Geographical Information in a Multi-domain Recommender System

2014 ◽  
pp. 315-321
Author(s):  
Tiffany Y. Tang ◽  
Pinata Winoto ◽  
Robert Ziqin Ye
Keyword(s):  
Recommender System ◽  
Geographical Information

scholarly journals A study of neighbour selection strategies for POI recommendation in LBSNs

2018 ◽  
Vol 44 (6) ◽  
pp. 802-817 ◽  
Author(s):  
Carlos Rios ◽  
Silvia Schiaffino ◽  
Daniela Godoy
Keyword(s):  
Social Networks ◽  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Location Based Services ◽  
Geographical Information ◽  
Good Prediction ◽  
General Terms ◽  
The Impact ◽  
Filtering Approach

Location-based recommender systems (LBRSs) are gaining importance with the proliferation of location-based services provided by mobile devices as well as user-generated content in social networks. Collaborative approaches for recommendation rely on the opinions of like-minded people, so-called neighbours, for prediction. Thus, an adequate selection of such neighbours becomes essential for achieving good prediction results. The aim of this work is to explore different strategies to select neighbours in the context of a collaborative filtering–based recommender system for POI (places of interest) recommendations. Whereas standard methods are based on user similarity to delimit a neighbourhood, in this work several strategies are proposed based on direct social relationships and geographical information extracted from location-based social networks (LBSNs). The impact of the different strategies proposed has been evaluated and compared against the traditional collaborative filtering approach using a dataset from a popular network as Foursquare. In general terms, the proposed strategies for selecting neighbours based on the different elements available in a LBSN achieve better results than the traditional collaborative filtering approach. Our findings can be helpful both to researchers in the recommender systems area and to recommender system developers in the context of LBSNs, since they can take into account our results to design and provide more effective services considering the huge amount of knowledge produced in LBSNs.

scholarly journals A Data-Driven Personalized Lighting Recommender System

2021 ◽  
Vol 4 ◽  
Author(s):  
Atousa Zarindast ◽  
Jonathan Wood
Keyword(s):  
Recommender System ◽  
Geographical Location ◽  
User Preferences ◽  
Geographical Information ◽  
User Interest ◽  
Smart Lighting ◽  
Home Based ◽  
Product Service ◽  
Color Scheme ◽  
Do So

Recommender systems attempt to identify and recommend the most preferable item (product-service) to individual users. These systems predict user interest in items based on related items, users, and the interactions between items and users. We aim to build an auto-routine and color scheme recommender system for home-based smart lighting that leverages a wealth of historical data and machine learning methods. We utilize an unsupervised method to recommend a routine for smart lighting. Moreover, by analyzing users’ daily logs, geographical location, temporal and usage information, we understand user preferences and predict their preferred light colors. To do so, users are clustered based on their geographical information and usage distribution. We then build and train a predictive model within each cluster and aggregate the results. Results indicate that models based on similar users increases the prediction accuracy, with and without prior knowledge about user preferences.

Assessment of land-use change in coastal areas through geographical information systems

2020 ◽  
Vol 13 (10) ◽  
Author(s):  
Verónica Lango-Reynoso ◽  
Karla Teresa González-Figueroa ◽  
Fabiola Lango-Reynoso ◽  
María del Refugio Castañeda-Chávez ◽  
Jesús Montoya-Mendoza
Keyword(s):  
Land Use ◽  
Land Use Change ◽  
Geographical Information Systems ◽  
Design Methodology ◽  
Scientific Information ◽  
Coastal Ecosystems ◽  
Coastal Areas ◽  
Geographical Information ◽  
Coastal Zones ◽  
Computer Based

Objective: This article describes and analyzes the main concepts of coastal ecosystems, these as a result of research concerning land-use change assessments in coastal areas. Design/Methodology/Approach: Scientific articles were searched using keywords in English and Spanish. Articles regarding land-use change assessment in coastal areas were selected, discarding those that although being on coastal zones and geographic and soil identification did not use Geographic Information System (GIS). Results: A GIS is a computer-based tool for evaluating the land-use change in coastal areas by quantifying variations. It is analyzed through GIS and its contributions; highlighting its importance and constant monitoring. Limitations of the study/Implications: This research analyzes national and international scientific information, published from 2007 to 2019, regarding the land-use change in coastal areas quantified with the digital GIS tool. Findings/Conclusions: GIS are useful tools in the identification and quantitative evaluation of changes in land-use in coastal ecosystems; which require constant evaluation due to their high dynamism.

A protocol for sampling pastures in hill country

2016 ◽  
Vol 78 ◽  
pp. 203-209 ◽  
Author(s):  
K.J. Hutchinson ◽  
D.R. Scobie ◽  
J. Beautrais ◽  
A.D. Mackay ◽  
G.M. Rennie ◽  
...  
Keyword(s):  
Random Sampling ◽  
Geographical Information Systems ◽  
Field Measurements ◽  
Decision Support Tool ◽  
Accurate Estimate ◽  
Ease Of Use ◽  
Geographical Information ◽  
Support Tool ◽  
Topographic Complexity ◽  
Hill Country

To develop a protocol to guide pasture sampling for estimation of paddock pasture mass in hill country, a range of pasture sampling strategies, including random sampling, transects and stratification based on slope and aspect, were evaluated using simulations in a Geographical Information Systems computer environment. The accuracy and efficiency of each strategy was tested by sampling data obtained from intensive field measurements across several farms, regions and seasons. The number of measurements required to obtain an accurate estimate was related to the overall pasture mass and the topographic complexity of a paddock, with more variable paddocks requiring more samples. Random sampling from average slopes provided the best balance between simplicity and reliability. A draft protocol was developed from the simulations, in the form of a decision support tool, where visual determination of the topographic complexity of the paddock, along with the required accuracy, were used to guide the number of measurements recommended. The protocol was field tested and evaluated by groups of users for efficacy and ease of use. This sampling protocol will offer farmers, consultants and researchers an efficient, reliable and simple way to determine pasture mass in New Zealand hill country settings. Keywords: hill country, feed budgeting, protocol pasture mass, slope

Sign in / Sign up

Export Citation Format

Share Document