Information Retrieval Algorithms Research Articles

Context-Aware Personal Information Retrieval From Multiple Social Networks

Abstract-People use a variety of social networking services to collect and organize web information for future reuse. When such contents are actually needed as reference to reply a post in an online conversation, however, the user may not be able to retrieve them with proper cues or may even forget their existence at all. In this paper, we study this problem in the online conversation context and investigate how to automatically retrieve the most context-relevant previously-seen web information without user intervention. We propose a Context-aware Personal Information Retrieval (CPIR) algorithm, which considers both the participatory and implicit-topical properties of the context to improve the retrieval performance. Since both the context and the user's web information are usually short and ambiguous, the participatory context is utilized to formulate and expand the query. Moreover, the implicit-topical context is exploited to implicitly determine the importance of each web information of the targeting user in the given context. The experimental results using real-world dataset demonstrate that CPIR can achieve significant improvements over several baselines.

A hierarchical knowledge-based approach for retrieving similar medical images described with semantic annotations

Computer-assisted image retrieval applications could assist radiologist interpretations by identifying similar images in large archives as a means to providing decision support. However, the semantic gap between low-level image features and their high level semantics may impair the system performances. Indeed, it can be challenging to comprehensively characterize the images using low-level imaging features to fully capture the visual appearance of diseases on images, and recently the use of semantic terms has been advocated to provide semantic descriptions of the visual contents of images. However, most of the existing image retrieval strategies do not consider the intrinsic properties of these terms during the comparison of the images beyond treating them as simple binary (presence/absence) features. We propose a new framework that includes semantic features in images and that enables retrieval of similar images in large databases based on their semantic relations. It is based on two main steps: (1) annotation of the images with semantic terms extracted from an ontology, and (2) evaluation of the similarity of image pairs by computing the similarity between the terms using the Hierarchical Semantic-Based Distance (HSBD) coupled to an ontological measure. The combination of these two steps provides a means of capturing the semantic correlations among the terms used to characterize the images that can be considered as a potential solution to deal with the semantic gap problem. We validate this approach in the context of the retrieval and the classification of 2D regions of interest (ROIs) extracted from computed tomographic (CT) images of the liver. Under this framework, retrieval accuracy of more than 0.96 was obtained on a 30-images dataset using the Normalized Discounted Cumulative Gain (NDCG) index that is a standard technique used to measure the effectiveness of information retrieval algorithms when a separate reference standard is available. Classification results of more than 95% were obtained on a 77-images dataset. For comparison purpose, the use of the Earth Mover’s Distance (EMD), which is an alternative distance metric that considers all the existing relations among the terms, led to results retrieval accuracy of 0.95 and classification results of 93% with a higher computational cost. The results provided by the presented framework are competitive with the state-of-the-art and emphasize the usefulness of the proposed methodology for radiology image retrieval and classification.

Pareto-depth for multiple-query image retrieval.

Most content-based image retrieval systems consider either one single query, or multiple queries that include the same object or represent the same semantic information. In this paper, we consider the content-based image retrieval problem for multiple query images corresponding to different image semantics. We propose a novel multiple-query information retrieval algorithm that combines the Pareto front method with efficient manifold ranking. We show that our proposed algorithm outperforms state of the art multiple-query retrieval algorithms on real-world image databases. We attribute this performance improvement to concavity properties of the Pareto fronts, and prove a theoretical result that characterizes the asymptotic concavity of the fronts.

Feature weighted naïve Bayes algorithm for information retrieval of enterprise systems

Automated information retrieval is critical for enterprise information systems to acquire knowledge from the vast amount of data sets. One challenge in information retrieval is text classification. Current practices rely heavily on the classical naïve Bayes algorithm due to its simplicity and robustness. However, results from this algorithm are not always satisfactory. In this article, the limitations of the naïve Bayes algorithm are discussed, and it is found that the assumption on the independence of terms is the main reason for an unsatisfactory classification in many real-world applications. To overcome the limitations, the dependent factors are considered by integrating a term frequency–inverse document frequency (TF-IDF) weighting algorithm in the naïve Bayes classification. Moreover, the TF-IDF algorithm itself is improved so that both frequencies and distribution information are taken into consideration. To illustrate the effectiveness of the proposed method, two simulation experiments were conducted, and the comparisons with other classification methods have shown that the proposed method has outperformed other existing algorithms in terms of precision and index recall rate.

Implementation of Information Retrieval (IR) Algorithm for Cloud Computing: A Comparative Study Between With and Without Mapreduce Mechanism

The procedure of Information Retrieval (IR) algorithm appears disingenuously modest when observed from the viewpoint of terminological explanation. However, the implementation mechanism of the IR Algorithm is quite complicated and particularly when implemented to gratify the definite organizational requirements. In this research, the Information Retrieval Algorithm is developed using the MapReduce mechanism to retrieve the information in a Cloud computing environment. The MapReduce algorithm was developed by Google for experimental evaluations. In the present study, the algorithm portrays the results in terms of number of buckets required to generate the output from the large chunk of data in Cloud computing. The algorithm is the part of the complete Business Intelligence tool to be implemented and the results to be delivered for Cloud computing architecture.

Intellectual capital disclosure and accounting standards

PurposeThis study aims to investigate the association between the intellectual capital disclosure level and the mandatory adoption of international financial reporting standards (IFRS). This paper reports an empirical evidence for the impact of the mandatory adoption of IFRS on the disclosure level of intellectual capital, intangible and knowledge assets. Intellectual capital is categorized into process focus, customer focus, human focus, research and development focus. The linkages between intellectual capital and IFRS adoption are investigated in companies of high technology sector in the UK. A novel approach to measure the effect of the IFRS adoption on intellectual capital disclosure level is presented.Design/methodology/approachThe proposed measure was adopted from the information retrieval algorithm and intellectual capital framework. The empirical model was expanded from the econometric model. The primary data for investigating the interrelationships between intellectual capital and IFRS adopting were hand collected from London Stock Exchange and listed firms' web sites. A comprehensive intellectual capital, intangible assets, and knowledge assets' dictionary were built based on related literature.FindingsThis study reports that the overall accuracy of information retrieval application is up to 78.2 percent. The disclosures of intellectual capital items are closely associated with the IFRS adoption. The results suggest that in older or larger companies, the intellectual capital disclosures increase in the post‐adoption period. Overall, the results confirm that companies in the high‐tech industry are associated with a higher disclosure level following the mandatory adoption of IFRS.Originality/valueThe adaption of information retrieval technique and intellectual capital framework enhances the understanding of the usefulness and readability of annual reports in the post‐adoption period of IFRS in high‐tech industry. This study corroborates and complements those of extant research and sheds light on the effect of IFRS adoption on voluntary disclosures. These findings will enable top management around the world to realize the impact of the IFRS adoption on intellectual capital elements so that long‐term strategic knowledge assets management may be emphasized for sustainable competitive edge.

Increasing the darkfield contrast-to-noise ratio using a deconvolution-based information retrieval algorithm in X-ray grating-based phase-contrast imaging

A novel information retrieval algorithm for X-ray grating-based phase-contrast imaging based on the deconvolution of the object and the reference phase stepping curve (PSC) as proposed by Modregger et al. was investigated in this paper. We applied the method for the first time on data obtained with a polychromatic spectrum and compared the results to those, received by applying the commonly used method, based on a Fourier analysis. We confirmed the expectation, that both methods deliver the same results for the absorption and the differential phase image. For the darkfield image, a mean contrast-to-noise ratio (CNR) increase by a factor of 1.17 using the new method was found. Furthermore, the dose saving potential was estimated for the deconvolution method experimentally. It is found, that for the conventional method a dose which is higher by a factor of 1.66 is needed to obtain a similar CNR value compared to the novel method. A further analysis of the data revealed, that the improvement in CNR and dose efficiency is due to the superior background noise properties of the deconvolution method, but at the cost of comparability between measurements at different applied dose values, as the mean value becomes dependent on the photon statistics used.

Retrieval of high-dimensional visual data: current state, trends and challenges ahead

Information retrieval algorithms have changed the way we manage and use various data sources, such as images, music or multimedia collections. First, free text information of documents from varying sources became accessible in addition to structured data in databases, initially for exact search and then for more probabilistic models. Novel approaches enable content-based visual search of images using computerized image analysis making visual image content searchable without requiring high quality manual annotations. Other multimedia data followed such as video and music retrieval, sometimes based on techniques such as extracting objects and classifying genre. 3D (surface) objects and solid textures have also been produced in quickly increasing quantities, for example in medical tomographic imaging. For these two types of 3D information sources, systems have become available to characterize the objects or textures and search for similar visual content in large databases. With 3D moving sequences (i.e., 4D), in particular medical imaging, even higher-dimensional data have become available for analysis and retrieval and currently present many multimedia retrieval challenges. This article systematically reviews current techniques in various fields of 3D and 4D visual information retrieval and analyses the currently dominating application areas. The employed techniques are analysed and regrouped to highlight similarities and complementarities among them in order to guide the choice of optimal approaches for new 3D and 4D retrieval problems. Opportunities for future applications conclude the article. 3D or higher-dimensional visual information retrieval is expected to grow quickly in the coming years and in this respect this article can serve as a basis for designing new applications.

On Multi Class Vector Space Model-based Information Retrieval

A new model of information retrieval algorithms, multi class vector space model, is proposed in this paper based on traditional vector space model. Web document has semi structured characteristic. The keyword or terms that are used for indexing purpose in any location, so content of this location represent important information in the web documents. Vector space model ignores the importance of these terms with respect to their position while calculating the weight of the indexing terms. The experimental result shows that this method can further improve the performance of vector space model, save storage space and speed up the retrieval speed with high precision and recall rate.

Research of Information Retrieval Based on Web Page Segmentation

A Web information retrieval algorithm based on Web page segment is designed, the key idea of which is to segment each Web page into different topic areas or segments according to its HTML tags and contents since Web pages are semi-structure. First, the algorithm builds a HTML tag tree, and then it combines nodes in the tree under the rule of content similarity and visual similarity. During the process of retrieval and ranking, the algorithm makes full use of the segmentation information to sequence the relevant pages. The experimental results show that this method is able to improve the precision in search significantly and it is also a good reference for the design of the future search engines.

Walking Pattern Classification and Walking Distance Estimation Algorithms Using Gait Phase Information

This paper presents a walking pattern classification and a walking distance estimation algorithm using gait phase information. A gait phase information retrieval algorithm was developed to analyze the duration of the phases in a gait cycle (i.e., stance, push-off, swing, and heel-strike phases). Based on the gait phase information, a decision tree based on the relations between gait phases was constructed for classifying three different walking patterns (level walking, walking upstairs, and walking downstairs). Gait phase information was also used for developing a walking distance estimation algorithm. The walking distance estimation algorithm consists of the processes of step count and step length estimation. The proposed walking pattern classification and walking distance estimation algorithm have been validated by a series of experiments. The accuracy of the proposed walking pattern classification was 98.87%, 95.45%, and 95.00% for level walking, walking upstairs, and walking downstairs, respectively. The accuracy of the proposed walking distance estimation algorithm was 96.42% over a walking distance.

Role of Ranking Algorithms for Information Retrieval

As the use of web is increasing more day by day, the web users get easily lost in the web's rich hyper structure. The main aim of the owner of the website is to give the relevant information according their needs to the users. We explained the Web mining is used to categorize users and pages by analyzing user's behavior, the content of pages and then describe Web Structure mining. This paper includes different Page Ranking algorithms and compares those algorithms used for Information Retrieval. Different Page Rank based algorithms like Page Rank (PR), WPR (Weighted Page Rank), HITS (Hyperlink Induced Topic Selection), Distance Rank and EigenRumor algorithms are discussed and compared. Simulation Interface has been designed for PageRank algorithm and Weighted PageRank algorithm but PageRank is the only ranking algorithm on which Google search engine works.

Minersoft

One of the main goals of Cloud and Grid infrastructures is to make their services easily accessible and attractive to end-users. In this article we investigate the problem of supporting keyword-based searching for the discovery of software files that are installed on the nodes of large-scale, federated Grid and Cloud computing infrastructures. We address a number of challenges that arise from the unstructured nature of software and the unavailability of software-related metadata on large-scale networked environments. We present Minersoft, a harvester that visits Grid/Cloud infrastructures, crawls their file systems, identifies and classifies software files, and discovers implicit associations between them. The results of Minersoft harvesting are encoded in a weighted, typed graph, called the Software Graph. A number of information retrieval (IR) algorithms are used to enrich this graph with structural and content associations, to annotate software files with keywords and build inverted indexes to support keyword-based searching for software. Using a real testbed, we present an evaluation study of our approach, using data extracted from production-quality Grid and Cloud computing infrastructures. Experimental results show that Minersoft is a powerful tool for software search and discovery.

Informatics in Radiology: Use of CouchDB for Document-based Storage of DICOM Objects

Picture archiving and communication systems traditionally have depended on schema-based Structured Query Language (SQL) databases for imaging data management. To optimize database size and performance, many such systems store a reduced set of Digital Imaging and Communications in Medicine (DICOM) metadata, discarding informational content that might be needed in the future. As an alternative to traditional database systems, document-based key-value stores recently have gained popularity. These systems store documents containing key-value pairs that facilitate data searches without predefined schemas. Document-based key-value stores are especially suited to archive DICOM objects because DICOM metadata are highly heterogeneous collections of tag-value pairs conveying specific information about imaging modalities, acquisition protocols, and vendor-supported postprocessing options. The authors used an open-source document-based database management system (Apache CouchDB) to create and test two such databases; CouchDB was selected for its overall ease of use, capability for managing attachments, and reliance on HTTP and Representational State Transfer standards for accessing and retrieving data. A large database was created first in which the DICOM metadata from 5880 anonymized magnetic resonance imaging studies (1,949,753 images) were loaded by using a Ruby script. To provide the usual DICOM query functionality, several predefined "views" (standard queries) were created by using JavaScript. For performance comparison, the same queries were executed in both the CouchDB database and a SQL-based DICOM archive. The capabilities of CouchDB for attachment management and database replication were separately assessed in tests of a similar, smaller database. Results showed that CouchDB allowed efficient storage and interrogation of all DICOM objects; with the use of information retrieval algorithms such as map-reduce, all the DICOM metadata stored in the large database were searchable with only a minimal increase in retrieval time over that with the traditional database management system. Results also indicated possible uses for document-based databases in data mining applications such as dose monitoring, quality assurance, and protocol optimization.

Integrating information retrieval, execution and link analysis algorithms to improve feature location in software

Data fusion is the process of integrating multiple sources of information such that their combination yields better results than if the data sources are used individually. This paper applies the idea of data fusion to feature location, the process of identifying the source code that implements specific functionality in software. A data fusion model for feature location is presented which defines new feature location techniques based on combining information from textual, dynamic, and web mining or link analyses algorithms applied to software. A novel contribution of the proposed model is the use of advanced web mining algorithms to analyze execution information during feature location. The results of an extensive evaluation on three Java systems indicate that the new feature location techniques based on web mining improve the effectiveness of existing approaches by as much as 87%.

Applications of the BIOPHYS Algorithm for Physically-Based Retrieval of Biophysical, Structural and Forest Disturbance Information

Canopy reflectance model inversion using look-up table approaches provides powerful and flexible options for deriving improved forest biophysical structural information (BSI) compared with traditional statistical empirical methods. The BIOPHYS algorithm is an improved, physically-based inversion approach for deriving BSI for independent use and validation and for monitoring, inventory and quantifying forest disturbance as well as input to ecosystem, climate and carbon models. Based on the multiple-forward mode (MFM) inversion approach, BIOPHYS results were summarised from different studies (Minnesota/NASA COVER; Virginia/LEDAPS; Saskatchewan/BOREAS), sensors (airborne MMR; Landsat; MODIS) and models (GeoSail; GOMS). Applications output included forest density, height, crown dimension, branch and green leaf area, canopy cover, disturbance estimates based on multi-temporal chronosequences, and structural change following recovery from forest fires over the last century. Good correspondences with validation field data were obtained. Integrated analyses of multiple solar and view angle imagery further improved retrievals compared with single pass data. Quantifying ecosystem dynamics such as the area and percent of forest disturbance, early regrowth and succession provide essential inputs to process-driven models of carbon flux. BIOPHYS is well suited for large-area, multi-temporal applications involving multiple image sets and mosaics for assessing vegetation disturbance and quantifying biophysical structural dynamics and change. It is also suitable for integration with forest inventory, monitoring, updating, and other programs.

MapReduce Based Information Retrieval Algorithms for Efficient Ranking of Webpages

In this paper, the authors discuss the MapReduce implementation of crawler, indexer and ranking algorithms in search engines. The proposed algorithms are used in search engines to retrieve results from the World Wide Web. A crawler and an indexer in a MapReduce environment are used to improve the speed of crawling and indexing. The proposed ranking algorithm is an iterative method that makes use of the link structure of the Web and is developed using MapReduce framework to improve the speed of convergence of ranking the WebPages. Categorization is used to retrieve and order the results according to the user choice to personalize the search. A new score is introduced in this paper that is associated with each WebPage and is calculated using user’s query and number of occurrences of the terms in the query in the document corpus. The experiments are conducted on Web graph datasets and the results are compared with the serial versions of crawler, indexer and ranking algorithms.

Web information retrieval and filtering course to undergraduates using open source programming

This paper describes how to engage actively students in web information retrieval and filtering course using open source programming. To teach this course, I utilized hands-on lab projects from various open source projects including the Galago search engine. Projects included, but were not limited to, implementing information retrieval (IR) algorithms, collaborative filtering (CF) algorithms, web-based interfaces, and adding features into an open-source search engine. By practicing with real-world open source programming, students found that they better understood how to connect background knowledge to real-world applications in preparation for industry jobs.

Bidirectional Shaping and Spaces of Convergence

This article proposes a new bi-directional way of understanding the convergence of biology and computing. It argues for a reciprocal interaction in which biology and computing have shaped and are currently reshaping each other. In so doing, we qualify both the view of a natural marriage and of a digital shaping of biology, which are common in the literature written by scientists, STS, and communication scholars. The DNA database is at the center of this interaction. We argue that DNA databases are spaces of convergence for computing and biology that change in form, meaning, and function from the 1960s to the 2000s. The first part of the article shows how, in the 1980s, DNA sequencing shifted from passively incorporating computers to be increasingly modeled in digital coding and decoding. Information retrieval algorithms, reciprocally, were altered according to the peculiarities of DNA in the first sequence-storage databases. The second part of the article investigates the impact of these reciprocal interactions and globalization on the organization of research centers, ways of conducting big science, and scientific values. Through convergence and new technologies such as data mining, biology and computing were transformed technologically, institutionally, and culturally into a new bio-data enterprise called genomics.

Low-dose multiple-information retrieval algorithm for X-ray grating-based imaging

The present work proposes a low dose information retrieval algorithm for X-ray grating-based multiple-information imaging (GB-MII) method, which can retrieve the attenuation, refraction and scattering information of samples by only three images. This algorithm aims at reducing the exposure time and the doses delivered to the sample. The multiple-information retrieval problem in GB-MII is solved by transforming a nonlinear equations set to a linear equations and adopting the nature of the trigonometric functions. The proposed algorithm is validated by experiments both on conventional X-ray source and synchrotron X-ray source, and compared with the traditional multiple-image-based retrieval algorithm. The experimental results show that our algorithm is comparable with the traditional retrieval algorithm and especially suitable for high Signal-to-Noise system.