Search

The Coronavirus has spread across the world and infected millions of people, causing devastating damage to the public health and global economies. To mitigate the impact of the coronavirus a reliable, fast, and accurate diagnostic system should be promptly implemented. In this study, we propose EpistoNet, a decision tree-based ensemble model using two mixtures of discriminative experts to classify COVID-19 lung infection from chest X-ray images. To optimize the architecture and hyper-parameters of the designed neural networks, we employed Epistocracy algorithm, a novel hyper-heuristic evolutionary method. Using 2,500 chest X-ray images consisting of 1,250 COVID-19 and 1,250 non-COVID-19 cases, we left out 500 images for testing and partitioned the remaining 2,000 images into 5 different clusters using K-means clustering algorithm. We trained multiple deep convolutional neural networks on each cluster to help build a mixture of strong discriminative experts from the top-performing models supervised by a gating network. The final ensemble model obtained 95% accuracy on COVID-19 images and 93% accuracy on non-COVID-19. The experimental results show that EpistoNet can accurately, and reliably be used to detect COVID-19 infection in the chest X-ray images, and Epistocracy algorithm can be effectively used to optimize the hyper-parameters of the proposed models.

This paper proposes a novel evolutionary algorithm called Epistocracy which incorporates human socio-political behavior and intelligence to solve complex optimization problems. The inspiration of the Epistocracy algorithm originates from a political regime where educated people have more voting power than the uneducated or less educated. The algorithm is a self-adaptive, and multi-population optimizer in which the evolution process takes place in parallel for many populations led by a council of leaders. To avoid stagnation in poor local optima and to prevent a premature convergence, the algorithm employs multiple mechanisms such as dynamic and adaptive leadership based on gravitational force, dynamic population allocation and diversification, variance-based step-size determination, and regression-based leadership adjustment. The algorithm uses a stratified sampling method called Latin Hypercube Sampling (LHS) to distribute the initial population more evenly for exploration of the search space and exploitation of the accumulated knowledge. To investigate the performance and evaluate the reliability of the algorithm, we have used a set of multimodal benchmark functions, and then applied the algorithm to the MNIST dataset to further verify the accuracy, scalability, and robustness of the algorithm. Experimental results show that the Epistocracy algorithm outperforms the tested state-of-the-art evolutionary and swarm intelligence algorithms in terms of performance, precision, and convergence.

Introduction: The Coronavirus has spread across the globe and infected millions of people, having devastating effect on the global public health and economies. A fast diagnostic system should be implemented to mitigate the impact of the virus and save lives. In this study, we propose a decision tree-based ensemble model using two mixtures of discriminative experts (MoE) to classify COVID-19 and non-COVID-19 lung infections on chest X-ray images. The Epistocracy algorithm, a hyper-heuristic evolutionary method, is employed to optimize the neural networks used in this work. Using this approach can help detect COVID-19 cases and accelerate treatment of those who need it the most. Data: we collected 2,500 chest X-ray images from Henry Ford Health System consisting of 1,250 Covid images and 1,250 non-Covid images. The input images have been cropped and resized to 224 by 224 pixels. Out of 2,500 images, we left out 500 images containing 250 Covid and 250 non-Covid for testing. The rest, 2,000 images, were used 80% for training and 20% for validation. Methods and Results: To improve the accuracy of the proposed model, first we divided our 2,000 images into 5 different clusters using K-Means clustering algorithm with VGG16 feature extractor to help build strong discriminative expert models to be used in our proposed classifier. We trained VGG16, VGG19, InceptionV3, InceptionResNetV2, MobileNetV2, EfficientNetB7, Xception, and DenseNet201 to classify each cluster into Covid and non-Covid cases. The best result was obtained from VGG16 as a base model with a deep neural network as a head model optimized by Epistocracy algorithm. Then we built a mixture of transfer learning-based experts consisting of 5 different VGG16 models supervised by InceptionV3 as a gating network. Finally, we built a decision tree-based ensemble model to determine the classification of the data using two different MoEs with highest accuracies. As a result, for initial clusters c1, c2, c3, c4, and c5 we obtained validation accuracy of 92.50%, 86.30%, 86.51%, 85.34%, and 93.62% respectively. The first MoE had 93.75% accuracy on validation, and the second MoE had 94.25%. The final ensemble model on average obtained 94% accuracy on the testing dataset. More specifically, we got 96% accuracy on Covid images and 92% accuracy on non-Covid. Conclusion: we showed that an ensemble model consisting of two mixtures of cluster-based discriminative convolutional neural network experts can be used to detect Covid from non-Covid with high accuracy, and Epistocracy algorithm can be effectively used to optimize the hyper-parameters of the proposed models. Citation Format: Seyed Ziae Mousavi Mojab, Seyedmohammad Shams, Farshad Fotouhi, Hamid Soltanian-Zadeh. EpistoNet: An ensemble of deep convolutional neural networks using mixture of discriminative experts for detecting COVID-19 on chest X-ray images [abstract]. In: Proceedings of the AACR Virtual Meeting: COVID-19 and Cancer; 2021 Feb 3-5. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(6_Suppl):Abstract nr P05.

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices.

Provenance has become increasingly important in scientific workflows to understand, verify, and reproduce the result of scientific data analysis. Most existing systems store provenance data in provenance stores with proprietary provenance data models and conduct query processing over the physical provenance storages using query languages, such as SQL, SPARQL, and XQuery, which are closely coupled to the underlying storage strategies. Querying provenance at such low level leads to poor usability of the system: a user needs to know the underlying schema to formulate queries; if the schema changes, queries need to be reformulated; and queries formulated for one system will not run in another system. In this paper, we present OPQL, a provenance query language that enables the querying of provenance directly at the graph level. An OPQL query takes a provenance graph as input and produces another provenance graph as output. Therefore, OPQL queries are not tightly coupled to the underlying provenance storage strategies. Our main contributions are: (i) we design OPQL, including six types of graph patterns, a provenance graph algebra, and OPQL syntax and semantics, that supports querying provenance at the graph level; (ii) we implement OPQL using a Web service via our OPMProv system; therefore, users can invoke the Web service to execute OPQL queries in a provenance browser, called OPMProVis. The result of OPQL queries is displayed as a provenance graph in OPMProVis. An experimental study is conducted to evaluate the feasibility and performance of OPMProv on OPQL provenance querying.

Provenance, the metadata that records the derivation history of scientific results, is essential in scientific workflows to support the reproducibility of scientific discovery, result interpretation, and problem diagnosis. To promote and facilitate interoperability among heterogeneous provenance systems, the Open Provenance Model (OPM) was first proposed in 2008 and since then has played an important role in the community. In this paper, we present OPMProv, a relational database-based scientific workflow provenance system, that is compliant with OPM (v1.1). Our main contributions are: (i) we design an entity-relationship diagram for OPM and translate it into a relational database schema for the storage of provenance; (ii) we show that provenance reasoning defined in OPM (v1.1) can be sufficiently supported by OPMProv using recursive views and SQL queries alone without any additional reasoning engine. Experiments are conducted to evaluate the performance of OPMProv in data insertion and provenance querying. A case study is performed, demonstrating that OPMProv can answer all except two queries out of the 16 queries defined in the Third Provenance Challenge.

XML is rapidly emerging as a standard for data representation and exchange over the World Wide Web and an increasing amount of sensitive business data is processed in XML format. Therefore, it is critical to have control mechanisms to restrict a user to access only the parts of XML documents that she is authorized to access. In this paper, we propose the first DTD-based access control model that employs graph matching to analyze if an input query is fully acceptable, fully rejectable, or partially acceptable. In this way, there will be no further security overhead for the processing of fully acceptable and rejectable queries. For partially acceptable queries, we propose a graph-matching based authorization model for an optimized rewriting procedure in which a recursive query (query with descendant axis `//') will be rewritten into an equivalent recursive one if possible and into a non-recursive one only if necessary, resulting queries that can fully take advantage of structural join based query optimization techniques. Moreover, we propose an index structure for XML element types to speed up the query rewriting procedure, a facility that is potentially useful for applications with large DTDs. Our performance study results showed that our algorithms armed with rewriting indexes are promising.

Provenance has become increasingly important in scientific workflows and services computing to capture the derivation history of a data product, including the original data sources, intermediate data products, and the steps that were applied to produce the data product. In many cases, both scientific results and the used protocol are sensitive and effective access control mechanisms are essential to protect their confidentiality. In this paper, we propose: 1) a formal scientific workflow provenance model as the basis for querying and access control for workflow provenance; 2) a security model for fine-grained access control for multilevel provenance and an algorithm for the derivation of a full security specification based on inheritance, overriding, and conflict resolution; 3) a formalization of the notion of security views and an algorithm for security view derivation; and 4) a formalization of the notion of secure abstraction views and an algorithm for its computation. A prototype called SecProv has been developed, and experiments show the effectiveness and efficiency of our approach.

Provenance metadata has become increasingly important to support scientific discovery reproducibility, result interpretation, and problem diagnosis in scientific workflow environments. The provenance management problem concerns the efficiency and effectiveness of the modeling, recording, representation, integration, storage, and querying of provenance metadata. Our approach to provenance management seamlessly integrates the interoperability, extensibility, and inference advantages of Semantic Web technologies with the storage and querying power of an RDBMS to meet the emerging requirements of scientific workflow provenance management. In this paper, we elaborate on the design of a relational RDF store, called RDFProv, which is optimized for scientific workflow provenance querying and management. Specifically, we propose: i) two schema mapping algorithms to map an OWL provenance ontology to a relational database schema that is optimized for common provenance queries; ii) three efficient data mapping algorithms to map provenance RDF metadata to relational data according to the generated relational database schema, and iii) a schema-independent SPARQL-to-SQL translation algorithm that is optimized on-the-fly by using the type information of an instance available from the input provenance ontology and the statistics of the sizes of the tables in the database. Experimental results are presented to show that our algorithms are efficient and scalable. The comparison with two popular relational RDF stores, Jena and Sesame, and two commercial native RDF stores, AllegroGraph and BigOWLIM, showed that our optimizations result in improved performance and scalability for provenance metadata management. Finally, our case study for provenance management in a real-life biological simulation workflow showed the production quality and capability of the RDFProv system. Although presented in the context of scientific workflow provenance management, many of our proposed techniques apply to general RDF data management as well.

In this paper, we address the problem of camera and object motion detection in the compressed domain. The estimation of camera motion and the moving object segmentation have been widely stated in a variety of context for video analysis, due to their capabilities of providing essential clues for interpreting the high-level semantics of video sequences. A novel compressed domain motion estimation and segmentation scheme is presented and applied in this paper. MPEG-2 compressed domain information, namely Motion Vectors (MV) and Discrete Cosine Transform (DCT) coefficients, is filtered and manipulated to obtain a dense and reliable Motion Vector Field (MVF) over consecutive frames. An iterative segmentation scheme based upon the generalized affine transformation model is exploited to effect the global camera motion detection. The foreground spatiotemporal objects are separated from the background using the temporal consistency check to the output of the iterative segmentation. This consistency check process can coalesce the resulting foreground blocks and weed out unqualified blocks. Illustrative examples are provided to demonstrate the efficacy of the proposed approach.

Most existing RDF stores, which serve as metadata repositories on the Semantic Web, use an RDBMS as a backend to manage RDF data. This motivates us to study the problem of translating SPARQL queries into equivalent SQL queries, which further can be optimized and evaluated by the relational query engine and their results can be returned as SPARQL query solutions. The main contributions of our research are: (i) We formalize a relational algebra based semantics of SPARQL, which bridges the gap between SPARQL and SQL query languages, and prove that our semantics is equivalent to the mapping-based semantics of SPARQL; (ii) Based on this semantics, we propose the first provably semantics preserving SPARQL-to-SQL translation for SPARQL triple patterns, basic graph patterns, optional graph patterns, alternative graph patterns, and value constraints; (iii) Our translation algorithm is generic and can be directly applied to existing RDBMS-based RDF stores; and (iv) We outline a number of simplifications for the SPARQL-to-SQL translation to generate simpler and more efficient SQL queries and extend our defined semantics and translation to support the bag semantics of a SPARQL query solution. The experimental study showed that our proposed generic translation can serve as a good alternative to existing schema dependent translations in terms of efficient query evaluation and/or ensured query result correctness.

Relational technology has shown to be very useful for scalable Semantic Web data management. Numerous researchers have proposed to use RDBMSs to store and query voluminous RDF data using SQL and RDF query languages. In this article, we study how RDF queries with the socalled well-designed graph patterns and nested optional patterns can be efficiently evaluated in an RDBMS. We propose to extend relational databases with a novel relational operator, nested optional join (NOJ), that is more efficient than left outer join in processing nested optional patterns of well-designed graph patterns. We design three efficient algorithms to implement the new operator in relational databases: (1) nested-loops NOJ algorithm (NL-NOJ); (2) sortmerge NOJ algorithm (SM-NOJ); and (3) simple hash NOJ algorithm (SH-NOJ). Based on a real-life RDF dataset, we demonstrate the efficiency of our algorithms by comparing them with the corresponding left outer join implementations and explore the effect of join selectivity on the performance of our algorithms.

This paper presents an analysis of several different LSI (latent semantic indexing) query approaches and proposes a novel rescaling technique, namely singular value rescaling (SVR). Experiments on a standardized TREC data set confirmed the effectiveness of SVR, showing an improvement ratio of 5.9% over the best conventional LSI query approach. In addition, we also compared SVR with another scaling technique in text retrieval called iterative residual rescaling (IRR). Experiments on TREC data set show that SVR performs better than IRR.

Data co-clustering refers to the problem of simultaneous clustering of two data types. Typically, the data is stored in a contingency or co-occurrence matrix C where rows and columns of the matrix represent the data types to be co-clustered. An entry C ij of the matrix signifies the relation between the data type represented by row i and column j. Co-clustering is the problem of deriving sub-matrices from the larger data matrix by simultaneously clustering rows and columns of the data matrix. In this paper, we present a novel graph theoretic approach to data co-clustering. The two data types are modeled as the two sets of vertices of a weighted bipartite graph. We then propose Isoperimetric Co-clustering Algorithm (ICA)--a new method for partitioning the bipartite graph. ICA requires a simple solution to a sparse system of linear equations instead of the eigenvalue or SVD problem in the popular spectral co-clustering approach. Our theoretical analysis and extensive experiments performed on publicly available datasets demonstrate the advantages of ICA over other approaches in terms of the quality, efficiency and stability in partitioning the bipartite graph.

Numerous researchers have proposed to use relational databases to store and query XML documents. In these systems, the elements selected by an XML query are returned to an application either by select mode or by reconstruct mode. For the reconstruct mode, the XML subtrees that are rooted at the selected elements need to be extracted and reconstructed from the relational storage of XML documents. Therefore, XML subtree reconstruction is an important problem since its efficiency has a significant impact on XML query response time. In this paper, we propose (i) a linear XML subtree reconstruction algorithm Reconstruct to reconstruct an XML subtree from the structure-encoded sequence of the subtree that is extracted from the relational database by a structure-encoded sequence retrieval algorithm, (ii) a generic efficient structure-encoded sequence retrieval algorithm RD-SB for a schema-based relational XML storage, and (iii) a generic efficient structure-encoded sequence retrieval algorithm RD-SL for a schema-less relational XML storage. To the best of our knowledge, our algorithms provide the first generic solutions to the XML subtree reconstruction problem that are applicable to all relational XML storage schemes proposed in the literature. Finally, our experiments show that our algorithms are efficient and scalable.

Storing and querying XML documents using a RDBMS is a challenging problem since one needs to resolve the conflict between the hierarchical, ordered nature of the XML data model and the flat, unordered nature of the relational data model. This conflict can be resolved by the following XML-to-Relational mappings: schema mapping, data mapping and query mapping. In this paper, we propose: (i) a lossless schema mapping algorithm to generate a database schema from a DTD, which makes several improvements over existing algorithms, (ii) two linear data mapping algorithms based on DOM and SAX, respectively, to map ordered XML data to relational data. To our best knowledge, there is no published linear schema-based data mapping algorithm for mapping ordered XML data to relational data. Experimental results are presented to show that our algorithms are efficient and scalable.

Relevance feedback and semantic retrieval have received extensive attention recently in the computer vision community. In this article, we present a semantic image query system with integrated feedback mechanism. Our system has two major components: the low-level feature space and the semantic space. In the low-level feature space, images are described by multidimensional vectors and are clustered based on the similarity of their contents. In the semantic space, the relationship among keywords is captured by a semantic hierarchy built by the aid of WordNet. Based on our system architecture, we propose a novel feedback solution for semantic retrieval called semantic feedback, which allows our system to interact with users directly at the semantic level. The short-term and long-term learning process of the semantic feedback substantially improves the image retrieval and annotation performance of our system. We demonstrate the effectiveness of our approach with experiments using 5,000 images from Corel database. The significant contribution of this article is in the scenario of having a relatively small training data set compared to the testing data set. Some of the previous work in the same direction has chosen a very large training set and a very small testing set. Clearly, the problem that we try to solve is more realistic and challenging.

The development of the Semantic Web, the next-generation Web, greatly relies on the availability of ontologies and powerful annotation tools. However, there is a lack of ontology-based annotation tools for linguistic multimedia data. Existing tools either lack ontology support or provide limited support for multimedia. To fill the gap, we present an ontology-based linguistic multimedia annotation tool, OntoELAN, which features: (1) the support for OWL ontologies; (2) the management of language profiles, which allow the user to choose a subset of ontological terms for annotation; (3) the management of ontological tiers, which can be annotated with language profile terms and, therefore, corresponding ontological terms; and (4) storing OntoELAN annotation documents in XML format based on multimedia and domain ontologies. To our best knowledge, OntoELAN is the first audio/video annotation tool in the linguistic domain that provides support for ontology-based annotation. It is expected that the availability of such a tool will greatly facilitate the creation of linguistic multimedia repositories as islands of the Semantic Web of language engineering.

In this paper, we describe the architecture of a protein interaction database and tools for manipulating Drosophila protein interaction data. The proposed system not only maintains interaction data collected by an experiment, but also associates the interaction data with valuable data from various genomic databases. The system inherits a layered-modular architecture by introducing a wrapper-mediator approach in order to solve the syntactic and semantic heterogeneity among multiple data sources. The component modules for wrapping and integrating the relevant data, querying the database, and visualizing the interaction data among proteins are discussed. The system wrapped the relevant data for 14,000 Drosophila proteins from 5 publicly accessible sources. A web-based query interface is developed to browse the database and a query result can be viewed as in a protein interaction map depicting functional pathways, complexes or networks. Protein interaction maps aid in understanding or predicting potential functions for uncharacterized proteins and in describing their functional networks in a biological context. We show that the proposed approach supports data association and data interoperability in a protein interaction database.

Temporal Object System (TOS) handles the structural and stature changes to an object in a uniform and temporal fashion. The TOS takes a hybrid approach of the class-based and prototype-based approaches in modeling the real-word objects and knowledge sharing among the objects. This hybrid approach makes it flexible than the two approaches, i.e., the class-based approach and the prototype-based approach. In this paper, we propose a model of knowledge sharing mechanism, Share-kno (SK) for object hierarchy of the TOS. We also formally prove that the Share-kno (SK) model encapsulates more knowledge than the inheritance hierarchy and delegation hierarchy models proposed by Stein.

A hypermedia system connects various types of information into a network where related nodes of information (text, audio, video) are connected by links. Clustering these nodes is an effective way to reduce information-overhead, allowing the user to browse through the clusters as well as the individual nodes. In this paper, we compare the use of two adaptive algorithms (genetic algorithms, and neural networks) in clustering hypermedia documents. These clusters allow the user to index into this overwhelming number of nodes and find needed information quickly. We base the clustering on the user's paths through the hypermedia document and not on the content of the nodes or the structure of the links in the document, thus the clustering reflects the unique relationships each user sees among the nodes. The original hypermedia document remains untouched, however each user will now have a personalized index into this document.

In this paper, the authors discuss the design and development of computer assisted studies planning and educational resources (CASPER). CASPER is a hypermedia information system that allows students to find up-to-date information on courses, instructors, announcements, transfer credit, and frequently asked questions. One of the most important features of CASPER is its capability to assist students in planning their course selections for future terms. Because CASPER is an online system, additional human counselors are free to deal personally with students on less routine matters.

Very large databases contain large amounts of interrelated information. This information is often stored in relational databases with hundreds of tables and thousands of rows per table. Clustering is an effective way to reduce the information-overhead associated with finding information among these tables, allowing the user to browse through the clusters as well as the individual tables. In this paper, we compare the use of two adaptive algorithms (genetic algorithms, and neural networks) in clustering the tables of a very large database. These clusters allow the user to index into this overwhelming number of tables and find the needed information quickly. We cluster the tables based on the user’s queries and not on the content of the tables, thus the clustering reflects the unique relationships each user sees among the tables. The original database remains untouched, however each user will now have a personalized index into this database.

In the areas of sciences, engineering and design, the entities experience both structural and state changes. Existing database models allow changes in the structure and state through the techniques of schema evolution and version management, respectively, but fail to capture and represent both of these changes together and at the same time. In this paper we formally introduce the Temporal Object-Oriented System (TOS) which allows simultaneous changes in both the structure and state of the objects. An object in TOS is called a temporal object (TO). An aggregation of different TOs of the system can give rise to a new object which is then referred to as a temporal complex object (TCO). Both temporal objects and temporal complex objects can replace and refresh their knowledge through a process called renovation. The paper also discusses the process of renovations for both TOs and TCOs and enumerate their temporal parameters (i.e., timespan, life-span and life-sequence). A query language for the TOS, called Temporal Object Query Language (TOQL), is also proposed which is a super-set of the relational query language SQL.

In medical domains with low tolerance for invalid predictions, classification confidence is highly important and traditional performance measures such as overall accuracy cannot provide adequate insight into classifications reliability. In this paper, a confident-prediction rate (CPR) which measures the upper limit of confident predictions has been proposed based on receiver operating characteristic (ROC) curves. It has been shown that heterogeneous ensemble of classifiers improves this measure. This ensemble approach has been applied to lateralization of focal epileptogenicity in temporal lobe epilepsy (TLE) and prediction of surgical outcomes. A goal of this study is to reduce extra operative electrocorticography (eECoG) requirement which is the practice of using electrodes placed directly on the exposed surface of the brain. We have shown that such goal is achievable with application of data mining techniques. Furthermore, all TLE surgical operations do not result in complete relief from seizures and it is not always possible for human experts to identify such unsuccessful cases prior to surgery. This study demonstrates the capability of data mining techniques in prediction of undesirable outcome for a portion of such cases.

Provenance, which is one kind of metadata that captures the derivation history of a data product, including its original data sources, intermediate products, and the steps that were applied to produce it, has become increasingly important in services computing and scientific workflows to validate, interpret, and analyze the result of scientific computing. Most existing systems store provenance data captured into their own provenance storages of proprietary provenance models and conduct query processing over the physical provenance storages using query languages, such as SQL, SPARQL, and Query, which are closely coupled to the underlying provenance storage strategies. In this paper, we present OPQL, an OPM-level provenance query language, that is directly defined over the Open Provenance Model (OPM). An OPQL query takes an OPM graph as input and produces an OPM graph as output. Therefore, OPQL queries are not tightly coupled to the underlying provenance storage strategies. Our main contributions are: (i) we design OPQL, including graph patterns and an OPM-based graph algebra for OPQL, that efficiently supports provenance lineage queries, (ii) we implement OPQ Lin our OPMPROV system, where the result of OPQL queries is displayed as an OPM graph via the OPMPROV browser. An experimental study is conducted to evaluate the performance and feasibility of OPQL for provenance querying. To our best knowledge, OPQL is the first OPM-level query language for scientific workflow provenance.

During the similarity join process, one or more sources may not allow sharing the whole data with other sources. In this case, privacy preserved similarity join is required. We showed in our previous work [4] that using long attributes, such as paper abstracts, movie summaries, product descriptions, and user feedbacks, could improve the similarity join accuracy under supervised learning. However, the existing secure protocols for similarity join methods can not be used to join tables using these long attributes. Moreover, the majority of the existing privacy-preserving protocols did not consider the semantic similarities during the similarity join process. In this paper, we introduce a secure efficient protocol to semantically join tables when the join attributes are long attributes. Furthermore, instead of using machine learning methods, which are not always applicable, we use similarity thresholds to decide matched pairs. Results show that our protocol can efficiently join tables using the long attributes by considering the semantic relationships among the long string values. Therefore, it improves the overall secure similarity join performance.

Despite its scientific, political, and practical value, comprehensive information about human languages, in all their variety and complexity, is not readily obtainable and searchable. One reason is that many language data are collected as audio and video recordings which imposes a challenge to document indexing and retrieval. Annotation of multimedia data provides an opportunity for making the semantics explicit and facilitates the searching of multimedia documents. We have developed OntoELAN, an ontology-based linguistic multimedia annotator that features: (1) support for loading and displaying ontologies specified in OWL; (2) creation of a language profile, which allows a user to choose a subset of terms from an ontology and conveniently rename them if needed; (3) creation of ontological tiers, which can be annotated with profile terms and, therefore, corresponding ontological terms; and (4) saving annotations in the XML format as Multimedia Ontology class instances and, linked to them, class instances of other ontologies used in ontological tiers. To our best knowledge, OntoELAN is the first audio/video annotation tool in linguistic domain that provides support for ontology-based annotation., Comment: Appeared in the Proceedings of the IEEE Sixth International Symposium on Multimedia Software Engineering (IEEE-MSE'04), pp. 329-336, Miami, FL, USA, December, 2004

The problem of computing multirelation (M-way) join queries on uniprocessor architectures has been considered by many researchers in the past. This paper lays the necessary foundation for work involving optimization of M-way joins in parallel architectures. We explain the inadequacies of previous uniprocessor strategies and describe a more suitable formulation based on the concept of matching in graph theory to approach the problem in a parallel environment. It has been shown that the problem of optimizing M-way joins is an NP-hard problem and hence we would expect that in a parallel processing environment the search space of possible solutions (join schedules) would be enormous, especially when a variable number of processors are considered. Our strategy seeks to reduce the region to search by partitioning the search space according to the number of available processors. Based on this a significant portion of the search space, which will produce non-optimal join schedules, may be ignored.

Scientific workflows have recently emerged as a new paradigm for scientists to formalize and structure complex and distributed scientific processes to enable and accelerate many scientific discoveries. In contrast to business workflows, which are typically control flow oriented, scientific workflows tend to be dataflow oriented, introducing a new set of requirements for system development. These requirements demand a new architectural design for scientific workflow management systems (SWFMSs). Although several SWFMSs have been developed that provide much experience for future research and development, a study from an architectural perspective is still missing. The main contributions of this paper are: (i) based on a comprehensive survey of the literature and identification of key requirements for SWFMSs, we propose the first reference architecture for SWFMSs, (ii) in compliance with the reference architecture, we further propose a service-oriented architecture for VIEW (a VIsual sciEntificWorkflow management system), (iii) we implement VIEW to validate the feasibility of the proposed architectures, and (iv) we present two case studies to showcase the applications of our VIEW system.

Several technologies for characterizing genes and proteins from humans and other organisms use yeast growth or color development as read outs. The yeast two-hybrid assay, for example, detects protein-protein interactions by measuring the growth of yeast on a specific solid medium, or the ability of the yeast to change color when grown on a medium containing a chromogenic substrate. Current systems for analyzing the results of these types of assays rely on subjective and inefficient scoring of growth or color by human experts. Here, an image analysis system is described for scoring yeast growth and color development in high throughput biological assays. The goal is to locate the spots and score them in color images of two types of plates named ldquoX-Galrdquo and ldquogrowth assayrdquo plates, with uniformly placed spots (cell areas) on each plate (both plates in one image). The scoring system relies on color for the X-Gal spots, and texture properties for the growth assay spots. A maximum likelihood projection-based segmentation is developed to automatically locate spots of yeast on each plate. Then color histogram and wavelet texture features are extracted for scoring using an optimal linear transformation. Finally, an artificial neural network is used to score the X-Gal and growth assay spots using the extracted features. The performance of the system is evaluated using spots of 60 images. After training the networks using training and validation sets, the system was assessed on the test set. The overall accuracies of 95.4% and 88.2% are achieved, respectively, for scoring the X-Gal and growth assay spots.

'Systematic identification of protein interactions for the bacterium Campylobacter jejuni using high-throughput yeast two-hybrid screens detected interactions for 80% of the organism's proteins., Background Data from large-scale protein interaction screens for humans and model eukaryotes have been invaluable for developing systems-level models of biological processes. Despite this value, only a limited amount of interaction data is available for prokaryotes. Here we report the systematic identification of protein interactions for the bacterium Campylobacter jejuni, a food-borne pathogen and a major cause of gastroenteritis worldwide. Results Using high-throughput yeast two-hybrid screens we detected and reproduced 11,687 interactions. The resulting interaction map includes 80% of the predicted C. jejuni NCTC11168 proteins and places a large number of poorly characterized proteins into networks that provide initial clues about their functions. We used the map to identify a number of conserved subnetworks by comparison to protein networks from Escherichia coli and Saccharomyces cerevisiae. We also demonstrate the value of the interactome data for mapping biological pathways by identifying the C. jejuni chemotaxis pathway. Finally, the interaction map also includes a large subnetwork of putative essential genes that may be used to identify potential new antimicrobial drug targets for C. jejuni and related organisms. Conclusion The C. jejuni protein interaction map is one of the most comprehensive yet determined for a free-living organism and nearly doubles the binary interactions available for the prokaryotic kingdom. This high level of coverage facilitates pathway mapping and function prediction for a large number of C. jejuni proteins as well as orthologous proteins from other organisms. The broad coverage also facilitates cross-species comparisons for the identification of evolutionarily conserved subnetworks of protein interactions.

CASMIL aims to develop a cost-effective and efficient approach to monitor and predict deformation during surgery, allowing accurate, and real-time intra-operative information to be provided reliably to the surgeon.CASMIL is a comprehensive Image-guided Neurosurgery System with extensive novel features. It is an integration of various modules including rigid and non-rigid body co-registration (image-image, image-atlas, and image-patient), automated 3D segmentation, brain shift predictor, knowledge based query tools, intelligent planning, and augmented reality. One of the vital and unique modules is the Intelligent Planning module, which displays the best surgical corridor on the computer screen based on tumor location, captured surgeon knowledge, and predicted brain shift using patient specific Finite Element Model. Also, it has multi-level parallel computing to provide near real-time interaction with iMRI (Intra-operative MRI). In addition, it has been securely web-enabled and optimized for remote web and PDA access.A version of this system is being used and tested using real patient data and is expected to be in use in the operating room at the Detroit Medical Center in the first half of 2006.CASMIL is currently under development and is targeted for minimally invasive surgeries. With minimal changes to the design, it can be easily extended and made available for other surgical procedures.

Provenance management has become increasingly important to support scientific discovery reproducibility, result interpretation, and problem diagnosis in scientific workflow environments. This paper proposes an approach to provenance management that seamlessly integrates the interoperability, extensibility, and reasoning advantages of semantic Web technologies with the storage and querying power of an RDBMS. Specifically, we propose: i) two schema mapping algorithms to map an arbitrary OWL provenance ontology to a relational database schema that is optimized for common provenance queries; ii) two efficient data mapping algorithms to map provenance RDF metadata to relational data according to the generated relational database schema, and iii) a schema-independent SPARQL-to-SQL translation algorithm that is optimized on-the-fly by using the type information of an instance available from the input provenance ontology and the statistics of the sizes of the tables in the database. Experimental results are presented to show that our algorithms are efficient and scalable.

Background Biological processes are mediated by networks of interacting genes and proteins. Efforts to map and understand these networks are resulting in the proliferation of interaction data derived from both experimental and computational techniques for a number of organisms. The volume of this data combined with the variety of specific forms it can take has created a need for comprehensive databases that include all of the available data sets, and for exploration tools to facilitate data integration and analysis. One powerful paradigm for the navigation and analysis of interaction data is an interaction graph or map that represents proteins or genes as nodes linked by interactions. Several programs have been developed for graphical representation and analysis of interaction data, yet there remains a need for alternative programs that can provide casual users with rapid easy access to many existing and emerging data sets. Description Here we describe a comprehensive database of Drosophila gene and protein interactions collected from a variety of sources, including low and high throughput screens, genetic interactions, and computational predictions. We also present a program for exploring multiple interaction data sets and for combining data from different sources. The program, referred to as the Interaction Map (IM) Browser, is a web-based application for searching and visualizing interaction data stored in a relational database system. Use of the application requires no downloads and minimal user configuration or training, thereby enabling rapid initial access to interaction data. IM Browser was designed to readily accommodate and integrate new types of interaction data as it becomes available. Moreover, all information associated with interaction measurements or predictions and the genes or proteins involved are accessible to the user. This allows combined searches and analyses based on either common or technique-specific attributes. The data can be visualized as an editable graph and all or part of the data can be downloaded for further analysis with other tools for specific applications. The database is available at http://proteome.wayne.edu/PIMdb.html Conclusion The Drosophila Interactions Database described here places a variety of disparate data into one easily accessible location. The database has a simple structure that maintains all relevant information about how each interaction was determined. The IM Browser provides easy, complete access to this database and could readily be used to publish other sets of interaction data. By providing access to all of the available information from a variety of data types, the program will also facilitate advanced computational analyses.

Background In recent years, clustering algorithms have been effectively applied in molecular biology for gene expression data analysis. With the help of clustering algorithms such as K-means, hierarchical clustering, SOM, etc, genes are partitioned into groups based on the similarity between their expression profiles. In this way, functionally related genes are identified. As the amount of laboratory data in molecular biology grows exponentially each year due to advanced technologies such as Microarray, new efficient and effective methods for clustering must be developed to process this growing amount of biological data. Results In this paper, we propose a new clustering algorithm, Incremental Genetic K-means Algorithm (IGKA). IGKA is an extension to our previously proposed clustering algorithm, the Fast Genetic K-means Algorithm (FGKA). IGKA outperforms FGKA when the mutation probability is small. The main idea of IGKA is to calculate the objective value Total Within-Cluster Variation (TWCV) and to cluster centroids incrementally whenever the mutation probability is small. IGKA inherits the salient feature of FGKA of always converging to the global optimum. C program is freely available at http://database.cs.wayne.edu/proj/FGKA/index.htm. Conclusions Our experiments indicate that, while the IGKA algorithm has a convergence pattern similar to FGKA, it has a better time performance when the mutation probability decreases to some point. Finally, we used IGKA to cluster a yeast dataset and found that it increased the enrichment of genes of similar function within the cluster.

We define several disclosure risk measures for microdata. We analyze disclosure risk based on the disclosure control techniques applied to initial microdata. Disclosure Control is the discipline concerned with the modification of data containing confidential information about individual entities, such as persons, households, businesses, etc. in order to prevent third parties working with these data from recognizing entities in the data and thereby disclosing information about these entities. In very broad terms, disclosure risk is the risk that a given form of disclosure will occur if a masked microdataset is released. Microdata represents a series of records, each record containing information on an individual unit. The disclosure risk measures presented in the paper are validated in our experiments.

Background: In recent years, clustering algorithms have been effectively applied in molecular biology for gene expression data analysis. With the help of clustering algorithms such as K-means, hierarchical clustering, SOM, etc, genes are partitioned into groups based on the similarity between their expression profiles. In this way, functionally related genes are identified. As the amount of laboratory data in molecular biology grows exponentially each year due to advanced technologies such as Microarray, new efficient and effective methods for clustering must be developed to process this growing amount of biological data. Results: In this paper, we propose a new clustering algorithm, Incremental Genetic K-means Algorithm (IGKA). IGKA is an extension to our previously proposed clustering algorithm, the Fast Genetic K-means Algorithm (FGKA). IGKA outperforms FGKA when the mutation probability is small. The main idea of IGKA is to calculate the objective value Total Within-Cluster Variation (TWCV) and to cluster centroids incrementally whenever the mutation probability is small. IGKA inherits the salient feature of FGKA of always converging to the global optimum. C program is freely available at http://database.cs.wayne.edu/proj/FGKA/index.htm. Conclusions: Our experiments indicate that, while the IGKA algorithm has a convergence pattern similar to FGKA, it has a better time performance when the mutation probability decreases to some point. Finally, we used IGKA to cluster a yeast dataset and found that it increased the enrichment of genes of similar function within the cluster.

In this paper we propose a new access path to a relation, called a Partial-Relation scheme, in order to speed up the relational join operations. We present two join algorithms which preprocess the Partial-Relations first and then join the selected tuples of the relations. We have considered join-only queries and queries involving restrictions, projections and joins. The performance of these algorithms is compared with sort-merge and hash-based join algorithms. The analysis is based on the cost of accesses to the secondary storage and the CPU usage. It has been shown that for wide range of selectivity factors and/or join factors the proposed algorithms perform better than the sort-merge and hash-based join algorithms.