Accurate Information Retrieval Research Articles

A Novel Boundary Loss Function in Deep Convolutional Networks to Improve the Buildings Extraction From High-Resolution Remote Sensing Images

In recent years, there has been a significant increase in the production of high-resolution aerial and satellite imagery. Analyzing and extracting urban features from these images, especially building components, is a significant challenge in photogrammetry and remote sensing. Meanwhile, deep convolution neural networks have been used as a powerful model in the semantic segmentation of building features. However, due to the structure of these types of deep convolution networks, accurate retrieval of building boundary information during training will be difficult, and this will lead to ambiguous boundary areas. On the other hand, the use of distributed-based loss functions, such as the binary cross-entropy loss alone cannot improve the segmentation accuracy in the boundary areas of building features. Accordingly, in this paper, a derivative boundary loss function is introduced to optimize and enhance the extraction of buildings in border areas. To calculate the proposed boundary loss function, distance transform image (DTI), is obtained from ground-truth images and predicted images, that derived from the segmentation network. In this paper, a derivative method for calculating DTI is presented. Another advantage of the proposed loss function is its ability to be used in a wide range of deep convolution segmentation networks. The proposed method was investigated and tested using the ISPRS Potsdam and Vaihingen data sets. The results of this implementation show the superiority in the criteria of evaluation and improvement of buildings extraction if the proposed boundary loss function is used along with the distributed-based loss function.

Multistage BiCross encoder for multilingual access to COVID-19 health information.

The Coronavirus (COVID-19) pandemic has led to a rapidly growing 'infodemic' of health information online. This has motivated the need for accurate semantic search and retrieval of reliable COVID-19 information across millions of documents, in multiple languages. To address this challenge, this paper proposes a novel high precision and high recall neural Multistage BiCross encoder approach. It is a sequential three-stage ranking pipeline which uses the Okapi BM25 retrieval algorithm and transformer-based bi-encoder and cross-encoder to effectively rank the documents with respect to the given query. We present experimental results from our participation in the Multilingual Information Access (MLIA) shared task on COVID-19 multilingual semantic search. The independently evaluated MLIA results validate our approach and demonstrate that it outperforms other state-of-the-art approaches according to nearly all evaluation metrics in cases of both monolingual and bilingual runs.

Fuzzy Data Mining Technology Based on Time Sequence in Archives Management System

The rapid development of data mining technology enables the processing of unstructured data in archives. It can help realize the multiple classification of archives, the accurate retrieval of archive information, the integrated presentation of archive content, and the scientific standardization of archive appraisal. This article mainly introduces the research of fuzzy data mining technology based on time series in archives management system. This paper uses the research on the time series-based fuzzy data mining technology in the archives management system, uses the data mining technology to plan and design the archives management system, and combines the relevant procedures of the archives management work to discuss what should be followed when designing the archives data mining model. It also introduces the basic framework of archive data mining in detail, mainly from the aspects of database construction, data preprocessing, data document establishment, training process design, application process architecture and so on. The experimental results of this paper show that the research on the time series-based fuzzy data mining technology in the file management system has increased the efficiency of file management by 19%. The limitation of the research on the time series-based fuzzy data mining technology in the file management system is the data Mining applications provide good methods and ways to analyze, discuss and summarize, so as to enrich the academic research results.

Artificial intelligence-assisted tools for redefining the communication landscape of the scholarly world

The flood of research output and increasing demands for peer reviewers have necessitated the intervention of artificial intelligence (AI) in scholarly publishing. Although human input is seen as essential for writing publications, the contribution of AI slowly and steadily moves ahead. AI may redefine the role of science communication experts in the future and transform the scholarly publishing industry into a technology-driven one. It can prospectively improve the quality of publishable content and identify errors in published content. In this article, we review various AI and other associated tools currently in use or development for a range of publishing obligations and functions that have brought about or can soon leverage much-demanded advances in scholarly communications. Several AI-assisted tools, with diverse scope and scale, have emerged in the scholarly market. AI algorithms develop summaries of scientific publications and convert them into plain-language texts, press statements, and news stories. Retrieval of accurate and sufficient information is prominent in evidence-based science publications. Semantic tools may empower transparent and proficient data extraction tactics. From detecting simple plagiarism errors to predicting the projected citation impact of an unpublished article, AI’s role in scholarly publishing is expected to be multidimensional. AI, natural language processing, and machine learning in scholarly publishing have arrived for writers, editors, authors, and publishers. They should leverage these technologies to enable the fast and accurate dissemination of scientific information to contribute to the betterment of humankind.

Unmanned aerial vehicle-based field phenotyping of crop biomass using growth traits retrieved from PROSAIL model

Unmanned aerial vehicle (UAV) platform has been perceived as a useful tool for high-throughput field phenotyping of crop growth traits. While interpretation of UAV image data and retrieval of reliable and accurate phenotypic information are still challengeable due to the variations in sensors, crops and environment conditions. The aim of this study, therefore, is to explore the potential of UAV-based field phenotyping with the PROSAIL model to estimate biomass of rice and oilseed rape crops. Field experiments were designed for rice and oilseed rape with different nitrogen (N) treatments, and a UAV platform mounted with a multispectral camera was used to collect multi-temporal field images. Simultaneously, field measurements of leaf chlorophyll content (Cab), leaf area index (LAI), canopy chlorophyll content (CCC) and biomass were conducted. The results showed that coupling UAV-based multispectral images at the spectral region of 604–872 nm with the PROSAIL model successfully retrieved Cab, LAI and CCC of rice with the root mean square error (RMSE) of 5.40 μg/cm2, 1.13, and 43.50 μg/cm2, respectively. Further, the Cab, LAI and CCC retrieved from the PROSAIL model achieved the satisfactory biomass estimation in rice with the RMSE of 0.32 kg/m2, 0.23 kg/m2 and 0.22 kg/m2, respectively, which was comparable or superior to those obtained from commonly used empirical models. The proposed method also presented the robust performance for rice biomass estimation at different growth stages. In addition, model validation with the oilseed rape dataset showed an acceptable accuracy of biomass estimation with the determination coefficient (r2), RMSE and relative RMSE of 0.81, 0.03 kg/m2 and 27.82%, respectively, and still outperformed the empirical models with the better estimation performance. These findings demonstrate the potential of the proposed biomass retrieval strategy for UAV-based multispectral images, which also extend the application of PROSAIL model in field phenotyping of crop growth traits.

Identification of potential rockfall sources using UAV-derived point cloud

Recent advances in remote sensing techniques and computer algorithms allow accurate, abundant, and high-resolution geometric information retrieval for rock mass characterization from 3D point clouds. The automatic application of the extracted information for local scale rockfall susceptibility assessment, where discontinuities characteristics play a major role in rocky slope stability, requires step by step logical procedures. This paper presents a novel methodology to use the extracted discontinuity set characteristics for a local scale rockfall susceptibility assessment, tailored for Uncrewed Aerial Vehicle (UAV) data acquisition. The method consists of 4 steps: (i) 3D slope model reconstruction using UAV digital photogrammetry, (ii) automatic characterization of discontinuity sets, (iii) slope stability analysis, and (iv) susceptibility assessment using a new Rockfall Susceptibility Index. The proposed method was applied to a road cut rocky slope in a mountainous area of the Samaria National Park, in Crete Island, Greece. Visual validation indicates that the areas of higher and moderate rockfall susceptibility on the 3D model of the rocky slope are adjacent to rockfall source areas marked by the presence of fallen blocks on the foot of the slope. The proposed methodological workflow presents novelties related to the use of point clouds for the estimation of the Rock Quality Designation (RQD) index, the visualization of discontinuity set spacing, the evaluation of the persistence and the Slope Mass Rating (SMR) index, as well as the incorporation of the persistence of overhangs into the rockfall susceptibility assessment and visualization.

Development for performance of Porter stemmer algorithm

The Porter stemmer algorithm is a broadly used, however, an essential tool for natural language processing in the area of information access. Stemming is used to remove words that add the final morphological and diacritical endings of words in English words to their root form to extract the word root, i.e. called stem/root in the primary text processing stage. In other words, it is a linguistic process that simply extracts the main part that may be close to the relative and related root. Text classification is a major task in extracting relevant information from a large volume of data. In this paper, we suggest ways to improve a version of the Porter algorithm with the aim of processing and overcome its limitations and to save time and memory by reducing the size of the words. The system uses the improved Porter derivation technique for word pruning. Whereas performs cognitive-inspired computing to discover morphologically related words from the corpus without any human intervention or language-specific knowledge. The improved Porter algorithm is compared to the original stemmer. The improved Porter algorithm has better performance and enables more accurate information retrieval (IR).

Blockchain-Based Digital Contact Tracing Apps for COVID-19 Pandemic Management: Issues, Challenges, Solutions, and Future Directions.

The COVID-19 pandemic has caused substantial global disturbance by affecting more than 42 million people (as of the end of October 2020). Since there is no medication or vaccine available, the only way to combat it is to minimize transmission. Digital contact tracing is an effective technique that can be utilized for this purpose, as it eliminates the manual contact tracing process and could help in identifying and isolating affected people. However, users are reluctant to share their location and contact details due to concerns related to the privacy and security of their personal information, which affects its implementation and extensive adoption. Blockchain technology has been applied in various domains and has been proven to be an effective approach for handling data transactions securely, which makes it an ideal choice for digital contact tracing apps. The properties of blockchain such as time stamping and immutability of data may facilitate the retrieval of accurate information on the trail of the virus in a transparent manner, while data encryption assures the integrity of the information being provided. Furthermore, the anonymity of the user’s identity alleviates some of the risks related to privacy and confidentiality concerns. In this paper, we provide readers with a detailed discussion on the digital contact tracing mechanism and outline the apps developed so far to combat the COVID-19 pandemic. Moreover, we present the possible risks, issues, and challenges associated with the available contact tracing apps and analyze how the adoption of a blockchain-based decentralized network for handling the app could provide users with privacy-preserving contact tracing without compromising performance and efficiency.

Automated Ontology Population and Enrichment of Scientific Publications

Scientific publications are the most important resources available to the research communities. Researchers want their work to be widely recognized and available and also need powerful search engines to identify other publications and researchers working in the same area. Therefore, a good representation and organization of scientific products is crucial for an accurate retrieval of information. This paper describes an approach for automated population and semantic enrichment of an ontology model that represents scientific publications. Specifically, the type of enrichment used in this approach consists of implementing semantic similarity measurements between publications. Several experiments were performed to identify the best similarity measurement, using a statistical approach and the precision of the measurements.

Designing a knowledge management system for Naval Materials Failures

NAVMAT Research project attempts an interdisciplinary approach by integrating Materials Engineering and Informatics under a platform of Knowledge Management. Failure analysis expands into forensics engineering for it aims not only to identify individual and symptomatic reasons of failure but to assess and understand repetitive failure patterns, which could be related to underlying material faults, design mistakes or maintenance omissions. NAVMAT approach utilizes a focused common-cause failure methodology for the naval and marine environment, to begin with. It will eventually support decision making through appropriate Artificial Intelligence and Natural Language Processing methods. The presented work describes the design of a knowledge based system dedicated to effective recording, efficient indexing, easy and accurate retrieval of information, history of maintenance and secure operation concerning failure incidents of marine materials, components and systems in a fleet organisation. Based on materials failure ontology, utilising artificial intelligence algorithms and modern approaches in data handling, NAVMAT aims at the optimisation of naval materials failure management and the support of decision making in Maintenance and Repair Operations (MRO), materials supplies and staff training.

Determining chronic pain data elements as a first step towards improving quality of care and research in chronic pain.

Background:Chronic pain is a significant clinical problem in the world. There is still no quite effective treatment for this pain due to its complex nature. Timely retrieval of accurate and comprehensive information through organized clinical and epidemiological studies is an essential prerequisite for providing high quality clinical care and more accurate health planning. We aimed to determine minimum set of data needed as a first step in design and development of a chronic pain registry system.Materials and Methods:This descriptive-applied study was carried out in three phases; identifying necessary minimum data, preparing a primary minimum dataset, and surveying expertsby questionnaire.Result:The literature review revealed that, theprimary minimum dataset consisted of 51 elements, which were reduced to 41 after applying the experts’ opinion. This dataset covered six areas:demographic information(8 elements), initial pain assessment(12 elements), medical history (8 elements), mental health and well-being(6 elements), diagnostic measures(3elements), and diagnosis and treatment plan (4 elements).Conclusion:Determining minimum set of chronic pain data will be an effective step towards integrating and improving information management of patients with chronic pain. It will also allow for proper storage and retrieval of information related to these patients.

Verb Sense Disambiguation by Measuring Semantic Relatedness between Verb and Surrounding Terms of Context

Word sense disambiguation (WSD) is considered an AI complete problem which may be defined as the ability to resolve the intended meaning of ambiguous words occurring in a language. Language has complex structure and is highly ambiguous which has deep rooted relations between its different components specifically words, sentences and paragraphs. Incidentally, human beings can easily comprehend and resolve the intended meanings of the ambiguous words. The difficulty arises in building a highly accurate machine translation system or information retrieval system because of ambiguity. A number of algorithms have been devised to solve ambiguity but the success rate of these algorithms are very much limited. Context might have played a decisive role in human judgment while deciphering the meaning of polysemic words. A significant number of psychological models have been proposed to emulate the way the human beings understand the meaning of words, sentences or text depending on the context. The pertinent question that the researchers want to address is how the meanings are represented by human beings in mental memory and whether it is feasible to simulate with a computational model. Latent Semantic Analysis (LSA), a mathematical technique which is effective in representation of meanings in the form of vectors that closely approximates human semantic space. By comparing the vectors in the LSA generated semantic space, the closest neighbours of the word vector can be derived which indirectly provides lot of information about a word. However, LSA does not provide a complete theory of meaning. That is why psychological process modules are combined with LSA to make the theory of meaning concrete. Predication algorithm with LSA was proposed by Kintch, 2001 which was sufficient to capture various word senses and was successful in homonym disambiguation. Meaning of a word might have multiple senses specifically verbs. For example, verb “run” has 42 senses in WordNet. In order to find the correct sense of a verb is really a daunting task and resolving verb ambiguity using psycholinguistic model is very much limited. The proposed method has exploited the high dimensional vector LSA space resulted from training samples by applying predication algorithm to derive the most appropriate semantic neighbours for the target polysemous verb from the semantic space. Finally the vector space of test samples are checked with the training samples i.e. semantic neighbours to classify the senses of polysemous words in accurate manner.

An Explanation of the False Drop in Information Retrieval in Human-Computer Interaction

Nowadays the field of information retrieval is quickly developing. Research on the human-computer interactions and designing of the interface is likely to lead to better results and greater empowerment for users and creators of information. One of the main and special issues related to the relationship between humans and computers in information storage and retrieval systems is the problem of accurate and correct information retrieval based on the user's information needs, due to there are still many false drops in the user's retrievals, although have the many advances come in this field. On the other hand, the human-computer interface environment is not well understood, compared to other forms of information retrieval, due to the complexity of human perception and detection compared to computer systems and the more difficult the detection and measurement of human motives and behaviors. In this paper, after reviewing the information storage and retrieval systems and their various evaluation metrics, the issue of the false drop and its effect on the human-machine interactions is discussed and finally, some solutions are presented. The principles of user interface design, providing informative feedback, reducing working memory load, providing alternative interface environments for novice and skilled users and visualizing information are among the proposed solutions of the present study.

Trait anxiety does not correlate with metacognitive confidence or reminder usage in a delayed intentions task.

Setting external reminders provides a convenient way to reduce cognitive demand and ensure accurate retrieval of information for prospective tasks. Recent experimental evidence has demonstrated that the decision to offload cognitive information to external resources is guided by metacognitive belief, that is, individuals’ confidence in their unaided ability. Other work has also suggested a relationship between metacognitive belief and trait anxiety. In the present study (N = 300), we bridged these two areas by investigating whether trait anxiety correlated with metacognitive belief and—consequently—propensity to offload information in a delayed intentions paradigm. Participants received a financial reward based on their ability to remember targets. However, participants could take a reduced reward per target if they decided to use reminders. We replicated previous findings that participants were biased to use more reminders than would be optimal, and this bias was correlated with metacognitive judgements. However, we show no evidence that trait anxiety held a relationship with metacognitive belief or reminder usage. Indeed, Bayesian analyses strongly favoured the null. Therefore, variation in self-reported trait anxiety does not necessarily influence confidence and strategy when participants remember delayed intentions.

Arquitetura para integração de bibliotecas digitais geográficas por meio de mecanismos de geoprocessamento no contexto da ciência da informação

Objetivo: Construir uma arquitetura conceitual, com elementos para a criação de uma Biblioteca Digital Geográfica, utilizando os padrões e os conceitos da Ciência da Informação em conjunto com o Geoprocessamento.Método: Por meio de um estudo teórico, exploratório e bibliográfico nas áreas de Ciência da Informação e Geoprocessamento, foi possível desenvolver um modelo conceitual de arquitetura para a Biblioteca Digital Geográfica. A proposta foi estruturada em três camadas: a Cliente, responsável pelo processo de visualização; a Aplicação, que possui os processos de gerenciamento e análise; e a camada de dados, que contempla os serviços Web de dados, com foco na recuperação de metadados, via protocolo PMH (Protocol Metadata Harvesting).Resultado: A arquitetura conceitual criada atendeu os requisitos de representação da informação, as formas de comunicação com o protocolo de coleta de metadados e objetos digitais, possibilitando assim, o compartilhamento dos acervos informacionais geográficos distribuídos em diferentes Bibliotecas Digitais Geográficas ao redor do mundo. Os elementos informacionais enfocados no Geoprocessamento e as formas de representação temática e descritiva, de organização e recuperação de informação da Ciência da Informação confirmou-se o potencial de utilização recíproca e compartilhada de conceitos e ferramentas destas duas áreas.Conclusões: Os principais aspectos da pesquisa foram: com a implantação das três camadas e quatro processos, é possível a utilização de sistema de informações geográficas e aplicativos de interface ao usuário para facilitar o processo de compartilhamento e recuperação da informação. A utilização do gerenciador e do padrão de metadados proporciona a recuperação de informação precisa, juntamente com o editor de geo-ontologia único para todas as bibliotecas participantes.

Evaluating Smart Assistant Responses for Accuracy and Misinformation Regarding Human Papillomavirus Vaccination: Content Analysis Study.

BackgroundAlmost half (46%) of Americans have used a smart assistant of some kind (eg, Apple Siri), and 25% have used a stand-alone smart assistant (eg, Amazon Echo). This positions smart assistants as potentially useful modalities for retrieving health-related information; however, the accuracy of smart assistant responses lacks rigorous evaluation.ObjectiveThis study aimed to evaluate the levels of accuracy, misinformation, and sentiment in smart assistant responses to human papillomavirus (HPV) vaccination–related questions.MethodsWe systematically examined responses to questions about the HPV vaccine from the following four most popular smart assistants: Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana. One team member posed 10 questions to each smart assistant and recorded all queries and responses. Two raters independently coded all responses (κ=0.85). We then assessed differences among the smart assistants in terms of response accuracy, presence of misinformation, and sentiment regarding the HPV vaccine.ResultsA total of 103 responses were obtained from the 10 questions posed across the smart assistants. Google Assistant data were excluded owing to nonresponse. Over half (n=63, 61%) of the responses of the remaining three smart assistants were accurate. We found statistically significant differences across the smart assistants (N=103, χ22=7.807, P=.02), with Cortana yielding the greatest proportion of misinformation. Siri yielded the greatest proportion of accurate responses (n=26, 72%), whereas Cortana yielded the lowest proportion of accurate responses (n=33, 54%). Most response sentiments across smart assistants were positive (n=65, 64%) or neutral (n=18, 18%), but Cortana’s responses yielded the largest proportion of negative sentiment (n=7, 12%).ConclusionsSmart assistants appear to be average-quality sources for HPV vaccination information, with Alexa responding most reliably. Cortana returned the largest proportion of inaccurate responses, the most misinformation, and the greatest proportion of results with negative sentiments. More collaboration between technology companies and public health entities is necessary to improve the retrieval of accurate health information via smart assistants.

The thematic representation of NASA digital images on Flickr

O crescimento das redes sociais e a forma de representar os seus recursos tornou-se objeto de diversos estudos na Ciência da Informação (CI). A imagem digital carrega uma dificuldade em relação a sua representação temática nesses redes sociais. Assim, o problema deste estudo consiste em investigar a recuperação da informação nas redes sociais, principalmente em redes que disponibilizam imagens digitais. Objetiva-se analisar as contribuições do Sistema de Organização do Conhecimento – SOC – da National Aeronautics and Space Administration - NASA, na representação temática de imagens digitais disponibilizadas em redes sociais do Flickr. Utilizou-se como metodologia a abordagem exploratória e descritiva, o que oportunizou o levantamento bibliográfico dos aspectos teóricos e a análise da terminologia em imagens digitais na NASA do Flickr. Por isso, foram analisados os termos de representação temática não controlados descritos por folksonomias e os termos controlados advindos do tesauro da NASA. Como resultados da análise destaca-se os desafios gerados no uso da folksonomia na representação temática de imagens digitais e as vantagens do uso do SOC no processos de representação temática e recuperação da informação nesses ambientes. Conclui-se que as folksonomias representam livremente os termos e refletem a realidade terminológica de uma comunidade; enquanto que os SOC contribuem para um controle de vocabulário e recuperação da informação mais precisa.

Towards Accuracy: A Model for the Analysis of Typographical Errors in Specialised Bilingual Dictionaries. Two Case Studies

This paper presents the results of research on typographical error analysis in two specialised bilingual paper dictionaries: Diccionario de terminos economicos, financieros y comerciales/ A Dictionary of Economic, Financial and Commercial Terms ( Ariel, 2012), and Diccionario de terminos juri dicos/A Dictionary of Legal Terms ( Ariel, 2012). A model of errors is described, including similar errors and errors that are repeated both intratextually and intertextually. The error frequency in A Dictionary of Economic, Financial and Commercial Terms is higher than the average error frequency in a reference corpus of fourteen dictionaries (mainly first editions). This indicates that repeated editions do not always guarantee a higher level of formal correctness. Our results also show that a high frequency of errors does not necessarily entail a high intratextual error repetition rate. On the other hand, we establish a relationship between typographical errors and the access function in dictionaries, as that kind of error can interfere with access to accurate lexicographical information and data retrieval (especially when they occur in lemmas or sublemmas).

Taxonomia corporativa e taxonomia facetada: usos e aplicações na ciência da informação no Brasil

Las taxonomías permiten una recuperación más precisa de la información, ya que ayudan al usuario a buscar a través de las etiquetas de las clases y subclases presentes en la estructura jerárquica. El objetivo de este artículo es presentar un resultado parcial de una investigación más amplia, ofreciendo los usos y aplicaciones de las taxonomías corporativas y facetadas como instrumentos de representación de la información y el conocimiento, descritos en trabajos académicos en el campo de las ciencias de la información. La metodología incluyó una encuesta bibliográfica en la Biblioteca Digital de Teses e Dissertações de Capes, para mapear las tesis y tesis de posgrado relacionadas con el tema. Sólo se recuperaron siete tesis de posgrado en ciencias de la información en el periodo de 15 años, y ninguna tesis. En el análisis de los documentos se utilizó el método de análisis de contenidos, a partir de las categorías objetivo, metodología, producto final y trabajos futuros. Los resultados mostraron el estado del arte de los usos y aplicaciones de los instrumentos investigados, así como las tendencias para estudios futuros. La pequeña cantidad de investigaciones evidenció la necesidad de realizar más estudios que involucren estos instrumentos.

Implementation of Text Base Information Retrieval Technique

Everyone is in the need of accurate and efficient information retrieval in no time. Search engines are the main source to extract the required information, when a user search a query and wants to generate the results. Different search engines provide different Application Programming Interface (API) and Libraries to the researchers and the programmers to access the data that has been stored in servers of the search engines. When a researcher or programmer search's a query by using API, it returns a Java Script Orientation Notation (JSON) file. In this JSON file, information is encapsulated where scraping techniques are used to filter out the text. The aim of this paper is to propose a different approach to effectively and efficiently filter out the queries based on text which has been searched by the search engines and return the most appropriate results to the users after matching the searched text because the previous techniques which are used are not enough efficient. We use different comparison techniques, i.e. Sequence Matcher Method and then compare the results of this technique with relevance feedback and in the end we found that our proposed technique is providing much better results.