Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 45) Show all publications
Cumbane, S. P., Yang, C. & Gidofalvi, G. (2019). A Framework for Traffic Prediction Integrated with Deep Learning. In: : . Paper presented at The 8th Symposium of the European Association for Research in Transportation.
Open this publication in new window or tab >>A Framework for Traffic Prediction Integrated with Deep Learning
2019 (English)Conference paper, Published paper (Refereed)
Abstract [en]

City-scale traffic prediction is an important task for public safety, traffic management, and deployment of intelligent transportation systems. Many approaches have been proposed to address traffic prediction task using machine learning techniques. In this paper, we present a framework to help on addressing the task at hand (density-, traffic flow- and origin-destination flow predictions) considering data type, features, deep learning techniques such as Convolutional Neural Networks (CNNs), e.g., Autoencoder, Recurrent Neural Networks (RNNs), e.g., Long Short Term Memory (LSTM), and Graph Convolutional Networks (GCNs). An autoencoder model is designed in this paper to predict traffic density based on historical data. Experiments on real-world taxi order data demonstrate the effectiveness of the model.

National Category
Natural Sciences
Identifiers
urn:nbn:se:kth:diva-254200 (URN)
Conference
The 8th Symposium of the European Association for Research in Transportation
Note

QC 20190625

Available from: 2019-06-24 Created: 2019-06-24 Last updated: 2019-06-25Bibliographically approved
Palmberg, R., Susilo, Y. & Gidofalvi, G. (2019). Developing and trialling an implicit interaction platform to monitor and aiding dementia travellers. In: : . Paper presented at Mobile Apps and Sensors in Surveys (MASS) Workshop, 4-5 March, Mannheim, Germany.
Open this publication in new window or tab >>Developing and trialling an implicit interaction platform to monitor and aiding dementia travellers
2019 (English)Conference paper, Oral presentation with published abstract (Other academic)
Abstract [en]

Age related cognitive diseases are becoming a growing problem in Sweden. With the fast ageing population and lowered mortality rate comes the spread of cognitive diseases related to dementia. In order to accommodate this growing target group in transport and the built environment, it is important to understand the mobility and travel behaviour of patients suffering from these diseases. One subset of this target group is travellers suffering from age induced illnesses related with dementia, which most often have fluctuating symptoms that are affecting the cognitive skills of the traveller. This makes it hard to use standardized forms and survey-based information that would require the traveller to actively respond retroactively, either in oral or written form, since the traveller might have forgotten or mixed up their past experiences, among other things, it becomes very hard to gain confidence in the results as it might be hard to tell in which condition the patient is during the collection.

We propose an automated collection of biometric data such as heart rate in combination with position. Since the validity of the information collected in this manner is directly related to the quality of the sensors used it means that the precision and accuracy of the results could be virtually endlessly improved by upgrading the hardware and optimizing the software. To take a first step towards a solution like this we have started developing a smart watch application which is utilizing PPG technology to collect heart rate and combine it with positions collected through GPS technology.

Early testing has shown the possibility to correlate the heart rate of a traveller to their specific location. The implications of this must be validated through data labelling as we wish to utilize machine learning algorithms to analyse the data collected.

Keywords
Ageing society, Built environment, Position data, Biometric data, Automated data collection, Implicit interaction
National Category
Human Computer Interaction Interaction Technologies Transport Systems and Logistics Social Sciences Interdisciplinary
Research subject
Transport Science; Transport Science
Identifiers
urn:nbn:se:kth:diva-254187 (URN)
Conference
Mobile Apps and Sensors in Surveys (MASS) Workshop, 4-5 March, Mannheim, Germany
Note

QC 20190823

Available from: 2019-06-21 Created: 2019-06-21 Last updated: 2019-08-23Bibliographically approved
Cumbane, S. P. & Gidofalvi, G. (2019). Review of Big Data and Processing Frameworks for Disaster Response Applications. ISPRS International Journal of Geo-Information, 8(9), Article ID 387.
Open this publication in new window or tab >>Review of Big Data and Processing Frameworks for Disaster Response Applications
2019 (English)In: ISPRS International Journal of Geo-Information, ISSN 2220-9964, Vol. 8, no 9, article id 387Article in journal (Refereed) Published
Abstract [en]

Natural hazards result in devastating losses in human life, environmental assets and personal, and regional and national economies. The availability of different big data such as satellite imageries, Global Positioning System (GPS) traces, mobile Call Detail Records (CDRs), social media posts, etc., in conjunction with advances in data analytic techniques (e.g., data mining and big data processing, machine learning and deep learning) can facilitate the extraction of geospatial information that is critical for rapid and effective disaster response. However, disaster response systems development usually requires the integration of data from different sources (streaming data sources and data sources at rest) with different characteristics and types, which consequently have different processing needs. Deciding which processing framework to use for a specific big data to perform a given task is usually a challenge for researchers from the disaster management field. Therefore, this paper contributes in four aspects. Firstly, potential big data sources are described and characterized. Secondly, the big data processing frameworks are characterized and grouped based on the sources of data they handle. Then, a short description of each big data processing framework is provided and a comparison of processing frameworks in each group is carried out considering the main aspects such as computing cluster architecture, data flow, data processing model, fault-tolerance, scalability, latency, back-pressure mechanism, programming languages, and support for machine learning libraries, which are related to specific processing needs. Finally, a link between big data and processing frameworks is established, based on the processing provisioning for essential tasks in the response phase of disaster management.

Keywords
big data; processing frameworks; disaster response
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:kth:diva-257858 (URN)10.3390/ijgi8090387 (DOI)000488826400047 ()2-s2.0-85072551156 (Scopus ID)
Note

QC 20190906. QC 20191028

Available from: 2019-09-05 Created: 2019-09-05 Last updated: 2019-10-28Bibliographically approved
Palmberg, R., Susilo, Y. & Gidofalvi, G. (2019). Uncovering Effects of Spatial and Transportation Elements on Travellers Using Biometric Data. In: Tuuli Toivonen, Karst Geurs, Elias Willberg (Ed.), TOWARDS HUMAN SCALE CITIES - OPEN AND HAPPY: . Paper presented at 15th biennial NECTAR conference University of Helsinki, Finland 5-7 June 2019. Helsinki: Department of Geosciences and Geography, University of Helsinki
Open this publication in new window or tab >>Uncovering Effects of Spatial and Transportation Elements on Travellers Using Biometric Data
2019 (English)In: TOWARDS HUMAN SCALE CITIES - OPEN AND HAPPY / [ed] Tuuli Toivonen, Karst Geurs, Elias Willberg, Helsinki: Department of Geosciences and Geography, University of Helsinki , 2019Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Travel surveys has been used for decades to observe the patterns, locations, and choices, which travellers chose and do during the given observed period. This information can be utilized as background for informed planning decisions. Despite the progress in the travel survey technologies, the applications mostly focus on more traditional travel parameters. With programmable smart watches now, we can also collect real time data that is not solely pertaining to position and travel mode choices, but also to users’ biometric data. Such an application would open another level of possibilities in dynamically integrating land use and transport planning with public health research.

Utilising a smart watch platform, we are aiming to develop a tool that will collect biometric data, in combination with spatial context, such as position, spatial features and objects in the built environment, and by utilizing machine learning algorithms, try to detect how travellers are affected by their choice of transport mode, the built environment in general as well as how the public transport is operated.

Early testing reveals the possibility to find correlations between heart rate and position, which in turn could reveal the effect of spatial and transportation elements on the traveller. By targeting widely available hardware, the scalability for this tool is virtually endless, making it possible to collect large amounts of data and utilizing machine learning algorithms to analyse it.

Place, publisher, year, edition, pages
Helsinki: Department of Geosciences and Geography, University of Helsinki, 2019
Keywords
Automated data collection, Biometric data, Built environment, Implicit interaction, Position data
National Category
Transport Systems and Logistics Interaction Technologies Social Sciences Interdisciplinary Human Computer Interaction
Research subject
Transport Science
Identifiers
urn:nbn:se:kth:diva-254183 (URN)978-951-51-4922-0 (ISBN)978-951-51-4921-3 (ISBN)
Conference
15th biennial NECTAR conference University of Helsinki, Finland 5-7 June 2019
Note

QC 20190823

Available from: 2019-06-21 Created: 2019-06-21 Last updated: 2019-08-23Bibliographically approved
Prelipcean, A. C., Susilo, Y. & Gidofalvi, G. (2018). Collecting travel diaries: Current state of the art, best practices, and future research directions. In: Transport Survey Methods in the era of big data: facing the challenges. Paper presented at 2017 ISCTC 11th International Conference on Transport Survey Methods, L'Esterel Resort39 Chemin Fridolin-SimardEsterel, Canada, 24 September 2017 through 29 September 2017 (pp. 155-166). Elsevier, 32
Open this publication in new window or tab >>Collecting travel diaries: Current state of the art, best practices, and future research directions
2018 (English)In: Transport Survey Methods in the era of big data: facing the challenges, Elsevier, 2018, Vol. 32, p. 155-166Conference paper, Published paper (Refereed)
Abstract [en]

The amount of useful information that can be extracted from travel diaries is matched by the difficulty of obtaining travel diaries in a modern era where the response rate to traditional travel diary collection methods has seen a decrease in most countries. Prompted by this, a body of research has been dedicated to study how travel diaries can be collected via new methods, namely location enabled devices such as smartphones, that have a higher penetration rate (in terms of device ownerships and user attachment) and are both easier and cheaper to manage compared to traditional data collection method, e.g. paper-and-pencil, phone, or web-based questionnaires. This paper offers an overview of the current state of travel diary collection, a potential future state and a practical checklist for travel diary collection case studies. A thorough discussion on different pros and cons of travel diary collection methods and efforts needed for the convergence of methods to collect travel diaries for all demographics are provided. The practical checklist to aid researchers to organise case studies is based on the authors' experience and it is meant to raise awareness of difficulties that can be encountered while collecting travel surveys with automated and semi-automated systems, and how to overcome them.

Place, publisher, year, edition, pages
Elsevier, 2018
Series
Transportation Research Procedia, ISSN 2352-1457 ; 32
Keywords
best practices, destination, purpose inferences, travel diary collection systems, travel mode
National Category
Transport Systems and Logistics
Identifiers
urn:nbn:se:kth:diva-241861 (URN)10.1016/j.trpro.2018.10.029 (DOI)000471307900017 ()2-s2.0-85058853296 (Scopus ID)
Conference
2017 ISCTC 11th International Conference on Transport Survey Methods, L'Esterel Resort39 Chemin Fridolin-SimardEsterel, Canada, 24 September 2017 through 29 September 2017
Note

QC 20190125

Available from: 2019-01-25 Created: 2019-01-25 Last updated: 2019-07-24Bibliographically approved
Palmberg, R., Gidofalvi, G. & Susilo, Y. (2018). Enabling Technologies to Serve the Ageing Urban Society Better (ENTRUST). In: : . Paper presented at Ny teknik i äldreomsorgen 24 maj 2018 Stockholm. Kungliga Tekniska högskolan
Open this publication in new window or tab >>Enabling Technologies to Serve the Ageing Urban Society Better (ENTRUST)
2018 (English)Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

The life span of the inhabitants of Sweden is increasing and with this comes age related cognitive diseases such as those related to dementia. Our society is not prepared to accommodate for the needs of the people who are affected by this.

The diseases related to dementia often affect the person’s ability to localize themselves and to remember previous and upcoming events. A common issue that occurs is a state called “elopement”.

Place, publisher, year, edition, pages
Kungliga Tekniska högskolan, 2018
National Category
Transport Systems and Logistics Interaction Technologies Human Computer Interaction
Research subject
Transport Science
Identifiers
urn:nbn:se:kth:diva-254185 (URN)
Conference
Ny teknik i äldreomsorgen 24 maj 2018 Stockholm
Note

QC 20190823

Available from: 2019-06-21 Created: 2019-06-21 Last updated: 2020-01-13Bibliographically approved
Prelipcean, A. C., Susilo, Y. O. & Gidofalvi, G. (2018). Future directions of research for automatic travel diary collection. In: Proceedings of the 11th International conference on Transport Survey Methods: . Paper presented at 11th International conference on Transport Survey Methods.
Open this publication in new window or tab >>Future directions of research for automatic travel diary collection
2018 (English)In: Proceedings of the 11th International conference on Transport Survey Methods, 2018Conference paper, Published paper (Refereed)
Abstract [en]

The amount of useful information that can be extracted from travel diaries is matched by the difficulty of obtaining travel diariesin a modern era where the response rate to traditional travel diary collection methods has seen a decrease in most countries.Prompted by this, a body of research has been dedicated to study how travel diaries can be collected via new methods, namelylocation enabled devices such as smartphones, that have a higher penetration rate (in terms of device ownerships and userattachment) and are both easier and cheaper to manage compared to traditional data collection method, e.g. paper-and-pencil,phone, or web-based questionnaires. This paper offers an overview of the current state of travel diary collection, a potentialfuture state and a practical checklist for travel diary collection case studies. A thorough discussion on different pros and cons oftravel diary collection methods and efforts needed for the convergence of methods to collect travel diaries for all demographicsare provided. The practical checklist to aid researchers to organise case studies is based on the authors’ experience and it is meantto raise awareness of difficulties that can be encountered while collecting travel surveys with automated and semi-automatedsystems, and how to overcome them.

Keywords
travel diary collection systems, travel mode destination and purpose inferences, best practices
National Category
Transport Systems and Logistics
Research subject
Transport Science
Identifiers
urn:nbn:se:kth:diva-227256 (URN)
Conference
11th International conference on Transport Survey Methods
Note

QC 20180508

Available from: 2018-05-04 Created: 2018-05-04 Last updated: 2018-05-08Bibliographically approved
Prelipcean, A. C., Gidofalvi, G. & Susilo, Y. (2018). MEILI: A travel diary collection, annotation and automation system. Computers, Environment and Urban Systems, 70(July 2018), 24-34
Open this publication in new window or tab >>MEILI: A travel diary collection, annotation and automation system
2018 (English)In: Computers, Environment and Urban Systems, ISSN 0198-9715, E-ISSN 1873-7587, Vol. 70, no July 2018, p. 24-34Article in journal (Refereed) Published
Abstract [en]

The increased interest in the automation of travel diary collection, together with the ease of access to new artificial intelligence methods led scientists to explore the prerequisites to the automatic generation of travel diaries. One of the most promising methods for this automation relies on collecting GPS traces of multiple users over a period of time, followed by asking the users to annotate their collected data by specifying the base entities for a travel diary, i.e., trips and triplegs. This led scientist on one of two paths: either develop an in-house solution for data collection and annotation, which is usually an undocumented prototype implementation limited to few users, or contract an external provider for the development, which results in additional costs. This paper provides a third path: an open-source highly modular system for the collection and annotation of travel diaries of multiple users, named MEILI. The paper discusses the architecture of MEILI with an emphasis on the data model, which allows scientists to implement and evaluate their methods of choice for the detection of the following entities: trip start/end, trip destination, trip purpose, tripleg start/end, and tripleg mode. Furthermore, the open source nature of MEILI allows scientists to modify the MEILI solution in compliance with their legal and ethical specifications. MEILI was successfully trialed in multiple case studies in Stockholm and Gothenburg, Sweden between 2014 and 2017.

Keywords
Travel diaries, Destinations purpose and travel mode inferences, Travel diary collection system, Open source, System design and architecture
National Category
Transport Systems and Logistics
Research subject
Transport Science; Geodesy and Geoinformatics; Computer Science
Identifiers
urn:nbn:se:kth:diva-227250 (URN)10.1016/j.compenvurbsys.2018.01.011 (DOI)000436887900003 ()2-s2.0-85041358233 (Scopus ID)
Funder
Swedish Transport Administration, TRV 2014/10422
Note

QC 20180605

Available from: 2018-05-04 Created: 2018-05-04 Last updated: 2018-07-18Bibliographically approved
Prelipcean, A. C., Susilo, Y. O. & Gidofalvi, G. (2017). A series of three case studies on the semi-automation of activity travel diary generation using smarpthones. In: Proceedings of TRB 2017 Annual Meeting: . Paper presented at Transportation Research Board 2017.
Open this publication in new window or tab >>A series of three case studies on the semi-automation of activity travel diary generation using smarpthones
2017 (English)In: Proceedings of TRB 2017 Annual Meeting, 2017Conference paper, Published paper (Refereed)
Abstract [en]

The growing need of acquiring data that is useful for travel behaviour analysis led scientists topursue new ways of obtaining travel diaries from large groups of people. The most promising al-ternative to traditional (declarative) travel diary collection methods are those that rely on collectingtrajectories from individuals and then extract travel diary semantics from the trajectories. However,most studies report on routines specific to the post-processing of data, and seldom focus on datacollection. Even the few studies that deal explicitly with data collection describe the final state ofthe collection system, but do not go at the lengths that are required to describe the decision thatwere taken to bring the system to its current state. This leads to a considerable amount of work thatis needed for designing collection systems that are often undocumented, which impedes the reuseof the aforementioned systems. In light of the aforementioned problems, this paper presents a series of three case studies behind the continuous development of MEILI, a travel diary collection,annotation and automation system, in an effort to: 1) illustrate the utility of the developed systemto collect travel diaries, 2) identify how MEILI and other semi-automatic travel diaries collectionsystems can be improved, and 3) propose MEILI as an open source system that has the potentialof being improved into a widely available semi-automated travel diary collection system.

Keywords
Travel Diary Collection, Case Studies, MEILI
National Category
Transport Systems and Logistics
Research subject
Transport Science; Transport Science
Identifiers
urn:nbn:se:kth:diva-227251 (URN)
Conference
Transportation Research Board 2017
Note

QC 201880508

Available from: 2018-05-04 Created: 2018-05-04 Last updated: 2018-05-08Bibliographically approved
Prelipcean, A. C., Gidofalvi, G. & Susilo, Y. O. (2016). Measures of transport mode segmentation of trajectories. International Journal of Geographical Information Science, 30(9), 1763-1784
Open this publication in new window or tab >>Measures of transport mode segmentation of trajectories
2016 (English)In: International Journal of Geographical Information Science, ISSN 1365-8816, E-ISSN 1365-8824, Vol. 30, no 9, p. 1763-1784Article in journal (Refereed) Published
Abstract [en]

Rooted in the philosophy of point- and segment-based approaches for transportation mode segmentation of trajectories, the measures that researchers have adopted to evaluate the quality of the results (1) are incomparable across approaches, hence slowing the progress in the field and (2) do not provide insight about the quality of the continuous transportation mode segmentation. To address these problems, this paper proposes new error measures that can be applied to measure how well a continuous transportation mode segmentation model performs. The error measures introduced are based on aligning multiple inferred continuous intervals to ground truth intervals, and measure the cardinality of the alignment and the spatial and temporal discrepancy between the corresponding aligned segments. The utility of this new way of computing errors is shown by evaluating the segmentation of three generic transportation mode segmentation approaches (implicit, explicit–holistic, and explicit–consensus-based transport mode segmentation), which can be implemented in a thick client architecture. Empirical evaluations on a large real-word data set reveal the superiority of explicit–consensus-based transport mode segmentation, which can be attributed to the explicit modeling of segments and transitions, which allows for a meaningful decomposition of the complex learning task.

Place, publisher, year, edition, pages
Taylor & Francis Group, 2016
Keywords
Continuous model evaluation, transportation mode segmentation and detection, trajectory data mining, error analysis, interval algebra
National Category
Transport Systems and Logistics Computer Sciences Other Mathematics
Research subject
Geodesy and Geoinformatics; Transport Science
Identifiers
urn:nbn:se:kth:diva-184485 (URN)10.1080/13658816.2015.1137297 (DOI)000378064300005 ()2-s2.0-84958541974 (Scopus ID)
Note

QC 20160509

Available from: 2016-03-31 Created: 2016-03-31 Last updated: 2018-05-07Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-1164-8403

Search in DiVA

Show all publications