Matching Items (302)
Filtering by
- Genre: Academic theses
- Creators: Li, Baoxin
- Creators: Liu, Huan
- Creators: Yu, Hongbin
- Resource Type: Text
- Status: Published
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
The increasing popularity of Twitter renders improved trustworthiness and relevance assessment of tweets much more important for search. However, given the limitations on the size of tweets, it is hard to extract measures for ranking from the tweet's content alone. I propose a method of ranking tweets by generating a reputation score for each tweet that is based not just on content, but also additional information from the Twitter ecosystem that consists of users, tweets, and the web pages that tweets link to. This information is obtained by modeling the Twitter ecosystem as a three-layer graph. The reputation score is used to power two novel methods of ranking tweets by propagating the reputation over an agreement graph based on tweets' content similarity. Additionally, I show how the agreement graph helps counter tweet spam. An evaluation of my method on 16~million tweets from the TREC 2011 Microblog Dataset shows that it doubles the precision over baseline Twitter Search and achieves higher precision than current state of the art method. I present a detailed internal empirical evaluation of RAProp in comparison to several alternative approaches proposed by me, as well as external evaluation in comparison to the current state of the art method.
ContributorsRavikumar, Srijith (Author) / Kambhampati, Subbarao (Thesis advisor) / Davulcu, Hasan (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Fluxgate sensors are magnetic field sensors that can measure DC and low frequency AC magnetic fields. They can measure much lower magnetic fields than other magnetic sensors like Hall effect sensors, magnetoresistive sensors etc. They also have high linearity, high sensitivity and low noise. The major application of fluxgate sensors is in magnetometers for the measurement of earth's magnetic field. Magnetometers are used in navigation systems and electronic compasses. Fluxgate sensors can also be used to measure high DC currents. Integrated micro-fluxgate sensors have been developed in recent years. These sensors have much lower power consumption and area compared to their PCB counterparts. The output voltage of micro-fluxgate sensors is very low which makes the analog front end more complex and results in an increase in power consumption of the system. In this thesis a new analog front-end circuit for micro-fluxgate sensors is developed. This analog front-end circuit uses charge pump based excitation circuit and phase delay based read-out chain. With these two features the power consumption of analog front-end is reduced. The output is digital and it is immune to amplitude noise at the output of the sensor. Digital output is produced without using an ADC. A SPICE model of micro-fluxgate sensor is used to verify the operation of the analog front-end and the simulation results show very good linearity.
ContributorsPappu, Karthik (Author) / Bakkaloglu, Bertan (Thesis advisor) / Christen, Jennifer Blain (Committee member) / Yu, Hongbin (Committee member) / Arizona State University (Publisher)
Created2013
Description
Automating aspects of biocuration through biomedical information extraction could significantly impact biomedical research by enabling greater biocuration throughput and improving the feasibility of a wider scope. An important step in biomedical information extraction systems is named entity recognition (NER), where mentions of entities such as proteins and diseases are located within natural-language text and their semantic type is determined. This step is critical for later tasks in an information extraction pipeline, including normalization and relationship extraction. BANNER is a benchmark biomedical NER system using linear-chain conditional random fields and the rich feature set approach. A case study with BANNER locating genes and proteins in biomedical literature is described. The first corpus for disease NER adequate for use as training data is introduced, and employed in a case study of disease NER. The first corpus locating adverse drug reactions (ADRs) in user posts to a health-related social website is also described, and a system to locate and identify ADRs in social media text is created and evaluated. The rich feature set approach to creating NER feature sets is argued to be subject to diminishing returns, implying that additional improvements may require more sophisticated methods for creating the feature set. This motivates the first application of multivariate feature selection with filters and false discovery rate analysis to biomedical NER, resulting in a feature set at least 3 orders of magnitude smaller than the set created by the rich feature set approach. Finally, two novel approaches to NER by modeling the semantics of token sequences are introduced. The first method focuses on the sequence content by using language models to determine whether a sequence resembles entries in a lexicon of entity names or text from an unlabeled corpus more closely. The second method models the distributional semantics of token sequences, determining the similarity between a potential mention and the token sequences from the training data by analyzing the contexts where each sequence appears in a large unlabeled corpus. The second method is shown to improve the performance of BANNER on multiple data sets.
ContributorsLeaman, James Robert (Author) / Gonzalez, Graciela (Thesis advisor) / Baral, Chitta (Thesis advisor) / Cohen, Kevin B (Committee member) / Liu, Huan (Committee member) / Ye, Jieping (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
Integrated photonics requires high gain optical materials in the telecom wavelength range for optical amplifiers and coherent light sources. Erbium (Er) containing materials are ideal candidates due to the 1.5 μm emission from Er3+ ions. However, the Er density in typical Er-doped materials is less than 1 x 1020 cm-3, thus limiting the maximum optical gain to a few dB/cm, too small to be useful for integrated photonics applications. Er compounds could potentially solve this problem since they contain much higher Er density. So far the existing Er compounds suffer from short lifetime and strong upconversion effects, mainly due to poor quality of crystals produced by various methods of thin film growth and deposition. This dissertation explores a new Er compound: erbium chloride silicate (ECS, Er3(SiO4)2Cl ) in the nanowire form, which facilitates the growth of high quality single crystals. Growth methods for such single crystal ECS nanowires have been established. Various structural and optical characterizations have been carried out. The high crystal quality of ECS material leads to a long lifetime of the first excited state of Er3+ ions up to 1 ms at Er density higher than 1022 cm-3. This Er lifetime-density product was found to be the largest among all Er containing materials. A unique integrating sphere method was developed to measure the absorption cross section of ECS nanowires from 440 to 1580 nm. Pump-probe experiments demonstrated a 644 dB/cm signal enhancement from a single ECS wire. It was estimated that such large signal enhancement can overcome the absorption to result in a net material gain, but not sufficient to compensate waveguide propagation loss. In order to suppress the upconversion process in ECS, Ytterbium (Yb) and Yttrium (Y) ions are introduced as substituent ions of Er in the ECS crystal structure to reduce Er density. While the addition of Yb ions only partially succeeded, erbium yttrium chloride silicate (EYCS) with controllable Er density was synthesized successfully. EYCS with 30 at. % Er was found to be the best. It shows the strongest PL emission at 1.5 μm, and thus can be potentially used as a high gain material.
ContributorsYin, Leijun (Author) / Ning, Cun-Zheng (Thesis advisor) / Chamberlin, Ralph (Committee member) / Yu, Hongbin (Committee member) / Menéndez, Jose (Committee member) / Ponce, Fernando (Committee member) / Arizona State University (Publisher)
Created2013
Description
Currently, to interact with computer based systems one needs to learn the specific interface language of that system. In most cases, interaction would be much easier if it could be done in natural language. For that, we will need a module which understands natural language and automatically translates it to the interface language of the system. NL2KR (Natural language to knowledge representation) v.1 system is a prototype of such a system. It is a learning based system that learns new meanings of words in terms of lambda-calculus formulas given an initial lexicon of some words and their meanings and a training corpus of sentences with their translations. As a part of this thesis, we take the prototype NL2KR v.1 system and enhance various components of it to make it usable for somewhat substantial and useful interface languages. We revamped the lexicon learning components, Inverse-lambda and Generalization modules, and redesigned the lexicon learning algorithm which uses these components to learn new meanings of words. Similarly, we re-developed an inbuilt parser of the system in Answer Set Programming (ASP) and also integrated external parser with the system. Apart from this, we added some new rich features like various system configurations and memory cache in the learning component of the NL2KR system. These enhancements helped in learning more meanings of the words, boosted performance of the system by reducing the computation time by a factor of 8 and improved the usability of the system. We evaluated the NL2KR system on iRODS domain. iRODS is a rule-oriented data system, which helps in managing large set of computer files using policies. This system provides a Rule-Oriented interface langauge whose syntactic structure is like any procedural programming language (eg. C). However, direct translation of natural language (NL) to this interface language is difficult. So, for automatic translation of NL to this language, we define a simple intermediate Policy Declarative Language (IPDL) to represent the knowledge in the policies, which then can be directly translated to iRODS rules. We develop a corpus of 100 policy statements and manually translate them to IPDL langauge. This corpus is then used for the evaluation of NL2KR system. We performed 10 fold cross validation on the system. Furthermore, using this corpus, we illustrate how different components of our NL2KR system work.
ContributorsKumbhare, Kanchan Ravishankar (Author) / Baral, Chitta (Thesis advisor) / Ye, Jieping (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2013
Description
We solve the problem of activity verification in the context of sustainability. Activity verification is the process of proving the user assertions pertaining to a certain activity performed by the user. Our motivation lies in incentivizing the user for engaging in sustainable activities like taking public transport or recycling. Such incentivization schemes require the system to verify the claim made by the user. The system verifies these claims by analyzing the supporting evidence captured by the user while performing the activity. The proliferation of portable smart-phones in the past few years has provided us with a ubiquitous and relatively cheap platform, having multiple sensors like accelerometer, gyroscope, microphone etc. to capture this evidence data in-situ. In this research, we investigate the supervised and semi-supervised learning techniques for activity verification. Both these techniques make use the data set constructed using the evidence submitted by the user. Supervised learning makes use of annotated evidence data to build a function to predict the class labels of the unlabeled data points. The evidence data captured can be either unimodal or multimodal in nature. We use the accelerometer data as evidence for transportation mode verification and image data as evidence for recycling verification. After training the system, we achieve maximum accuracy of 94% when classifying the transport mode and 81% when detecting recycle activity. In the case of recycle verification, we could improve the classification accuracy by asking the user for more evidence. We present some techniques to ask the user for the next best piece of evidence that maximizes the probability of classification. Using these techniques for detecting recycle activity, the accuracy increases to 93%. The major disadvantage of using supervised models is that it requires extensive annotated training data, which expensive to collect. Due to the limited training data, we look at the graph based inductive semi-supervised learning methods to propagate the labels among the unlabeled samples. In the semi-supervised approach, we represent each instance in the data set as a node in the graph. Since it is a complete graph, edges interconnect these nodes, with each edge having some weight representing the similarity between the points. We propagate the labels in this graph, based on the proximity of the data points to the labeled nodes. We estimate the performance of these algorithms by measuring how close the probability distribution of the data after label propagation is to the probability distribution of the ground truth data. Since labeling has a cost associated with it, in this thesis we propose two algorithms that help us in selecting minimum number of labeled points to propagate the labels accurately. Our proposed algorithm achieves a maximum of 73% increase in performance when compared to the baseline algorithm.
ContributorsDesai, Vaishnav (Author) / Sundaram, Hari (Thesis advisor) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
This dissertation is on the study of structural and optical properties of some III-V and II-VI compound semiconductors. The first part of this dissertation is a study of the deformation mechanisms associated with nanoindentation and nanoscratching of InP, GaN, and ZnO crystals. The second part is an investigation of some fundamental issues regarding compositional fluctuations and microstructure in GaInNAs and InAlN alloys. In the first part, the microstructure of (001) InP scratched in an atomic force microscope with a small diamond tip has been studied as a function of applied normal force and crystalline direction in order to understand at the nanometer scale the deformation mechanisms in the zinc-blende structure. TEM images show deeper dislocation propagation for scratches along <110> compared to <100>. High strain fields were observed in <100> scratches, indicating hardening due to locking of dislocations gliding on different slip planes. Reverse plastic flow have been observed in <110> scratches in the form of pop-up events that result from recovery of stored elastic strain. In a separate study, nanoindentation-induced plastic deformation has been studied in c-, a-, and m-plane ZnO single crystals and c-plane GaN respectively, to study the deformation mechanism in wurtzite hexagonal structures. TEM results reveal that the prime deformation mechanism is slip on basal planes and in some cases, on pyramidal planes, and strain built up along particular directions. No evidence of phase transformation or cracking was observed in both materials. CL imaging reveals quenching of near band-edge emission by dislocations. In the second part, compositional inhomogeneity in quaternary GaInNAs and ternary InAlN alloys has been studied using TEM. It is shown that exposure to antimony during growth of GaInNAs results in uniform chemical composition in the epilayer, as antimony suppresses the surface mobility of adatoms that otherwise leads to two-dimensional growth and elemental segregation. In a separate study, compositional instability is observed in lattice-matched InAlN films grown on GaN, for growth beyond a certain thickness. Beyond 200 nm of thickness, two sub-layers with different indium content are observed, the top one with lower indium content.
ContributorsHuang, Jingyi (Author) / Ponce, Fernando A. (Thesis advisor) / Carpenter, Ray W (Committee member) / Smith, David J. (Committee member) / Yu, Hongbin (Committee member) / Treacy, Michael Mj (Committee member) / Arizona State University (Publisher)
Created2013
Description
One dimensional (1D) and quasi-one dimensional quantum wires have been a subject of both theoretical and experimental interest since 1990s and before. Phenomena such as the "0.7 structure" in the conductance leave many open questions. In this dissertation, I study the properties and the internal electron states of semiconductor quantum wires with the path integral Monte Carlo (PIMC) method. PIMC is a tool for simulating many-body quantum systems at finite temperature. Its ability to calculate thermodynamic properties and various correlation functions makes it an ideal tool in bridging experiments with theories. A general study of the features interpreted by the Luttinger liquid theory and observed in experiments is first presented, showing the need for new PIMC calculations in this field. I calculate the DC conductance at finite temperature for both noninteracting and interacting electrons. The quantized conductance is identified in PIMC simulations without making the same approximation in the Luttinger model. The low electron density regime is subject to strong interactions, since the kinetic energy decreases faster than the Coulomb interaction at low density. An electron state called the Wigner crystal has been proposed in this regime for quasi-1D wires. By using PIMC, I observe the zig-zag structure of the Wigner crystal. The quantum fluctuations suppress the long range correla- tions, making the order short-ranged. Spin correlations are calculated and used to evaluate the spin coupling strength in a zig-zag state. I also find that as the density increases, electrons undergo a structural phase transition to a dimer state, in which two electrons of opposite spins are coupled across the two rows of the zig-zag. A phase diagram is sketched for a range of densities and transverse confinements. The quantum point contact (QPC) is a typical realization of quantum wires. I study the QPC by explicitly simulating a system of electrons in and around a Timp potential (Timp, 1992). Localization of a single electron in the middle of the channel is observed at 5 K, as the split gate voltage increases. The DC conductance is calculated, which shows the effect of the Coulomb interaction. At 1 K and low electron density, a state similar to the Wigner crystal is found inside the channel.
ContributorsLiu, Jianheng, 1982- (Author) / Shumway, John B (Thesis advisor) / Schmidt, Kevin E (Committee member) / Chen, Tingyong (Committee member) / Yu, Hongbin (Committee member) / Ros, Robert (Committee member) / Arizona State University (Publisher)
Created2012