Matching Items (136)
Filtering by
- Genre: Doctoral Dissertation
- Creators: Li, Baoxin
- Member of: Theses and Dissertations
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
As crystalline silicon solar cells continue to get thinner, the recombination of carriers at the surfaces of the cell plays an ever-important role in controlling the cell efficiency. One tool to minimize surface recombination is field effect passivation from the charges present in the thin films applied on the cell surfaces. The focus of this work is to understand the properties of charges present in the SiNx films and then to develop a mechanism to manipulate the polarity of charges to either negative or positive based on the end-application. Specific silicon-nitrogen dangling bonds (·Si-N), known as K center defects, are the primary charge trapping defects present in the SiNx films. A custom built corona charging tool was used to externally inject positive or negative charges in the SiNx film. Detailed Capacitance-Voltage (C-V) measurements taken on corona charged SiNx samples confirmed the presence of a net positive or negative charge density, as high as +/- 8 x 1012 cm-2, present in the SiNx film. High-energy (~ 4.9 eV) UV radiation was used to control and neutralize the charges in the SiNx films. Electron-Spin-Resonance (ESR) technique was used to detect and quantify the density of neutral K0 defects that are paramagnetically active. The density of the neutral K0 defects increased after UV treatment and decreased after high temperature annealing and charging treatments. Etch-back C-V measurements on SiNx films showed that the K centers are spread throughout the bulk of the SiNx film and not just near the SiNx-Si interface. It was also shown that the negative injected charges in the SiNx film were stable and present even after 1 year under indoor room-temperature conditions. Lastly, a stack of SiO2/SiNx dielectric layers applicable to standard commercial solar cells was developed using a low temperature (< 400 °C) PECVD process. Excellent surface passivation on FZ and CZ Si substrates for both n- and p-type samples was achieved by manipulating and controlling the charge in SiNx films.
ContributorsSharma, Vivek (Author) / Bowden, Stuart (Thesis advisor) / Schroder, Dieter (Committee member) / Honsberg, Christiana (Committee member) / Roedel, Ronald (Committee member) / Alford, Terry (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
Ball Grid Array (BGA) using lead-free or lead-rich solder materials are widely used as Second Level Interconnects (SLI) in mounting packaged components to the printed circuit board (PCB). The reliability of these solder joints is of significant importance to the performance of microelectronics components and systems. Product design/form-factor, solder material, manufacturing process, use condition, as well as, the inherent variabilities present in the system, greatly influence product reliability. Accurate reliability analysis requires an integrated approach to concurrently account for all these factors and their synergistic effects. Such an integrated and robust methodology can be used in design and development of new and advanced microelectronics systems and can provide significant improvement in cycle-time, cost, and reliability. IMPRPK approach is based on a probabilistic methodology, focusing on three major tasks of (1) Characterization of BGA solder joints to identify failure mechanisms and obtain statistical data, (2) Finite Element analysis (FEM) to predict system response needed for life prediction, and (3) development of a probabilistic methodology to predict the reliability, as well as, the sensitivity of the system to various parameters and the variabilities. These tasks and the predictive capabilities of IMPRPK in microelectronic reliability analysis are discussed.
ContributorsFallah-Adl, Ali (Author) / Tasooji, Amaneh (Thesis advisor) / Krause, Stephen (Committee member) / Alford, Terry (Committee member) / Jiang, Hanqing (Committee member) / Mahajan, Ravi (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
ABSTRACT Along with the fast development of science and technology, the studied materials are becoming more complicated and smaller. All these achievements have advanced with the fast development of powerful tools currently, such as Scanning electron microscopy (SEM), Focused Ion Beam (FIB), Transmission electron microscopy (TEM), Energy dispersive X-ray spectroscopy (EDX), Electron energy loss spectroscopy (EELS) and so on. SiTiO3 thin film, which is grown on Si (100) single crystals, attracts a lot of interest in its structural and electronic properties close to its interface. Valence EELS is used to investigate the Plasmon excitations of the ultrathin SrTiO3 thin film which is sandwiched between amorphous Si and crystalline Si layers. On the other hand, theoretical simulations based on dielectric functions have been done to interpret the experimental results. Our findings demonstrate the value of valence electron energy-loss spectroscopy in detecting a local change in the effective electron mass. Recently it is reported that ZnO-LiYbO2 hybrid phosphor is an efficient UV-infrared convertor for silicon solar cell but the mechanism is still not very clear. The microstructure of Li and Yb co-doped ZnO has been studied by SEM and EDX, and our results suggest that a reaction (or diffusion) zone is very likely to exist between LiYbO2 and ZnO. Such diffusion regions may be responsible for the enhanced infrared emission in the Yb and Li co-doped ZnO. Furthermore, to help us study the diffusion zone under TEM in future, the radiation damage on synthesized LiYbO2 has been studied at first, and then the electronic structure of the synthesized LiYbO2 is compared with Yb2O3 experimentally and theoretically, by EELS and FEFF8 respectively.
ContributorsYang, Bo (Author) / Alford, Terry (Thesis advisor) / Jiang, Nan (Committee member) / Theodore, N. David (Committee member) / Arizona State University (Publisher)
Created2013
Description
Organic optoelectronic devices have remained a research topic of great interest over the past two decades, particularly in the development of efficient organic photovoltaics (OPV) and organic light emitting diodes (OLED). In order to improve the efficiency, stability, and materials variety for organic optoelectronic devices a number of emitting materials, absorbing materials, and charge transport materials were developed and employed in a device setting. Optical, electrical, and photophysical studies of the organic materials and their corresponding devices were thoroughly carried out. Two major approaches were taken to enhance the efficiency of small molecule based OPVs: developing material with higher open circuit voltages or improved device structures which increased short circuit current. To explore the factors affecting the open circuit voltage (VOC) in OPVs, molecular structures were modified to bring VOC closer to the effective bandgap, ∆EDA, which allowed the achievement of 1V VOC for a heterojunction of a select Ir complex with estimated exciton energy of only 1.55eV. Furthermore, the development of anode interfacial layer for exciton blocking and molecular templating provide a general approach for enhancing the short circuit current. Ultimately, a 5.8% PCE was achieved in a single heterojunction of C60 and a ZnPc material prepared in a simple, one step, solvent free, synthesis. OLEDs employing newly developed deep blue emitters based on cyclometalated complexes were demonstrated. Ultimately, a peak EQE of 24.8% and nearly perfect blue emission of (0.148,0.079) was achieved from PtON7dtb, which approaches the maximum attainable performance from a blue OLED. Furthermore, utilizing the excimer formation properties of square-planar Pt complexes, highly efficient and stable white devices employing a single emissive material were demonstrated. A peak EQE of over 20% for pure white color (0.33,0.33) and 80 CRI was achieved with the tridentate Pt complex, Pt-16. Furthermore, the development of a series of tetradentate Pt complexes yielded highly efficient and stable single doped white devices due to their halogen free tetradentate design. In addition to these benchmark achievements, the systematic molecular modification of both emissive and absorbing materials provides valuable structure-property relationship information that should help guide further developments in the field.
ContributorsFleetham, Tyler Blain (Author) / Li, Jian (Thesis advisor) / Alford, Terry (Committee member) / Adams, James (Committee member) / Arizona State University (Publisher)
Created2014
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
Organic light emitting diodes (OLEDs) are a promising approach for display and solid state lighting applications. However, further work is needed in establishing the availability of efficient and stable materials for OLEDs with high external quantum efficiency's (EQE) and high operational lifetimes. Recently, significant improvements in the internal quantum efficiency or ratio of generated photons to injected electrons have been achieved with the advent of phosphorescent complexes with the ability to harvest both singlet and triplet excitons. Since then, a variety of phosphorescent complexes containing heavy metal centers including Os, Ni, Ir, Pd, and Pt have been developed. Thus far, the majority of the work in the field has focused on iridium based complexes. Platinum based complexes, however, have received considerably less attention despite demonstrating efficiency's equal to or better than their iridium analogs. In this study, a series of OLEDs implementing newly developed platinum based complexes were demonstrated with efficiency's or operational lifetimes equal to or better than their iridium analogs for select cases.
In addition to demonstrating excellent device performance in OLEDs, platinum based complexes exhibit unique photophysical properties including the ability to form excimer emission capable of generating broad white light emission from a single emitter and the ability to form narrow band emission from a rigid, tetradentate molecular structure for select cases. These unique photophysical properties were exploited and their optical and electrical properties in a device setting were elucidated.
Utilizing the unique properties of a tridentate Pt complex, Pt-16, a highly efficient white device employing a single emissive layer exhibited a peak EQE of over 20% and high color quality with a CRI of 80 and color coordinates CIE(x=0.33, y=0.33). Furthermore, by employing a rigid, tetradentate platinum complex, PtN1N, with a narrow band emission into a microcavity organic light emitting diode (MOLED), significant enhancement in the external quantum efficiency was achieved. The optimized MOLED structure achieved a light out-coupling enhancement of 1.35 compared to the non-cavity structure with a peak EQE of 34.2%. In addition to demonstrating a high light out-coupling enhancement, the microcavity effect of a narrow band emitter in a MOLED was elucidated.
In addition to demonstrating excellent device performance in OLEDs, platinum based complexes exhibit unique photophysical properties including the ability to form excimer emission capable of generating broad white light emission from a single emitter and the ability to form narrow band emission from a rigid, tetradentate molecular structure for select cases. These unique photophysical properties were exploited and their optical and electrical properties in a device setting were elucidated.
Utilizing the unique properties of a tridentate Pt complex, Pt-16, a highly efficient white device employing a single emissive layer exhibited a peak EQE of over 20% and high color quality with a CRI of 80 and color coordinates CIE(x=0.33, y=0.33). Furthermore, by employing a rigid, tetradentate platinum complex, PtN1N, with a narrow band emission into a microcavity organic light emitting diode (MOLED), significant enhancement in the external quantum efficiency was achieved. The optimized MOLED structure achieved a light out-coupling enhancement of 1.35 compared to the non-cavity structure with a peak EQE of 34.2%. In addition to demonstrating a high light out-coupling enhancement, the microcavity effect of a narrow band emitter in a MOLED was elucidated.
ContributorsEcton, Jeremy David (Author) / Li, Jian (Thesis advisor) / Adams, James (Committee member) / Alford, Terry (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