Search Content

Batch mode active learning for multimedia pattern recognition

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…

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

Estimations of reductions in household vehicle miles traveled under scenarios of shifts in vehicle type choice

Description

Vehicle type choice is a significant determinant of fuel consumption and energy sustainability; larger, heavier vehicles consume more fuel, and expel twice as many pollutants, than their smaller, lighter counterparts. Over the course of the past few decades, vehicle type choice has seen a vast shift, due to many households…

Vehicle type choice is a significant determinant of fuel consumption and energy sustainability; larger, heavier vehicles consume more fuel, and expel twice as many pollutants, than their smaller, lighter counterparts. Over the course of the past few decades, vehicle type choice has seen a vast shift, due to many households making more trips in larger vehicles with lower fuel economy. During the 1990s, SUVs were the fastest growing segment of the automotive industry, comprising 7% of the total light vehicle market in 1990, and 25% in 2005. More recently, due to rising oil prices, greater awareness to environmental sensitivity, the desire to reduce dependence on foreign oil, and the availability of new vehicle technologies, many households are considering the use of newer vehicles with better fuel economy, such as hybrids and electric vehicles, over the use of the SUV or low fuel economy vehicles they may already own. The goal of this research is to examine how vehicle miles traveled, fuel consumption and emissions may be reduced through shifts in vehicle type choice behavior. Using the 2009 National Household Travel Survey data it is possible to develop a model to estimate household travel demand and total fuel consumption. If given a vehicle choice shift scenario, using the model it would be possible to calculate the potential fuel consumption savings that would result from such a shift. In this way, it is possible to estimate fuel consumption reductions that would take place under a wide variety of scenarios.

ContributorsChristian, Keith (Author) / Pendyala, Ram M. (Thesis advisor) / Chester, Mikhail (Committee member) / Kaloush, Kamil (Committee member) / Ahn, Soyoung (Committee member) / Arizona State University (Publisher)

Created2013

Building adaptive computational systems for physiological and biomedical data

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.…

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

Robust implementation of NL2KR system and it's application in iRODS domain

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…

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

Texture structure analysis

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…

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

Development of paint stripe testing protocol

Description

Nighttime visibility of pavement markings is provided by glass beads embedded into the striping surface. The glass beads take light from the vehicle headlamps and reflect it back to the driver. This phenomenon is known as retroreflection. Literature suggests that the amount of the bead embedded into the striping surface…

Nighttime visibility of pavement markings is provided by glass beads embedded into the striping surface. The glass beads take light from the vehicle headlamps and reflect it back to the driver. This phenomenon is known as retroreflection. Literature suggests that the amount of the bead embedded into the striping surface has a profound impact on the intensity of the retroreflected light. In order to gain insight into how the glass beads provide retroreflection, an experiment was carried out to produce paint stripes with glass beads and measure the retroreflection. Samples were created at various application rates and embedment depths, in an attempt to verify the optimal embedment and observe the effect of application rate on retroreflection. The experiment was conducted using large, airport quality beads and small, road quality beads. Image analysis was used to calculate the degree to which beads were embedded and in an attempt to quantify bead distribution on the stripe surface. The results from the large beads showed that retroreflection was maximized when the beads were embedded approximately seventy percent by bead volume. The results also showed that as the application rate increased, the retroreflection increased, up to a point and then decreased. A model was developed to estimate the retroreflectivity given the amount of beads, bead spacing, and distribution of bead embedment. Results from the small beads were less conclusive, but did demonstrate that the larger beads are better at providing retroreflection. Avenues for future work in this area were identified as the experiment was conducted.

ContributorsStevens, Ryan David (Author) / Underwood, Shane (Thesis advisor) / Kaloush, Kamil (Committee member) / Mamlouk, Michael S. (Committee member) / Arizona State University (Publisher)

Created2014

Demographic evolution modeling system for activity-based travel behavior analysis and demand forecasting

Description

The activity-based approach to travel demand analysis and modeling, which has been developed over the past 30 years, has received tremendous success in transportation planning and policy analysis issues, capturing the multi-way joint relationships among socio-demographic, economic, land use characteristics, activity participation, and travel behavior. The development of synthesizing population…

The activity-based approach to travel demand analysis and modeling, which has been developed over the past 30 years, has received tremendous success in transportation planning and policy analysis issues, capturing the multi-way joint relationships among socio-demographic, economic, land use characteristics, activity participation, and travel behavior. The development of synthesizing population with an array of socio-demographic and socio-economic attributes has drawn remarkable attention due to privacy and cost constraints in collecting and disclosing full scale data. Although, there has been enormous progress in producing synthetic population, there has been less progress in the development of population evolution modeling arena to forecast future year population. The objective of this dissertation is to develop a well-structured full-fledged demographic evolution modeling system, capturing migration dynamics and evolution of person level attributes, introducing the concept of new household formations and apprehending the dynamics of household level long-term choices over time. A comprehensive study has been conducted on demography, sociology, anthropology, economics and transportation engineering area to better understand the dynamics of evolutionary activities over time and their impacts in travel behavior. This dissertation describes the methodology and the conceptual framework, and the development of model components. Demographic, socio-economic, and land use data from American Community Survey, National Household Travel Survey, Census PUMS, United States Time Series Economic Dynamic data and United States Center for Disease Control and Prevention have been used in this research. The entire modeling system has been implemented and coded using programming language to develop the population evolution module named `PopEvol' into a computer simulation environment. The module then has been demonstrated for a portion of Maricopa County area in Arizona to predict the milestone year population to check the accuracy of forecasting. The module has also been used to evolve the base year population for next 15 years and the evolutionary trend has been investigated.

ContributorsPaul, Sanjay (Author) / Pendyala, Ram M. (Thesis advisor) / Kaloush, Kamil (Committee member) / Ahn, Soyoung (Committee member) / Arizona State University (Publisher)

Created2014

The effects of a visual disability on marital relationships

Description

This qualitative study examines the major changes in relationship closeness of married couples when one spouse acquires a vision disability. Turning Points analysis and Retrospective Interview Technique (RIT) were utilized which required participants to plot their relational journey on a graph after the onset of the disability. A sample of…

This qualitative study examines the major changes in relationship closeness of married couples when one spouse acquires a vision disability. Turning Points analysis and Retrospective Interview Technique (RIT) were utilized which required participants to plot their relational journey on a graph after the onset of the disability. A sample of 32 participants generating 100 unique turning points and 32 RIT graphs lent in-depth insight into the less explored area of the impact of a visual disability on marital relationships. A constant comparison method employed for the analysis of these turning points revealed six major categories, which include Change in Relational Dynamics, Realization of the Disability, Regaining Normality in Life, Resilience, Reactions to Assistance, and Dealing with the Disability. These turning points differ in terms of their positive or negative impact on the relational closeness between partners. In addition, the 32 individual RIT graphs were also analyzed and were grouped into four categories based on visual similarity, which include Erratic Relational Restoration, Erratic Relational Increase, Consistent Closeness and Gradual Relational Increase. Results provide theoretical contributions to disability and marriage literature. Implications for the application of turning points to the study of post-disability marital relationships are also discussed, and research directions identified.

ContributorsBhagchandani, Bhoomika (Author) / Kassing, Jeffrey W. (Thesis advisor) / Kelley, Douglas L. (Committee member) / Fisher, Carla L. (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)

Created2014

Multi-task learning and its applications to biomedical informatics

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…

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

Use of micro-mechanical models to study the mastic level structure of asphalt concretes containing reclaimed asphalt pavement

Description

This study investigates the mastic level structure of asphalt concrete containing RAP materials. Locally sourced RAP material was screened and sieved to separate the coated fines (passing #200) from the remaining sizes. These binder coated fines were mixed with virgin filler at proportions commensurate with 0%, 10%, 30%, 50% and…

This study investigates the mastic level structure of asphalt concrete containing RAP materials. Locally sourced RAP material was screened and sieved to separate the coated fines (passing #200) from the remaining sizes. These binder coated fines were mixed with virgin filler at proportions commensurate with 0%, 10%, 30%, 50% and 100% RAP dosage levels. Mastics were prepared with these blended fillers and a PG 64-22 binder at a filler content of 27% by volume. Rheological experiments were conducted on the resulting composites as well as the constituents, virgin binder, solvent extracted RAP binder. The results from the dynamic modulus experiments showed an expected increase in stiffness with increase in dosage levels. These results were used to model the hypothesized structure of the composite. The study presented discusses the different micromechanical models employed, their applicability and suitability to correctly predict the blended mastic composite. The percentage of blending between virgin and RAP binder estimated using Herve and Zaoui model decreased with increase in RAP content.

ContributorsGundla, Akshay (Author) / Underwood, Shane (Thesis advisor) / Kaloush, Kamil (Committee member) / Mamlouk, Michael S. (Committee member) / Arizona State University (Publisher)

Created2014

ASU Electronic Theses and Dissertations