Anytime mining of sequential discriminative patterns in labeled sequences

Mathonat, Romain; Nurbakova, Diana; Boulicaut, Jean-François; Kaytoue, Mehdi

doi:10.1007/s10115-020-01523-7

Cited by 5 publications

(4 citation statements)

References 41 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the performance of the proposed SLGMF algorithm, the experiment selects two POI recommendation algorithms that integrate social relationships and geographic factors: MGMPFM [3] and LORE [5]. In addition, to examine the impact of different factors on POI recommendation, this paper splits the SLGMF algorithm into a recommendation algorithm S-MF that only integrates social relationships, and a recommendation algorithm LG-MF that only integrates local geographic factors, and compares it by itself.…”

Section: Comparison Methods and Parameter Settingmentioning

confidence: 99%

“…In order to prevent inaccuracies brought on by the uniform distribution of all users and to construct a model for the influence of geographic factors, Helu et al [4] employed kernel density estimation to mimic the distance distribution between any two POIs. In order to combine sequence influence, social influence, and geographic factor influence into a single recommendation framework, Mathonat et al [5] mine sequence patterns from the position sequence. Yali et al, [6] proposed a personalized point-of-interest recommendation model based on collaborative filtering based on friends, comprehensively considering social relationships and geographic location characteristics.…”

Section: Basic Theorymentioning

confidence: 99%

See 1 more Smart Citation

Point-of-Interest (POI) Recommendation Model Simulation using Social Relationships and Geographical Factors

Chakraborty¹

2022

JSER

View full text Add to dashboard Cite

This research suggests a point-of-interest recommendation model that incorporates social interactions and some geographical parameters in order to address the issue of data sparsity in Point-of-Interest (POI) recommendation. The model first suggested a user similarity measurement method based on the shared sign-in and distance between users in the social relationship, and based on the collaborative filtering of users, it was possible to determine the degree to which the social relationship influenced the user's sign-in behavior. Second, divide the local activity area for each user, fully evaluate the check-in correlation between the nearby POIs that haven't been visited, and determine the extent to which the user's check-in behavior is influenced by the surrounding geography. Finally, a POI recommendation model that is more in line with the user's preference is constructed, which effectively solves the problem of data sparsity. It is based on the weighted matrix decomposition, the user's preference model and combined with the social relationship and local geographic factors considered above. Experiments on the Gowalla dataset show that the proposed SLGMF algorithm has good recommendation performance.

show abstract

Section: Comparison Methods and Parameter Settingmentioning

confidence: 99%

Section: Basic Theorymentioning

confidence: 99%

Point-of-Interest (POI) Recommendation Model Simulation using Social Relationships and Geographical Factors

Chakraborty¹

2022

JSER

View full text Add to dashboard Cite

show abstract

“…Their work combines EMM with sequential pattern mining, the task to identify frequent subsequences, and as such they develop a search strategy based on GP-growth (Lemmerich et al 2012) and PrefixSpan (Pei et al 2004). Mathonat et al (2021) also combine sequential pattern mining with EMM, developing the MCTSExtent method building on Monte Carlo Tree Search (MCTS) (Bosc et al 2018). Both MCTSExtent and SEPP consider the data to be in the traditional sequential pattern mining form where X t is an itemset.…”

Section: Markov Chainsmentioning

confidence: 99%

Reactive Water Sorbents for the Sorption-Enhanced Reverse Water–Gas Shift

Pieterse¹,

Elzinga²,

Booneveld³

et al. 2021

Catal Lett

View full text Add to dashboard Cite

published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User

show abstract

Section: Markov Chainsmentioning

confidence: 99%

Mining sequences with exceptional transition behaviour of varying order using quality measures based on information-theoretic scoring functions

Schouten

Bueno

Duivesteijn

et al. 2021

Data Min Knowl Disc

View full text Add to dashboard Cite

Discrete Markov chains are frequently used to analyse transition behaviour in sequential data. Here, the transition probabilities can be estimated using varying order Markov chains, where order k specifies the length of the sequence history that is used to model these probabilities. Generally, such a model is fitted to the entire dataset, but in practice it is likely that some heterogeneity in the data exists and that some sequences would be better modelled with alternative parameter values, or with a Markov chain of a different order. We use the framework of Exceptional Model Mining (EMM) to discover these exceptionally behaving sequences. In particular, we propose an EMM model class that allows for discovering subgroups with transition behaviour of varying order. To that end, we propose three new quality measures based on information-theoretic scoring functions. Our findings from controlled experiments show that all three quality measures find exceptional transition behaviour of varying order and are reasonably sensitive. The quality measure based on Akaike’s Information Criterion is most robust for the number of observations. We furthermore add to existing work by seeking for subgroups of sequences, as opposite to subgroups of transitions. Since we use sequence-level descriptive attributes, we form subgroups of entire sequences, which is practically relevant in situations where you want to identify the originators of exceptional sequences, such as patients. We show this relevance by analysing sequences of blood glucose values of adult persons with diabetes type 2. In the experiments, we find subgroups of patients based on age and glycated haemoglobin (HbA1c), a measure known to correlate with average blood glucose values. Clinicians and domain experts confirmed the transition behaviour as estimated by the fitted Markov chain models.

show abstract

Anytime mining of sequential discriminative patterns in labeled sequences

Cited by 5 publications

References 41 publications

Point-of-Interest (POI) Recommendation Model Simulation using Social Relationships and Geographical Factors

Point-of-Interest (POI) Recommendation Model Simulation using Social Relationships and Geographical Factors

Reactive Water Sorbents for the Sorption-Enhanced Reverse Water–Gas Shift

Mining sequences with exceptional transition behaviour of varying order using quality measures based on information-theoretic scoring functions

Contact Info

Product

Resources

About