Matching Items (210)
Filtering by
- All Subjects: Computer Science
- All Subjects: Machine Learning
- Creators: Davulcu, Hasan
- Creators: Sen, Arunabha
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
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
Query Expansion is a functionality of search engines that suggest a set of related queries for a user issued keyword query. In case of exploratory or ambiguous keyword queries, the main goal of the user would be to identify and select a specific category of query results among different categorical options, in order to narrow down the search and reach the desired result. Typical corpus-driven keyword query expansion approaches return popular words in the results as expanded queries. These empirical methods fail to cover all semantics of categories present in the query results. More importantly these methods do not consider the semantic relationship between the keywords featured in an expanded query. Contrary to a normal keyword search setting, these factors are non-trivial in an exploratory and ambiguous query setting where the user's precise discernment of different categories present in the query results is more important for making subsequent search decisions. In this thesis, I propose a new framework for keyword query expansion: generating a set of queries that correspond to the categorization of original query results, which is referred as Categorizing query expansion. Two approaches of algorithms are proposed, one that performs clustering as pre-processing step and then generates categorizing expanded queries based on the clusters. The other category of algorithms handle the case of generating quality expanded queries in the presence of imperfect clusters.
ContributorsNatarajan, Sivaramakrishnan (Author) / Chen, Yi (Thesis advisor) / Candan, Selcuk (Committee member) / Sen, Arunabha (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
The video game graphics pipeline has traditionally rendered the scene using a polygonal approach. Advances in modern graphics hardware now allow the rendering of parametric methods. This thesis explores various smooth surface rendering methods that can be integrated into the video game graphics engine. Moving over to parametric or smooth surfaces from the polygonal domain has its share of issues and there is an inherent need to address various rendering bottlenecks that could hamper such a move. The game engine needs to choose an appropriate method based on in-game characteristics of the objects; character and animated objects need more sophisticated methods whereas static objects could use simpler techniques. Scaling the polygon count over various hardware platforms becomes an important factor. Much control is needed over the tessellation levels, either imposed by the hardware limitations or by the application, to be able to adaptively render the mesh without significant loss in performance. This thesis explores several methods that would help game engine developers in making correct design choices by optimally balancing the trade-offs while rendering the scene using smooth surfaces. It proposes a novel technique for adaptive tessellation of triangular meshes that vastly improves speed and tessellation count. It develops an approximate method for rendering Loop subdivision surfaces on tessellation enabled hardware. A taxonomy and evaluation of the methods is provided and a unified rendering system that provides automatic level of detail by switching between the methods is proposed.
ContributorsAmresh, Ashish (Author) / Farin, Gerlad (Thesis advisor) / Razdan, Anshuman (Thesis advisor) / Wonka, Peter (Committee member) / Hansford, Dianne (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
A statement appearing in social media provides a very significant challenge for determining the provenance of the statement. Provenance describes the origin, custody, and ownership of something. Most statements appearing in social media are not published with corresponding provenance data. However, the same characteristics that make the social media environment challenging, including the massive amounts of data available, large numbers of users, and a highly dynamic environment, provide unique and untapped opportunities for solving the provenance problem for social media. Current approaches for tracking provenance data do not scale for online social media and consequently there is a gap in provenance methodologies and technologies providing exciting research opportunities. The guiding vision is the use of social media information itself to realize a useful amount of provenance data for information in social media. This departs from traditional approaches for data provenance which rely on a central store of provenance information. The contemporary online social media environment is an enormous and constantly updated "central store" that can be mined for provenance information that is not readily made available to the average social media user. This research introduces an approach and builds a foundation aimed at realizing a provenance data capability for social media users that is not accessible today.
ContributorsBarbier, Geoffrey P (Author) / Liu, Huan (Thesis advisor) / Bell, Herbert (Committee member) / Li, Baoxin (Committee member) / Sen, Arunabha (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