The objective is to also provide an unambiguous and semi-formal knowledge representation with the help of conceptual diagrams such as class diagrams. While the report is the rst step towards providing a more general framework to support railway decision-mak ers to assess and understand AI usability, it is not in the scope of this specic deliverable to report the state-of-the-art of AI in railways since that will be addressed in the continuation of the project and in particular in deliverable D1.2. GA 881782 Page 9 79.
Prolog Programming For Artificial Intelligence 4Th Edition Download Citation CopyRonghui Liu University of Leeds Zhiyuan Lin University of Leeds Show all 10 authors Hide Download full-text PDF Read full-text Download full-text PDF Read full-text Download citation Copy link Link copied Read full-text Download citation Copy link Link copied References (275) Figures (10) Abstract and Figures This deliverable is the output of RAILS Work Package 1 Task 1.1.As such, it provides a.The deliverable aims at providing a taxonomic overview of relevant AI concepts to support decisions about which AI techniques would be most appropriate in order to tackle the challenges associated to modern smart-railways.
In addition, several advanced AI concepts such as trustworthy AI and AI ethics are introduced; the European directives and resolutions are considered in taking into account the ethical dimension of AI when investigating AI for railway systems. The taxonomy is the first step towards providing a general framework to support railway decision-makers to assess and understand the usability of AI-based approaches and to support industry stakeholders to promptly determine promising AI solutions to solve certain railway problems. The objective of this deliverable is to contribute in bridging the gap between AI and railway-domain experts in terms of basic concepts and terminology. An ML Class Diagram (extract from Figure 4.1) Scheme for Tabular datasets Timeline defined by the EC for AI infrastructure development. Figures - uploaded by Francesco Flammini Author content All figure content in this area was uploaded by Francesco Flammini Content may be subject to copyright. Prolog Programming For Artificial Intelligence 4Th Edition Free Public FullDiscover the worlds research 20 million members 135 million publications 700k research projects Join for free Public Full-text 1 Content uploaded by Francesco Flammini Author content All content in this area was uploaded by Francesco Flammini on Sep 01, 2020 Content may be subject to copyright. Disclaimer The information and views set out in this document are those of the author(s) and do not necessarily reect the ofcial opinion of Shift2Rail Joint Undertaking. The JU does not guarantee the accuracy of the data included in this document. Neither the JU nor any person acting on the JUs behalf ma y be held responsible for the use which ma y be made of the information contained therein. Guidelines and regulations on AI 35 5.1 The European Viewpoint 35 5.2 General Data Protection Regulation 36 5.3 Ethics guidelines for trustworthy AI 38 5.4 A European strategy for data 40 5.5 A European approach to excellence and trust 40 5.6 Safety and liability implications of AI 42 5.7 Explainable AI 43 6. Mapping of Articial Intelligence on Railway Subdomains 45 6.1 Railway subdomains 45 6.2 Mapping results 47 6.2.1 Existing intersections (Y) 48 6.2.2 Potential intersections (P) 53 6.2.3 Uncertain insersections (U) 54 7. Articial Intelligence in related domains 55 7.1 AI in manufacturing 55 7.2 AI in supply chain management and logistics 55 7.3 AI in aviation 56 7.4 AI in road transport 57 7.5 AI in public transport 58 8. The deliverable aims at pro viding a taxonomical overview of relev ant AI concepts to support decisions about which AI techniques would be most appropriate in order to tackle the challenges associated to modern smar t-railways. In addition, several advanced AI concepts such as trustworthy AI and AI ethics are introduced; the European directives and resolu- tions are considered in taking into account the ethical dimension of AI when investigating AI for railwa y systems. The taxonomy is the rst step towards providing a general framew ork to support railway decision-makers to assess and understand the usability of AI-based approaches and to support industr y stakeholders to promptly determine promising AI solutions to solve certain railway problems. The objective of this deliv erable is to contribute in bridging the gap between AI and railway-domain e xperts in terms of basic concepts and terminology. ![]() Relevant applications of AI from other high-tech sectors are also considered but they are just an input f or a deeper investigation that will be conducted in Work Pac kages 2,3, and 4 as part of transferabiliy analysis. The project is in the framework of Shift2Rail s Innovation Programme IPX. As such, RAILS does not focus on a specic domain, nor does directly contribute to specic T echnical Demonstrators but contributes to Disruptive Innov ation and Explorator y Research in the eld of Articial Intelligence within the Shift2Rail Innovation Programme. Deliverable D 1.1 describes the work carried out in T ask 1.1 of Work Pac kage 1 whose objectives are: Dene a taxonomy of AI to enable its application in railwa y transpor t; Determine the state-of-the-ar t of AI techniques in railway tr ansport; Determine the state-of-the-ar t of AI application in Shift2Rail projects; Identify application areas of AI in railways. Work Pac kage 1 identies essential conditions: it provides specic needs, investigates capabilities and gaps; it surveys techniques and methods for picking the right AI technology able to solve open prob lems or improve perf or mance in railway scenarios. A taxonomy of suitable AI techniques to be adopted f or railways (this Deliv erable); ii. A map of the current state-of-the-art of AI aplication in railway research, including Shift2Rail projects and other relevant projects (Deliv erable D 1.2); iii. A set of current and potential application areas (Deliverable D 1.3). GA 881782 Page 8 79. Relevant applications of AI from other high-tech sectors are considered, but a deeper investigation will be conducted in W ork Packages 2,3, and 4 as part of transferabiliy analysis. The deliverable provides an extensiv e descr iption of concepts and denitions that are relevant in the AI and r ailway domain and are essential f or a deeper understanding of the interconnections between all those concepts. The objective is to also provide an unambiguous and semi-formal knowledge representation with the help of conceptual diagrams such as class diagrams. While the report is the rst step towards providing a more general framework to support railway decision-mak ers to assess and understand AI usability, it is not in the scope of this specic deliverable to report the state-of-the-art of AI in railways since that will be addressed in the continuation of the project and in particular in deliverable D1.2. GA 881782 Page 9 79.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |