Manual Indexing Research Articles

Automatic extraction of significant terms from the title and abstract of scientific papers using the machine learning algorithm: A multiple module approach

Keyword extraction is the task of identifying important terms or phrase that are most representative of the sourcedocument. Although the process of automatic extraction of keywords from title is an old method, it was mainly forextraction from a single web document. Our approach differs from previous research works on keyword extraction in severalaspects. For those who are non-expert of the scientific fields, understating scientific research trends is difficult. The purposeof this study is to develop an automatic method of obtaining overviews of a scientific field for non-experts by capturingresearch trends. This empirical study excavates significant term extraction using Natural Language Processing (NLP) tools.More than 15000 titles saved in a .csv file was our dataset and scripts written in Python were our process to compare how farsignificant terms of scientific title corpus are similar or different to the terms available in the abstract of that same scientificarticle corpus. A light-weight unsupervised title extractor, Yet Another Keyword Extractor (YAKE) was used to extract theresults. Based on our analysis, it can be concluded that these algorithms can be used for other fields too by the non-expertsof that subject field to perform automatic extraction of significant words and understanding trends. Our algorithm could be asolution to reduce the labour-intensive manual indexing process.

Deck of cards to help track design trends to assist the creation of new products

The more competition becomes important, the more companies need to innovate in order to survive. This requires creative, adaptable, strategic intelligence ability. We will focus here on the latter capacity and particularly on knowledge acquisition for anticipating product design changes and recognizing opportunities as well as threats related to possible innovations. To do this, we propose to focus on the search for and the identification of signals that allow us to identify trends and design constants to interpret some of them as opportunities or threats of disruptive innovations in product design. The specificity of our proposition is about a knowledge acquisition system that used a physical card game as a tool for data collection. The data collection is based on common points recognized in images during several games of a card deck that are not always played by the same people. Its drawback is that it requires manual indexing of the collected data and a paper printout of the cards. We have tested the feasibility of using this type of collection with students, which we also discuss in this paper.

Coastal forest cover change detection using satellite images and convolutional neural networks in Vietnam

<span lang="EN-US">Monitoring forest cover changes is an important task for forest resource management and planning. In this context, remote sensing images have shown a high potential in forest cover changes detection. In Vietnam, although the existence of a large number of such images and ground-truth labels, current researches still relied on classical methods employed manual indices, such as multi-variant change vector analysis (MVCA) and normalized difference vegetation index. These methods highly require domain knowledge to determine threshold values for forest change that are applicable only for studied areas. Therefore, in this paper, we propose a method to detect coastal forest cover changes, which can exploit available dataset and ground-truth labels. Moreover, the proposed method does not require much domain knowledge. We used multi-temporal Sentinel-2 imagery to train a segmentation model, that is based on the U-Net network. It was used then to detect forest areas at the same location taken at different times. Lastly, we compared obtained results to identify forest disturbances. Experimental results demonstrated that our method provided a high accuracy of 95.4% on the testing set. Furthermore, we compared our model with the MVCA method and found that our model outperforms this popular method by 3.8%.</span>

Automatic text searching for information retrieval

The capabilities of automatic text search systems are reviewed and evaluation results are cited comparing the performance of automatic text searching systems with the effectiveness of manual controlled-term indexing methods. Some possibilities arethen examined for improving automatic text search systems, including the use of complex content identifiers instead of single words, and the introduction of user-system interaction. A likely scenario is given for the operations of future automatic text search systems.

Applications of Digital Health in Public Health: The China Experience

Applications of Digital Health in Public Health: The China Experience

Comparison of Field and SAR-Derived Descriptors in the Retrieval of Soil Moisture from Oil Palm Crops Using PALSAR-2

Synthetic-aperture radar’s (SAR’s) capacity to resolve the cloud cover concerns encountered while gathering optical data has tremendous potential for soil moisture data retrieval using SAR data. It is possible to use SAR data to recover soil moisture because the backscatter coefficient is sensitive to both soil and vegetation by penetrating through the vegetation layer. This study investigated the feasibility of employing a SAR-derived radar vegetation index (RVI), the ratios of the backscatter coefficients using polarizations of HH/HV (RHH/HV) and HV/HH (RHH/HV) to an oil palm crops as vegetation indicators in the water cloud model (WCM) using phased-array L-band SAR-2 (PALSAR-2). These data were compared to the manual leaf area index (LAI) and a physical soil sampling method for computing soil moisture. The field data included the LAI input parameters and, more importantly, physical soil samples from which to calculate the soil moisture. The fieldwork was carried out in Chuping District, Perlis State, Malaysia. Corresponding PALSAR-2 data were collected on three observation dates in 2019: 17 January, 16 April, and 9 July. The results showed that the WCM modeled using the LAI under HV polarization demonstrated promising accuracy, with the root mean square error recorded as 0.033 m3/m3. This was comparable to the RVI and RHH/HV under HV polarization, which had accuracies of 0.031 and 0.049 m3/m3, respectively. The findings of this study suggest that SAR-based indicators, RHH/HV and RVI using PALSAR-2, can be used to reduce field-related input in the retrieval of soil moisture data using the WCM for oil palm crop.

An automatic system for pest recognition and forecasting.

Pests cause significant damage to agricultural crops and reduce crop yields. Use of manual methods of pest forecasting for integrated pest management is labor-intensive and time-consuming. Here, we present an automatic system for monitoring pests in large fields, with the aim of replacing manual forecasting. The system comprises an automatic detection and counting system and a human-computer data statistical fitting system. Image data sets of the target pests from large fields are first input into the system. The number of pests in the image is then counted both manually and using the automatic system. Finally, a mapping relationship between counts obtained using the automated system and by agricultural experts is established using the statistical fitting system. Trends in the pest-count curves produced using the manual and automated counting methods were very similar. To sample the number of pests for manual statistics, plants were shaken to transfer the pests from the plant to a plate. Hence, pests hiding within plant crevices were also sampled and included in the count, whereas the automatic method counted only the pests visible in the images. Therefore, the computer index threshold was much lower than the manual index threshold. However, the proposed system correctly reflected trends in pest numbers obtained using computer vision. The experimental results demonstrate that our automatic pest-monitoring system can generate pest grades and can replace manual forecasting methods in large fields. © 2021 Society of Chemical Industry.

Kratt: Developing an Automatic Subject Indexing Tool for the National Library of Estonia

Manual subject indexing in libraries is a time-consuming and costly process and the quality of the assigned subjects is affected by the cataloger’s knowledge on the specific topics contained in the book. Trying to solve these issues, we exploited the opportunities arising from artificial intelligence to develop Kratt: a prototype of an automatic subject indexing tool. Kratt is able to subject index a book independent of its extent and genre with a set of keywords present in the Estonian Subject Thesaurus. It takes Kratt approximately one minute to subject index a book, outperforming humans 10–15 times. Although the resulting keywords were not considered satisfactory by the catalogers, the ratings of a small sample of regular library users showed more promise. We also argue that the results can be enhanced by including a bigger corpus for training the model and applying more careful preprocessing techniques.

Video Index Point Detection and Extraction Framework Using Custom YoloV4 Darknet Object Detection Model

The trend of learning from videos instead of documents has increased. There could be hundreds and thousands of videos on a single topic, with varying degrees of context, content, and depth of the topic. The literature claims that learners are nowadays less interested in viewing a complete video but prefers the topic of their interests. This develops the need for indexing of video lectures. Manual annotation or topic-wise indexing is not new in the case of videos. However, manual indexing is time-consuming due to the length of a typical video lecture and intricate storylines. Automatic indexing and annotation are, therefore, better and efficient solutions. This research aims to identify the need for automatic video indexing for better information retrieval and ease users navigating topics inside a video. The automatically identified topics are referred to as “Index Points.” 137-layer YoloV4 Darknet Neural Network creates a custom object detector model. The model is trained on approximately 6000 video frames and then tested on a suite of 50 videos of around 20 hours of run time. Shot Boundary detection is performed using Structural Similarity fused with a Binary Search Pattern algorithm which outperformed the state-of-the-art SSIM technique by reducing the processing time to approximately 21% and providing around 96% accuracy. Generation of accurate index points in terms of true positives and false negatives is detected through precision, recall, and F1 score, which varies between 60–80% for every video. The results show that the proposed algorithm successfully generates a digital index with reasonable accuracy in topic detection.

Intelligent Indexing and Sorting Management System – Automated Search Indexing and Sorting of Various Topics

An issue that the majority of the databases face is the static and manual character of indexing activities. This traditional method of indexing and sorting different topics is confirmed to shake the dataset performance somewhat, making downtime and a potential effect in the presentation that is normally addressed by manually indexing operations. Numerous data mining methods can accelerate this process by using proper indexing structures. Choosing the appropriate index generally relies upon the kind of operation that the algorithm performs against the dataset. Topic indexing is the operation of recognizing the principal topics covered by a document. These are helpful for some reasons: as subject headings in libraries, as keywords in scholarly articles, and as hashtags on social media platforms. Knowing a document’s topic assists individuals with deciding its importance quickly. In any case, assigning topics manually is a tedious and redundant task. This paper shows the best way to create them automatically in a way that contends with manual indexing done by humans. This paper also talks about the issues and the techniques for identifying applicable data in a huge variety of documents. The contribution of this thesis to this issue is to foster better content analysis techniques that can be utilized to describe document content with automated index terms. Index terms can be used as meta-data that defines documents and is utilized for seeking various topics. The main point of this paper is to show the way toward creating an automatic indexer which analyzes the topic of documents by integrating proof from word frequencies and proof from the linguistic analysis given by a syntactic parser. The indexer weighs the expressions of a document as per their assessed significance for depicting the topic of a given document based on the content analysis.

MeSHProbeNet-P

Indexing biomedical research articles with Medical Subject Headings (MeSH) can greatly facilitate biomedical research and information retrieval. Currently MeSH indexing is performed by human experts. To alleviate the time consumption and monetary cost caused by manual indexing, many automatic MeSH indexing models have been developed, such as MeSHProbeNet, DeepMeSH, and NLM’s official model Medical Text Indexer. In this article, we propose an end-to-end framework, MeSHProbeNet-P, which extends MeSHProbeNet with personalizable MeSH probes. In MeSHProbeNet-P, each MeSH probe carries certain aspects of biomedical knowledge and extracts related information from input articles. MeSHProbeNet-P is able to automatically personalize its MeSH probes for different input articles to ensure that the current MeSH probes best fit the current input article and the most informative features can be extracted from the article. We demonstrate the effectiveness of MeSHProbeNet-P in a real-world large-scale MeSH indexing challenge. MeSHProbeNet-P won the first place in the first batch of Task A in the 2019 BioASQ challenge. The result on the first test set of the challenge is reported in this article. We also provide ablation studies to show the advantages of personalizable MeSH probes.

Testing the validity of Wikipedia categories for subject matter labelling of open-domain corpus data

The Wikipedia category system was designed to enable browsing and navigation of Wikipedia. It is also a useful resource for knowledge organisation and document indexing, especially using automatic approaches. However, it has received little attention as a resource for manual indexing. In this article, a hierarchical taxonomy of three-level depth is extracted from the Wikipedia category system. The resulting taxonomy is explored as a lightweight alternative to expert-created knowledge organisation systems (e.g. library classification systems) for the manual labelling of open-domain text corpora. Combining quantitative and qualitative data from a crowd-based text labelling study, the validity of the taxonomy is tested and the results quantified in terms of interrater agreement. While the usefulness of the Wikipedia category system for automatic document indexing is documented in the pertinent literature, our results suggest that at least the taxonomy we derived from it is not a valid instrument for manual subject matter labelling of open-domain text corpora.

Automatic Concept Extraction for Domain and Student Modeling in Adaptive Textbooks

The increasing popularity of digital textbooks as a new learning media has resulted in a growing interest in developing a new generation of adaptive textbooks that can help readers to learn better through adapting to the readers’ learning goals and the current state of knowledge. These adaptive textbooks are most frequently powered by internal knowledge models, which associate a list of unique domain knowledge concepts with each section of the textbook. With this kind of concept-level knowledge representation, a number of intelligent operations could be performed, which include student modeling, adaptive navigation support, and content recommendation. However, manual indexing of each textbook section with concepts is challenging, time-consuming, and prone to errors. Modern research in the area of natural language processing offers an attractive alternative, called automatic keyphrase extraction. While a range of keyphrase and concept extraction methods have been developed over the last twenty years, few of the known approaches were applied and evaluated in a textbook context. In this paper, we present FACE, a supervised feature-based machine learning method for automatic concept extractions from digital textbooks. This method has been created for building domain and student models that form the core of intelligent textbooks. We evaluated FACE on a newly constructed full-scale dataset by assessing how well it approximates concept annotations produced by human experts and how well it supports the needs of student modeling. The results show that FACE outperforms several state-of-the-art keyphrase extraction methods.

FoodEx2vec: New foods’ representation for advanced food data analysis

In food and toxicology science, a huge amount of research and other data has been collected. To enable its full utilization, advanced statistical and computer methods are required. All data is related to food items, but additionally include different kinds of information. Nowadays the consumption of avocado has increased. To understand the full impact of this increased consumption on public health and the environment, different data related to avocado need to be considered.In this paper, we present an approach for representing foods in the form of vectors of continuous numbers (food embeddings) as an alternative solution to manual indexing. The utility of representing food data as a vector of continuous numbers was evaluated and demonstrated in four tasks: i) automated determination of different food groups, ii) automated detection of the food class for each food concept (raw, derivative or composite), iii) identification of most similar food concepts for a given food concept, and iv) qualitative evaluation by a food expert. The experimental results showed that these kind of vector representations outperform the traditional representational methods used for food data analysis, and thus they present a step forward to more advanced food data analysis used for discovering new knowledge.

Advanced Spectral Analysis Program.

Advanced Spectral Analysis Program is a LabVIEW-based program intended for rapid and accurate analysis of large sets of spectral data. It can handle a range of different types of data including angle-resolved and energy-dispersive powder diffraction and Raman spectra. We present it here with a focus on high-temperature high-pressure powder diffraction. The program contains a novel graphical user interface that allows rapid manual fitting and indexing of peaks which require precise fitting ranges and includes tools for fitting any Bravais lattice and arbitrary user-defined multivariate equations of state. The program allows the user to simultaneously view and manipulate multiple data sets from an experiment. The user can save and load analysis progress at any point, allowing for repeatable calculations to be performed, and to allow the fast comparison of different analysis parameters.

Automatic index selection for large-scale datalog computation

Datalog has been applied to several use cases that require very high performance on large rulesets and factsets. It is common to create indexes for relations to improve search performance. However, the existing indexing schemes either require manual index selection or result in insufficient performance on very large tasks. In this paper, we propose an automatic scheme to select indexes. We automatically create the minimum number of indexes to speed up all the searches in a given Datalog program. We have integrated our indexing scheme into an open-source Datalog engine S OUFFLÉ. We obtain performance on a par with what users have accepted from hand-optimized Datalog programs running on state-of-the-art Datalog engines, while we do not require the effort of manual index selection. Extensive experiments on large real Datalog programs demonstrate that our indexing scheme results in considerable speedups (up to 2x) and significantly less memory usage (up to 6x) compared with other automated index selections.

A consistência na indexação automática por atribuição de artigos científicos na área de Ciência da Informação

Avalia a qualidade da indexação automática por atribuição de artigos científicos brasileiros na área de Ciência da Informação via índice de consistência. Trata-se de uma pesquisa exploratória e experimental. O experimento computacional constitui da indexação automática por atribuição do corpus de 60 artigos científicos selecionados por Souza (2005), aplicando o Sistema de Indización Semi-Automático (SISA) com os descritores do Tesauro Brasileiro de Ciência da Informação (TBCI). Os termos atribuídos pelo SISA foram comparados com as palavras-chave dos autores, adotando-se o critério de consistência relaxada. Foi obtido um índice de consistência médio de 14% com a atribuição de termos gerais habilitada na configuração do SISA, e 19% sem habilitar a atribuição de termos gerais. Conclui-se que, a indexação automática por atribuição de artigos do corpus gera uma qualidade satisfatória em termos de índice de consistência quando não são incluídos os termos gerais. Também foi constatado que a atribuição de palavras-chave pelos autores precisa de uma melhor qualidade e quantidade para representar o conteúdo informacional dos artigos.

Transmission Kikuchi diffraction from nano-crystalline Ti and TiN thin-films

Nano-crystalline Ti and TiN thin-films fabricated on <100> P-type Si wafers via magnetron sputtering are characterized by transmission Kikuchi Diffraction (TKD) in an FEI Sirion scanning electron microscope (SEM). A simple and cost-effective sample preparation combined with the TKD experiment at working distance of ∼ 3 mm and a tilt of 35° produced indexable Kikuchi patterns. Pole figures generated by automatic and manual indexing revealed <0001>|| normal direction (ND) fiber texture and <111>||ND fiber texture in monolithic Ti and TiN thin-films, respectively. Glancing angle x-ray diffraction results corroborated the texture in the samples. Spatial resolution of ∼ 60 nm is achieved that is close to the limit of resolution in conventional electron backscatter diffraction (EBSD). It is demonstrated that a simple sample preparation method in TKD technique combined with selected area electron diffraction (SAED) in transmission electron microscope (TEM) may reveal fundamental knowledge about different mechanisms occurring during fabrication and processing of the thin-film systems.

Does Joystick Training Facilitate Relational Learning?

Thirteen naïve capuchin monkeys (Cebus [Sapajus] apella) were manually tested with the Transfer Index procedure, a species-fair paradigm for assessing the capacity to learn and to transfer learning. The animals were then trained to manipulate a joystick to control a cursor and to respond to stimuli on a computer screen. After the animals had mastered the remote cause-effect relations required by the computerized test system, they were returned to manual Transfer Index testing to determine whether the joystick-training intervention had affected the monkeys’ capacity for efficient and relational learning. Transfer Index scores and overall accuracy was higher following the joystick intervention, but these differences were not statistically significant. Two-choice discrimination learning and reversal appeared to be associative in nature, and there was no evidence that joystick training made the monkeys more rule-like or relational in their learning. Despite the absence of significant differences, the patterns of results encourage further study of the ways that changes in the cognitive competencies of nonhuman animals might be catalyzed by significant learning experiences.

Assessment of Performance Validity Using Embedded Saccadic and Manual Indices on a Continuous Performance Test.

In addition to manual (i.e., "button press") metrics, oculomotor metrics demonstrate considerable promise as tools for detecting invalid responding in neurocognitive assessment. This study was conducted to evaluate saccadic and manual metrics from a computerized continuous performance test as embedded indices of performance validity. Receiver operating characteristic analyses, logistic regressions, and ANOVAs were performed to evaluate saccadic and manual metrics in classification of healthy adults instructed to feign deficits ("Fake Bad" group; n = 24), healthy adults instructed to perform their best ("Best Effort" group; n = 26), and adults with a history of mild traumatic brain injury (TBI) who passed a series of validity indices ("mTBI-Pass" group; n = 19). Several saccadic and manual metrics achieved outstanding classification accuracy between Fake Bad versus Best Effort and mTBI-Pass groups, including variability (consistency) of saccadic and manual response time (RT), saccadic commission errors, and manual omission errors. Very large effect sizes were obtained between Fake Bad and Best Effort groups (Cohen's d range: 1.89-2.90; r range: .75-.78) as well as between Fake Bad and mTBI-Pass groups (Cohen's d range: 1.32-2.21; r range: .69-.71). The Fake Bad group consistently had higher saccadic and manual RT variability, more saccadic commission errors, and more manual omission errors than the Best Effort and mTBI-Pass groups. These findings are the first to demonstrate that eye movements can be used to detect invalid responding in neurocognitive assessment. These results also provide compelling evidence that concurrently measured saccadic and manual metrics can detect invalid responding with high levels of sensitivity and specificity.