scholarly journals A user preference tree based personalized route recommendation system for constraint tourism and travel

2021 ◽  
Author(s):  
U. Kanimozhi ◽  
Ganapathy Sannasi ◽  
D. Manjula ◽  
Kannan Arputharaj
Keyword(s):  
Recommendation System ◽  
User Preference ◽  
Route Recommendation

scholarly journals Design and Development of a Real-Time Optimal Route Recommendation System Using Big Data for Tourists in Jeju Island

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 506 ◽  
Author(s):  
Faisal Mehmood ◽  
Shabir Ahmad ◽  
DoHyeun Kim
Keyword(s):  
Big Data ◽  
Real Time ◽  
Recommendation System ◽  
Tourism Industry ◽  
Jeju Island ◽  
Third Party ◽  
User Preference ◽  
Optimal Route ◽  
Route Recommendation ◽  
Travel Route Recommendation

Nowadays researchers and engineers are trying to build travel route recommendation systems to guide tourists around the globe. The tourism industry is on the rise and it has attracted researchers to provide such systems for comfortable and convenient traveling. Mobile internet growth is increasing rapidly. Mobile data usage and traffic growth has increased interest in building mobile applications for tourists. This research paper aims to provide design and implementation of a travel route recommendation system based on user preference. Real-time big data is collected from Wi-Fi routers installed at more than 149 unique locations in Jeju Island, South Korea. This dataset includes tourist movement patterns collected from thousands of mobile tourists in the year 2016–2017. Data collection and analysis is necessary for a country to make public policies and development of the global travel and tourism industry. In this research paper we propose an optimal travel route recommendation system by performing statistical analysis of tourist movement patterns. Route recommendation is based on user preferences. User preference can vary over time and differ from one user to another. We have taken three main factors into consideration to the recommend optimal route i.e., time, distance, and popularity of location. Beside these factors, we have also considered weather and traffic condition using a third-party application program interfaces (APIs). We have classified regions into six major categories. Popularity of location can vary from season to season. We used a Naïve Bayes classifier to find the probability of tourists going to visit next location. Third-party APIs are used to find the longitude and latitude of the location. The Haversine formula is used to calculate the distance between unique locations. On the basis of these factors, we recommend the optimal route for tourists. The proposed system is highly responsive to mobile users. The results of this system show that the recommended route is convenient and allows tourists to visit maximum number of famous locations as compared to previous data.

scholarly journals Personalized Mobile Video Recommendation Based on User Preference Modeling by Deep Features and Social Tags

2019 ◽  
Vol 9 (18) ◽  
pp. 3858
Author(s):  
Jiafeng Li ◽  
Chenhao Li ◽  
Jihong Liu ◽  
Jing Zhang ◽  
Li Zhuo ◽  
...  
Keyword(s):  
Recommendation System ◽  
Moving Average ◽  
Likelihood Estimation ◽  
User Preference ◽  
Personalized Recommendation ◽  
Mobile Video ◽  
Preference Modeling ◽  
Social Tags ◽  
Personalized Video ◽  
Video Recommendation

With the explosive growth of mobile videos, helping users quickly and effectively find mobile videos of interest and further provide personalized recommendation services are the developing trends of mobile video applications. Mobile videos are characterized by their wide variety, single content, and short duration, and thus traditional personalized video recommendation methods cannot produce effective recommendation performance. Therefore, a personalized mobile video recommendation method is proposed based on user preference modeling by deep features and social tags. The main contribution of our work is three-fold: (1) deep features of mobile videos are extracted by an improved exponential linear units-3D convolutional neural network (ELU-3DCNN) for representing video content; (2) user preference is modeled by combining user preference for deep features with user preference for social tags that are respectively modeled by maximum likelihood estimation and exponential moving average method; (3) a personalized mobile video recommendation system based on user preference modeling is built after detecting key frames with a differential evolution optimization algorithm. Experiments on YouTube-8M dataset have shown that our method outperforms state-of-the-art methods in terms of both precision and recall of personalized mobile video recommendation.

Sign in / Sign up

Export Citation Format

Share Document