A hierarchical hidden semi-Markov model for modeling mobility data

Baratchi, Mitra; Meratnia, Nirvana; Havinga, Paul J.M.; Skidmore, Andrew K.; Toxopeus, Bert A. K. G.

doi:10.1145/2632048.2636068

Cited by 38 publications

(25 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2015) [10] [11] assumes diverse situations, such as disaster from the perspective of location prediction (Sudo et al 2016) [12]. Markov chainbased approach has been applied on human mobility pattern and achieved remarkable performance on the next location prediction based on human mobility pattern(Baratchi et al 2014) [13]. In the previous period, researchers have applied the data mining, trajectory pattern tree and Markov chain tools mainly.…”

Section: Related Workmentioning

confidence: 99%

Generating Human Mobility Route Based on Generative Adversarial Network

Song

Baek

Sung

2019

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Recently, many researches on human mobility are aiming to suggest the personal customized solution in the diverse field, usually by academia and industry. Combined with deep learning methods, it is able to predict and generate novel routes of objects from the mobility data including the given past trends. In this work, Generative Adversarial Network (GAN) model is introduced for creating individual mobility routes based on sets of accumulated personal mobility data. The mobility data had been collected by use of geopositioning system and personal mobile devices. GAN has Discriminator and Generator which are composed of neural networks, and can train and extract geopositionig information. A sequence of longitude and latitude can be geographically mapped, and matrices including all these information can be handled by GAN. The GAN-based model successfully handled individual mobility routes in this way. Consequently, our model can generate and suggest unexplored routes from the existing sets of personal geolocation data.

show abstract

Section: Related Workmentioning

confidence: 99%

Generating Human Mobility Route Based on Generative Adversarial Network

Song

Baek

Sung

2019

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…Models. Markov models have been widely used to predict individual level mobility patterns [4,36]. An…”

Section: Markovmentioning

confidence: 99%

Creating full individual-level location timelines from sparse social media data

Rehman

Relia

Chunara

2018

Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

In many domain applications, a continuous timeline of human locations is critical; for example for understanding possible locations where a disease may spread, or the flow of traffic. While data sources such as GPS trackers or Call Data Records are temporally-rich, they are expensive, often not publicly available or garnered only in select locations, restricting their wide use. Conversely, geo-located social media data are publicly and freely available, but present challenges especially for full timeline inference due to their sparse nature. We propose a stochastic framework, Intermediate Location Computing (ILC) which uses prior knowledge about human mobility patterns to predict every missing location from an individual's social media timeline. We compare ILC with a state-of-the-art RNN baseline as well as methods that are optimized for next-location prediction only. For three major cities, ILC predicts the top 1 location for all missing locations in a timeline, at 1 and 2-hour resolution, with up to 77.2% accuracy (up to 6% better accuracy than all compared methods). Specifically, ILC also outperforms the RNN in settings of low data; both cases of very small number of users (under 50), as well as settings with more users, but with sparser timelines. In general, the RNN model needs a higher number of users to achieve the same performance as ILC. Overall, this work illustrates the tradeoff between prior knowledge of heuristics and more data, for an important societal problem of filling in entire timelines using freely available, but sparse social media data.

show abstract

“…Baratchi et al and Yu et al proposed extended models of HSMM that can treat missing data. Their proposal can model the sequential data even if they include missing intervals [34,35]. These studies are motivated to complement the missing data so that the 'interval of missing' might have variable status in all sequences.…”

Section: Requirement Verification For Extended Hmm Modelsmentioning

confidence: 99%

State duration and interval modeling in hidden semi-Markov model for sequential data analysis

Narimatsu

Kasai

2017

Ann Math Artif Intell

View full text Add to dashboard Cite

Sequential data modeling and analysis have become indispensable tools for analyzing sequential data such as time-series data because a larger amount of sensed event data have become available. These methods capture the sequential structure of data of interest, such as inputoutput relationship and correlation among datasets. However, since most studies in this area are specialized or limited for their respective applications, rigorous requirement analysis on such a model has not been examined in a general point of view. Hence, we particularly examine the structure of sequential data, and extract the necessity of "state duration" and "state duration" of events for efficient and rich representation of sequential data. Specifically addressing the hidden semi-Markov model (HSMM) that represents such state duration inside a model, we attempt to newly add representational capability of state interval of events onto HSMM. To this end, we propose two extended models; one is interval state hidden semi-Markov model (IS-HSMM) to express the length of state interval with a special state node designated as "interval state node". The other is interval length probability hidden semi-Markov model (ILP-HSMM) which represents the length of state interval with a new probabilistic parameter "interval length probability." From exhaustive simulations, we show superior performances of the proposed models in comparison with HSMM. To the best of our knowledge, our proposed models are the first extensions of HMM to support state interval representation as well as state duration representation.

show abstract

A hierarchical hidden semi-Markov model for modeling mobility data

Cited by 38 publications

References 33 publications

Generating Human Mobility Route Based on Generative Adversarial Network

Generating Human Mobility Route Based on Generative Adversarial Network

Creating full individual-level location timelines from sparse social media data

State duration and interval modeling in hidden semi-Markov model for sequential data analysis

Contact Info

Product

Resources

About