CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Creating Knowledge with Data Science for Design in Systems
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH). (Biomedical Engineering and Health Systems)ORCID iD: 0000-0001-5118-4856
2019 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Designing in large-scale engineering systems is a difficult cognitive task undertaken by experts. Knowledge of experts continually changes as they are confronted with similar by different problems in designing in such systems. However, it is also important that designers are presented information that is representative of the system,and that they are cognizant of activities on a system scale so they can create diverse choices for designs in early phase of design process.Data Science has been proven to be effective at informing people for decisions at immediate horizons. But the use of data science to drive long terms designs where experts have to make the right series of decisions i.e. designs is yet unknown. The use of data science is to inform decision makers of activities at system scale.In this thesis, I have looked at how data science can be used to create knowledge in designers for designing in large scale systems. I have also investigated further questions regarding imitation of expertise using AI, and in generating similar knowledge by creating diverse options in design.The results point out that data science can indeed inform designers, change their designs and hence create knowledge. They also point out that design cognition in experts can be partly imitated in data science itself, through careful modeling of the ill-defined problem in design. This therefore points to a promising future direction where data can be used as an interface between human thinking and machine learning, by translation of conceptual forms such as differential diagnoses and cognitive artefacts using data.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2019. , p. 33
Series
TRITA-CBH-FOU ; 46
Keywords [en]
Data Science, Design Cognition, Transport, Healthcare, Artificial Intelligence, Imitation, Design Space Exploration
National Category
Computer Systems Health Sciences Transport Systems and Logistics
Research subject
Technology and Health
Identifiers
URN: urn:nbn:se:kth:diva-259566ISBN: 978-91-7873-299-9 (electronic)OAI: oai:DiVA.org:kth-259566DiVA, id: diva2:1352481
Public defence
2019-10-11, T2, Hälsovägen 11, 141 57, Huddinge, 09:30 (English)
Opponent
Supervisors
Note

QC 2019-09-20

Available from: 2019-09-20 Created: 2019-09-18 Last updated: 2019-10-18Bibliographically approved
List of papers
1. A Feasibility Study for Gamification in Transport Maintenance: Requirements to implement gamification in heterogeneous organizations
Open this publication in new window or tab >>A Feasibility Study for Gamification in Transport Maintenance: Requirements to implement gamification in heterogeneous organizations
2015 (English)In: Games and Virtual Worlds for Serious Applications (VS-Games), 2015 7th International Conference on, IEEE conference proceedings, 2015, p. 1-7Conference paper, Published paper (Refereed)
Abstract [en]

Gamification has been successfully applied in many domains, but mostly for simple, isolated and operational tasks. The hope for gamification as a method to radically change and improve behavior, to provide incentives for sustained engagement has proven to be more difficult to get right. Applying gamification in large networked organizations with heterogeneous tasks remains a challenge. Applying gamification in such enterprise environments posits different requirements, and a match between these requirements and the institution needs to be investigated before venturing into the design and implementation of gamification. The current paper contributes a study where the authors investigate the feasibility of implementing gamification in Trafikverket, the Swedish transport administration. Through an investigation of the institutional arrangements around data collection, procurement processes and links to institutional structures, the study finds areas within Trafikverket where gamification could be successfully applied, and suggests gaps and methods to apply gamification in other areas.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2015
Keywords
gamification, feasibility, requirements, data mining, procurement
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-181420 (URN)10.1109/VS-GAMES.2015.7295758 (DOI)000380426500001 ()2-s2.0-84954518787 (Scopus ID)
External cooperation:
Conference
2015 IEEE 7th International Conference on Games and Virtual Worlds for Serious Applications,16-18 Sept. 2015 , Skövde, Sweden
Note

QC 20160215

Available from: 2016-02-02 Created: 2016-02-01 Last updated: 2019-09-18Bibliographically approved
2. Spatial Big Data for designing large scale infrastructure A case-study of Electrical Road Systems
Open this publication in new window or tab >>Spatial Big Data for designing large scale infrastructure A case-study of Electrical Road Systems
2016 (English)In: 2016 3RD IEEE/ACM INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING, APPLICATIONS AND TECHNOLOGIES (BDCAT), IEEE , 2016, p. 143-148Conference paper, Published paper (Refereed)
Abstract [en]

Decision making and planning of large scale infrastructures within cities is often a long process encompassing years, between multiple institutions represented by experts that require negotiations and consensus of demands and goals. The role big data plays in such design could be crucial, by providing access to otherwise elusive information on movements of people and goods in a city which can then transparently inform the design process, especially about possible demands and related complexities on the infrastructure being planned. To harness this data, it is necessary to formulate the problem technically such that data can inform experts, by articulating their expertise through the data. In this paper we present an application to analyze millions of instances of spatial data to identify potential locations for electrical road installation(s) in a city, to aid urban planners and other relevant stakeholders in planning and designing an Electrical Road System for a city. The dataset being used is gathered from a major vehicle manufacturer in Sweden, containing millions of instances of GPS data emitted by thousands of vehicles. A plan for electrified transport system is formulated by retrieving locations suitable for both static and dynamic charging installations. We investigate the technical formulation of methods and metrics for such a complex design problem, based on criteria set by experts, thus contributing to the science of big data for design of infrastructure and to methodology of data science in an institutional context.

Place, publisher, year, edition, pages
IEEE, 2016
Keywords
spatio-temporal data, decision making, infrastructure design, urban planning, big data
National Category
Other Computer and Information Science
Identifiers
urn:nbn:se:kth:diva-214919 (URN)10.1145/3006299.3006334 (DOI)000408919800016 ()2-s2.0-85013218416 (Scopus ID)978-1-4503-4617-7 (ISBN)
Conference
3rd IEEE/ACM International Conference on Big Data Computing Applications and Technologies (BDCAT), DEC 06-09, 2016, Shanghai, PEOPLES R CHINA
Note

QC 20170925

Available from: 2017-09-25 Created: 2017-09-25 Last updated: 2019-09-18Bibliographically approved
3. Analytics on public transport delays with spatial big data
Open this publication in new window or tab >>Analytics on public transport delays with spatial big data
2016 (English)In: Proceedings of the 5th ACM SIGSPATIAL International Workshop on Analytics for Big Geospatial Data, BigSpatial 2016, ACM Digital Library, 2016, p. 28-33Conference paper, Published paper (Refereed)
Abstract [en]

The increasing pervasiveness of location-aware technologies is leading to the rise of large, spatio-temporal datasets and to the opportunity of discovering usable knowledge about the behaviors of people and objects. Applied extensively in transportation, spatial big data and its analytics can deliver useful insights on a number of different issues such as congestion, delays, public transport reliability and so on. Predominantly studied for its use in operational management, spatial big data can be used to provide insight in strategic applications as well, from planning and design to evaluation and management. Such large scale, streaming spatial big data can be used in the improvement of public transport, for example the design of public transport networks and reliability. In this paper, we analyze GTFS data from the cities of Stockholm and Rome to gain insight on the sources and factors influencing public transport delays in the cities. The analysis is performed on a combination of GTFS data with data from other sources. The paper points to key issues in the analysis of real time data, driven by the contextual setting in the two cities. © 2016, Association for Computing Machinery, Inc. All rights reserved.

Place, publisher, year, edition, pages
ACM Digital Library, 2016
Keywords
Big data, Decision making, Public transport, Behavioral research, Gain insight, Location-aware technology, Operational management, Planning and design, Public transport networks, Real-time data, Spatio temporal
National Category
Medical Engineering
Identifiers
urn:nbn:se:kth:diva-202280 (URN)10.1145/3006386.3006387 (DOI)2-s2.0-85005781400 (Scopus ID)9781450345811 (ISBN)
Conference
5th ACM SIGSPATIAL International Workshop on Analytics for Big Geospatial Data, BigSpatial 2016, 31 October 2016
Note

Conference Paper. QC 20170221

Available from: 2017-02-21 Created: 2017-02-21 Last updated: 2019-09-18Bibliographically approved
4. Opening the search space for the design of a future transport system using ‘big data’
Open this publication in new window or tab >>Opening the search space for the design of a future transport system using ‘big data’
2017 (English)In: 15th International Conference on Computers in Urban Planning and Urban Management, 2017, Springer Berlin/Heidelberg, 2017, Vol. Part F4, p. 247-261Conference paper (Refereed)
Abstract [en]

The advent of ‘big data’ already enables a wide range of conveniences to citizens. However, the dominant utilization of this data for systematic improvement is geared towards operations such as informing on real-time events in cities. The impact of big data on the long-term planning and design purposes in cities is still unclear. This chapter presents an application of big data where locations, suitable for deploying charging infrastructure for vehicles, are mined. We conducted an experiment to observe the impact of this information on designs of Electrical Road Systems (ERS). Results prove that insights mined from big data outside the design process do influence the designing process and the resulting designs. Therefore it seems promising to further explore this influence on the quality of designing.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2017
Keywords
Big data, Design process, Transport system
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:kth:diva-214645 (URN)10.1007/978-3-319-57819-4_14 (DOI)2-s2.0-85028673684 (Scopus ID)9783319578187 (ISBN)
Conference
15th International Conference on Computers in Urban Planning and Urban Management, 2017, Adelaide, Australia, 11 July 2017 through 14 July 2017
Note

QC 20170919

Available from: 2017-09-19 Created: 2017-09-19 Last updated: 2019-09-18Bibliographically approved
5. Aiding Remote Diagnosis with Text Mining
Open this publication in new window or tab >>Aiding Remote Diagnosis with Text Mining
2018 (English)In: Proceedings of the 31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018, 2018Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Along with the increase of digital healthcare providers, theinterest in diagnostic aids for remote diagnosis has increasedas well. As patients write about their symptoms themselves,we have access to a type of data which previously was rarelyrecorded, and which has not been filtered by a healthcareprofessional. Knowledge of similar patients and similarsymptoms is beneficial for doctors to arrive at a diagnosis.Therefore, the remote diagnostic process could be aided bypresenting patient cases together with information aboutsimilar patients and their self-reported symptom descriptions.Apart from online diagnosis, such an aid could bebeneficial in many healthcare settings, such as long-distancevisits and knowledge gain from patient diaries.In this paper, we present the impact of aiding remote diagnosisby presenting clusters of similar symptoms, usingsymptom descriptions collected from a virtual visit applicationby the Swedish telemedicine provider KRY. Symptomdescriptions were represented using the bag-of-words modeland were then clustered using the k-means algorithm. Anexperiment was then conducted with 13 doctors, where patientcases were presented together with the most representativewords of the associated cluster, to measure howtheir work was impacted. Results indicated that it was usefulin more complicated cases, but also that future experimentswill require further instructions on how the information is tobe interpreted.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-259567 (URN)2-s2.0-85071902648 (Scopus ID)
Conference
The Thirty-First International Florida Artificial Intelligence Research Society Conference (FLAIRS-31)
Note

QC 20190930

Available from: 2019-09-17 Created: 2019-09-17 Last updated: 2019-09-30Bibliographically approved
6. Creating Designs of Future Systems with Interpretation of Cognitive Artifacts in Reinforcement Learning
Open this publication in new window or tab >>Creating Designs of Future Systems with Interpretation of Cognitive Artifacts in Reinforcement Learning
(English)In: Design Science Journal, ISSN 2053-4701Article in journal (Refereed) Submitted
Abstract [en]

Designing future systems such as transport or healthcare in a city takes astute expertise. Design aids in such situations usually offer information in the form of projections or what-if analysis, using which experts make a series of decisions to create bounded designs. We present a case in which Reinforcement Learning (RL) is used to design the future transport system of a city. RL is used to create artifacts that reflect where the transport system can be changed. These agent-produced artifacts are then compared with designs made by human experts. This is achieved by analogizing the city as gridworld and using the same information that the human experts acted on as rewards. The interpretation of agent activity as cognitive artifacts of agents, along with measures of precision and recall to compare real and artificial artifacts form the basis of this work. This paper explores the use of RL in a real world context and the interpretability of results of RL with respect to design problems. The results indicate a robust initial approach to imitating expertise of designers and devising valid creativity in Socio-Technical Systems.

Keywords
Design Science, Mimicking, Creativity, Interpretability, Socio-Technical Systems
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:kth:diva-259568 (URN)
Available from: 2019-09-17 Created: 2019-09-17 Last updated: 2019-09-20
7. Imitating Design Cognition with Reinforcement Learning – Reflecting upon the Epistemology of Data Science
Open this publication in new window or tab >>Imitating Design Cognition with Reinforcement Learning – Reflecting upon the Epistemology of Data Science
(English)In: Minds and Machines, ISSN 0924-6495, E-ISSN 1572-8641Article in journal (Refereed) Submitted
Abstract [en]

The complexity of (re)design of large-scale systems in a metropolitan context is challenging its designers and their design methods. Data science has the potential to influence the designing process, but the question is to what extent and in what way. In this paper, we present an approach with reinforcement learning to imitate design cognition in a use case on Electric Road Systems, by acting on information produced by data science. This takes place in a loose game that is an abstract representation of the real system, thus artificially producing knowledge. We further discuss the episteme of that knowledge produced by the artificial.

National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:kth:diva-259569 (URN)
Available from: 2019-09-17 Created: 2019-09-17 Last updated: 2019-09-20

Open Access in DiVA

Kappa proof(803 kB)61 downloads
File information
File name FULLTEXT03.pdfFile size 803 kBChecksum SHA-512
ab37812267d99405e765d034ce14444ac03b724d2572ab74704715941baacb4c04eb5804140955b7cfd28d2d2f306180a8c5c988c40375c133405b8a847a848e
Type fulltextMimetype application/pdf

Authority records BETA

Shreenath, Vinutha Magal

Search in DiVA

By author/editor
Shreenath, Vinutha Magal
By organisation
School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH)
Computer SystemsHealth SciencesTransport Systems and Logistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 83 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 325 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf