Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Results
References

Text Classification Techniques in Oil Industry Applications

Profile image of Nayat Sanchez-PiNayat Sanchez-PiProfile image of Ana Cristina Bicharra GarcíaAna Cristina Bicharra García

2014, Advances in Intelligent Systems and Computing

https://doi.org/10.1007/978-3-319-01854-6_22
visibility

…

description

10 pages

link

1 file

Abstract

The development of automatic methods to produce usable structured information from unstructured text sources is extremely valuable to the oil and gas industry. A structured resource would allow researches and industry professionals to write relatively simple queries to retrieve all the information regards transcriptions of any accident. Instead of the thousands of abstracts provided by querying the unstructured corpus, the queries on structured corpus would result in a few hundred well-formed results. On this paper we propose and evaluate information extraction techniques in occupational health control process, particularly, for the case of automatic detection of accidents from unstructured texts. Our proposal divides the problem in subtasks such as text analysis, recognition and classification of failed occupational health control, resolving accidents.

Related papers

Extraction and Extended Analysis of Good Jobs from Safety Reports Using Text Mining - Focusing on the Voluntary Information Contributory to Enhancement of the Safety (VOICES) Data
Miwa Nakanishi

Lecture Notes in Computer Science, 2021

To incorporate Safety-II, which pertains to the continuation of stable operations, into safety management, we must understand why and how everyday operations are successfully carried out. However, there are no effective methods that enable such analysis since successful operations do not have to be reported in depth and are rarely analyzed. In this research, we extracted and undertook an additional analysis of the efforts or actions practiced at the sharp end to make things go right (Good Jobs) from safety reports describing events where an accident or a disaster had been successfully avoided or overcome. Specifically, we analyzed the Voluntary Information Contributory to Enhancement of the Safety (VOICES), which is one of the safety reports widely used in the field of Japanese aviation and is open to the public. In this paper, the discussions are focused on the practical analysis of the extracted Good Jobs so that they could be evaluated in depth.

View PDFchevron_right
Sentence Classification and Information Retrieval for Petroleum Engineering
Ismael Santos

Anais do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), 2020

Classifying sentences in industrial, technical or scientific reports can enhance text mining and information retrieval tasks with useful machinereadable metadata. This paper describes a search engine that employs sentence classification so as to search for abstracts from scholarly papers in Petroleum Engineering. The sentences were classified into four classes, based on the popular IMRAD categories. We produced a dataset containing more than 2,200 manually labeled sentences from 278 scholarly articles in the field of Petroleum Engineering in order to be used as training and testing data. The classifier with best results was logistic regression, with an accuracy of 86.4%. The information retrieval system built on top of the classification system yielded a mAP of 0.80.

View PDFchevron_right
RECKONition: a NLP-based system for Industrial Accidents at Work Prevention (Discussion Paper)
Emilia Lenzi

SEBD, 2021

Extracting patterns and useful information from Natural Language datasets is a challenging task, especially when dealing with data written in a language different from English, like Italian. Machine and Deep Learning, together with Natural Language Processing (NLP) techniques have widely spread and improved lately, providing a plethora of useful methods to address both Supervised and Unsupervised problems on textual information. We propose RECKONition, a NLP-based system for Industrial Accidents at Work Prevention. RECKONition, which is meant to provide Natural Language Understanding, Clustering and Inference, is the result of a joint partnership with the Italian National Institute for Insurance against Accidents at Work (INAIL). The obtained results showed the ability to process textual data written in Italian describing industrial accidents dynamics and consequences.

View PDFchevron_right
A Natural Language Processing method for the identification of the factors influencing road accident severity
Dario Valcamonico

2021

Although road safety has improved in the last decades, the rate of accidents with severe and fatal consequences is still exceeding the safety objectives (European Commission 2019; World Health Organization 2018).This work explores the possibility of using Natural Language Processing (NLP) techniques for the automatic extraction of knowledge from road accidents reports, with the objective of supporting the safety management of the road infrastructure system (Persia et al. 2016).To this aim, we consider databases of textual reports on road accidents, provided by the local public authorities. These reports contain the descriptions of the accidents and the results of the post-accident investigations. The aim is to analyze the reports by NLP to extract the features that most influence the accidents, for informing road safety management.For the analysis of the reports, we develop a method that combines Hierarchical Dirichlet Processes (HDPs) (Teh et al. 2006), Artificial Neural Networks (...

View PDFchevron_right
An NLP Approach to a Specific Type of Texts: Car Accident reports
Françoise Gayral

Arxiv preprint cmp-lg/9502032, 1995

Abstract: The work reported here is the result of a study done within a larger project on the``Semantics of Natural Languages''viewed from the field of Artificial Intelligence and Computational Linguistics. In this project, we have chosen a corpus of insurance claim reports. These texts deal with a relatively circumscribed domain, that of road traffic, thereby limiting the extra-linguistic knowledge necessary to understand them. Moreover, these texts present a number of very specific characteristics, insofar as they are written in a quasi- ...

View PDFchevron_right
RECKONition: a NLP-based system for Industrial Accidents at Work Prevention
Silvia Ansaldi

2021

Extracting patterns and useful information from Natural Language datasets is a challenging task, especially when dealing with data written in a language different from English, like Italian. Machine and Deep Learning, together with Natural Language Processing (NLP) techniques have widely spread and improved lately, providing a plethora of useful methods to address both Supervised and Unsupervised problems on textual information. We propose RECKONition, a NLP-based system for Industrial Accidents at Work Prevention. RECKONition, which is meant to provide Natural Language Understanding, Clustering and Inference, is the result of a joint partnership with the Italian National Institute for Insurance against Accidents at Work (INAIL). The obtained results showed the ability to process textual data written in Italian describing industrial accidents dynamics and consequences.

View PDFchevron_right
Industrial information extraction through multi-phase classification using ontology for unstructured documents
Sudha Selvaraj

Comput. Ind., 2018

The increased availability of unstructured text documents in industries such as e-mails, office documents, PDF files etc., has inspired many researchers towards Information Extraction. The objective of the proposal is to extract information from unstructured tender documents of power plant industries. The extraction efficiency of recent works depends on the linguistic structure and keyword taxonomy. Hence, these approaches are unsuitable for domain specific applications that demand semantic and contextual taxonomy together. In this paper, a two-phase classification approach for information extraction with feature weighing is proposed. The proposal performs sentence classification in first phase followed by word classification. As industries spans across multiple domains, a multi domain layered industrial ontology is used for knowledge representation. The unstructured documents are enhanced into DAG based semi-structured text with enriched features. A unique feature transformation ap...

View PDFchevron_right
A computer leaning approach to obtain safety information from multi-lingual accident reports
Rawia El Rashidy

Safety and Reliability – Safe Societies in a Changing World, 2018

Accident reports provide a valuable source of data for any safety management system. In multilingual jurisdictions, accident reports can be provided in more than one language. For example the Swiss transport authority collects accident reports that are written in either German, French, or Italian. The unstructured nature of free-text makes it difficult to extract information from large numbers of accident reports. Machine-reading of text is an emerging area of research, however there are few instances of information being extracted from text in more than one language. This paper introduces an ontology-based interactive learning method between a human and computer software to identify safety-related information by analysing text written in three different languages. The results of the method were analysed by fluent speakers of each language, who rated the overall accuracy of the method to be 98.5%. The method stores and processes the data in a NoSQL graph database, which provides a powerful tool to readily integrate the analysis with other data sources, for example train movement data, passenger census data, or even comparative data from other railways.

View PDFchevron_right
Understanding Construction Site Safety Hazards Through Open Data: Text Mining Approach
Heshani Rupasinghe

ASEAN Engineering Journal, 2021

Construction is an industry well known for its very high rate of injuries and accidents around the world. Even though many researchers are engaged in analysing the risks of this industry using various techniques, construction accidents still require much attention in safety science. According to existing literature, it has been found that hazards related to workers, technology, natural factors, surrounding activities and organisational factors are primary causes of accidents. Yet, there has been limited research aimed to ascertain the extent of these hazards based on the actual reported accidents. Therefore, the study presented in this paper was conducted with the purpose of devising an approach to extract sources of hazards from publicly available injury reports by using Text Mining (TM) and Natural Language Processing (NLP) techniques. This paper presents a methodology to develop a rule-based extraction tool by providing full details of lexicon building, devising extraction rules ...

View PDFchevron_right
Framework for the Optimisation of Full Text Queries on Safety Incident Reports
Matthew Newall

2020

The Railway Industry in Great Britain is on the brink of a seed change in the methods used to carry out safety and risk management. Advances in technology over the past few decades have enabled the collection of varied and detailed information regarding the state of track, vehicles, stations, facilities, and personnel at an ever-increasing scale. As more and more industry processes embrace data driven techniques, the growing volume of data being recorded poses a significant challenge in terms of processing and knowledge extraction.

View PDFchevron_right

References (16)

  1. Lewis, D.D.: Naive (Bayes) at forty: The independence assumption in information retrieval. ECML-98, 10th European Conference on Machine Learning, Chemnitz, DE (1998)
  2. Vapnik, V.: The nature of statistical learning theory. Springer Verlag (1995)
  3. Deerwester, S., Dumais, S., Furnas, G.W., Landauer, T.K., Harshman, R.: Index- ing by Latent Semantic Analysis. Journal of the Society for Information Science (1990) 41 (1990) 391-407
  4. Sebastiani, F.: Machine learning in automated text categorization. ACM Com- puting Surveys (CSUR) 34 (2002) 1 -47
  5. Bloehdorn, S., Hotho,A.: Text Classification by Boosting Weak Learners based on Terms and Concepts. 4th IEEE International Conference on Data Mining (ICDM'04) (2004)
  6. Nagarajan, M., Sheth, A.P., Aguilera, M., Keeton, K., Merchant, A., Uysal, M.: Altering Document Term Vectors for Classification -Ontologies as Expectations of Co-occurrence. LSDIS Technical Report (November, 2006)
  7. Fang, J., Guo, L., Wang, X., Yang, N.: Ontology-Based Automatic Classifica- tion and Ranking for Web Documents. Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007). 627-631 (2007).
  8. Camous, F., Blott, S., Smeaton, A.: Ontology-based MEDLINE document classi- fication. Bioinformatics Research and Development. Lecture Notes in Computer Science Volume 4414, 439-452 (2007).
  9. Gabrilovich, E., Markovitch, S.: Overcomingthe Brittleness Bottleneck using Wikipedia: Enhancing Text Categorization with Encyclopedic Knowledge. 21th National Conference on Artificial Intelligence, Boston, MA, USA (2006)
  10. Wu, S.-H., Tsai, T.-H., Hsu, W.-L.: Text categorization using automatically ac- quired domain ontology. 6th international workshop on Information retrieval with Asian languages -Volume 11, Sapporo, Japan (2003)
  11. Sheth, A.P., Bertram, C., Avant, D., Hammond, B., Kochut, K.J., Warke, Y.: Se- mantic Content Management for Enterprises and the Web. IEEE Internet Com- puting July/August 2002 (2002)
  12. Hammond, B., Sheth, A.P., Kochut, K.J.: Semantic Enhancement Engine: A Mod- ular Document Enhancement Platform for Semantic Applications over Heteroge- neous Content. Real World Semantic Web Applications, IOS Press, 2002 (2002)
  13. Gruber, T.: A Translation Approach to Portable Ontology Specifications. Knowl- edge Acquisition 5 (1993) 199-220, 1993
  14. Sheth, A.P., Arpinar, I.B., Kashyap, V.: Relationships at the Heart of Semantic Web: Modeling, Discovering, and Exploiting Complex Semantic Relationships. In: Nikravesh, M., Azvin, B., Yager, R., Zadeh, L. (eds.): Enhancing the Power of the Internet: Studies in Fuzziness and Soft Computing. Springer Verlag (2003)
  15. Gospodnetic, O.; Hatcher, E., McCandless M.: Lucene in Action (2nd ed.). Man- ning Publications. ISBN 1-9339-8817-7 (2009).
  16. DicSin: Dicionário de Sinônimos Português Brasil. Apache OpenOffice.org http://extensions.openoffice.org/en/project/DicSin-Brasil (2013)

Related papers

Information Extraction Techniques for Health, Safety and Environment Applications in Oil Industry
Cristina Garcia, Nayat Sanchez-Pi, Ana Cristina Bicharra García

The accident investigation process in oil industry is a critical activity. In accident investigation, the volume of information collected and analyzed, makes analysis of its causes a challenging task. Making sense of its large volume of information is also a challenging task because of the diverse interpretations made by experts and auditors. With the advances of new technologies, data of these systems have become increasingly huge. The main objective is to propose and evaluate information extraction techniques in occupational health control process, particularly, for automatic detection of accidents from unstructured texts. Our proposal divides the problem in subtasks such as text analysis, recognition and classification of failed occupational health control, resolving accidents.

View PDFchevron_right
Ontology-based Heuristic Algorithm for Text Classification in Oil Industry Application
Nayat Sanchez-Pi

Today, with the advances of new technologies, accidents, incidents and occupational health records are stored in diverse repositories. The amount of information of HSE that is daily generated has become increasingly huge. Most of this information is stored as unstructured data. The challenge of unstructured data is a top priority for industries that are looking for ways to search, sort, analyze and extract knowledge from masses of data. In this paper we provide with a solution to oil and gas industry for accident investigation using information extraction techniques. The main objective is to propose and evaluate information extraction techniques in occupational health control process, particularly, for automatic detection of accidents from unstructured texts. Our proposal divides the problem in subtasks such as text analysis, recognition and classification of failed occupational health control, resolving accidents.

View PDFchevron_right
Industrial Accident Report Analysis Using Natural Language Processing
Dr. Praveen Sankarasubramanian

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH, 2020

Industrial safety stays basic worry in many nations. Industrial accidents cause human suffering as well as result in immense money related misfortune and ecological effects. To counteract these accidents in the future, the examination of the risk control plan is basic. In every industry, casualty and accident reports could be accessible for past accidents. This-design research paper‖ proposes the Accident reports mining using NLP.

View PDFchevron_right
Potential Threat Detection from Industrial Accident Reports Using Text Mining
Arnab Mondal

Intelligent Computing and Communication, 2020

Analysis of industrial incident reports may aid in identifying potential danger and means to avoid them. We aim to automate the potential threat detection process as much as possible using text mining techniques such as multiclass classification and information extraction. While most of the related works concentrate mostly on either the cause of the incident or its effect and consider only a limited number of possible categories, we aim to predict both hazardous elements and accidents while not considering any fixed number of classes. Further, we also predict the potential target and the potential threat the incident poses. Keywords Industrial accidents • Text mining • Support vector machines • Information extraction 1 Introduction Accident refers to an unfortunate incident that occurs unexpectedly and unintentionally, typically resulting in damage or an injury. With advancements in technologies and increasing socio-technical interaction in the workplace, the number of incidents

View PDFchevron_right
Improving ontology-based text classification: An occupational health and security application
Nayat Sanchez-Pi

Journal of Applied Logic, 2015

Information retrieval has been widely study due to the growing amounts of textual information available electronically. Nowadays organizations and industries are facing the challenge of organizing, analyzing and extract knowledge from masses of unstructured information for decision making process. The development of automatic methods to produce usable structured information from unstructured text sources is extremely valuable to them. Opposed to the traditional text classification methods that needs a set of well-classified trained corpus to perform efficient classification; the ontology-based classifier benefits from the domain knowledge and provides more accuracy. In a previous work we proposed and evaluated an ontology-based heuristic algorithm [1] for occupational health control process, particularly, for the case of automatic detection of accidents from unstructured texts. Our extended proposal is more domain dependent because it use techniques terms and contrast the relevance of these techniques terms into the text, so the heuristic is more accurate. It divides the problem in subtasks such as: (i) text analysis, (ii) recognition and (iii) classification of failed occupational health control, resolving accidents as text analysis, recognition and classification of failed occupational health control, resolving accidents.

View PDFchevron_right

Cited by

Classification and pattern extraction of incidents: a deep learning-based approach
Sobhan Sarkar, Ph.D.

Neural Computing and Applications, 2022

Classifying or predicting occupational incidents using both structured and unstructured (text) data are an unexplored area of research. Unstructured texts, i.e., incident narratives are often unutilized or underutilized. Besides the explicit information, there exist a large amount of hidden information present in a dataset, which cannot be explored by the traditional machine learning (ML) algorithms. There is a scarcity of studies that reveal the use of deep neural networks (DNNs) in the domain of incident prediction, and its parameter optimization for achieving better prediction power. To address these issues, initially, key terms are extracted from the unstructured texts using LDA-based topic modeling. Then, these key terms are added with the predictor categories to form the feature vector, which is further processed for noise reduction and fed to the adaptive moment estimation (ADAM)-based DNN (i.e., ADNN) for classification, as ADAM is superior to GD, SGD, and RMSProp. To evalua...

View PDFchevron_right
Knowledge-Infused Text Classification for the Biomedical Domain
Sonika Malik

International Journal of Information System Modeling and Design

Extracting knowledge from unstructured text and then classifying it is gaining importance after the data explosion on the web. The traditional text classification approaches are becoming ubiquitous, but the hybrid of semantic knowledge representation with statistical techniques can be more promising. The developed method attempts to fabricate neural networks to expedite and improve the simulation of ontology-based classification. This paper weighs upon the accurate results between the ontology-based text classification and traditional classification based on the artificial neural network (ANN) using distinguished parameters such as accuracy, precision, etc. The experimental analysis shows that the proposed findings are substantially better than the conventional text classification, taking the course of action into account. The authors also ran tests to compare the results of the proposed research model with one of the latest researches, resulting in a cut above accuracy and F1 score...

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved