Modeling POI-Specific Spatial-Temporal Context for Point-of-Interest Recommendation
Ontology highlight
ABSTRACT:
SUBMITTER: Lauw H
PROVIDER: S-EPMC7206255 | biostudies-literature | 2020 Apr
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:With the popularity of Location-based Social Networks, Point-of-Interest (POI) recommendation has become an important task, which learns the users’ preferences and mobility patterns to recommend POIs. Previous studies show that incorporating contextual information such as geographical and temporal influences is necessary to improve POI recommendation by addressing the data sparsity problem. However, existing methods model the geographical influence based on the physical distance between POIs and users, while ignoring the temporal characteristics of such geographical influences. In this paper, we perform a study on the user mobility patterns where we find out that users’ check-ins happen around several centers depending on their current temporal state. Next, we propose a spatio-temporal activity-centers algorithm to model users’ behavior more accurately. Finally, we demonstrate the effectiveness of our proposed contextual model by incorporating it into the matrix factorization model under two different settings: (i) static and (ii) temporal. To show the effectiveness of our proposed method, which we refer to as STACP, we conduct experiments on two well-known real-world datasets acquired from Gowalla and Foursquare LBSNs. Experimental results show that the STACP model achieves a statistically significant performance improvement, compared to the state-of-the-art techniques. Also, we demonstrate the effectiveness of capturing geographical and temporal information for modeling users’ activity centers and the importance of modeling them jointly.
| S-EPMC7148222 | biostudies-literature
Project description:Point of interest (POI) recommendation is a popular personalized location-based service. This paper proposes a Geographic Personal Matrix Factorization (GPMF) model that makes effective use of geographic information from the perspective of the relationship between POIs and users. This model considers the role of geographic information from multiple perspectives based on the locational relationship among users, the distributional relationship between users and POIs, and the proximity and clustering relationship among POIs. The GPMF mines the influence of geographic information on different objects and carries out unique modeling through cosine similarity, non-linear function, and k nearest neighbor (KNN). This study explored the influence of geographic information on POI recommendation through extensive experiments with data from Foursquare. The result shows that GPMF performs better than the commonly used POI recommendation algorithm in terms of both precision and recall. Geographic information through proximity relations effectively improves the recommendation algorithm.
| S-EPMC9012400 | biostudies-literature
Project description:Understanding how background levels of dissolved minerals vary in streams temporally and spatially is needed to assess salinization of fresh water, establish reasonable thresholds and restoration goals, and determine vulnerability to extreme climate events like drought. We developed a random forest model that predicts natural background specific conductivity (SC), a measure of total dissolved ions, for all stream segments in the contiguous United States at monthly time steps between the years 2001 to 2015. Models were trained using 11 796 observations made at 1785 minimally impaired stream segments and validated with observations from an additional 92 segments. Static predictors of SC included geology, soils, and vegetation parameters. Temporal predictors were related to climate and enabled the model to make predictions for different dates. The model explained 95% of the variation in SC among validation observations (mean absolute error = 29 μS/cm, Nash-Sutcliffe efficiency = 0.85). The model performed well across the period of interest but exhibited bias in Coastal Plain and Xeric regions (26 and 30%, respectively). National model predictions showed large spatial variation with the greatest SC predicted to occur in the desert southwest and plains. Model predictions also reflected changes at individual streams during drought.
| S-EPMC7153567 | biostudies-literature
Project description:Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the "music mainstream" strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervized learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user's country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-à-vis state-of-the-art algorithms that do not exploit this type of context information.
| S-EPMC7990101 | biostudies-literature
Project description:Geographical characteristics have been proven to be effective in improving the quality of point-of-interest (POI) recommendation. However, existing works on POI recommendation focus on cost (time or money) of travel for a user. An important geographical aspect that has not been studied adequately is the neighborhood effect, which captures a user's POI visiting behavior based on the user's preference not only to a POI, but also to the POI's neighborhood. To provide an interpretable framework to fully study the neighborhood effect, first, we develop different sets of insightful features, representing different aspects of neighborhood effect. We employ a Yelp data set to evaluate how different aspects of the neighborhood effect affect a user's POI visiting behavior. Second, we propose a deep learning-based recommendation framework that exploits the neighborhood effect. Experimental results show that our approach is more effective than two state-of-the-art matrix factorization-based POI recommendation techniques.
| S-EPMC8341514 | biostudies-literature
Project description:Epithelial-mesenchymal transition (EMT) is well established as playing a crucial role in cancer progression and being a potential therapeutic target. To elucidate the gene regulation that drives the decision making of EMT, many previous studies have been conducted to model EMT gene regulatory circuits (GRCs) using interactions from the literature. While this approach can depict the generic regulatory interactions, it falls short of capturing context-specific features. Here, we explore the effectiveness of a combined bioinformatics and mathematical modeling approach to construct context-specific EMT GRCs directly from transcriptomics data. Using time-series single cell RNA-sequencing data from four different cancer cell lines treated with three EMT-inducing signals, we identify context-specific activity dynamics of common EMT transcription factors. In particular, we observe distinct paths during the forward and backward transitions, as is evident from the dynamics of major regulators such as NF-KB (e.g., NFKB2 and RELB) and AP-1 (e.g., FOSL1 and JUNB). For each experimental condition, we systematically sample a large set of network models and identify the optimal GRC capturing context-specific EMT states using a mathematical modeling method named Random Circuit Perturbation (RACIPE). The results demonstrate that the approach can build high quality GRCs in certain cases, but not others and, meanwhile, elucidate the role of common bioinformatics parameters and properties of network structures in determining the quality of GRCs. We expect the integration of top-down bioinformatics and bottom-up systems biology modeling to be a powerful and generally applicable approach to elucidate gene regulatory mechanisms of cellular state transitions.
| S-EPMC7190801 | biostudies-literature
Project description:As an important factor for improving recommendations, time information has been introduced to model users' dynamic preferences in many papers. However, the sequence of users' behaviour is rarely studied in recommender systems. Due to the users' unique behavior evolution patterns and personalized interest transitions among items, users' similarity in sequential dimension should be introduced to further distinguish users' preferences and interests. In this paper, we propose a new collaborative filtering recommendation method based on users' interest sequences (IS) that rank users' ratings or other online behaviors according to the timestamps when they occurred. This method extracts the semantics hidden in the interest sequences by the length of users' longest common sub-IS (LCSIS) and the count of users' total common sub-IS (ACSIS). Then, these semantics are utilized to obtain users' IS-based similarities and, further, to refine the similarities acquired from traditional collaborative filtering approaches. With these updated similarities, transition characteristics and dynamic evolution patterns of users' preferences are considered. Our new proposed method was compared with state-of-the-art time-aware collaborative filtering algorithms on datasets MovieLens, Flixster and Ciao. The experimental results validate that the proposed recommendation method is effective and outperforms several existing algorithms in the accuracy of rating prediction.
| S-EPMC4873175 | biostudies-literature
Project description:Behavioral state modulates neural activity throughout the visual system; this is largely due to changes in arousal that alter internal brain state. However, behaviors are constrained by the external environmental context, so it remains unclear if this context itself dictates the regime of visual processing, apart from ongoing changes in arousal. Here, we addressed this question in awake head-fixed mice while they passively viewed visual stimuli in two different environmental contexts: either a cylindrical tube, or a circular running wheel. We targeted high-density silicon probe recordings to the dorsal lateral geniculate nucleus (dLGN) and simultaneously measured several electrophysiological and behavioral correlates of arousal changes, and thus controlled for them across contexts. We found surprising differences in spatial and temporal processing in dLGN across contexts, even in identical states of alertness and stillness. The wheel context (versus tube) showed elevated baseline activity, faster visual responses, and smaller but less selective spatial receptive fields. Further, arousal caused similar changes to visual responsiveness across all conditions, but the environmental context mainly changed the overall set-point for this relationship. Together, our results reveal an unexpected influence of the physical environmental context on fundamental aspects of visual processing in the early visual system.
| S-EPMC11291113 | biostudies-literature
Project description:Functional magnetic resonance imaging (fMRI) data sets are large and characterized by complex dependence structures driven by highly sophisticated neurophysiology and aspects of the experimental designs. Typical analyses investigating task-related changes in measured brain activity use a two-stage procedure in which the first stage involves subject-specific models and the second-stage specifies group (or population) level parameters. Customarily, the first-level accounts for temporal correlations between the serial scans acquired during one scanning session. Despite accounting for these correlations, fMRI studies often include multiple sessions and temporal dependencies may persist between the corresponding estimates of mean neural activity. Further, spatial correlations between brain activity measurements in different locations are often unaccounted for in statistical modeling and estimation. We propose a two-stage, spatio-temporal, autoregressive model that simultaneously accounts for spatial dependencies between voxels within the same anatomical region and for temporal dependencies between a subject's estimates from multiple sessions. We develop an algorithm that leverages the special structure of our covariance model, enabling relatively fast and efficient estimation. Using our proposed method, we analyze fMRI data from a study of inhibitory control in cocaine addicts.
| S-EPMC2942991 | biostudies-literature
Project description:Modeling of background radiation for the urban environment plays an important role in homeland security. However, background radiation is difficult to assess due to its spatial-temporal fluctuations caused by the variation in soil composition, building materials, and weather patterns etc. To address the challenge of background radiation modeling, we developed a mobile sensor network to continuously monitor the background radiation; we also proposed a maximum likelihood estimation algorithm to decouple and estimate the background's spatial distribution and temporal fluctuation. Experimental results demonstrated how this background radiation monitoring system accurately recognized high background regions in the experimental area, and successfully captured temporal fluctuation trends of background radiation during rains. Our system provides an efficient solution to model the temporal fluctuation and spatial distribution of background radiation.
| S-EPMC6195270 | biostudies-literature