Data Extraction System Research Articles

Understanding key factors in automated vehicle collisions: Automating data extraction and analyzing key insights using explainable AI

With the growing development and deployment of automated vehicles (AVs), it is crucial to understand the associated risks and factors contributing to collisions involving AVs. California possesses an immense amount of publicly available data from AV testing due to the requirement laid out by the California Department of Motor Vehicles (DMV), which requires all automated vehicle operators to report collisions for any level of severity. However, this information is reported in specific forms and requires a laborious task to aggregate data from these reports. This study creates an automated data extraction system for these reports and analyses collision characteristics using logistic regression models as well as XGBoost models with SHapley Additive exPlanation (SHAP) interpretation. Additionally, these characteristics are matched with the characteristics of non-automated vehicles (non-AVs) for the same region. The results of the study indicate that rear-end collisions are the most common type of collision observed in currently deployed AVs. The analysis further revealed an increased likelihood of injury-prone rear-end collisions in AVs at intersections compared to non-AVs. Transportation policymakers and researchers should take these safety concerns into account when addressing AV deployment and developing appropriate measures to mitigate collision risks in mixed fleet conditions.

Testing a Cloud-Based Model for Active Surveillance of Medical Devices with Analyses of Coronary Stent Safety Using the Data Extraction and Longitudinal Trend Analysis (DELTA) System.

To demonstrate the use of the Data Extraction and Longitudinal Trend Analysis (DELTA) system in the National Evaluation System for health Technology's (NEST) medical device surveillance cloud environment by analyzing coronary stent safety using real world clinical data and comparing results to clinical trial findings. Electronic health record (EHR) data from two health systems, the Social Security Death Master File, and device databases were ingested into the NEST cloud, and safety analyses of two stents were performed using DELTA. This is an observational study of patients receiving zotarolimus drug-eluting coronary stents (ZES) or everolimus eluting coronary stents (EES) between July 1, 2015 and December 31, 2017. After exclusions, 3334 patients receiving EES and 1002 receiving ZES were available for study. Analysis using inverse probability weighting showed no significant difference in one-year mortality or major adverse cardiac events (MACE) for EES compared to ZES [Mortality Odds Ratio 0.94 (95% CI 0.81-1.175); p = 0.780] [MACE Odds Ratio 1.04 (95% CI 0.92-1.16; p = 0.551]). Analysis using propensity matching showed no significant difference in EES one-year mortality (547 of 992 alive and available after censoring) compared to ZES (546 of 992) [Log-Rank statistic 0.3348 (p = 0.563)]. Automated cloud-based medical device safety surveillance using EHR data is feasible and was efficiently performed using DELTA. No statistically significant differences in 1-year safety outcomes between ZES and EES were identified using two statistical approaches, consistent with randomized trial findings.

Data-driven information extraction and enrichment of molecular profiling data for cancer cell lines.

With the proliferation of research means and computational methodologies, published biomedical literature is growing exponentially in numbers and volume. Cancer cell lines are frequently used models in biological and medical research that are currently applied for a wide range of purposes, from studies of cellular mechanisms to drug development, which has led to a wealth of related data and publications. Sifting through large quantities of text to gather relevant information on cell lines of interest is tedious and extremely slow when performed by humans. Hence, novel computational information extraction and correlation mechanisms are required to boost meaningful knowledge extraction. In this work, we present the design, implementation, and application of a novel data extraction and exploration system. This system extracts deep semantic relations between textual entities from scientific literature to enrich existing structured clinical data concerning cancer cell lines. We introduce a new public data exploration portal, which enables automatic linking of genomic copy number variants plots with ranked, related entities such as affected genes. Each relation is accompanied by literature-derived evidences, allowing for deep, yet rapid, literature search, using existing structured data as a springboard. Our system is publicly available on the web at https://cancercelllines.org.

A novel automated label data extraction and data base generation system from herbarium specimen images using OCR and NER

Digital extraction of label data from natural history specimens along with more efficient procedures of data entry and processing is essential for improving documentation and global information availability. Herbaria have made great advances in this direction lately. In this study, using optical character recognition (OCR) and named entity recognition (NER) techniques, we have been able to make further advancements towards fully automatic extraction of label data from herbarium specimen images. This system can be developed and run on a consumer grade desktop computer with standard specifications, and can also be applied to extracting label data from diverse kinds of natural history specimens, such as those in entomological collections. This system can facilitate the digitization and publication of natural history museum specimens around the world.

Automatic Data Extraction Utilizing Structural Similarity From A Set of Portable Document Format (PDF) Files

Instead of storing data in databases, common computer-aided office workers often choose to keep data related to their work in the form of document or report files that they can conveniently and comfortably access with popular off-the-shelf softwares, such as in Portable Document Format (PDF) format files. Their workplaces may actually use databases but they usually do not possess the privilege nor the proficiency to fully utilize them. Said workplaces likely have front-end systems such as Management Information System (MIS) from where workers get their data containing reports or documents.These documents are meant for immediate or presentational uses but workers often keep these files for the data inside which may come to be useful later on. This way, they can manipulate and combine data from one or more report files to suit their work needs, on the occasions that their MIS were not able to fulfill such needs. To do this, workers need to extract data from the report files. However, the files also contain formatting and other contents such as organization banners, signature placeholders, and so on. Extracting data from these files is not easy and workers are often forced to use repeated copy and paste actions to get the data they want. This is not only tedious but also time-consuming and prone to errors. Automatic data extraction is not new, many existing solutions are available but they typically require human guidance to help the data extraction before it can become truly automatic. They may also require certain expertise which can make workers hesitant to use them in the first place. A particular function of an MIS can produce many report files, each containing distinct data, but still structurally similar. If we target all PDF files that come from such same source, in this paper we demonstrated that by exploiting the similarity it is possible to create a fully automatic data extraction system that requires no human guidance. First, a model is generated by analyzing a small sample of PDFs and then the model is used to extract data from all PDF files in the set. Our experiments show that the system can quickly achieve 100% accuracy rate with very few sample files. Though there are occasions where data inside all the PDFs are not sufficiently distinct from each other resulting in lower than 100% accuracy, this can be easily detected and fixed with slight human intervention. In these cases, total no human intervention may not be possible but the amount needed can be significantly reduced.

GeoDeepShovel: A platform for building scientific database from geoscience literature withAIassistance

AbstractWith the rapid development of big data science, the research paradigm in the field of geosciences has also begun to shift to big data‐driven scientific discovery. Researchers need to read a huge amount of literature to locate, extract and aggregate relevant results and data that are published and stored in PDF format for building a scientific database to support the big data‐driven discovery. In this paper, based on the findings of a study about how geoscientists annotate literature and extract and aggregate data, we proposed GeoDeepShovel, a publicly available AI‐assisted data extraction system to support their needs. GeoDeepShovel leverages state‐of‐the‐art neural network models to support researcher(s) easily and accurately annotate papers (in the PDF format) and extract data from tables, figures, maps, etc., in a human–AI collaboration manner. As a part of the Deep‐Time Digital Earth (DDE) program, GeoDeepShovel has been deployed for 8 months, and there are already 400 users from 44 geoscience research teams within the DDE program using it to construct scientific databases on a daily basis, and more than 240 projects and 50,000 documents have been processed for building scientific databases.

RNA‐seq‐driven expression analysis to investigate cardiovascular disease genes with associated phenotypes among atrial fibrillation patients

RNA‐seq‐driven expression analysis to investigate cardiovascular disease genes with associated phenotypes among atrial fibrillation patients

Building Self-Healing Feature Based on Faster R-CNN Deep Learning Technique in Web Data Extraction Systems

Web data extraction has evolved over the years with extracting data from documents to today’s World Wide Web (WWW). The WWW growth has placed data at the centre of this ecosystem and benefited society at large, businesses and consumers. The proposed system uses deep learning technique, Faster region convolutional neural network (R-CNN) for automated navigation, extraction of data and self-healing of data extraction engine to adapt to dynamic changes in website layout. The proposed system trains the Faster R-CNN model for detection of product in the web page using bounding box image detection technique and extracts product details with high extraction accuracy. Deep learning technique has advanced rapidly in the different fields for image detection, but its application in data extraction makes this paper unique. An ecommerce retail website is used as real-world example to prove the self-healing capability of the proposed automated web data extraction system.

Interoperable data extraction and information enrichment system to support smart manufacturing: an experimental application on CNC machining lines of a healthcare product

Paper aims This research develops an expert system for interoperable data acquirement and information enrichment in the manufacturing lines of a healthcare product, ensuring the correct data and information sharing and supporting the decision-making process. Originality The research contributes to creating and developing a novel method of knowledge representation that systematises the data collection and creates semantic relationships that allow the analysis of the productive performance of healthcare product manufacturing through semantic rules and inference engines. Research method The Interoperable Data Extraction and Information Enrichment system 4.0 (IDEIEs 4.0) was developed using an ontological approach and experimentally applied in an implantable Vascular Access Catheterindicated production process, which involves a machining controlling process. Main findings The developed system application pointed out the reduction of human mistakes in the data collecting, errors in the production control and data loss due to the digital automatic and interoperable collection process that brings precision in data collection and security in their storage. Implications for theory and practice The solution presented here can be used as a starting point for new directions of research to support the decision-making process with extra and formalised information, improving product quality, flexibilities the manufacturing process and reducing the time wasted.

Trends in web data extraction using machine learning

Web data extraction has seen significant development in the last decade since its inception in the early nineties. It has evolved from a simple manual way of extracting data from web page and documents to automated extraction to an intelligent extraction using machine learning algorithms, tools and techniques. Data extraction is one of the key components of end-to-end life cycle in web data extraction process that includes navigation, extraction, data enrichment and visualization. This paper presents the journey of web data extraction over the last many years highlighting evolution of tools, techniques, frameworks and algorithms for building intelligent web data extraction systems. The paper also throws light into challenges, opportunities for future research and emerging trends over the years in web data extraction with specific focus on machine learning techniques. Both traditional and machine learning approaches to manual and automated web data extraction are experimented and results published with few use cases demonstrating the challenges in web data extraction in the event of changes in the website layout. This paper introduces novel ideas such as self-healing capability in web data extraction and proactive error detection in the event of changes in website layout as an area of future research. This unique perspective will help readers to get deeper insights in to the present and future of web data extraction.

Intelligent and adaptive web data extraction system using convolutional and long short-term memory deep learning networks

Data are crucial to the growth of e-commerce in today's world of highly demanding hyper-personalized consumer experiences, which are collected using advanced web scraping technologies. However, core data extraction engines fail because they cannot adapt to the dynamic changes in website content. This study investigates an intelligent and adaptive web data extraction system with convolutional and Long Short-Term Memory (LSTM) networks to enable automated web page detection using the You only look once (Yolo) algorithm and Tesseract LSTM to extract product details, which are detected as images from web pages. This state-of-the-art system does not need a core data extraction engine, and thus can adapt to dynamic changes in website layout. Experiments conducted on real-world retail cases demonstrate an image detection (precision) and character extraction accuracy (precision) of 97% and 99%, respectively. In addition, a mean average precision of 74%, with an input dataset of 45 objects or images, is obtained.

Improving Data Extraction System to Parse Data from Scraped Job Advertisements

Extracting the information from an online job advertisement might be a little tricky. The information is wrapped with redundant information, called boilerplate, that is not related to the job at all. The information also needs to be segmented and classified into the right class or groups. After the information has been classified, it is easier to find the features (e.g., required skills and required education) that make the later processing faster.

The smallest extraction problem

We introduce landmark grammars , a new family of context-free grammars aimed at describing the HTML source code of pages published by large and templated websites and therefore at effectively tackling Web data extraction problems. Indeed, they address the inherent ambiguity of HTML, one of the main challenges of Web data extraction, which, despite over twenty years of research, has been largely neglected by the approaches presented in literature. We then formalize the Smallest Extraction Problem (SEP), an optimization problem for finding the grammar of a family that best describes a set of pages and contextually extract their data. Finally, we present an unsupervised learning algorithm to induce a landmark grammar from a set of pages sharing a common HTML template, and we present an automatic Web data extraction system. The experiments on consolidated benchmarks show that the approach can substantially contribute to improve the state-of-the-art.

JAMIP: an artificial-intelligence aided data-driven infrastructure for computational materials informatics

Materials informatics has emerged as a promisingly new paradigm for accelerating materials discovery and design. It exploits the intelligent power of machine learning methods in massive materials data from experiments or simulations to seek new materials, functionality, and principles, etc. Developing specialized facilities to generate, collect, manage, learn, and mine large-scale materials data is crucial to materials informatics. We herein developed an artificial-intelligence-aided data-driven infrastructure named Jilin Artificial-intelligence aided Materials-design Integrated Package (JAMIP), which is an open-source Python framework to meet the research requirements of computational materials informatics. It is integrated by materials production factory, high-throughput first-principles calculations engine, automatic tasks submission and monitoring progress, data extraction, management and storage system, and artificial intelligence machine learning based data mining functions. We have integrated specific features such as an inorganic crystal structure prototype database to facilitate high-throughput calculations and essential modules associated with machine learning studies of functional materials. We demonstrated how our developed code is useful in exploring materials informatics of optoelectronic semiconductors by taking halide perovskites as typical case. By obeying the principles of automation, extensibility, reliability, and intelligence, the JAMIP code is a promisingly powerful tool contributing to the fast-growing field of computational materials informatics.

Procedure for the Contextual, Textual and Ontological Construction of Specialized Knowledge Bases

Information Retrieval (IR) from data sources such as the web, databases, sensors, etc., and structuring it through ontologies is an ambitious research field that leads to the reduction of information search time, improvement of the quality of found information and the efficient decision making. In this work, we have proposed a system for extracting information from several data sources to enrich an ontology in the field of plant pathology. The objective of this work is to develop a knowledge base in the field of plant pathology, by structuring the data present in various data sources accessible mainly through the web. To do this, we first propose a modular development approach of a domain ontology. The construction of the ontology at first uses the text-based construction technique and then, we use the generic architecture of a web data extraction system technique from literature to propose a data extraction system for the enrichment of the different ontology modules of the domain. For each subsystem of our extraction system, we have developed the algorithms to be implemented.

An Improved Approach for Deep Web Data Extraction

The World Wide Web is a valuable wellspring of data which contains information in a wide range of organizations. The different organizations of pages go about as a boundary for performing robotized handling. Numerous business associations require information from the World Wide Web for doing insightful undertakings like business knowledge, item insight, serious knowledge, dynamic, assessment mining, notion investigation, and so on Numerous scientists face trouble in tracking down the most fitting diary for their exploration article distribution. Manual extraction is arduous which has directed the requirement for the computerized extraction measure. In this paper, approach called ADWDE is proposed. This drew closer is essentially founded on heuristic methods. The reason for this exploration is to plan an Automated Web Data Extraction System (AWDES) which can recognize the objective of information extraction with less measure of human intercession utilizing semantic marking and furthermore to perform extraction at a satisfactory degree of precision. In AWDES, there consistently exists a compromise between the degree of human intercession and precision. The objective of this examination is to diminish the degree of human intercession and simultaneously give exact extraction results independent of the business space to which the site page has a place.

DisKnow: A Social-Driven Disaster Support Knowledge Extraction System

This research is aimed at creating and presenting DisKnow, a data extraction system with the capability of filtering and abstracting tweets, to improve community resilience and decision-making in disaster scenarios. Nowadays most people act as human sensors, exposing detailed information regarding occurring disasters, in social media. Through a pipeline of natural language processing (NLP) tools for text processing, convolutional neural networks (CNNs) for classifying and extracting disasters, and knowledge graphs (KG) for presenting connected insights, it is possible to generate real-time visual information about such disasters and affected stakeholders, to better the crisis management process, by disseminating such information to both relevant authorities and population alike. DisKnow has proved to be on par with the state-of-the-art Disaster Extraction systems, and it contributes with a way to easily manage and present such happenings.

Antimicrobial stewardship in remote primary healthcare across northern Australia.

BackgroundThe high burden of infectious disease and associated antimicrobial use likely contribute to the emergence of antimicrobial resistance in remote Australian Aboriginal communities. We aimed to develop and apply context-specific tools to audit antimicrobial use in the remote primary healthcare setting.MethodsWe adapted the General Practice version of the National Antimicrobial Prescribing Survey (GP NAPS) tool to audit antimicrobial use over 2–3 weeks in 15 remote primary healthcare clinics across the Kimberley region of Western Australia (03/2018–06/2018), Top End of the Northern Territory (08/2017–09/2017) and far north Queensland (05/2018–06/2018). At each clinic we reviewed consecutive clinic presentations until 30 presentations where antimicrobials had been used were included in the audit. Data recorded included the antimicrobials used, indications and treating health professional. We assessed the appropriateness of antimicrobial use and functionality of the tool.ResultsWe audited the use of 668 antimicrobials. Skin and soft tissue infections were the dominant treatment indications (WA: 35%; NT: 29%; QLD: 40%). Compared with other settings in Australia, narrow spectrum antimicrobials like benzathine benzylpenicillin were commonly given and the appropriateness of use was high (WA: 91%; NT: 82%; QLD: 65%). While the audit was informative, non-integration with practice software made the process manually intensive.ConclusionsPatterns of antimicrobial use in remote primary care are different from other settings in Australia. The adapted GP NAPS tool functioned well in this pilot study and has the potential for integration into clinical care. Regular stewardship audits would be facilitated by improved data extraction systems.

VIDE - Vault App Identification and Extraction System for iOS Devices

Content hiding (or vault) apps are a class of applications that allow users to hide photos, videos, documents and other content securely. A subclass of these applications called decoy apps further supports secret hiding by having a mode which mimics standard apps such as calculators but can turn into a vault app through entering a specific input. In this work we focus on iOS devices and first describe how to identify content hiding applications from the App Store. We consider not only the US Store but also give results for App Stores in Russia, India and China. We show an effective and very fast identification of content hiding apps through a two-phase process: initial categorization using keywords followed by more precise binary classification. We next turn to understanding the behavior and features of these vault apps and how to extract the hidden information from artifacts of the app's stored data. Based on this work, we have designed and built a fully automated vault app identification and extraction system that first identifies and then extracts the hidden data from the apps on an iOS smartphone. Using our vault identification and data extraction system (VIDE), law enforcement investigators can more easily identify and extract data from such apps as needed. Although vault apps are removed regularly from the App Store, VIDE can still identify removed apps as our system continues to maintain information on such apps in our vault database.

SARS-CoV-2 in children and adolescents in Norway: confirmed infection, hospitalisations and underlying conditions.

Children and adolescents are at lower risk of disease caused by SARS-CoV-2. We describe the incidence of confirmed infection and hospitalisation of children and adolescents under the age of 20 in Norway, and specifically among those with underlying conditions. The Norwegian Directorate of Health has collaborated with the Norwegian Institute of Public Health on the establishment of a data extraction system to monitor the coronavirus outbreak. Data from the specialist health service (Norwegian Patient Registry, NPR), and the primary health service (Norwegian Registry for Primary Health Care, NRPHC) are linked to data on positive SARS-CoV-2 tests from the Surveillance System for Communicable Diseases (MSIS). This covers all persons living in Norway as of 1 March 2020, with data on confirmed infection up to and including 13 May 2020 and on hospitalisations up to and including 30 April 2020. Of 8 125persons with confirmed SARS-CoV-2 in the whole population, 493 (6.1%) were under 20 years old. The median age of the under-20s was 15 years, and 252 (51%) were girls. 3% were hospitalised. No deaths were registered among patients aged under 20 in Norway. We found a somewhat larger share with confirmed SARS-CoV-2 in the group with diseases of the neuromuscular system. Few children and adolescents have had SARS-CoV-2 confirmed, and only a very few have been hospitalised. Underlying conditions may result in a lower threshold for testing, and hence a higher incidence of confirmed infection in this group, although higher risk cannot be excluded.