MPE: a mobility pattern embedding model for predicting next locations

Chen, Meng; Yu, Xiaohui; Liu, Yang

doi:10.1007/s11280-018-0616-8

Cited by 24 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we aim to integrate our TTDM with more location prediction models, e.g., the mobility pattern embedding model [9], the recurrent neural network based model [14]. Further, we plan to apply the joint model on more types of traffic data (e.g., Uber ride data, and Didi trajectory data).…”

Section: Discussionmentioning

confidence: 99%

“…Zhao et al [22] adopt the framework of word2vec by treating each user as a "document", checkins in a day as a "sentence", and each POI as a "word", and proposed a Geo-Temporal sequential embedding rank (Geo-Teaser) model for POI recommendation. Chen et al [9] focused on the traffic trajectory data and proposed a Mobility Pattern Embedding (MPE) method to embed the time slots, current locations and next locations together as points in a latent space, and predicted the next locations based on the embedding vectors.…”

Section: B Prediction With Deep Learning Modelsmentioning

confidence: 99%

See 1 more Smart Citation

TTDM: A Travel Time Difference Model for Next Location Prediction

Liu

Zuo

et al. 2019

2019 20th IEEE International Conference on Mobile Data Management (MDM)

Self Cite

View full text Add to dashboard Cite

Next location prediction is of great importance for many location-based applications and provides essential intelligence to business and governments. In existing studies, a common approach to next location prediction is to learn the sequential transitions with massive historical trajectories based on conditional probability. Unfortunately, due to the time and space complexity, these methods (e.g., Markov models) only use the just passed locations to predict next locations, without considering all the passed locations in the trajectory. In this paper, we seek to enhance the prediction performance by considering the travel time from all the passed locations in the query trajectory to a candidate next location. In particular, we propose a novel method, called Travel Time Difference Model (TTDM), which exploits the difference between the shortest travel time and the actual travel time to predict next locations. Further, we integrate the TTDM with a Markov model via a linear interpolation to yield a joint model, which computes the probability of reaching each possible next location and returns the top-rankings as results. We have conducted extensive experiments on two real datasets: the vehicle passage record (VPR) data and the taxi trajectory data. The experimental results demonstrate significant improvements in prediction accuracy over existing solutions. For example, compared with the Markov model, the top-1 accuracy improves by 40% on the VPR data and by 15.6% on the Taxi data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: B Prediction With Deep Learning Modelsmentioning

confidence: 99%

TTDM: A Travel Time Difference Model for Next Location Prediction

Liu

Zuo

et al. 2019

2019 20th IEEE International Conference on Mobile Data Management (MDM)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to retrieve the most befitting ingredients, we propose an embeddingbased ingredient predictor (IP-embedding), in which the ingredients are projected into a latent space and the ones that usually occur in a recipe are close to each other. Inspired by the recent progress of deep learning and neural networks [24,25,26], we propose to use a distributed representation method to model the amountof CandidateIngredients = AmountPredictor(prSet) 5: bestIngredient = FindBestIngredientToAdd(candidateIngredients, 6: amountof CandidateIngredients) 7: prSet += bestIngredient 8: end for 9: pseudoRecipe = CreateRecipeFromSet(prSet) 10: l = FindSimilarRecipes(pseudoRecipe, cos, k) 11: return l generation of the given recipe. Given a recipe r : {i 1 , i 2 , · · · , i Nr } containing N r ingredients, the objective function is to maximize the probability of each target ingredient i a given its corresponding context information:…”

Section: Model Descriptionmentioning

confidence: 99%

Eating healthier: Exploring nutrition information for healthier recipe recommendation

Chen

Jia

Gorbonos

et al. 2020

Information Processing & Management

Self Cite

View full text Add to dashboard Cite

With the booming of personalized recipe sharing networks (e.g., Yummly), a deluge of recipes from different cuisines could be obtained easily. In this paper, we aim to solve a problem which many home-cooks encounter when searching for recipes online. Namely, finding recipes which best fit a handy set of ingredients while at the same time follow healthy eating guidelines. This task is especially difficult since the lions share of online recipes have been shown to be unhealthy.In this paper we propose a novel framework named NutRec, which models the interactions between ingredients and their proportions within recipes for the purpose of offering healthy recommendation. Specifically, NutRec consists of three main components: 1) using an embedding-based ingredient predictor to predict the relevant ingredients with user-defined initial ingredients, 2) predicting the amounts of the relevant ingredients with a multi-layer perceptronbased network, 3) creating a healthy pseudo-recipe with a list of ingredients and their amounts according to the nutritional information and recommending the top similar recipes with the pseudo-recipe. We conduct the experiments on two recipe datasets, including Allrecipes with 36,429 recipes and Yummly with 89,413 recipes, respectively. The empirical results support the framework's * This is to indicate the corresponding authors.intuition and showcase its ability to retrieve healthier recipes.

show abstract

“…Representation learning for trajectory data [14][15][16][23][24][25][26][27] has attracted the attention of researchers and has become an emerging topic. Li et al, proposed t2vec [14], which learns embedding vectors for trajectories based on the recurrent neural network-based denoising autoencoder through a reconstruction process of raw and disrupted trajectories.…”

Section: Trajectory Representation Learningmentioning

confidence: 99%

Multi-Aspect Embedding for Attribute-Aware Trajectories

Boonchoo

2019

Symmetry

View full text Add to dashboard Cite

Motivated by the proliferation of trajectory data produced by advanced GPS-enabled devices, trajectory is gaining in complexity and beginning to embroil additional attributes beyond simply the coordinates. As a consequence, this creates the potential to define the similarity between two attribute-aware trajectories. However, most existing trajectory similarity approaches focus only on location based proximities and fail to capture the semantic similarities encompassed by these additional asymmetric attributes (aspects) of trajectories. In this paper, we propose multi-aspect embedding for attribute-aware trajectories (MAEAT), a representation learning approach for trajectories that simultaneously models the similarities according to their multiple aspects. MAEAT is built upon a sentence embedding algorithm and directly learns whole trajectory embedding via predicting the context aspect tokens when given a trajectory. Two kinds of token generation methods are proposed to extract multiple aspects from the raw trajectories, and a regularization is devised to control the importance among aspects. Extensive experiments on the benchmark and real-world datasets show the effectiveness and efficiency of the proposed MAEAT compared to the state-of-the-art and baseline methods. The results of MAEAT can well support representative downstream trajectory mining and management tasks, and the algorithm outperforms other compared methods in execution time by at least two orders of magnitude.

show abstract

MPE: a mobility pattern embedding model for predicting next locations

Cited by 24 publications

References 29 publications

TTDM: A Travel Time Difference Model for Next Location Prediction

TTDM: A Travel Time Difference Model for Next Location Prediction

Eating healthier: Exploring nutrition information for healthier recipe recommendation

Multi-Aspect Embedding for Attribute-Aware Trajectories

Contact Info

Product

Resources

About