skill execution and thus limit the potential for evaluating real-life surgery. However, having a method to judge skills automatically in real-life conditions should be the ultimate goal, since only with such features that a system would be widely adopted. This research proposes a novel video-based approach for observing surgeons' hand and surgical tool movements in minimally invasive surgical training exercises as well as during laparoscopic surgery. Because our system does not require surgeons to wear special sensors, it has the distinct advantage over alternatives of offering skills assessment in both learning and real-life environments. The system automatically detects major skill-measuring features from surgical task videos using a computing system composed of a series of computer vision algorithms and provides on-screen real-time performance feedback for more efficient skill learning. Finally, the machine-learning approach is used to develop an observer-independent composite scoring model through objective and quantitative measurement of surgical skills. To increase effectiveness and usability of the developed system, it is integrated with a cloud-based tool, which automatically assesses surgical videos upload to the cloud.
ContributorsIslam, Gazi (Author) / Li, Baoxin (Thesis advisor) / Liang, Jianming (Thesis advisor) / Dinu, Valentin (Committee member) / Greenes, Robert (Committee member) / Smith, Marshall (Committee member) / Kahol, Kanav (Committee member) / Patel, Vimla L. (Committee member) / Arizona State University (Publisher)
Created2013
Description
The origin and function of color in animals has been a subject of great interest for taxonomists and ecologists in recent years. Coloration in animals is useful for many important functions like species identification, camouflage and understanding evolutionary relationships. Quantitative measurements of color signal and patch size in mammals, birds and reptiles, to name a few are strong indicators of sexual selection cues and individual health. These measurements provide valuable insights into the impact of environmental conditions on habitat and breeding of mammals, birds and reptiles. Recent advances in the area of digital cameras and sensors have led to a significant increase in the use of digital photography as a means of color quantification in animals. Although a significant amount of research has been conducted on ways to standardize image acquisition conditions and calibrate cameras for use in animal color quantification, almost no work has been done on designing automated methods for animal color quantification. This thesis presents a novel perceptual"–"based framework for the automated extraction and quantification of animal coloration from digital images with slowly varying (almost homogenous) background colors. This implemented framework uses a combination of several techniques including color space quantization using a few dominant colors, foreground"–"background identification, Bayesian classification and mixture Gaussian modelling of conditional densities, edge"–"enhanced model"–"based classification and Saturation"–"Brightness quantization to extract the colored patch. This approach assumes no prior information about the color of either the subject or the background and also the position of the subject in the image. The performance of the proposed method is evaluated for the plumage color of the wild house finches. Segmentation results obtained using the implemented framework are compared with manually scored results to illustrate the performance of this system. The segmentation results show a high correlation with manually scored images. This novel framework also eliminates common problems in manual scoring of digital images such as low repeatability and inter"–"observer error.
ContributorsBorkar, Tejas (Author) / Karam, Lina J (Thesis advisor) / Li, Baoxin (Committee member) / McGraw, Kevin J. (Committee member) / Arizona State University (Publisher)
Created2013
Description
Colorful ornaments in animals often serve as sexually selected signals of quality. While pigment-based colors are well-studied in these regards, structural colors that result from the interaction of light with photonic nanostructures are comparatively understudied in terms of their consequences in social contexts, their costs of production, and even the best way to measure them. Iridescent colors are some of the most brilliant and conspicuous colors in nature, and I studied the measurement, condition-dependence, and signaling role of iridescence in Anna's hummingbirds (Calypte anna). While most animal colors are easily quantified using well-established spectrophotometric techniques, the unique characteristics of iridescent colors present challenges to measurement and opportunities to quantify novel color metrics. I designed and tested an apparatus for careful control and measurement of viewing geometry and highly repeatable measurements. These measurements could be used to accurately characterize individual variation in iridescent Anna's hummingbirds to examine their condition-dependence and signaling role. Next, I examined the literature published to date for evidence of condition-dependence of structural colors in birds. Using meta-analyses, I found that structural colors of all three types - white, ultra-violet/blue, and iridescence - are significantly condition-dependent, meaning that they can convey information about quality to conspecifics. I then investigated whether iridescent colors were condition-dependent in Anna's hummingbirds both in a field correlational study and in an experimental study. Throughout the year, I found that iridescent feathers in both male and female Anna's hummingbirds become less brilliant as they age. Color was not correlated with body condition in any age/sex group. However, iridescent coloration in male Anna's hummingbirds was significantly affected by experimental protein in the diet during feather growth, indicating that iridescent color may signal diet quality. Finally, I examined how iridescent colors were used to mediate social competitions in male and female Anna's hummingbirds. Surprisingly, males that were less colorful won significantly more contests than more colorful males, and colorful males received more aggression. Less colorful males may be attempting to drive away colorful neighbors that may be preferred mates. Female iridescent ornament size and color was highly variable, but did not influence contest outcomes or aggression.
ContributorsMeadows, Melissa (Author) / McGraw, Kevin J. (Thesis advisor) / Rutowski, Ronald L (Committee member) / Sabo, John L (Committee member) / Alcock, John (Committee member) / Deviche, Pierre (Committee member) / Arizona State University (Publisher)
Created2012
Description
Differences between males and females can evolve through a variety of mechanisms, including sexual and ecological selection. Because coloration is evolutionarily labile, sexually dichromatic species are good models for understanding the evolution of sex differences. While many jumping spiders exhibit diverse and brilliant coloration, they have been notably absent from such studies. In the genus Habronattus, females are drab and cryptic while males are brilliantly colored, displaying some of these colors to females during elaborate courtship dances. Here I test multiple hypotheses for the control and function of male color. In the field, I found that Habronattus males indiscriminately court any female they encounter (including other species), so I first examined the role that colors play in species recognition. I manipulated male colors in H. pyrrithrix and found that while they are not required for species recognition, the presence of red facial coloration improves courtship success, but only if males are courting in the sun. Because light environment affects transmission of color signals, the multi-colored displays of males may facilitate communication in variable and unpredictable environments. Because these colors can be costly to produce and maintain, they also have the potential to signal reliable information about male quality to potential female mates. I found that both red facial and green leg coloration is condition dependent in H. pyrrithrix and thus has the potential to signal quality. Yet, surprisingly, this variation in male color does not appear to be important to females. Males of many Habronattus species also exhibit conspicuous markings on the dorsal surface of their abdomens that are not present in females and are oriented away from females during courtship. In the field, I found that these markings are paired with increased leg-waving behavior in a way that resembles the pattern and behavior of wasps; this may provide protection by exploiting the aversions of predators. My data also suggest that different activity levels between the sexes have placed different selection pressures on their dorsal color patterns. Overall, these findings challenge some of the traditional ways that we think about color signaling and provide novel insights into the evolution of animal coloration.
ContributorsTaylor, Lisa Anne (Author) / McGraw, Kevin J. (Thesis advisor) / Clark, David L. (Committee member) / Johnson, James C. (Committee member) / Alcock, John (Committee member) / Rutowski, Ronald L (Committee member) / Arizona State University (Publisher)
Created2012
Description
Continuous advancements in biomedical research have resulted in the production of vast amounts of scientific data and literature discussing them. The ultimate goal of computational biology is to translate these large amounts of data into actual knowledge of the complex biological processes and accurate life science models. The ability to rapidly and effectively survey the literature is necessary for the creation of large scale models of the relationships among biomedical entities as well as hypothesis generation to guide biomedical research. To reduce the effort and time spent in performing these activities, an intelligent search system is required. Even though many systems aid in navigating through this wide collection of documents, the vastness and depth of this information overload can be overwhelming. An automated extraction system coupled with a cognitive search and navigation service over these document collections would not only save time and effort, but also facilitate discovery of the unknown information implicitly conveyed in the texts. This thesis presents the different approaches used for large scale biomedical named entity recognition, and the challenges faced in each. It also proposes BioEve: an integrative framework to fuse a faceted search with information extraction to provide a search service that addresses the user's desire for "completeness" of the query results, not just the top-ranked ones. This information extraction system enables discovery of important semantic relationships between entities such as genes, diseases, drugs, and cell lines and events from biomedical text on MEDLINE, which is the largest publicly available database of the world's biomedical journal literature. It is an innovative search and discovery service that makes it easier to search
avigate and discover knowledge hidden in life sciences literature. To demonstrate the utility of this system, this thesis also details a prototype enterprise quality search and discovery service that helps researchers with a guided step-by-step query refinement, by suggesting concepts enriched in intermediate results, and thereby facilitating the "discover more as you search" paradigm.
avigate and discover knowledge hidden in life sciences literature. To demonstrate the utility of this system, this thesis also details a prototype enterprise quality search and discovery service that helps researchers with a guided step-by-step query refinement, by suggesting concepts enriched in intermediate results, and thereby facilitating the "discover more as you search" paradigm.
ContributorsKanwar, Pradeep (Author) / Davulcu, Hasan (Thesis advisor) / Dinu, Valentin (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2010
Description
Animals have evolved a diversity of signaling traits, and in some species, they co-occur and are used simultaneously to communicate. Although much work has been done to understand why animals possess multiple signals, studies do not typically address the role of inter-signal interactions, which may vary intra- and inter-specifically and help drive the evolutionary diversity in signals. For my dissertation, I tested how angle-dependent structural coloration, courtship displays, and the display environment interact and co-evolved in hummingbird species from the “bee” tribe (Mellisugini). Most “bee” hummingbird species possess an angle-dependent structurally colored throat patch and stereotyped courtship (shuttle) display. For 6 U.S. “bee” hummingbird species, I filmed male shuttle displays and mapped out the orientation- and-position-specific movements during the displays. With such display paths, I was able to then recreate each shuttle display in the field by moving plucked feathers from each male in space and time, as if they were naturally displaying, in order to measure each male’s color appearance during their display (i.e. the interactions between male hummingbird plumage, shuttle displays, and environment) from full-spectrum photographs. I tested how these interactions varied intra- and inter-specifically, and which of these originating traits might explain that variation. I first found that the solar-positional environment played a significant role in explaining variation in male color appearance within two species (Selasphorus platycercus and Calypte costae), and that different combinations of color-behavior-environment interactions made some males (in both species) appear bright, colorful, and flashy (i.e. their color appearance changes throughout a display), while other males maintained a consistent (non-flashing) color display. Among species, I found that plumage flashiness positively co-varied with male display behaviors, while another measure of male color appearance (average brightness/colorfulness) co-varied with the feather reflectance characteristics themselves. Additionally, species that had more exaggerated plumage features had less exaggerated shuttle displays. Altogether, my dissertation work illustrates the complexity of multiple signal evolution and how color-behavior-environment interactions are vital to understanding the evolution of colorful and behavioral display traits in animals.
ContributorsSimpson, Richard Kendall (Author) / McGraw, Kevin J. (Thesis advisor) / Rutowski, Ronald L (Committee member) / Pratt, Stephen C (Committee member) / Clark, Christopher J (Committee member) / McGuire, Jimmy A. (Committee member) / Arizona State University (Publisher)
Created2018
Description
Sexual and social signals have long been thought to play an important role in speciation and diversity; hence, investigations of intraspecific communication may lead to important insights regarding key processes of evolution. Though we have learned much about the control, function, and evolution of animal communication by studying several very common signal types, investigating rare classes of signals may provide new information about how and why animals communicate. My dissertation research focused on rapid physiological color change, a rare signal-type used by relatively few taxa. To answer longstanding questions about this rare class of signals, I employed novel methods to measure rapid color change signals of male veiled chameleons Chamaeleo calyptratus in real-time as seen by the intended conspecific receivers, as well as the associated behaviors of signalers and receivers. In the context of agonistic male-male interactions, I found that the brightness achieved by individual males and the speed of color change were the best predictors of aggression and fighting ability. Conversely, I found that rapid skin darkening serves as a signal of submission for male chameleons, reducing aggression from winners when displayed by losers. Additionally, my research revealed that the timing of maximum skin brightness and speed of brightening were the best predictors of maximum bite force and circulating testosterone levels, respectively. Together, these results indicated that different aspects of color change can communicate information about contest strategy, physiology, and performance ability. Lastly, when I experimentally manipulated the external appearance of chameleons, I found that "dishonestly" signaling individuals (i.e. those whose behavior did not match their manipulated color) received higher aggression from unpainted opponents. The increased aggression received by dishonest signalers suggests that social costs play an important role in maintaining the honesty of rapid color change signals in veiled chameleons. Though the color change abilities of chameleons have interested humans since the time of Aristotle, little was previously known about the signal content of such changes. Documenting the behavioral contexts and information content of these signals has provided an important first step in understanding the current function, underlying control mechanisms, and evolutionary origins of this rare signal type.
ContributorsLigon, Russell (Author) / McGraw, Kevin J. (Committee member) / DeNardo, Dale F (Committee member) / Karsten, Kristopher B (Committee member) / Rutowski, Ronald L (Committee member) / Deviche, Pierre (Committee member) / Arizona State University (Publisher)
Created2015
Description
Cardiovascular disease (CVD) is the leading cause of mortality yet largely preventable, but the key to prevention is to identify at-risk individuals before adverse events. For predicting individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable, offering several advantages over CT coronary artery calcium score. However, each CIMT examination includes several ultrasound videos, and interpreting each of these CIMT videos involves three operations: (1) select three enddiastolic ultrasound frames (EUF) in the video, (2) localize a region of interest (ROI) in each selected frame, and (3) trace the lumen-intima interface and the media-adventitia interface in each ROI to measure CIMT. These operations are tedious, laborious, and time consuming, a serious limitation that hinders the widespread utilization of CIMT in clinical practice. To overcome this limitation, this paper presents a new system to automate CIMT video interpretation. Our extensive experiments demonstrate that the suggested system significantly outperforms the state-of-the-art methods. The superior performance is attributable to our unified framework based on convolutional neural networks (CNNs) coupled with our informative image representation and effective post-processing of the CNN outputs, which are uniquely designed for each of the above three operations.
ContributorsShin, Jaeyul (Author) / Liang, Jianming (Thesis advisor) / Maciejewski, Ross (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2016
Description
Although mimetic animal coloration has been studied since Darwin's time, many questions on the efficacy, evolution, and function of mimicry remain unanswered. Müller (1879) hypothesized that unpalatable individuals converge on the same conspicuous coloration to reduce predation. However, there are many cases where closely related, unpalatable species have diverged from a shared conspicuous pattern. What selection pressures have led to divergence in warning colors? Environmental factors such as ambient light have been hypothesized to affect signal transmission and efficacy in animals. Using two mimetic pairs of Heliconius butterflies, Postman and Blue-white, I tested the hypothesis that animals with divergent mimetic colors segregate by light environment to maximize conspicuousness of the aposematic warning signal under their particular environmental conditions. Each mimetic pair was found in a light environment that differed in brightness and spectral composition, which affected visual conspicuousness differently depending on mimetic color patch. I then used plasticine models in the field to test the hypothesis that mimics had higher survival in the habitat where they occurred. Although predation rates differed between the two habitats, there was no interactive effect of species by habitat type. Through choice experiments, I demonstrated that mimetic individuals preferred to spend time in the light environment where they were most often found and that their absolute visual sensitivity corresponds to the ambient lighting of their respective environment. Eye morphology was then studied to determine if differences in total corneal surface area and/or facet diameters explained the differences in visual sensitivities, but the differences found in Heliconius eye morphology did not match predictions based upon visual sensitivity. To further understand how eye morphology varies with light environments, I studied many tropical butterflies from open and closed habitats to reveal that forest understory butterflies have larger facets compared to butterflies occupying open habitats. Lastly, I tested avian perception of mimicry in a putative Heliconius mimetic assemblage and show that the perceived mimetic resemblance depends upon visual system. This dissertation reveals the importance of light environments on mimicry, coloration, behavior and visual systems of tropical butterflies.
ContributorsSeymoure, Brett M (Author) / Rutowski, Ronald L (Thesis advisor) / McGraw, Kevin J. (Thesis advisor) / McMillan, W. Owen (Committee member) / Pratt, Stephen (Committee member) / Gadau, Jürgen (Committee member) / Arizona State University (Publisher)
Created2016