scholarly journals A Spatial-Temporal Self-Attention Network (STSAN) for Location Prediction

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Shuang Wang ◽  
AnLiang Li ◽  
Shuai Xie ◽  
WenZhu Li ◽  
BoWei Wang ◽  
...  
Keyword(s):  
New York ◽  
Geographic Location ◽  
Temporal Information ◽  
Location Prediction ◽  
Trajectory Data ◽  
Attention Network ◽  
Trajectory Representation ◽  
Activity Preference ◽  
Location Based Social Networks ◽  
Significant Attention

With the popularity of location-based social networks, location prediction has become an important task and has gained significant attention in recent years. However, how to use massive trajectory data and spatial-temporal context information effectively to mine the user’s mobility pattern and predict the users’ next location is still unresolved. In this paper, we propose a novel network named STSAN (spatial-temporal self-attention network), which can integrate spatial-temporal information with the self-attention for location prediction. In STSAN, we design a trajectory attention module to learn users’ dynamic trajectory representation, which includes three modules: location attention, which captures the location sequential transitions with self-attention; spatial attention, which captures user’s preference for geographic location; and temporal attention, which captures the user temporal activity preference. Finally, extensive experiments on four real-world check-ins datasets are designed to verify the effectiveness of our proposed method. Experimental results show that spatial-temporal information can effectively improve the performance of the model. Our method STSAN gains about 39.8% Acc@1 and 4.4% APR improvements against the strongest baseline on New York City dataset.

scholarly journals Hidden location prediction using check-in patterns in location-based social networks

2018 ◽  
Vol 57 (3) ◽  
pp. 571-601 ◽  
Author(s):  
Pramit Mazumdar ◽  
Bidyut Kr. Patra ◽  
Korra Sathya Babu ◽  
Russell Lock
Keyword(s):  
Social Networks ◽  
Location Prediction ◽  
Location Based Social Networks

scholarly journals When paths cross: maintaining utility of trajectory data in geomasking

2017 ◽  
pp. 29-40
Author(s):  
Dara E. Seidl
Keyword(s):  
New York ◽  
New York City ◽  
Data Collection ◽  
Random Perturbation ◽  
Location Based Services ◽  
Trajectory Data ◽  
Mobile Data ◽  
Mobile Data Collection ◽  
Viable Solution ◽  
Transportation Research

With an increase in mobile data collection through GPS and other location-based services, there have been a number of attempts to apply geomasking techniques to published route data in order to protect trajectory privacy. Yet, the utility of masked trajectory data and its value to transportation research remain in question. This study examines how the inferred route changes when origin and destination data are masked to protect privacy, as well as calculates the anonymity of each route traveled by a sample of New York City taxi cabs. It is determined that the routes between locations masked by random perturbation are significantly different from the original routes and that a network-based data product suppressing unique routes is a viable solution to release both accurate route statistics and protect confidentiality

scholarly journals HST-LSTM: A Hierarchical Spatial-Temporal Long-Short Term Memory Network for Location Prediction

2018 ◽  
Author(s):  
Dejiang Kong ◽  
Fei Wu
Keyword(s):  
Real Time ◽  
Short Term Memory ◽  
Location Based Services ◽  
Location Prediction ◽  
Trajectory Data ◽  
Short Term ◽  
Data Set ◽  
Term Memory ◽  
Long Time ◽  
Long Short Term Memory

The widely use of positioning technology has made mining the movements of people feasible and plenty of trajectory data have been accumulated. How to efficiently leverage these data for location prediction has become an increasingly popular research topic as it is fundamental to location-based services (LBS). The existing methods often focus either on long time (days or months) visit prediction (i.e., the recommendation of point of interest) or on real time location prediction (i.e., trajectory prediction). In this paper, we are interested in the location prediction problem in a weak real time condition and aim to predict users' movement in next minutes or hours. We propose a Spatial-Temporal Long-Short Term Memory (ST-LSTM) model which naturally combines spatial-temporal influence into LSTM to mitigate the problem of data sparsity. Further, we employ a hierarchical extension of the proposed ST-LSTM (HST-LSTM) in an encoder-decoder manner which models the contextual historic visit information in order to boost the prediction performance. The proposed HST-LSTM is evaluated on a real world trajectory data set and the experimental results demonstrate the effectiveness of the proposed model.

scholarly journals Location prediction in location-based social networks

2017 ◽  
Vol 7 (3) ◽  
pp. 149-156
Author(s):  
Mucahit Baydar ◽  
Songul Albayrak
Keyword(s):  
Social Networks ◽  
Wireless Networks ◽  
Social Network ◽  
Mobile Devices ◽  
New Method ◽  
Time Range ◽  
Location Prediction ◽  
The Social ◽  
Location Based Social Network ◽  
Location Based Social Networks

AbstractDevelopments in mobile devices and wireless networks have led to the increasing popularity of location-based social networks. These networks allow users to explore new places, share their location, videos and photos and make friends. They give information about the mobility of users, which can be used to improve the networks. This paper studies the problem of predicting the next check-in of users of location-based social networks. For an accurate prediction, we first analyse the datasets that are obtained from the social networks, Foursquare and Gowalla. Then we obtain some features like place popularity, place popular time range, place distance to user’s home, user’s past visits, category preferences and friendships ,which are used for prediction and deeper understanding of the user behaviours. We use each feature individually, and then in combination, using the new method. Finally, we compare the acquired results and observe the improvement with the new method.Keywords: Location prediction, location-based social network, check-in data.

scholarly journals Location Prediction with Personalized Federated Learning

2021 ◽  
Author(s):  
shuang wang ◽  
Bowei Wang ◽  
Shuai Yao ◽  
Jiangqin Qu ◽  
Yuezheng Pan
Keyword(s):  
Human Mobility ◽  
Prediction Method ◽  
Human Movement ◽  
Movement Behavior ◽  
Location Prediction ◽  
Learning Framework ◽  
User Behaviors ◽  
Learning Techniques ◽  
Location Based Social Networks ◽  
Privacy Issues

Abstract Location prediction has attracted wide attention in human mobility prediction because of the popularity of location-based social networks. Existing location prediction methods have achieved remarkable development in centrally stored datasets. However, these datasets contain privacy data about user behaviors and may cause privacy issues. A location prediction method is proposed in our work to predict human movement behavior using federated learning techniques in which the data is stored in different clients and different clients cooperate to train to extract useful users’ behavior information and prevent the disclosure of privacy. Firstly, we put forward an innovative spatial-temporal location prediction framework(STLPF) for location prediction by integrating spatial-temporal information in local and global views on each client, and propose a new loss function to optimize the model. Secondly, we design a new personalized federated learning framework in which clients can cooperatively train their personalized models in the absence of a global model. Finally, the numerous experimental results on check-in datasets further show that our privacy-protected method is superior and more effective than various baseline approaches.

Narratives of Fracture

2017 ◽  
Author(s):  
Ylce Irizarry
Keyword(s):  
New York ◽  
New York City ◽  
Cultural Identity ◽  
Puerto Rican ◽  
Political Ideology ◽  
Puerto Ricans ◽  
Geographic Location ◽  
Family Values ◽  
Ethnic Populations ◽  
Large Populations

This chapter illustrates how one's cultural identity is defined just as much by geographic location, gender, class, and political ideology than by perceived race or ethnic self-identification. It studies two texts by Puerto Rican authors to show how individuals challenge rigid notions of ethnonationalism: Judith Ortiz Cofer's The Latin Deli: Telling the Lives of Barrio Women (1993) and Ernesto Quiñonez's Bodega Dreams (2000). Set in the proximate urban Northeastern cities—Paterson, New Jersey, and New York City, respectively—with large populations of Puerto Ricans, other kinds of Latinas/os, and other underrepresented ethnic populations, the books challenge persistent definitions of puertorriqueñidad—the essence of one's Puerto Rican identity. Ortiz Cofer portrays the confinement women experience due to patriarchal Puerto Rican family values while Quiñonez portrays the confinement Puerto Rican men experience due to their ethnonational loyalties.

TREAD: Privacy Preserving Incentivized Connected Vehicle Mobility Data Storage on InterPlanetary-File-System-Enabled Blockchain

2021 ◽  
pp. 036119812110450
Author(s):  
Junaid Ahmed Khan ◽  
Kavyashree Umesh Bangalore ◽  
Abdullah Kurkcu ◽  
Kaan Ozbay
Keyword(s):  
New York ◽  
Data Storage ◽  
File System ◽  
Technology Development ◽  
Personal Information ◽  
Storage System ◽  
Connected Vehicle ◽  
Test Bed ◽  
Trajectory Data ◽  
Mobility Data

Trajectory data from connected vehicles (CVs) and other micromobility sources such as e-scooters, bikes, and pedestrians is important for researchers, policy makers, and other stakeholders for leveraging the location, speed, and heading, along with other mobility data, to improve safety and bolster technology development toward innovative location-based applications for citizens. Such raw data needs to be stored and accessed from a non-proprietary database while the obfuscation and encryption techniques on current cloud-based proprietary solutions incur data losses that are deemed inefficient for accurate usage, particularly in time-sensitive real-time operations. In this paper, we target the problem of scalably storing and retrieving potentially sensitive data generated by vehicles and propose TREAD, a blockchain-based system comprising smart contracts to store this mobility data on a distributed ledger such that multiple peers can access and utilize it in different location-based applications while not revealing users’ sensitive personal information. It is, however, challenging to scalably store large amounts of constantly generated trajectories, and to achieve scalability we leverage InterPlanetary File System (IPFS), a scalable distributed peer-to-peer data storage system. To avoid users injecting malicious/fake trajectories into the ledger, we develop efficient consensus algorithms for the stakeholders to validate the storage and retrieval process in a distributed manner. We implemented TREAD on the open-source Hyperledger Fabric blockchain platform using trajectory data generated for 700 vehicles in a simulation environment well calibrated with vehicle trajectories from a real-world test-bed in New York City. Results show that TREAD scalably stores trajectory data with lower delay and overhead.

Comparison of Simultaneous Airborne and Radiometric Measurements of Supercooled Liquid Water

1991 ◽  
Vol 30 (7) ◽  
pp. 1043-1046 ◽  
Author(s):  
Geoffrey E. Hill
Keyword(s):  
New York ◽  
Melting Point ◽  
Liquid Water ◽  
Microwave Radiometer ◽  
Geographic Location ◽  
Supercooled Liquid ◽  
Cloud Base ◽  
Dual Frequency ◽  
Radiometric Measurements ◽  
Cloud Tops

Abstract Simultaneous measurements of supercooled liquid water by an instrumented aircraft and a dual-frequency microwave radiometer were made at Lake Ontario, New York, during wintertime. The geographic location and typical meteorological conditions for making the measurements were specifically selected to facilitate the comparisons. Flight paths from below cloud base to above cloud tops were made over the radiometer site. Seven flights were made; supercooled liquid water was measured by a calibrated Rosemount icing meter. The primary finding is that when the temperature of the atmosphere in the viewing path of the radiometer is below the melting point of ice, the airborne liquid-water measurements are in general agreement with the radiometric measurements. When an inversion with the temperature above the melting point is present, the radiometric readings of liquid water are much larger than the values found from the aircraft. Also, the, possibility is raised that in very heavy snowfall with large ice particles the amount of supercooled liquid water will appear too large according to the radiometer.

Sign in / Sign up

Export Citation Format

Share Document