GALLOP Global Feature Location Predication for Different Check in Scenarios

1croreprojects@gmail.com

ABSTRACT

Location prediction is widely used to forecast users’ next place to visit based on his/her mobility logs. It is an essential problem in location data processing, invaluable for surveillance, business, and personal applications. It is very challenging due to the sparsity issues of check-in data. An often ignored problem in recent studies is the variety across different check-in scenarios, which is becoming more urgent due to the increasing availability of more location check-in  pplications. we propose a new feature fusion based prediction approach, GALLOP, i.e., GlobAL feature fused LOcation Prediction for different check-in scenarios. Based on the carefully designed feature extraction methods, we utilize a novel combined prediction framework. Specifically, we set out to utilize the density estimation model to profile geographical features, i.e., context information, the factorization method to extract collaborative information, and a graph structure to extract location transition patterns of users’ temporal check-in sequence, i.e., content information.

 

Click Here:-  Latest IEEE 2018 Dot Net Projects

 

SYSTEM ANALYSIS

EXISTING SYSTEM

 

We propose a new feature fusion approach, i.e., GlobAL feature fusion for LOcation Prediction (GALLOP), to cope with the variety problem in location prediction. To improve the applicability of location prediction approach, We utilize several kinds of features and discuss their different characteristics in the variety of check-in scenarios. Three classes of features are used in GALLOP: context feature(geographical aspects), collaboration feature(users’ latent interest space) and content feature(places’ description attributes). We introduce intuitive ways to model these check-in features and then formalize a combination framework to deliver the predicted target places to end users.

 

DISADVANTAGES

 

In contrast, spatial feature based methods use the gravity and locality closeness measurements to fit into the location setting, but are usually difficult to generalize the temporal and other related features.

Though some recent work pay attention to these check-in behavior differences, the inherent variety between this check-ins and their affect to location prediction is usually missing

That existing predication methods cannot be directly applied to all check-in scenarios, where their performance vary greatly

 

PROPOSED SYSTEM

 

We design a multiple granularity model to profile the geographical closeness. We select the predicted candidates based on the combination of local district, local city and state scales. The weights of each scale are learned from training data.

We propose a new feature fusion approach, i.e., GlobAL feature fusion for LOcation Prediction (GALLOP), to cope with the variety problem in location prediction. To improve the applicability of location prediction approach, we utilize several kinds of features and discuss their different characteristics in the variety of check-in scenarios.

Three classes of features are used in GALLOP: context feature (geographical aspects), collaboration feature (users’ latent interest space) and content feature (places’ description attributes). We introduce intuitive ways to model these check-in features and then formalize a combination framework to deliver the predicted target places to end users.

ADVANTAGES

We proposed in this work can be extended to enable incremental updating. And new Comprehensive location prediction and update setting can be utilized.

The feature fusion approach shows the advantage of feature combination to deliver improved accuracy

The proposed GALLOP prediction approach is not only general over different check-in scenarios but also comprehensive of different features

To improve the prediction robustness and generality

Prove that the general location prediction approach is a better choice to tackle the location prediction challenges

 

SYSTEM SPECIFICATION

HARDWARE SPECIFICATION

 

  • System          :  Pentium IV 2.4 GHz.
  • Hard Disk       :  40 GB.
  • Floppy Drive   :  1.44 Mb.
  • Monitor          :  15 VGA Colour.
  • Mouse            :  Logitech.

 

SOFTWARE SPECIFICATION

 

  • Operating system  :   Windows XP/7.
  • Coding Language   :   ASP.net, C#.net
  • Tool                      :   Visual Studio 2010
  • Database               :   SQL SERVER 2008

 

CONCLUSIONS

 

 A new feature fusion method for location prediction problem. We systematically analyze the check-in characteristics of different scenarios and propose to model three categories of features and combine them in a global way. The geographical, collaborative and categorical information are all utilized. We propose new models to include more global features to improve the generality and robustness of the prediction method. Besides, the approach is versatile and easy to extend. It shows impressive advantage on different datasets and significantly improve the prediction accuracy. This research has several interesting future directions.A better ways to improve the feature preprocessing stage and design the compact structure to maintain the extracted features. It is also valuable to exploit the evolving factors in the location prediction. Additionally, the feature extraction methods we proposed in this work can be extended to enable incremental updating. And new comprehensive location prediction and update setting can be utilized.

 



Leave a comment

*

*

*