Matching Items (187)
Filtering by
- All Subjects: Computer Science
- Creators: Davulcu, Hasan
- Creators: Ye, Jieping
Description
Currently Java is making its way into the embedded systems and mobile devices like androids. The programs written in Java are compiled into machine independent binary class byte codes. A Java Virtual Machine (JVM) executes these classes. The Java platform additionally specifies the Java Native Interface (JNI). JNI allows Java code that runs within a JVM to interoperate with applications or libraries that are written in other languages and compiled to the host CPU ISA. JNI plays an important role in embedded system as it provides a mechanism to interact with libraries specific to the platform. This thesis addresses the overhead incurred in the JNI due to reflection and serialization when objects are accessed on android based mobile devices. It provides techniques to reduce this overhead. It also provides an API to access objects through its reference through pinning its memory location. The Android emulator was used to evaluate the performance of these techniques and we observed that there was 5 - 10 % performance gain in the new Java Native Interface.
ContributorsChandrian, Preetham (Author) / Lee, Yann-Hang (Thesis advisor) / Davulcu, Hasan (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2011
Description
As pointed out in the keynote speech by H. V. Jagadish in SIGMOD'07, and also commonly agreed in the database community, the usability of structured data by casual users is as important as the data management systems' functionalities. A major hardness of using structured data is the problem of easily retrieving information from them given a user's information needs. Learning and using a structured query language (e.g., SQL and XQuery) is overwhelmingly burdensome for most users, as not only are these languages sophisticated, but the users need to know the data schema. Keyword search provides us with opportunities to conveniently access structured data and potentially significantly enhances the usability of structured data. However, processing keyword search on structured data is challenging due to various types of ambiguities such as structural ambiguity (keyword queries have no structure), keyword ambiguity (the keywords may not be accurate), user preference ambiguity (the user may have implicit preferences that are not indicated in the query), as well as the efficiency challenges due to large search space. This dissertation performs an expansive study on keyword search processing techniques as a gateway for users to access structured data and retrieve desired information. The key issues addressed include: (1) Resolving structural ambiguities in keyword queries by generating meaningful query results, which involves identifying relevant keyword matches, identifying return information, composing query results based on relevant matches and return information. (2) Resolving structural, keyword and user preference ambiguities through result analysis, including snippet generation, result differentiation, result clustering, result summarization/query expansion, etc. (3) Resolving the efficiency challenge in processing keyword search on structured data by utilizing and efficiently maintaining materialized views. These works deliver significant technical contributions towards building a full-fledged search engine for structured data.
ContributorsLiu, Ziyang (Author) / Chen, Yi (Thesis advisor) / Candan, Kasim S (Committee member) / Davulcu, Hasan (Committee member) / Jagadish, H V (Committee member) / Arizona State University (Publisher)
Created2011
Description
Reliable extraction of human pose features that are invariant to view angle and body shape changes is critical for advancing human movement analysis. In this dissertation, the multifactor analysis techniques, including the multilinear analysis and the multifactor Gaussian process methods, have been exploited to extract such invariant pose features from video data by decomposing various key contributing factors, such as pose, view angle, and body shape, in the generation of the image observations. Experimental results have shown that the resulting pose features extracted using the proposed methods exhibit excellent invariance properties to changes in view angles and body shapes. Furthermore, using the proposed invariant multifactor pose features, a suite of simple while effective algorithms have been developed to solve the movement recognition and pose estimation problems. Using these proposed algorithms, excellent human movement analysis results have been obtained, and most of them are superior to those obtained from state-of-the-art algorithms on the same testing datasets. Moreover, a number of key movement analysis challenges, including robust online gesture spotting and multi-camera gesture recognition, have also been addressed in this research. To this end, an online gesture spotting framework has been developed to automatically detect and learn non-gesture movement patterns to improve gesture localization and recognition from continuous data streams using a hidden Markov network. In addition, the optimal data fusion scheme has been investigated for multicamera gesture recognition, and the decision-level camera fusion scheme using the product rule has been found to be optimal for gesture recognition using multiple uncalibrated cameras. Furthermore, the challenge of optimal camera selection in multi-camera gesture recognition has also been tackled. A measure to quantify the complementary strength across cameras has been proposed. Experimental results obtained from a real-life gesture recognition dataset have shown that the optimal camera combinations identified according to the proposed complementary measure always lead to the best gesture recognition results.
ContributorsPeng, Bo (Author) / Qian, Gang (Thesis advisor) / Ye, Jieping (Committee member) / Li, Baoxin (Committee member) / Spanias, Andreas (Committee member) / Arizona State University (Publisher)
Created2011
Description
With the introduction of compressed sensing and sparse representation,many image processing and computer vision problems have been looked at in a new way. Recent trends indicate that many challenging computer vision and image processing problems are being solved using compressive sensing and sparse representation algorithms. This thesis assays some applications of compressive sensing and sparse representation with regards to image enhancement, restoration and classication. The first application deals with image Super-Resolution through compressive sensing based sparse representation. A novel framework is developed for understanding and analyzing some of the implications of compressive sensing in reconstruction and recovery of an image through raw-sampled and trained dictionaries. Properties of the projection operator and the dictionary are examined and the corresponding results presented. In the second application a novel technique for representing image classes uniquely in a high-dimensional space for image classification is presented. In this method, design and implementation strategy of the image classification system through unique affine sparse codes is presented, which leads to state of the art results. This further leads to analysis of some of the properties attributed to these unique sparse codes. In addition to obtaining these codes, a strong classier is designed and implemented to boost the results obtained. Evaluation with publicly available datasets shows that the proposed method outperforms other state of the art results in image classication. The final part of the thesis deals with image denoising with a novel approach towards obtaining high quality denoised image patches using only a single image. A new technique is proposed to obtain highly correlated image patches through sparse representation, which are then subjected to matrix completion to obtain high quality image patches. Experiments suggest that there may exist a structure within a noisy image which can be exploited for denoising through a low-rank constraint.
ContributorsKulkarni, Naveen (Author) / Li, Baoxin (Thesis advisor) / Ye, Jieping (Committee member) / Sen, Arunabha (Committee member) / Arizona State University (Publisher)
Created2011
Description
Genes have widely different pertinences to the etiology and pathology of diseases. Thus, they can be ranked according to their disease-significance on a genomic scale, which is the subject of gene prioritization. Given a set of genes known to be related to a disease, it is reasonable to use them as a basis to determine the significance of other candidate genes, which will then be ranked based on the association they exhibit with respect to the given set of known genes. Experimental and computational data of various kinds have different reliability and relevance to a disease under study. This work presents a gene prioritization method based on integrated biological networks that incorporates and models the various levels of relevance and reliability of diverse sources. The method is shown to achieve significantly higher performance as compared to two well-known gene prioritization algorithms. Essentially, no bias in the performance was seen as it was applied to diseases of diverse ethnology, e.g., monogenic, polygenic and cancer. The method was highly stable and robust against significant levels of noise in the data. Biological networks are often sparse, which can impede the operation of associationbased gene prioritization algorithms such as the one presented here from a computational perspective. As a potential approach to overcome this limitation, we explore the value that transcription factor binding sites can have in elucidating suitable targets. Transcription factors are needed for the expression of most genes, especially in higher organisms and hence genes can be associated via their genetic regulatory properties. While each transcription factor recognizes specific DNA sequence patterns, such patterns are mostly unknown for many transcription factors. Even those that are known are inconsistently reported in the literature, implying a potentially high level of inaccuracy. We developed computational methods for prediction and improvement of transcription factor binding patterns. Tests performed on the improvement method by employing synthetic patterns under various conditions showed that the method is very robust and the patterns produced invariably converge to nearly identical series of patterns. Preliminary tests were conducted to incorporate knowledge from transcription factor binding sites into our networkbased model for prioritization, with encouraging results. Genes have widely different pertinences to the etiology and pathology of diseases. Thus, they can be ranked according to their disease-significance on a genomic scale, which is the subject of gene prioritization. Given a set of genes known to be related to a disease, it is reasonable to use them as a basis to determine the significance of other candidate genes, which will then be ranked based on the association they exhibit with respect to the given set of known genes. Experimental and computational data of various kinds have different reliability and relevance to a disease under study. This work presents a gene prioritization method based on integrated biological networks that incorporates and models the various levels of relevance and reliability of diverse sources. The method is shown to achieve significantly higher performance as compared to two well-known gene prioritization algorithms. Essentially, no bias in the performance was seen as it was applied to diseases of diverse ethnology, e.g., monogenic, polygenic and cancer. The method was highly stable and robust against significant levels of noise in the data. Biological networks are often sparse, which can impede the operation of associationbased gene prioritization algorithms such as the one presented here from a computational perspective. As a potential approach to overcome this limitation, we explore the value that transcription factor binding sites can have in elucidating suitable targets. Transcription factors are needed for the expression of most genes, especially in higher organisms and hence genes can be associated via their genetic regulatory properties. While each transcription factor recognizes specific DNA sequence patterns, such patterns are mostly unknown for many transcription factors. Even those that are known are inconsistently reported in the literature, implying a potentially high level of inaccuracy. We developed computational methods for prediction and improvement of transcription factor binding patterns. Tests performed on the improvement method by employing synthetic patterns under various conditions showed that the method is very robust and the patterns produced invariably converge to nearly identical series of patterns. Preliminary tests were conducted to incorporate knowledge from transcription factor binding sites into our networkbased model for prioritization, with encouraging results. To validate these approaches in a disease-specific context, we built a schizophreniaspecific network based on the inferred associations and performed a comprehensive prioritization of human genes with respect to the disease. These results are expected to be validated empirically, but computational validation using known targets are very positive.
ContributorsLee, Jang (Author) / Gonzalez, Graciela (Thesis advisor) / Ye, Jieping (Committee member) / Davulcu, Hasan (Committee member) / Gallitano-Mendel, Amelia (Committee member) / Arizona State University (Publisher)
Created2011
Description
Bridging semantic gap is one of the fundamental problems in multimedia computing and pattern recognition. The challenge of associating low-level signal with their high-level semantic interpretation is mainly due to the fact that semantics are often conveyed implicitly in a context, relying on interactions among multiple levels of concepts or low-level data entities. Also, additional domain knowledge may often be indispensable for uncovering the underlying semantics, but in most cases such domain knowledge is not readily available from the acquired media streams. Thus, making use of various types of contextual information and leveraging corresponding domain knowledge are vital for effectively associating high-level semantics with low-level signals with higher accuracies in multimedia computing problems. In this work, novel computational methods are explored and developed for incorporating contextual information/domain knowledge in different forms for multimedia computing and pattern recognition problems. Specifically, a novel Bayesian approach with statistical-sampling-based inference is proposed for incorporating a special type of domain knowledge, spatial prior for the underlying shapes; cross-modality correlations via Kernel Canonical Correlation Analysis is explored and the learnt space is then used for associating multimedia contents in different forms; model contextual information as a graph is leveraged for regulating interactions among high-level semantic concepts (e.g., category labels), low-level input signal (e.g., spatial/temporal structure). Four real-world applications, including visual-to-tactile face conversion, photo tag recommendation, wild web video classification and unconstrained consumer video summarization, are selected to demonstrate the effectiveness of the approaches. These applications range from classic research challenges to emerging tasks in multimedia computing. Results from experiments on large-scale real-world data with comparisons to other state-of-the-art methods and subjective evaluations with end users confirmed that the developed approaches exhibit salient advantages, suggesting that they are promising for leveraging contextual information/domain knowledge for a wide range of multimedia computing and pattern recognition problems.
ContributorsWang, Zhesheng (Author) / Li, Baoxin (Thesis advisor) / Sundaram, Hari (Committee member) / Qian, Gang (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2011
Description
Most existing approaches to complex event processing over streaming data rely on the assumption that the matches to the queries are rare and that the goal of the system is to identify these few matches within the incoming deluge of data. In many applications, such as stock market analysis and user credit card purchase pattern monitoring, however the matches to the user queries are in fact plentiful and the system has to efficiently sift through these many matches to locate only the few most preferable matches. In this work, we propose a complex pattern ranking (CPR) framework for specifying top-k pattern queries over streaming data, present new algorithms to support top-k pattern queries in data streaming environments, and verify the effectiveness and efficiency of the proposed algorithms. The developed algorithms identify top-k matching results satisfying both patterns as well as additional criteria. To support real-time processing of the data streams, instead of computing top-k results from scratch for each time window, we maintain top-k results dynamically as new events come and old ones expire. We also develop new top-k join execution strategies that are able to adapt to the changing situations (e.g., sorted and random access costs, join rates) without having to assume a priori presence of data statistics. Experiments show significant improvements over existing approaches.
ContributorsWang, Xinxin (Author) / Candan, K. Selcuk (Thesis advisor) / Chen, Yi (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2011
Description
Data-driven applications are becoming increasingly complex with support for processing events and data streams in a loosely-coupled distributed environment, providing integrated access to heterogeneous data sources such as relational databases and XML documents. This dissertation explores the use of materialized views over structured heterogeneous data sources to support multiple query optimization in a distributed event stream processing framework that supports such applications involving various query expressions for detecting events, monitoring conditions, handling data streams, and querying data. Materialized views store the results of the computed view so that subsequent access to the view retrieves the materialized results, avoiding the cost of recomputing the entire view from base data sources. Using a service-based metadata repository that provides metadata level access to the various language components in the system, a heuristics-based algorithm detects the common subexpressions from the queries represented in a mixed multigraph model over relational and structured XML data sources. These common subexpressions can be relational, XML or a hybrid join over the heterogeneous data sources. This research examines the challenges in the definition and materialization of views when the heterogeneous data sources are retained in their native format, instead of converting the data to a common model. LINQ serves as the materialized view definition language for creating the view definitions. An algorithm is introduced that uses LINQ to create a data structure for the persistence of these hybrid views. Any changes to base data sources used to materialize views are captured and mapped to a delta structure. The deltas are then streamed within the framework for use in the incremental update of the materialized view. Algorithms are presented that use the magic sets query optimization approach to both efficiently materialize the views and to propagate the relevant changes to the views for incremental maintenance. Using representative scenarios over structured heterogeneous data sources, an evaluation of the framework demonstrates an improvement in performance. Thus, defining the LINQ-based materialized views over heterogeneous structured data sources using the detected common subexpressions and incrementally maintaining the views by using magic sets enhances the efficiency of the distributed event stream processing environment.
ContributorsChaudhari, Mahesh Balkrishna (Author) / Dietrich, Suzanne W (Thesis advisor) / Urban, Susan D (Committee member) / Davulcu, Hasan (Committee member) / Chen, Yi (Committee member) / Arizona State University (Publisher)
Created2011
Description
This thesis addresses the problem of online schema updates where the goal is to be able to update relational database schemas without reducing the database system's availability. Unlike some other work in this area, this thesis presents an approach which is completely client-driven and does not require specialized database management systems (DBMS). Also, unlike other client-driven work, this approach provides support for a richer set of schema updates including vertical split (normalization), horizontal split, vertical and horizontal merge (union), difference and intersection. The update process automatically generates a runtime update client from a mapping between the old the new schemas. The solution has been validated by testing it on a relatively small database of around 300,000 records per table and less than 1 Gb, but with limited memory buffer size of 24 Mb. This thesis presents the study of the overhead of the update process as a function of the transaction rates and the batch size used to copy data from the old to the new schema. It shows that the overhead introduced is minimal for medium size applications and that the update can be achieved with no more than one minute of downtime.
ContributorsTyagi, Preetika (Author) / Bazzi, Rida (Thesis advisor) / Candan, Kasim S (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2011
Description
Multi-label learning, which deals with data associated with multiple labels simultaneously, is ubiquitous in real-world applications. To overcome the curse of dimensionality in multi-label learning, in this thesis I study multi-label dimensionality reduction, which extracts a small number of features by removing the irrelevant, redundant, and noisy information while considering the correlation among different labels in multi-label learning. Specifically, I propose Hypergraph Spectral Learning (HSL) to perform dimensionality reduction for multi-label data by exploiting correlations among different labels using a hypergraph. The regularization effect on the classical dimensionality reduction algorithm known as Canonical Correlation Analysis (CCA) is elucidated in this thesis. The relationship between CCA and Orthonormalized Partial Least Squares (OPLS) is also investigated. To perform dimensionality reduction efficiently for large-scale problems, two efficient implementations are proposed for a class of dimensionality reduction algorithms, including canonical correlation analysis, orthonormalized partial least squares, linear discriminant analysis, and hypergraph spectral learning. The first approach is a direct least squares approach which allows the use of different regularization penalties, but is applicable under a certain assumption; the second one is a two-stage approach which can be applied in the regularization setting without any assumption. Furthermore, an online implementation for the same class of dimensionality reduction algorithms is proposed when the data comes sequentially. A Matlab toolbox for multi-label dimensionality reduction has been developed and released. The proposed algorithms have been applied successfully in the Drosophila gene expression pattern image annotation. The experimental results on some benchmark data sets in multi-label learning also demonstrate the effectiveness and efficiency of the proposed algorithms.
ContributorsSun, Liang (Author) / Ye, Jieping (Thesis advisor) / Li, Baoxin (Committee member) / Liu, Huan (Committee member) / Mittelmann, Hans D. (Committee member) / Arizona State University (Publisher)
Created2011