Matching Items (149)
Filtering by
- Genre: Doctoral Dissertation
- Creators: Li, Baoxin
- Creators: Goryll, Michael
Description
The rapid escalation of technology and the widespread emergence of modern technological equipments have resulted in the generation of humongous amounts of digital data (in the form of images, videos and text). This has expanded the possibility of solving real world problems using computational learning frameworks. However, while gathering a large amount of data is cheap and easy, annotating them with class labels is an expensive process in terms of time, labor and human expertise. This has paved the way for research in the field of active learning. Such algorithms automatically select the salient and exemplar instances from large quantities of unlabeled data and are effective in reducing human labeling effort in inducing classification models. To utilize the possible presence of multiple labeling agents, there have been attempts towards a batch mode form of active learning, where a batch of data instances is selected simultaneously for manual annotation. This dissertation is aimed at the development of novel batch mode active learning algorithms to reduce manual effort in training classification models in real world multimedia pattern recognition applications. Four major contributions are proposed in this work: $(i)$ a framework for dynamic batch mode active learning, where the batch size and the specific data instances to be queried are selected adaptively through a single formulation, based on the complexity of the data stream in question, $(ii)$ a batch mode active learning strategy for fuzzy label classification problems, where there is an inherent imprecision and vagueness in the class label definitions, $(iii)$ batch mode active learning algorithms based on convex relaxations of an NP-hard integer quadratic programming (IQP) problem, with guaranteed bounds on the solution quality and $(iv)$ an active matrix completion algorithm and its application to solve several variants of the active learning problem (transductive active learning, multi-label active learning, active feature acquisition and active learning for regression). These contributions are validated on the face recognition and facial expression recognition problems (which are commonly encountered in real world applications like robotics, security and assistive technology for the blind and the visually impaired) and also on collaborative filtering applications like movie recommendation.
ContributorsChakraborty, Shayok (Author) / Panchanathan, Sethuraman (Thesis advisor) / Balasubramanian, Vineeth N. (Committee member) / Li, Baoxin (Committee member) / Mittelmann, Hans (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
Continuous monitoring in the adequate temporal and spatial scale is necessary for a better understanding of environmental variations. But field deployments of molecular biological analysis platforms in that scale are currently hindered because of issues with power, throughput and automation. Currently, such analysis is performed by the collection of large sample volumes from over a wide area and transporting them to laboratory testing facilities, which fail to provide any real-time information. This dissertation evaluates the systems currently utilized for in-situ field analyses and the issues hampering the successful deployment of such bioanalytial instruments for environmental applications. The design and development of high throughput, low power, and autonomous Polymerase Chain Reaction (PCR) instruments, amenable for portable field operations capable of providing quantitative results is presented here as part of this dissertation. A number of novel innovations have been reported here as part of this work in microfluidic design, PCR thermocycler design, optical design and systems integration. Emulsion microfluidics in conjunction with fluorinated oils and Teflon tubing have been used for the fluidic module that reduces cross-contamination eliminating the need for disposable components or constant cleaning. A cylindrical heater has been designed with the tubing wrapped around fixed temperature zones enabling continuous operation. Fluorescence excitation and detection have been achieved by using a light emitting diode (LED) as the excitation source and a photomultiplier tube (PMT) as the detector. Real-time quantitative PCR results were obtained by using multi-channel fluorescence excitation and detection using LED, optical fibers and a 64-channel multi-anode PMT for measuring continuous real-time fluorescence. The instrument was evaluated by comparing the results obtained with those obtained from a commercial instrument and found to be comparable. To further improve the design and enhance its field portability, this dissertation also presents a framework for the instrumentation necessary for a portable digital PCR platform to achieve higher throughputs with lower power. Both systems were designed such that it can easily couple with any upstream platform capable of providing nucleic acid for analysis using standard fluidic connections. Consequently, these instruments can be used not only in environmental applications, but portable diagnostics applications as well.
ContributorsRay, Tathagata (Author) / Youngbull, Cody (Thesis advisor) / Goryll, Michael (Thesis advisor) / Blain Christen, Jennifer (Committee member) / Yu, Hongyu (Committee member) / Arizona State University (Publisher)
Created2013
Description
In recent years, machine learning and data mining technologies have received growing attention in several areas such as recommendation systems, natural language processing, speech and handwriting recognition, image processing and biomedical domain. Many of these applications which deal with physiological and biomedical data require person specific or person adaptive systems. The greatest challenge in developing such systems is the subject-dependent data variations or subject-based variability in physiological and biomedical data, which leads to difference in data distributions making the task of modeling these data, using traditional machine learning algorithms, complex and challenging. As a result, despite the wide application of machine learning, efficient deployment of its principles to model real-world data is still a challenge. This dissertation addresses the problem of subject based variability in physiological and biomedical data and proposes person adaptive prediction models based on novel transfer and active learning algorithms, an emerging field in machine learning. One of the significant contributions of this dissertation is a person adaptive method, for early detection of muscle fatigue using Surface Electromyogram signals, based on a new multi-source transfer learning algorithm. This dissertation also proposes a subject-independent algorithm for grading the progression of muscle fatigue from 0 to 1 level in a test subject, during isometric or dynamic contractions, at real-time. Besides subject based variability, biomedical image data also varies due to variations in their imaging techniques, leading to distribution differences between the image databases. Hence a classifier learned on one database may perform poorly on the other database. Another significant contribution of this dissertation has been the design and development of an efficient biomedical image data annotation framework, based on a novel combination of transfer learning and a new batch-mode active learning method, capable of addressing the distribution differences across databases. The methodologies developed in this dissertation are relevant and applicable to a large set of computing problems where there is a high variation of data between subjects or sources, such as face detection, pose detection and speech recognition. From a broader perspective, these frameworks can be viewed as a first step towards design of automated adaptive systems for real world data.
ContributorsChattopadhyay, Rita (Author) / Panchanathan, Sethuraman (Thesis advisor) / Ye, Jieping (Thesis advisor) / Li, Baoxin (Committee member) / Santello, Marco (Committee member) / Arizona State University (Publisher)
Created2013
Description
Distributed inference has applications in a wide range of fields such as source localization, target detection, environment monitoring, and healthcare. In this dissertation, distributed inference schemes which use bounded transmit power are considered. The performance of the proposed schemes are studied for a variety of inference problems. In the first part of the dissertation, a distributed detection scheme where the sensors transmit with constant modulus signals over a Gaussian multiple access channel is considered. The deflection coefficient of the proposed scheme is shown to depend on the characteristic function of the sensing noise, and the error exponent for the system is derived using large deviation theory. Optimization of the deflection coefficient and error exponent are considered with respect to a transmission phase parameter for a variety of sensing noise distributions including impulsive ones. The proposed scheme is also favorably compared with existing amplify-and-forward (AF) and detect-and-forward (DF) schemes. The effect of fading is shown to be detrimental to the detection performance and simulations are provided to corroborate the analytical results. The second part of the dissertation studies a distributed inference scheme which uses bounded transmission functions over a Gaussian multiple access channel. The conditions on the transmission functions under which consistent estimation and reliable detection are possible is characterized. For the distributed estimation problem, an estimation scheme that uses bounded transmission functions is proved to be strongly consistent provided that the variance of the noise samples are bounded and that the transmission function is one-to-one. The proposed estimation scheme is compared with the amplify and forward technique and its robustness to impulsive sensing noise distributions is highlighted. It is also shown that bounded transmissions suffer from inconsistent estimates if the sensing noise variance goes to infinity. For the distributed detection problem, similar results are obtained by studying the deflection coefficient. Simulations corroborate our analytical results. In the third part of this dissertation, the problem of estimating the average of samples distributed at the nodes of a sensor network is considered. A distributed average consensus algorithm in which every sensor transmits with bounded peak power is proposed. In the presence of communication noise, it is shown that the nodes reach consensus asymptotically to a finite random variable whose expectation is the desired sample average of the initial observations with a variance that depends on the step size of the algorithm and the variance of the communication noise. The asymptotic performance is characterized by deriving the asymptotic covariance matrix using results from stochastic approximation theory. It is shown that using bounded transmissions results in slower convergence compared to the linear consensus algorithm based on the Laplacian heuristic. Simulations corroborate our analytical findings. Finally, a robust distributed average consensus algorithm in which every sensor performs a nonlinear processing at the receiver is proposed. It is shown that non-linearity at the receiver nodes makes the algorithm robust to a wide range of channel noise distributions including the impulsive ones. It is shown that the nodes reach consensus asymptotically and similar results are obtained as in the case of transmit non-linearity. Simulations corroborate our analytical findings and highlight the robustness of the proposed algorithm.
ContributorsDasarathan, Sivaraman (Author) / Tepedelenlioğlu, Cihan (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Reisslein, Martin (Committee member) / Goryll, Michael (Committee member) / Arizona State University (Publisher)
Created2013
Description
This research emphasizes the use of low energy and low temperature post processing to improve the performance and lifetime of thin films and thin film transistors, by applying the fundamentals of interaction of materials with conductive heating and electromagnetic radiation. Single frequency microwave anneal is used to rapidly recrystallize the damage induced during ion implantation in Si substrates. Volumetric heating of the sample in the presence of the microwave field facilitates quick absorption of radiation to promote recrystallization at the amorphous-crystalline interface, apart from electrical activation of the dopants due to relocation to the substitutional sites. Structural and electrical characterization confirm recrystallization of heavily implanted Si within 40 seconds anneal time with minimum dopant diffusion compared to rapid thermal annealed samples. The use of microwave anneal to improve performance of multilayer thin film devices, e.g. thin film transistors (TFTs) requires extensive study of interaction of individual layers with electromagnetic radiation. This issue has been addressed by developing detail understanding of thin films and interfaces in TFTs by studying reliability and failure mechanisms upon extensive stress test. Electrical and ambient stresses such as illumination, thermal, and mechanical stresses are inflicted on the mixed oxide based thin film transistors, which are explored due to high mobilities of the mixed oxide (indium zinc oxide, indium gallium zinc oxide) channel layer material. Semiconductor parameter analyzer is employed to extract transfer characteristics, useful to derive mobility, subthreshold, and threshold voltage parameters of the transistors. Low temperature post processing anneals compatible with polymer substrates are performed in several ambients (oxygen, forming gas and vacuum) at 150 °C as a preliminary step. The analysis of the results pre and post low temperature anneals using device physics fundamentals assists in categorizing defects leading to failure/degradation as: oxygen vacancies, thermally activated defects within the bandgap, channel-dielectric interface defects, and acceptor-like or donor-like trap states. Microwave anneal has been confirmed to enhance the quality of thin films, however future work entails extending the use of electromagnetic radiation in controlled ambient to facilitate quick post fabrication anneal to improve the functionality and lifetime of these low temperature fabricated TFTs.
ContributorsVemuri, Rajitha (Author) / Alford, Terry L. (Thesis advisor) / Theodore, N David (Committee member) / Goryll, Michael (Committee member) / Arizona State University (Publisher)
Created2013
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
Zinc oxide (ZnO), a naturally n-type semiconductor has been identified as a promising candidate to replace indium tin oxide (ITO) as the transparent electrode in solar cells, because of its wide bandgap (3.37 eV), abundant source materials and suitable refractive index (2.0 at 600 nm). Spray deposition is a convenient and low cost technique for large area and uniform deposition of semiconductor thin films. In particular, it provides an easier way to dope the film by simply adding the dopant precursor into the starting solution. In order to reduce the resistivity of undoped ZnO, many works have been done by doping in the ZnO with either group IIIA elements or VIIA elements using spray pyrolysis. However, the resistivity is still too high to meet TCO's resistivity requirement. In the present work, a novel co-spray deposition technique is developed to bypass a fundamental limitation in the conventional spray deposition technique, i.e. the deposition of metal oxides from incompatible precursors in the starting solution. With this technique, ZnO films codoped with one cationic dopant, Al, Cr, or Fe, and an anionic dopant, F, have been successfully synthesized, in which F is incompatible with all these three cationic dopants. Two starting solutions were prepared and co-sprayed through two separate spray heads. One solution contained only the F precursor, NH 4F. The second solution contained the Zn and one cationic dopant precursors, Zn(O 2CCH 3) 2 and AlCl 3, CrCl 3, or FeCl 3. The deposition was carried out at 500 °C; on soda-lime glass in air. Compared to singly-doped ZnO thin films, codoped ZnO samples showed better electrical properties. Besides, a minimum sheet resistance, 55.4 Ω/sq, was obtained for Al and F codoped ZnO films after vacuum annealing at 400 °C;, which was lower than singly-doped ZnO with either Al or F. The transmittance for the Al and F codoped ZnO samples was above 90% in the visible range. This co-spray deposition technique provides a simple and cost-effective way to synthesize metal oxides from incompatible precursors with improved properties.
ContributorsZhou, Bin (Author) / Tao, Meng (Thesis advisor) / Goryll, Michael (Committee member) / Vasileska, Dragica (Committee member) / Yu, Hongbin (Committee member) / Arizona State University (Publisher)
Created2013
Description
Chalcogenide glass (ChG) materials have gained wide attention because of their applications in conductive bridge random access memory (CBRAM), phase change memories (PC-RAM), optical rewritable disks (CD-RW and DVD-RW), microelectromechanical systems (MEMS), microfluidics, and optical communications. One of the significant properties of ChG materials is the change in the resistivity of the material when a metal such as Ag or Cu is added to it by diffusion. This study demonstrates the potential radiation-sensing capabilities of two metal/chalcogenide glass device configurations. Lateral and vertical device configurations sense the radiation-induced migration of Ag+ ions in germanium selenide glasses via changes in electrical resistance between electrodes on the ChG. Before irradiation, these devices exhibit a high-resistance `OFF-state' (in the order of 10E12) but following irradiation, with either 60-Co gamma-rays or UV light, their resistance drops to a low-resistance `ON-state' (around 10E3). Lateral devices have exhibited cyclical recovery with room temperature annealing of the Ag doped ChG, which suggests potential uses in reusable radiation sensor applications. The feasibility of producing inexpensive flexible radiation sensors has been demonstrated by studying the effects of mechanical strain and temperature stress on sensors formed on flexible polymer substrate. The mechanisms of radiation-induced Ag/Ag+ transport and reactions in ChG have been modeled using a finite element device simulator, ATLAS. The essential reactions captured by the simulator are radiation-induced carrier generation, combined with reduction/oxidation for Ag species in the chalcogenide film. Metal-doped ChGs are solid electrolytes that have both ionic and electronic conductivity. The ChG based Programmable Metallization Cell (PMC) is a technology platform that offers electric field dependent resistance switching mechanisms by formation and dissolution of nano sized conductive filaments in a ChG solid electrolyte between oxidizable and inert electrodes. This study identifies silver anode agglomeration in PMC devices following large radiation dose exposure and considers device failure mechanisms via electrical and material characterization. The results demonstrate that by changing device structural parameters, silver agglomeration in PMC devices can be suppressed and reliable resistance switching may be maintained for extremely high doses ranging from 4 Mrad(GeSe) to more than 10 Mrad (ChG).
ContributorsDandamudi, Pradeep (Author) / Kozicki, Michael N (Thesis advisor) / Barnaby, Hugh J (Committee member) / Holbert, Keith E. (Committee member) / Goryll, Michael (Committee member) / Arizona State University (Publisher)
Created2013
Description
Texture analysis plays an important role in applications like automated pattern inspection, image and video compression, content-based image retrieval, remote-sensing, medical imaging and document processing, to name a few. Texture Structure Analysis is the process of studying the structure present in the textures. This structure can be expressed in terms of perceived regularity. Our human visual system (HVS) uses the perceived regularity as one of the important pre-attentive cues in low-level image understanding. Similar to the HVS, image processing and computer vision systems can make fast and efficient decisions if they can quantify this regularity automatically. In this work, the problem of quantifying the degree of perceived regularity when looking at an arbitrary texture is introduced and addressed. One key contribution of this work is in proposing an objective no-reference perceptual texture regularity metric based on visual saliency. Other key contributions include an adaptive texture synthesis method based on texture regularity, and a low-complexity reduced-reference visual quality metric for assessing the quality of synthesized textures. In order to use the best performing visual attention model on textures, the performance of the most popular visual attention models to predict the visual saliency on textures is evaluated. Since there is no publicly available database with ground-truth saliency maps on images with exclusive texture content, a new eye-tracking database is systematically built. Using the Visual Saliency Map (VSM) generated by the best visual attention model, the proposed texture regularity metric is computed. The proposed metric is based on the observation that VSM characteristics differ between textures of differing regularity. The proposed texture regularity metric is based on two texture regularity scores, namely a textural similarity score and a spatial distribution score. In order to evaluate the performance of the proposed regularity metric, a texture regularity database called RegTEX, is built as a part of this work. It is shown through subjective testing that the proposed metric has a strong correlation with the Mean Opinion Score (MOS) for the perceived regularity of textures. The proposed method is also shown to be robust to geometric and photometric transformations and outperforms some of the popular texture regularity metrics in predicting the perceived regularity. The impact of the proposed metric to improve the performance of many image-processing applications is also presented. The influence of the perceived texture regularity on the perceptual quality of synthesized textures is demonstrated through building a synthesized textures database named SynTEX. It is shown through subjective testing that textures with different degrees of perceived regularities exhibit different degrees of vulnerability to artifacts resulting from different texture synthesis approaches. This work also proposes an algorithm for adaptively selecting the appropriate texture synthesis method based on the perceived regularity of the original texture. A reduced-reference texture quality metric for texture synthesis is also proposed as part of this work. The metric is based on the change in perceived regularity and the change in perceived granularity between the original and the synthesized textures. The perceived granularity is quantified through a new granularity metric that is proposed in this work. It is shown through subjective testing that the proposed quality metric, using just 2 parameters, has a strong correlation with the MOS for the fidelity of synthesized textures and outperforms the state-of-the-art full-reference quality metrics on 3 different texture databases. Finally, the ability of the proposed regularity metric in predicting the perceived degradation of textures due to compression and blur artifacts is also established.
ContributorsVaradarajan, Srenivas (Author) / Karam, Lina J (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Li, Baoxin (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2014
Description
In many fields one needs to build predictive models for a set of related machine learning tasks, such as information retrieval, computer vision and biomedical informatics. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores important connections among the tasks. Multi-task learning aims at simultaneously building models for all tasks in order to improve the generalization performance, leveraging inherent relatedness of these tasks. In this thesis, I firstly propose a clustered multi-task learning (CMTL) formulation, which simultaneously learns task models and performs task clustering. I provide theoretical analysis to establish the equivalence between the CMTL formulation and the alternating structure optimization, which learns a shared low-dimensional hypothesis space for different tasks. Then I present two real-world biomedical informatics applications which can benefit from multi-task learning. In the first application, I study the disease progression problem and present multi-task learning formulations for disease progression. In the formulations, the prediction at each point is a regression task and multiple tasks at different time points are learned simultaneously, leveraging the temporal smoothness among the tasks. The proposed formulations have been tested extensively on predicting the progression of the Alzheimer's disease, and experimental results demonstrate the effectiveness of the proposed models. In the second application, I present a novel data-driven framework for densifying the electronic medical records (EMR) to overcome the sparsity problem in predictive modeling using EMR. The densification of each patient is a learning task, and the proposed algorithm simultaneously densify all patients. As such, the densification of one patient leverages useful information from other patients.
ContributorsZhou, Jiayu (Author) / Ye, Jieping (Thesis advisor) / Mittelmann, Hans (Committee member) / Li, Baoxin (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)
Created2014