Query Retrieval Research Articles

Ranking genes based on kernels

Retrieval queries in microarray databases can rank genes according either to their similarity by detecting functionally related genes, or to their importance by detecting genes with significant regulation role. Although both rankings are useful, they

Special issue: Advances in medical intelligent decision support systems

This special issue is concerned with Advances in Medical Decision Support Systems. Computer science contributions to the biomedical community started with the first expert systems. Since then advances have taken place in both the medical and biological domains and also in computer science technology. This means that additional automated support can be made available to these types of applications. These advances and their contribution to the biomedical community are the focus of this special issue. The application of Intelligent Decision Support Systems in medicine is the subject of considerable ongoing research, which concentrates on modelling some of the human actions or thinking processes, recognising diseases from a variety of input sources and even extends to the representation and querying of gene data from microarray databases. Five papers have been selected, after rigorous review, for this special issue. These cover two categories: the first set of papers focuses on the medical domain and mainly on classification of medical data for accurate diagnoses. The second set of papers focuses on biological data and more importantly retrieval queries from microarray data and relationships between gene products. Computational intelligent methodologies are used for the detection of breast cancer in the paper by Geraldo Braz Junior et al. Breast cancer is the major cause

Secbase: Database Module To Retrieve Secondary Structure Elements with Ligand Binding Motifs

Secbase is presented as a novel extension module of Relibase. It integrates the information about secondary structure elements into the retrieval facilities of Relibase. The data are accessible via the extended Relibase user interface, and integrated retrieval queries can be addressed using an extended version of Reliscript. The primary information about alpha-helices and beta-sheets is used as provided by the PDB. Furthermore, a uniform classification of all turn families, based on recent clustering methods, and a new helix assignment that is based on this turn classification has been included. Algorithms to analyze the geometric features of helices and beta-strands were also implemented. To demonstrate the performance of the Secbase implementation, some application examples are given. They provide new insights into the involvement of secondary structure elements in ligand binding. A survey of water molecules detected next to the N-terminus of helices is analyzed to show their involvement in ligand binding. Additionally, the parallel oriented NH groups at the alpha-helix N-termini provide special binding motifs to bind particular ligand functional groups with two adjacent oxygen atoms, e.g., as found in negatively charged carboxylate or phosphate groups, respectively. The present study also shows that the specific structure of the first turn of alpha-helices provides a suitable explanation for stabilizing charged structures. The magnitude of the overall helix macrodipole seems to have no or only a minor influence on binding. Furthermore, an overview of the involvement of secondary structure elements with the recognition of some important endogenous ligands such as cofactors shows some distinct preference for particular binding motifs and amino acids.

Can eyes reveal interest? Implicit queries from gaze patterns

We study a new research problem, where an implicit information retrieval query is inferred from eye movements measured when the user is reading, and used to retrieve new documents. In the training ...

Efficient retrieval of the top-k most relevant spatial web objects

The conventional Internet is acquiring a geo-spatial dimension. Web documents are being geo-tagged, and geo-referenced objects such as points of interest are being associated with descriptive text documents. The resulting fusion of geo-location and documents enables a new kind of top- k query that takes into account both location proximity and text relevancy. To our knowledge, only naive techniques exist that are capable of computing a general web information retrieval query while also taking location into account. This paper proposes a new indexing framework for location-aware top- k text retrieval. The framework leverages the inverted file for text retrieval and the R-tree for spatial proximity querying. Several indexing approaches are explored within the framework. The framework encompasses algorithms that utilize the proposed indexes for computing the top- k query, thus taking into account both text relevancy and location proximity to prune the search space. Results of empirical studies with an implementation of the framework demonstrate that the paper's proposal offers scalability and is capable of excellent performance.

Improving legal information retrieval using an ontological framework

A variety of legal documents are increasingly being made available in electronic format. Automatic Information Search and Retrieval algorithms play a key role in enabling efficient access to such digitized documents. Although keyword-based search is the traditional method used for text retrieval, they perform poorly when literal term matching is done for query processing, due to synonymy and ambivalence of words. To overcome these drawbacks, an ontological framework to enhance the user's query for retrieval of truly relevant legal judgments has been proposed in this paper. Ontologies ensure efficient retrieval by enabling inferences based on domain knowledge, which is gathered during the construction of the knowledge base. Empirical results demonstrate that ontology-based searches generate significantly better results than traditional search methods.

Node Labeling Schemes in XML Query Optimization: A Survey and Trends

With the rapid emergence of XML as a data exchange and data transfer medium over the Web, querying XML data has become a major concern. Labeling schemes have been developed to optimize query retrieval, since they provide a quick way to determine the type of relationships that are present among the nodes. In this paper, we analyze how each approach works, as well as its advantages and disadvantages. In addition, we discuss some of the current trends in labeling methods, which indicate a clear shift towards hybrid approaches. Hybrid systems open the possibility of balancing one technology’s weakness with another technology’s strengths.

Lossless Compression of Microarray Images Using Image-Dependent Finite-Context Models

The use of microarray expression data in state-of-the-art biology has been well established. The widespread adoption of this technology, coupled with the significant volume of data generated per experiment, in the form of images, has led to significant challenges in storage and query retrieval. In this paper, we present a lossless bitplane-based method for efficient compression of microarray images. This method is based on arithmetic coding driven by image-dependent multibitplane finite-context models. It produces an embedded bitstream that allows progressive, lossy-to-lossless decoding. We compare the compression efficiency of the proposed method with three image compression standards (JPEG2000, JPEG-LS, and JBIG) and also with the two most recent specialized methods for microarray image coding. The proposed method gives better results for all images of the test sets and confirms the effectiveness of bitplane-based methods and finite-context modeling for the lossless compression of microarray images.

On the use of negation in Boolean IR queries

The negation operator, in various forms in which it appears in Information Retrieval queries, is investigated. The applications include negated terms in Boolean queries, more specifically in the presence of metrical constraints, but also negated characters used in the definition of extended keywords by means of regular expressions. Exact definitions are suggested and their usefulness is shown on several examples. Finally, some implementation issues are discussed, in particular as to the order in which the terms of long queries, with or without negated keywords, should be processed, and efficient heuristics for choosing a good order are suggested.

Efficient processing of probabilistic reverse nearest neighbor queries over uncertain data

Reverse nearest neighbor (RNN) search is very crucial in many real applications. In particular, given a database and a query object, an RNN query retrieves all the data objects in the database that have the query object as their nearest neighbors. Often, due to limitation of measurement devices, environmental disturbance, or characteristics of applications (for example, monitoring moving objects), data obtained from the real world are uncertain (imprecise). Therefore, previous approaches proposed for answering an RNN query over exact (precise) database cannot be directly applied to the uncertain scenario. In this paper, we re-define the RNN query in the context of uncertain databases, namely probabilistic reverse nearest neighbor (PRNN) query, which obtains data objects with probabilities of being RNNs greater than or equal to a user-specified threshold. Since the retrieval of a PRNN query requires accessing all the objects in the database, which is quite costly, we also propose an effective pruning method, called geometric pruning (GP), that significantly reduces the PRNN search space yet without introducing any false dismissals. Furthermore, we present an efficient PRNN query procedure that seamlessly integrates our pruning method. Extensive experiments have demonstrated the efficiency and effectiveness of our proposed GP-based PRNN query processing approach, under various experimental settings.

A relevance model for a data warehouse contextualized with documents

This paper presents a relevance model to rank the facts of a data warehouse that are described in a set of documents retrieved with an information retrieval (IR) query. The model is based in language modeling and relevance modeling techniques. We estimate the relevance of the facts by the probability of finding their dimensions values and the query keywords in the documents that are relevant to the query. The model is the core of the so-called contextualized warehouse, which is a new kind of decision support system that combines structured data sources and document collections. The paper evaluates the relevance model with the Wall Street Journal (WSJ) TREC test subcollection and a self-constructed fact database.

Canonical Polygon Queries on the Plane: A New Approach

The polygon retrieval problem on points is the problem of preprocessing a set of n points on the plane, so that given a polygon query, the subset of points lying inside it can be reported efficiently. It is of great interest in areas such as Computer Graphics, CAD applications, Spatial Databases and GIS developing tasks. In this paper we study the problem of canonical k-vertex polygon queries on the plane. A canonical k-vertex polygon query always meets the following specific property: a point retrieval query can be transformed into a linear number (with respect to the number of vertices) of point retrievals for orthogonal objects such as rectangles and triangles (throughout this work we call a triangle orthogonal iff two of its edges are axisparallel). We present two new algorithms for this problem. The first one requires O(n log 2 n) space and O(k log 3 n/loglogn +A) query time. A simple modification scheme on first algorithm lead us to a second solution, which consumes O(n 2 ) space and O(k logn/loglogn + A) query time, where A denotes the size of the answer and k is the number of vertices. The best previous solution for the general polygon retrieval problem uses O(n 2 ) space and answers a query in O(k log n + A) time, where k is the number of vertices. It is also very complicated and difficult to be implemented in a standard imperative programming language such as C or C++.

Efficient Preprocesses for Fast Storage and Query Retrieval in Native XML Database

XML (extensible mark-up language) has emerged as one of the popular data representation standards for information storage and exchange. In this paper, we propose an extended INLAB architecture, INLAB2, focusing on preprocessing the XML document for fast native storage and accurate query retrieval. Firstly, we propose our xParse parser to check the well-formedness of an XML document. Next, we use a ( self-end) labeling scheme to encode each element in the XML database, by its positional information, to establish parent-child (P-C) or ancestor-descendant (A-D) relationships between nodes. Subsequently, our TwigINLAB2 algorithm is used to optimize query retrieval. TwigINLAB2 is a generalization of TwigStack, the stack-based algorithm for matching twig query. However, the TwigStack algorithm is efficient for A-D relationship queries only. Thus, in order to overcome this limitation, we enhance query retrieval by utilizing indices to speed up the matching and merging phases. Experimental results indicate that TwigINLAB2 can, on an average, process twig queries 23% better than the TwigStack algorithm and 10% better than TwigINLAB1, in terms of execution time.

Efficient range queries in spatial databases over Peer-to-Peer Networks

Peer-to-Peer (P2P) network, e.g., Chord, is designed mainly for one-dimensional data retrieval and point queries. Multimedia and spatial applications require efficient execution of range queries. This paper proposes an efficient scheme to support range query over Chord while balancing the storage load. The paper proposes a rotating token scheme that places the joining nodes in appropriate locations to share loads with overloaded nodes. To support range queries, we utilise an order-preserving mapping function to map keys to nodes in an order preserving manner. Simulation experiments show significant gain in storage load balancing and the performance of range queries over Chord.

Construction of a Test Collection for Spoken Document Retrieval from Lecture Audio Data

The lecture is one of the most valuable genres of audiovisual data. Though spoken document processing is a promising technology for utilizing the lecture in various ways, it is difficult to evaluate because the evaluation require a subjective judgment and/or the verification of large quantities of evaluation data. In this paper, a test collection for the evaluation of spoken lecture retrieval is reported. The test collection consists of the target spoken documents of about 2, 700 lectures (604 hours) taken from the Corpus of Spontaneous Japanese (CSJ), 39 retrieval queries, the relevant passages in the target documents for each query, and the automatic transcription of the target speech data. This paper also reports the retrieval performance targeting the constructed test collection by applying a standard spoken document retrieval (SDR) method, which serves as a baseline for the forthcoming SDR studies using the test collection.

Ventrolateral prefrontal cortex and self-initiated semantic elaboration during memory retrieval

Left ventrolateral prefrontal cortex (LVPFC) is often implicated in neuroimaging studies of context memory retrieval. This activation has been argued to reflect proactive semantic processing that facilitates recollection of past events, or instead to reflect a reactive response to experienced episodic interference. We investigated these characterizations in an fMRI study that manipulated the relative distinctiveness of encoding across subsequent targets and lures by varying encoding task manipulations. Critically, during later testing, retrieval queries and prior target processing where held constant across the distinctive and non-distinctive testing conditions, and therefore any differences in cortical activity would be linked to subject-initiated retrieval strategies. We found that LVPFC activity was specific to context retrieval under distinctive conditions even though this condition demonstrated the least interference. The results suggest that this region is critical for self-initiated semantic elaboration during retrieval, and this conclusion was bolstered by finding that LVPFC activity predicted individual differences in context memory discrimination. In line with Tulving's Encoding Specificity Principle, we suggest that subjects actively construct semantic retrieval cues, reflected in increased VLPFC activation, in an attempt to isolate the distinctive semantic features of hypothetical experiences when possible. If successful, this improves the match between retrieval cue and engram and facilitates performance.

Speech retrieval from unsegmented finnish audio using statistical morpheme-like units for segmentation, recognition, and retrieval

This article examines the use of statistically discovered morpheme-like units for Spoken Document Retrieval (SDR). The morpheme-like units ( morphs ) are used both for language modeling in speech recognition and as index terms. Traditional word-based methods suffer from out-of-vocabulary words. If a word is not in the recognizer vocabulary, any occurrence of the word in speech will be missing from the transcripts. The problem is especially severe for languages with a high number of distinct word forms such as Finnish. With the morph language model, even previously unseen words can be recognized by identifying its component morphs. Similarly in information retrieval queries, complex word forms, even unseen ones, can be matched to data after segmenting them to morphs. Retrieval performance can be further improved by expanding the transcripts with alternative recognition results from confusion networks . In this article, a novel retrieval evaluation corpus consisting of unsegmented Finnish radio programs, 25 queries and corresponding human relevance assessments was constructed. Previous results on using morphs and confusion networks for Finnish SDR are confirmed and extended to the unsegmented case. As previously, using morphs or base forms as index terms yields about equal performance but combination methods, including a new one, are found to work better than either alone. Using alternative morph segmentations of the query words is found to further improve the results. Lexical similarity-based story segmentation was applied and performance using morphs, base forms, and their combinations was compared for the first time.

Concept analysis via rough set and AFS algebra

Formal concept analysis (FCA) was originally proposed by Wille (1982), which is an important theory for data analysis and knowledge discovery. AFS (axiomatic fuzzy set) algebra was proposed by Liu [X. Liu, The fuzzy theory based on AFS algebras and AFS structure, Journal of Mathematical Analysis and Applications 217 (1998) 459–478; X. Liu, The topology on AFS algebra and AFS structure, Journal of Mathematical Analysis and Applications 217 (1998) 479–489], which is a semantic methodology relating to the fuzzy theory. Combining above two theories, we propose AFS formal concept, which can be viewed as the generalization and development of monotone concept proposed by Deogun and Saquer (2003). Moreover, we show that the set of all AFS formal concepts forms a complete lattice. AFS formal concept can be applied to represent the logic operations of queries in information retrieval. Furthermore, we give an approach to find the AFS formal concepts whose intents (extents) approximate any element of AFS algebra by virtue of rough set theory.

The Research on Integrated Approach of Query Translation and Retrieval Process to CLIR

The Research on Integrated Approach of Query Translation and Retrieval Process to CLIR

An analysis of failed queries for web image retrieval

This paper examines a large number of failed queries submitted to a web image search engine, including real users' search terms and written requests. The results show that failed image queries have a much higher specificity than successful queries because users often employ various refined types to specify their queries. The study explores the refined types further, and finds that failed queries consist of far more conceptual than perceptual refined types. The widely used content-based image retrieval technique, CBIR, can only deal with a small proportion of failed queries; hence, appropriate integration of concept-based techniques is desirable. Based on using the concepts of uniqueness and refinement for categorization, the study also provides a useful discussion on the gaps between image queries and retrieval techniques. The initial results enhance the understanding of failed queries and suggest possible ways to improve image retrieval systems.