Related Experiment Video
Updated: Apr 25, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
N-screen aware multicriteria hybrid recommender system using weight based subspace clustering.
Farman Ullah1, Ghulam Sarwar1, Sungchang Lee1
1Department of Information & Communication, Korea Aerospace University, Goyang 412-791, Republic of Korea.
This study introduces an N-screen aware recommender system that enhances user experience by considering device attributes and usage patterns. The system improves recommendation accuracy and addresses common issues like sparsity and cold start.
Area of Science:
- Computer Science
- Human-Computer Interaction
Background:
- N-screen services allow users to access content across multiple devices.
- Existing recommender systems do not account for diverse device capabilities or user context.
Purpose of the Study:
- To develop an N-screen aware recommender system for improved user experience.
- To address limitations of current recommender systems in multi-device environments.
Main Methods:
- Introduced a user device profile collaboration agent, manager, and control server.
- Developed a multicriteria hybrid framework incorporating device information, user preferences, and demographics.
- Proposed an individual feature and subspace weight based clustering (IFSWC) algorithm.
Main Results:
- The system significantly improves recommendation accuracy, precision, and scalability.
- Effectively addresses sparsity and cold start issues in N-screen environments.
- Simulation results validate the system's effectiveness.
Conclusions:
- The proposed N-screen aware recommender system enhances user experience by personalizing content delivery across devices.
- The IFSWC algorithm and hybrid framework offer a robust solution for multi-device recommendation challenges.
Related Concept Videos
Weighted Mean
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
Cluster Sampling Method
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
Classification of Systems-II
Classification of Systems-I
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Response Surface Methodology
The process of RSM involves several key steps:
Quantifying and Rejecting Outliers: The Grubbs Test