Location Based Recommender Systems: Architecture, Trends and Research Areas

Author(s):  
S. Tiwari ◽  
S. Tiwari ◽  
P. Jagwani ◽  
S. Kaushik
2021 ◽  
Vol 11 (4) ◽  
pp. 1366
Author(s):  
Wafa Shafqat ◽  
Yung-Cheol Byun

With the ever-growing amount of online data and information, recommender systems are becoming overwhelmingly popular as an adequate approach for overcoming the challenge of information overload. Artificial Intelligence (AI) and Deep Learning (DL) have accumulated significant interest in many research areas, and recommender systems are one of them. In this paper, a Graph Convolutional Neural Network (GCNN)-based approach was used for online product recommendation. Graph-based methods have undergone substantial consideration for several recommendation tasks, with effective results. However, handling the computational complexities and training large datasets remain a challenge for such a model. Even though they are useful, the excessive measure of the model’s boundaries obstructs their applications in real-world recommender frameworks to a great extent. The recursive way of generating neighbor node embeddings for each node in the graph makes it more challenging to train a deep and large GCNN model. Therefore, we propose a model that incorporates measures of similarity between two different nodes, and these similarity measures help us to sample the neighbors beforehand. We estimate the similarity based on their interaction probability distribution with other nodes. We use KL divergence on different probability distributions to find the distance between them. This way, we set a threshold criterion for neighbor selection and generate other clusters. These clusters are then converted to subgraphs and are used as input for the proposed GCNN model. This approach simplifies the task of neighbor sampling for GCNN, and hence, we can observe a significant improvement in the computational complexity of the GCNN model. Finally, we compared the results with those for the previously proposed OpGCN model, basic GCNN model, and other traditional approaches such as collaborative filtering and probabilistic matrix factorization. The experiments showed that the complexity and computational time were decreased by estimating the similarity among nodes and sampling the nodes before training.


2020 ◽  
Vol 54 (1) ◽  
pp. 1-23
Author(s):  
Manos Tsagkias ◽  
Tracy Holloway King ◽  
Surya Kallumadi ◽  
Vanessa Murdock ◽  
Maarten de Rijke

With the rapid adoption of online shopping, academic research in the eCommerce domain has gained traction. However, significant research challenges remain, spanning from classic eCommerce search problems such as matching textual queries to multi-modal documents and ranking optimization for two-sided marketplaces to human-computer interaction and recommender systems for discovery and browsing. These research areas are important for understanding customer behavior, driving engagement, and improving product discoverability and conversion. In this article we identify the challenges and highlight research opportunities to improve the eCommerce customer experience.


Author(s):  
U. Gross ◽  
P. Hagemann

By addition of analytical equipment, scanning transmission accessories and data processing equipment the basic transmission electron microscope (TEM) has evolved into a comprehensive information gathering system. This extension has led to increased complexity of the instrument as compared with the straightforward imaging microscope, since in general new information capacity has required the addition of new control hardware. The increased operational complexity is reflected in a proliferation of knobs and buttons.In the conventional electron microscope design the operating panel of the instrument has distinct control elements to alter optical conditions of the microscope column in different modes. As a consequence a multiplicity of control functions has been inevitable. Examples of this are the three pairs of focus and magnification controls needed for TEM imaging, diffraction patterns, and STEM images.


2008 ◽  
Vol 16 (3) ◽  
pp. 131-134
Author(s):  
Urte Scholz ◽  
Rainer Hornung

Abstract. The main research areas of the Social and Health Psychology group at the Department of Psychology at the University of Zurich, Switzerland, are introduced. Exemplarily, three currently ongoing projects are described. The project ”Dyadic exchange processes in couples facing dementia” examines social exchanges in couples with the husband suffering from dementia and is based on Equity Theory. This project applies a multi-method approach by combining self-report with observational data. The ”Swiss Tobacco Monitoring System” (TMS) is a representative survey on smoking behaviour in Switzerland. Besides its survey character, the Swiss TMS also allows for testing psychological research questions on smoking with a representative sample. The project, ”Theory-based planning interventions for changing nutrition behaviour in overweight individuals”, elaborates on the concept of planning. More specifically, it is tested whether there is a critical amount of repetitions of a planning intervention (e.g., three or nine times) in order to ensure long-term effects.


2010 ◽  
Vol 49 (S 01) ◽  
pp. S11-S15
Author(s):  
C. Schütze ◽  
M. Krause ◽  
A. Yaromina ◽  
D. Zips ◽  
M. Baumann

SummaryRadiobiological and cell biological knowledge is increasingly used to further improve local tumour control or to reduce normal tissue damage after radiotherapy. Important research areas are evolving which need to be addressed jointly by nuclear medicine and radiation oncology. For this differences of the biological distribution of diagnostic and therapeutic nuclides compared with the more homogenous dose-distribution of external beam radiotherapy have to be taken into consideration. Examples for interdisciplinary biology-based cancer research in radiation oncology and nuclear medicine include bioimaging of radiobiological parameters characterizing radioresistance, bioimage-guided adaptive radiotherapy, and the combination of radiotherapy with molecular targeted drugs.


2020 ◽  
Vol 36 (4) ◽  
pp. 1199-1211
Author(s):  
Jennifer Parker ◽  
Kristen Miller ◽  
Yulei He ◽  
Paul Scanlon ◽  
Bill Cai ◽  
...  

The National Center for Health Statistics is assessing the usefulness of recruited web panels in multiple research areas. One research area examines the use of close-ended probe questions and split-panel experiments for evaluating question-response patterns. Another research area is the development of statistical methodology to leverage the strength of national survey data to evaluate, and possibly improve, health estimates from recruited panels. Recruited web panels, with their lower cost and faster production cycle, in combination with established population health surveys, may be useful for some purposes for statistical agencies. Our initial results indicate that web survey data from a recruited panel can be used for question evaluation studies without affecting other survey content. However, the success of these data to provide estimates that align with those from large national surveys will depend on many factors, including further understanding of design features of the recruited panel (e.g. coverage and mode effects), the statistical methods and covariates used to obtain the original and adjusted weights, and the health outcomes of interest.


2009 ◽  
pp. 83-99
Author(s):  
A. Libman

Economic policy in the modern world can be treated as an outcome of interaction of multiple territorial centers of public authority: nation-states, subnational and supranational jurisdictions. In the last decades economics has increased its attention to the factors which influence the distribution of power among jurisdictions. The paper surveys two main research areas in this literature: economics of conflicts and theory of endogenous decentralization. It discusses the basic models of both approaches and their modifications applied in the literature as well as factors of conflict formation and bargaining over devolution.


Sign in / Sign up

Export Citation Format

Share Document