Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357210
Marit Hoff-Hoffmeyer-Zlotnik, Tobias Sprodowski, M. Freitag
With rising transshipment volumes, new challenges arise for vehicle transshipment compounds: They have to facilitate the complex logistics processes of intermodal transports of vehicles on their compounds with ever shorter loading and unloading times of ships and trains in order to satisfy external stake holders. In addition, customised services for vehicles offered by the compound operator cause inter-terminal transport (ITT). All transports of vehicles have to be carried out by human workers who drive the vehicles from one location to the next. Usually, the drivers are transported across the compound by shuttles and therefore grouped together in teams. Accordingly, the drivers are modelled in cohorts but not individually. In this paper, we set up a model with a control algorithm that handles each driver individually. New orders are assigned to each driver based on their current location. By doing so, we allow for the possibility to individually assign orders that are within walking distance so that shuttle rides and associated waiting times can be avoided. Shuttles are still available for longer distances. We state the problem as an assignment problem to find the time-minimising combination of drivers, shuttles and orders. The proposed control algorithm includes the actual states of drivers, shuttles and available orders as a feedback control. It is carried out in a rolling planning horizon manner to periodically obtain a new solution based on the actual state of the compound. We verify the proposed control algorithm and conduct simulations with two variants of the algorithm which differ in terms of shuttle routing. The results show that the proposed model and control algorithm are suitable to simulate order assignments in a real-case vehicle compound scenario. Moreover, including the possibility to reach orders by walking offers large potential for the productivity on vehicle compounds.
{"title":"Revisiting order assignment problems in a real-case vehicle compound scenario","authors":"Marit Hoff-Hoffmeyer-Zlotnik, Tobias Sprodowski, M. Freitag","doi":"10.1109/CiSt49399.2021.9357210","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357210","url":null,"abstract":"With rising transshipment volumes, new challenges arise for vehicle transshipment compounds: They have to facilitate the complex logistics processes of intermodal transports of vehicles on their compounds with ever shorter loading and unloading times of ships and trains in order to satisfy external stake holders. In addition, customised services for vehicles offered by the compound operator cause inter-terminal transport (ITT). All transports of vehicles have to be carried out by human workers who drive the vehicles from one location to the next. Usually, the drivers are transported across the compound by shuttles and therefore grouped together in teams. Accordingly, the drivers are modelled in cohorts but not individually. In this paper, we set up a model with a control algorithm that handles each driver individually. New orders are assigned to each driver based on their current location. By doing so, we allow for the possibility to individually assign orders that are within walking distance so that shuttle rides and associated waiting times can be avoided. Shuttles are still available for longer distances. We state the problem as an assignment problem to find the time-minimising combination of drivers, shuttles and orders. The proposed control algorithm includes the actual states of drivers, shuttles and available orders as a feedback control. It is carried out in a rolling planning horizon manner to periodically obtain a new solution based on the actual state of the compound. We verify the proposed control algorithm and conduct simulations with two variants of the algorithm which differ in terms of shuttle routing. The results show that the proposed model and control algorithm are suitable to simulate order assignments in a real-case vehicle compound scenario. Moreover, including the possibility to reach orders by walking offers large potential for the productivity on vehicle compounds.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124575916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357252
Khadija Ouazzani Touhami, N. Souissi
In recent years, special and growing importance has been given to data on road traffic accidents and their victims. Road safety generally concerns several actors from different sectors, legal, health, insurance, transport and equipment. National and international statistical studies, based on data from road accidents and their victims, are carried out jointly and regularly, which makes it possible to assess and monitor this scourge with dramatic consequences. However, outside the statistics, can we understand what seems random? Moreover, to what extent can the monitoring and balances established help to understand the evolutions even to make forecasts using structural models? To answer these questions, we have developed a life cycle of a simulation project that describes the process to follow in order to carry out a predictive analysis. This paper presents a simulation case study allowing the estimation of some indicators on traffic accidents and their victims in Morocco for the coming decade.
{"title":"Simulation Project Life Cycle Applied to Road Safety: A Case Study of Morocco","authors":"Khadija Ouazzani Touhami, N. Souissi","doi":"10.1109/CiSt49399.2021.9357252","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357252","url":null,"abstract":"In recent years, special and growing importance has been given to data on road traffic accidents and their victims. Road safety generally concerns several actors from different sectors, legal, health, insurance, transport and equipment. National and international statistical studies, based on data from road accidents and their victims, are carried out jointly and regularly, which makes it possible to assess and monitor this scourge with dramatic consequences. However, outside the statistics, can we understand what seems random? Moreover, to what extent can the monitoring and balances established help to understand the evolutions even to make forecasts using structural models? To answer these questions, we have developed a life cycle of a simulation project that describes the process to follow in order to carry out a predictive analysis. This paper presents a simulation case study allowing the estimation of some indicators on traffic accidents and their victims in Morocco for the coming decade.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121676653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Commerce was an important literary review founded in Paris by Princess Margherita Caetani, Prince Roffredo Cae-tani's wife. Born in America, she was polyglot and maecenas. Between 1924 and 1932 she surrounded herself with three prestigious collaborators: Paul Valéry, Léon-Paul Fargue, Valéry Larbaud. The review promoted the translation of World and European literature in French, translating some of the most important authors like Joyce, T.S. Eliot, Pirandello, Ungaretti, Saint-John Perse, Rilke, Hofmannsthal. The aim of this project is to promote by digitizing the dissemination of the review, to develop studies and research concerning the Caetani family's cultural activities in Europe. All the volumes of the literary review Commerce have been scanned, acquired by OCR and encoded in TEI-XML. The cultural value of the operation is discussed and the work-flow to create the digital textual corpus is described in detail.
{"title":"Digitizing and Encoding a Multilingual Literary Review: Commerce Numérique","authors":"Antonietta Sanna, Rachele Cinerari, Federico Boschetti, Ouafae Nahli","doi":"10.1109/CiSt49399.2021.9357208","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357208","url":null,"abstract":"Commerce was an important literary review founded in Paris by Princess Margherita Caetani, Prince Roffredo Cae-tani's wife. Born in America, she was polyglot and maecenas. Between 1924 and 1932 she surrounded herself with three prestigious collaborators: Paul Valéry, Léon-Paul Fargue, Valéry Larbaud. The review promoted the translation of World and European literature in French, translating some of the most important authors like Joyce, T.S. Eliot, Pirandello, Ungaretti, Saint-John Perse, Rilke, Hofmannsthal. The aim of this project is to promote by digitizing the dissemination of the review, to develop studies and research concerning the Caetani family's cultural activities in Europe. All the volumes of the literary review Commerce have been scanned, acquired by OCR and encoded in TEI-XML. The cultural value of the operation is discussed and the work-flow to create the digital textual corpus is described in detail.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124148933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357314
F. Zaoui, N. Souissi
The Covid-19 pandemic crisis has made companies consider alternatives to the usual operating methods in order to ensure the continuity of their employees work and the offer of products and services to their customers. The current economic situation has therefore anchored the positioning of digital transformation as a lever for economic revival and evolution, and has reminded companies of the need to conduct this transformation in order to remain competitive. This paper is part of this debate and is in line with previous work on digital transformation frameworks. It develops the digital reflection from a strategic and above all multidimensional perspective. By adopting this vision, and starting from a global digital-oriented business strategy, it is proposed to decline it into business strategies through a digital roadmap. The article also proposes a framework of digital transformation based on these strategic guidelines and making all the dimensions that must be involved in a transformative process interact with each other.
{"title":"A Framework For A Strategic Digital Transformation","authors":"F. Zaoui, N. Souissi","doi":"10.1109/CiSt49399.2021.9357314","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357314","url":null,"abstract":"The Covid-19 pandemic crisis has made companies consider alternatives to the usual operating methods in order to ensure the continuity of their employees work and the offer of products and services to their customers. The current economic situation has therefore anchored the positioning of digital transformation as a lever for economic revival and evolution, and has reminded companies of the need to conduct this transformation in order to remain competitive. This paper is part of this debate and is in line with previous work on digital transformation frameworks. It develops the digital reflection from a strategic and above all multidimensional perspective. By adopting this vision, and starting from a global digital-oriented business strategy, it is proposed to decline it into business strategies through a digital roadmap. The article also proposes a framework of digital transformation based on these strategic guidelines and making all the dimensions that must be involved in a transformative process interact with each other.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115308943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357318
A. Ghani, Ahmed Zinedine, M. E. Mohajir
The appearance of Covid-19 proves the deficiency of world health care systems to handle exponentially infected-patients and to deal with lack of personal health records (PHR). As it is known, data is valuable in such situation. Current solutions for storing and sharing PHR data adopt centralized solutions, such as cloud-based totally centralized data centers, which requires a fully-trusted third party. Therefore, it suffers from single point of failure, data deleting and network delay. To overcome these issues, we propose in this paper a Blockchain-based secure PHR data storage and sharing framework that leverages the benefits of IPFS (Inter Planetary File System). Our aim is to ensure privacy with patient full control over his data and to enhance scalability. To this end, we use steganography to hide sensitive data within PHR data, and then it is uploaded to IPFS network. However, IPFS Hash delivered by IPFS network is divided into n secret shares using Shamir's Secret Sharing (SSS) algorithm, which ensures security. Moreover, Ethereum smart contract automates the execution of access control strategies defined by the owner, as well as, traceability and auditability insurance.
{"title":"A Blockchain-based secure PHR data storage and sharing framework","authors":"A. Ghani, Ahmed Zinedine, M. E. Mohajir","doi":"10.1109/CiSt49399.2021.9357318","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357318","url":null,"abstract":"The appearance of Covid-19 proves the deficiency of world health care systems to handle exponentially infected-patients and to deal with lack of personal health records (PHR). As it is known, data is valuable in such situation. Current solutions for storing and sharing PHR data adopt centralized solutions, such as cloud-based totally centralized data centers, which requires a fully-trusted third party. Therefore, it suffers from single point of failure, data deleting and network delay. To overcome these issues, we propose in this paper a Blockchain-based secure PHR data storage and sharing framework that leverages the benefits of IPFS (Inter Planetary File System). Our aim is to ensure privacy with patient full control over his data and to enhance scalability. To this end, we use steganography to hide sensitive data within PHR data, and then it is uploaded to IPFS network. However, IPFS Hash delivered by IPFS network is divided into n secret shares using Shamir's Secret Sharing (SSS) algorithm, which ensures security. Moreover, Ethereum smart contract automates the execution of access control strategies defined by the owner, as well as, traceability and auditability insurance.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"29 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131604012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357251
M. Othman, N. Ahmad, Hanita Bunjari, Salmiah Ramli
The public sector is moving towards the digital government to serve the citizens better. This digital transformation will allow the citizens to enjoy a seamless, connected and efficient service. Therefore, a Government Enterprise Architecture practice is initiated to achieve the ultimate goal of the digital government. However, the Enterprise Architecture (EA) benefits are not being realized in the public sector organization resulting in the challenging and slow adoption of EA. The purpose of this paper is to examine the problems that impede the adoption of the EA and to identify its influence factors. The results of the case study found that the issues and factors of adoption of EA in the Accountant General's Department are derived from the technological, organizational, environmental and organizational pressure dimensions. The EA adoption discussed in this paper will be a valuable guideline for EA initiator in public sector organizations.
{"title":"Exploring Enterprise Architecture Adoption in Public Sector Organization: A Case Study of Accountant General's Department of Malaysia","authors":"M. Othman, N. Ahmad, Hanita Bunjari, Salmiah Ramli","doi":"10.1109/CiSt49399.2021.9357251","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357251","url":null,"abstract":"The public sector is moving towards the digital government to serve the citizens better. This digital transformation will allow the citizens to enjoy a seamless, connected and efficient service. Therefore, a Government Enterprise Architecture practice is initiated to achieve the ultimate goal of the digital government. However, the Enterprise Architecture (EA) benefits are not being realized in the public sector organization resulting in the challenging and slow adoption of EA. The purpose of this paper is to examine the problems that impede the adoption of the EA and to identify its influence factors. The results of the case study found that the issues and factors of adoption of EA in the Accountant General's Department are derived from the technological, organizational, environmental and organizational pressure dimensions. The EA adoption discussed in this paper will be a valuable guideline for EA initiator in public sector organizations.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127047415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357202
R. Gratta, Federico Boschetti, Luigi Bambaci, F. Sarnari
We introduce a formal approach to document and text analysis. The method proposed herein results in a mathematical and physical model/framework which can formalize different challenges in research fields such as computational linguistics, digital philology, and software engineering, principally if applied to document and text analysis. We examine texts and documents from an evolutionary perspective, where both corruption and correction are involved. We describe document evolution via fiber bundles formalism.
{"title":"Approaching document analysis with a formal model","authors":"R. Gratta, Federico Boschetti, Luigi Bambaci, F. Sarnari","doi":"10.1109/CiSt49399.2021.9357202","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357202","url":null,"abstract":"We introduce a formal approach to document and text analysis. The method proposed herein results in a mathematical and physical model/framework which can formalize different challenges in research fields such as computational linguistics, digital philology, and software engineering, principally if applied to document and text analysis. We examine texts and documents from an evolutionary perspective, where both corruption and correction are involved. We describe document evolution via fiber bundles formalism.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126873790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357283
Sascha Kaven, Lorenz Bornholdt, V. Skwarek
Location as part of the node's identity can make an essential contribution to the prevention of Sybil- and man-in-the-middle-attacks to verify the authenticity of nodes. This requires point-to-point communication between several end-devices which is not possible in LoRaWAN due to the stars-of-stars topology. This research paper provides an approach to overcome this problem by introducing an additional LoRa-mesh phase for LoRaWAN. This makes it possible to confirm the position of a LoRa end-device by RSSI-based localization.
{"title":"Authentication by RSSI-Position Based Localization in a LoRa LPWAN","authors":"Sascha Kaven, Lorenz Bornholdt, V. Skwarek","doi":"10.1109/CiSt49399.2021.9357283","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357283","url":null,"abstract":"Location as part of the node's identity can make an essential contribution to the prevention of Sybil- and man-in-the-middle-attacks to verify the authenticity of nodes. This requires point-to-point communication between several end-devices which is not possible in LoRaWAN due to the stars-of-stars topology. This research paper provides an approach to overcome this problem by introducing an additional LoRa-mesh phase for LoRaWAN. This makes it possible to confirm the position of a LoRa end-device by RSSI-based localization.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123729098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357237
Sandhya Harikumar, Viveka Mannam, C. Mahanta, M. Smitha, Shazia Zaman
This project aims to build a smart map, named VAWMap (Violence Against Women Map), that displays the intensity of various crimes against women across the states and districts of India in efforts to inspire action to combat this prevalent violence. The data set to be depicted on the map consists of the number of victims of rape, dowry deaths, kidnapping, cruelty by husbands, insult to modesty, and assault for each district of every state in India through the years between 2001–2013. Depicted states and their respective districts include Rajasthan, Punjab, and Haryana. Two algorithms, QR Decomposition with Column Pivoting and the Projected Clustering Algorithm, are leveraged to reveal prominent crimes and their locations-effectively yielding certain hot spot crime areas of North India. Two novel strategies to depict the intricate statistics obtained from these ML algorithms are proposed using a map-making platform, Mapbox. The result is two maps of India that display the intensity of the most prevalent crimes through a color gradient. The effectiveness, in terms of data reduction and visualization, between the two algorithms are compared and discussed.
{"title":"Interactive Map Using Data Visualization and Machine Learning","authors":"Sandhya Harikumar, Viveka Mannam, C. Mahanta, M. Smitha, Shazia Zaman","doi":"10.1109/CiSt49399.2021.9357237","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357237","url":null,"abstract":"This project aims to build a smart map, named VAWMap (Violence Against Women Map), that displays the intensity of various crimes against women across the states and districts of India in efforts to inspire action to combat this prevalent violence. The data set to be depicted on the map consists of the number of victims of rape, dowry deaths, kidnapping, cruelty by husbands, insult to modesty, and assault for each district of every state in India through the years between 2001–2013. Depicted states and their respective districts include Rajasthan, Punjab, and Haryana. Two algorithms, QR Decomposition with Column Pivoting and the Projected Clustering Algorithm, are leveraged to reveal prominent crimes and their locations-effectively yielding certain hot spot crime areas of North India. Two novel strategies to depict the intricate statistics obtained from these ML algorithms are proposed using a map-making platform, Mapbox. The result is two maps of India that display the intensity of the most prevalent crimes through a color gradient. The effectiveness, in terms of data reduction and visualization, between the two algorithms are compared and discussed.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128110181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-05DOI: 10.1109/CiSt49399.2021.9357263
Matthias Bay, Daniel Bruneß, Miriam Herold, Christian Schulze, Michael Guckert, Mirjam Minor
In this paper we present a new method for the extraction of discipline-specific terms from medical documents. Due to the small text corpora and the specific nature of medical documents, there are limitations for approaches that are solely based on term frequencies. A combination of such methods with procedures that are sensitive to semantic aspects is therefore promising. We use word embeddings in a neighborhood context based method which we call Snowball because of its layerwise way of working. Snowball is integrated together with established methods into an end to end pipeline with which we can process documents to extract relevant terms. Proof of concept is given on a gold standard created recently together with experts in medical coding. The preliminary results highlight the feasibility of our approach and its potential for automated, machine learning based text processing in the medical context.
{"title":"Term Extraction from Medical Documents Using Word Embeddings","authors":"Matthias Bay, Daniel Bruneß, Miriam Herold, Christian Schulze, Michael Guckert, Mirjam Minor","doi":"10.1109/CiSt49399.2021.9357263","DOIUrl":"https://doi.org/10.1109/CiSt49399.2021.9357263","url":null,"abstract":"In this paper we present a new method for the extraction of discipline-specific terms from medical documents. Due to the small text corpora and the specific nature of medical documents, there are limitations for approaches that are solely based on term frequencies. A combination of such methods with procedures that are sensitive to semantic aspects is therefore promising. We use word embeddings in a neighborhood context based method which we call Snowball because of its layerwise way of working. Snowball is integrated together with established methods into an end to end pipeline with which we can process documents to extract relevant terms. Proof of concept is given on a gold standard created recently together with experts in medical coding. The preliminary results highlight the feasibility of our approach and its potential for automated, machine learning based text processing in the medical context.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"25 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124025211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：