Information Retrieval In Order Research Articles

Bayes R-CNN: An Uncertainty-Aware Bayesian Approach to Object Detection in Remote Sensing Imagery for Enhanced Scene Interpretation

Remote sensing technology has been modernized by artificial intelligence, which has made it possible for deep learning algorithms to extract useful information from images. However, overfitting and lack of uncertainty quantification, high-resolution images, information loss in traditional feature extraction, and background information retrieval for detected objects limit the use of deep learning models in various remote sensing applications. This paper proposes a Bayes by backpropagation (BBB)-based system for scene-driven identification and information retrieval in order to overcome the above-mentioned problems. We present the Bayes R-CNN, a two-stage object detection technique to reduce overfitting while also quantifying uncertainty for each object recognized within a given image. To extract features more successfully, we replace the traditional feature extraction model with our novel Multi-Resolution Extraction Network (MRENet) model. We propose the multi-level feature fusion module (MLFFM) in the inner lateral connection and a Bayesian Distributed Lightweight Attention Module (BDLAM) to reduce information loss in the feature pyramid network (FPN). In addition, our system incorporates a Bayesian image super-resolution model which enhances the quality of the image to improve the prediction accuracy of the Bayes R-CNN. Notably, MRENet is used to classify the background of the detected objects to provide detailed interpretation of the object. Our proposed system is comprehensively trained and assessed utilizing the state-of-the-art DIOR and HRSC2016 datasets. The results demonstrate our system’s ability to detect and retrieve information from remote sensing scene images.

Assessing Large-Scale, Cross-Domain Knowledge Bases for Semantic Search

Semantic Search refers to set of approaches dealing with usage of Semantic Web technologies for information retrieval in order to make the process machine understandable and fetch precise results. Knowledge Bases (KB) act as the backbone for semantic search approaches to provide machine interpretable information for query processing and retrieval of results. These KB include Resource Description Framework (RDF) datasets and populated ontologies. In this paper, an assessment of the largest cross-domain KB is presented that are exploited in large scale semantic search and are freely available on Linked Open Data Cloud. Analysis of these datasets is a prerequisite for modeling effective semantic search approaches because of their suitability for particular applications. Only the large scale, cross-domain datasets are considered, which are having sizes more than 10 million RDF triples. Survey of sizes of the datasets in triples count has been depicted along with triples data format(s) supported by them, which is quite significant to develop effective semantic search models.

Quality Collection Analysis of Digital Library of Universitas Airlangga

Digital library is a library that has a collection of books in the form of digital formats and which can be accessed by computer. The digital collection is usually a collection of research, thesis, thesis, desertation and e-book. The quality of the collection is crucial to the development of digital libraries. This study uses IFLA standard (2001), where the quality of digital collections can be measured from the quality of the content, access collection and information retrieval. This study aims to analyze the quality of digital library collection of Airlangga University using quantitative discriptive method with 100 respondents. Based on the research result, it can be concluded that the quality of digital library collection of Airlangga University is very good, that is 87.32% with assessment for collection content (86.72%), access collection (93.33%) and information retrieval (81.93%). Development needs to be done to model information retrieval in order to use the weighting method and index because the method used only uses query methods without considering the user's searching behavior.

Perception of Leitmotives in Richard Wagner's Der Ring des Nibelungen.

The music of Richard Wagner tends to generate very diverse judgments indicative of the complex relationship between listeners and the sophisticated musical structures in Wagner's music. This paper presents findings from two listening experiments using the music from Wagner's Der Ring des Nibelungen that explores musical as well as individual listener parameters to better understand how listeners are able to hear leitmotives, a compositional device closely associated with Wagner's music. Results confirm findings from a previous experiment showing that specific expertise with Wagner's music can account for a greater portion of the variance in an individual's ability to recognize and remember musical material compared to measures of generic musical training. Results also explore how acoustical distance of the leitmotives affects memory recognition using a chroma similarity measure. In addition, we show how characteristics of the compositional structure of the leitmotives contributes to their salience and memorability. A final model is then presented that accounts for the aforementioned individual differences factors, as well as parameters of musical surface and structure. Our results suggest that that future work in music perception may consider both individual differences variables beyond musical training, as well as symbolic features and audio commonly used in music information retrieval in order to build robust models of musical perception and cognition.

Optimization of Clusters of Web Query Sessions using Genetic Algorithm for Effective Personalized Web Search

Personalization of web search is used for effective Information Retrieval in order to better satisfy the information need of the user on the web. The web usage mining has been used widely in Personalization of Web Search(PWS). The effectiveness of the Personalization of Web Search based on clustered web usage data depends on the quality of clusters. It is found in research that there exist no clustering algorithms that produce clusters of 100% quality. In this paper the Genetic Algorithm(GA) is used for clusters optimization in order to improve the quality of clusters for effective Personalized web search. Experiment was conducted on the data set of query sessions captured on the web in Academics, Entertainment and Sports Domain. The search results confirm the improvement in the average precision of the PWS(with cluster optimization) in comparison to PWS( without cluster optimization).

Applying Genetic Algorithms to Information Retrieval Using Vector Space Model

Genetic algorithms are usually used in information retrieval systems (IRs) to enhance the information retrieval process, and to increase the efficiency of the optimal information retrieval in order to meet the users' needs and help them find what they want exactly among the growing numbers of available information. The improvement of adaptive genetic algorithms helps to retrieve the information needed by the user accurately, reduces the retrieved relevant files and excludes irrelevant files. In this study, the researcher explored the problems embedded in this process, attempted to find solutions such as the way of choosing mutation probability and fitness function, and chose Cranfield English Corpus test collection on mathematics. Such collection was conducted by Cyrial Cleverdon and used at the University of Cranfield in 1960 containing 1400 documents, and 225 queries for simulation purposes. The researcher also used cosine similarity and jaccards to compute similarity between the query and documents, and used two proposed adaptive fitness function, mutation operators as well as adaptive crossover. The process aimed at evaluating the effectiveness of results according to the measures of precision and recall. Finally, the study concluded that we might have several improvements when using adaptive genetic algorithms. �

APPLYING GENETIC ALGORITHMS TO INFORMATION RETRIEVAL USING VECTOR SPACE MODEL

Genetic algorithms are usually used in information retrieval systems (IRs) to enhance the information retrieval process, and to increase the efficiency of the optimal information retrieval in order to meet the users’ needs and help them find what they want exactly among the growing numbers of available information. The improvement of adaptive genetic algorithms helps to retrieve the information needed by the user accurately, reduces the retrieved relevant files and excludes irrelevant files. In this study, the researcher explored the problems embedded in this process, attempted to find solutions such as the way of choosing mutation probability and fitness function, and chose Cranfield English Corpus test collection on mathematics. Such collection was conducted by Cyrial Cleverdon and used at the University of Cranfield in 1960 containing 1400 documents, and 225 queries for simulation purposes. The researcher also used cosine similarity and jaccards to compute similarity between the query and documents, and used two proposed adaptive fitness function, mutation operators as well as adaptive crossover. The process aimed at evaluating the effectiveness of results according to the measures of precision and recall. Finally, the study concluded that we might have several improvements when using adaptive genetic algorithms.

Fallout and miss in journal peer review

PurposeThe authors exploit the analogy between journal peer review and information retrieval in order to quantify some imperfections of journal peer review.Design/methodology/approachThe authors define fallout rate and missing rate in order to describe quantitatively the weak papers that were accepted and the strong papers that were missed, respectively. To assess the quality of manuscripts the authors use bibliometric measures.FindingsFallout rate and missing rate are put in relation with the hitting rate and success rate. Conclusions are drawn on what fraction of weak papers will be accepted in order to have a certain fraction of strong accepted papers.Originality/valueThe paper illustrates that these curves are new in peer review research when interpreted in the information retrieval terminology.

Categorization of services for seeking information in biomedical literature: a typology for improvement of practice

Biomedical researchers have to efficiently explore the scientific literature, keeping the focus on their research. This goal can only be achieved if the available means for accessing the literature meet the researchers' retrieval needs and if they understand how the tools filter the perpetually increasing number of documents. We have examined existing web-based services for information retrieval in order to give users guidance to improve their everyday practice of literature analysis. We propose two dimensions along which the services may be categorized: categories of input and output formats; and categories of behavioural usage. The categorization would be helpful for biologists to understand the differences in the input and output formats and the tasks they fulfil in information-retrieval activities. Also, they may inspire future bioinformaticians to further innovative development in this field.

On the conceptualisation of the query refinement task

PurposeTo resolve the drawback in the existing methods for query refinement by using semantic technologies. Design/methodology/approach – The article introduces a conceptual space (ontology) in which a query refinement problem will be treated. In that space a query is modeled as a set of logic formulas, query refinement process is modeled as an inferencing process. The approach is focused on the positive conjunctive queries.FindingsThis (re)opens a question about a need for a more semantic‐based indexing of documents in the traditional information retrieval in order to improve the overall retrieval performances. This experimental study has shown that the semantics arisen (emerged) from row documents has enough quality to enable building query refinement methods that outperform the most advanced syntactic‐driven methods. Consequently, one can imagine a more emergent‐semantic based indexing process that will retain the autonomy of web data, but will significantly increase the precision of the retrieval process performed by a traditional search engine.Originality/valueA novel approach for the query refinement is presented. It deals with the conceptual level of a user's query. Another benefits is that this conceptual structure emerges from the textual data automatically. The case study shows how a traditional full‐text search engine can benefit from applying this approach.

Serial retrieval processes in the recovery of order information.

The retrieval of temporal order and item information from short-term memory (STM) are examined with the cued-response speed-accuracy trade-off (CR-SAT) procedure and a complementary reaction time (RT) task. The retrieval of order information was examined with a two-alternative forced-choice (2AFC), relative judgment of recency (JOR) task. Analyses of the pattern of mean RT, RT accuracy, and the overall shape of the RT distribution for correct JORs suggest that order information is retrieved by a serial retrieval mechanism. Analyses of SAT retrieval functions confirm that order information is retrieved by a recency-based, serial retrieval process. These results contrast with previous SAT analyses of STM item recognition (B. McElree & B. A. Dosher, 1989), which indicate that item information is retrieved by a parallel or direct-access mechanism. The dissociation between item and order information retrieval was further documented in a 2AFC item recognition SAT study

Knowledge-based indexing of the medical literature: the Indexing Aid Project.

This article describes the Indexing Aid Project for conducting research in the areas of knowledge representation and indexing for information retrieval in order to develop interactive knowledge-based systems for computer-assisted indexing of the periodical medical literature. The system uses an experimental frame-based knowledge representation language, FrameKit, implemented in Franz Lisp. The initial prototype is designed to interact with trained MEDLINE indexers who will be prompted to enter subject terms as slot values in filling in document-specific frame data structures that are derived from the knowledge-base frames. In addition, the automatic application of rules associated with the knowledge-base frames produces a set of Medical Subject Heading (MeSH) keyword indices to the document. Important features of the system are representation of explicit relationships through slots which express the relations; slot values, restrictions, and rules made available by inheritance through "is-a" hierarchies; slot values denoted by functions that retrieve values from other slots; and restrictions on slot values displayable during data entry.