Video Popularity Prediction: An Autoencoder Approach With Clustering
Autoencoders implemented by artificial neural networks (ANNs) are utilized to learn the latent space representation of data in an unsupervised manner, and they have been widely used in recommender systems. For instance, several collaborative denoising autoencoder (CDAE) models have shown that their...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9139947/ |
id |
doaj-efea74e3c1ec4a3aa02e385083e28470 |
---|---|
record_format |
Article |
spelling |
doaj-efea74e3c1ec4a3aa02e385083e284702021-03-30T04:40:21ZengIEEEIEEE Access2169-35362020-01-01812928512929910.1109/ACCESS.2020.30092539139947Video Popularity Prediction: An Autoencoder Approach With ClusteringYu-Tai Lin0https://orcid.org/0000-0003-0564-8618Chia-Cheng Yen1https://orcid.org/0000-0002-8420-9762Jia-Shung Wang2https://orcid.org/0000-0003-2157-6108Department of Computer Science, National Tsing Hua University, Hsinchu, TaiwanDepartment of Computer Science, University of California at Davis, Davis, CA, USADepartment of Computer Science, National Tsing Hua University, Hsinchu, TaiwanAutoencoders implemented by artificial neural networks (ANNs) are utilized to learn the latent space representation of data in an unsupervised manner, and they have been widely used in recommender systems. For instance, several collaborative denoising autoencoder (CDAE) models have shown that their performance gains outperform that of the collaborative filtering based (CF-based) models. In this work, a near-optimal Top-K forecasting solution is proposed for our advanced autoencoder recommender systems. We propose a method which utilizes CDAE model in predicting the Top-K popular videos in an upcoming time period. In order to improve the prediction accuracy, we also propose an autoencoder based recommendation algorithm with the help of K-means clustering that upgrades the performance of the original autoencoder model. The experimental results show that our method increases significantly the Average Precision (AP) and Recall values by nearly 30%. We then further utilize our proposed autoencoder model with clustering in predicting Top-K popular videos. The applications of predicting Top-K popular videos can be used in the video delivery for the Mobile Edge Computing (MEC) environment to avoid bottleneck in the constricted capacity of backhaul link. Namely, the performance gain will be upgraded if our proposed method precisely predicts and caches the Top-K popular videos in advance with the help of a better forecasting model.https://ieeexplore.ieee.org/document/9139947/Top-K ranking and predictingautoencodercachingK-means |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yu-Tai Lin Chia-Cheng Yen Jia-Shung Wang |
spellingShingle |
Yu-Tai Lin Chia-Cheng Yen Jia-Shung Wang Video Popularity Prediction: An Autoencoder Approach With Clustering IEEE Access Top-K ranking and predicting autoencoder caching K-means |
author_facet |
Yu-Tai Lin Chia-Cheng Yen Jia-Shung Wang |
author_sort |
Yu-Tai Lin |
title |
Video Popularity Prediction: An Autoencoder Approach With Clustering |
title_short |
Video Popularity Prediction: An Autoencoder Approach With Clustering |
title_full |
Video Popularity Prediction: An Autoencoder Approach With Clustering |
title_fullStr |
Video Popularity Prediction: An Autoencoder Approach With Clustering |
title_full_unstemmed |
Video Popularity Prediction: An Autoencoder Approach With Clustering |
title_sort |
video popularity prediction: an autoencoder approach with clustering |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Autoencoders implemented by artificial neural networks (ANNs) are utilized to learn the latent space representation of data in an unsupervised manner, and they have been widely used in recommender systems. For instance, several collaborative denoising autoencoder (CDAE) models have shown that their performance gains outperform that of the collaborative filtering based (CF-based) models. In this work, a near-optimal Top-K forecasting solution is proposed for our advanced autoencoder recommender systems. We propose a method which utilizes CDAE model in predicting the Top-K popular videos in an upcoming time period. In order to improve the prediction accuracy, we also propose an autoencoder based recommendation algorithm with the help of K-means clustering that upgrades the performance of the original autoencoder model. The experimental results show that our method increases significantly the Average Precision (AP) and Recall values by nearly 30%. We then further utilize our proposed autoencoder model with clustering in predicting Top-K popular videos. The applications of predicting Top-K popular videos can be used in the video delivery for the Mobile Edge Computing (MEC) environment to avoid bottleneck in the constricted capacity of backhaul link. Namely, the performance gain will be upgraded if our proposed method precisely predicts and caches the Top-K popular videos in advance with the help of a better forecasting model. |
topic |
Top-K ranking and predicting autoencoder caching K-means |
url |
https://ieeexplore.ieee.org/document/9139947/ |
work_keys_str_mv |
AT yutailin videopopularitypredictionanautoencoderapproachwithclustering AT chiachengyen videopopularitypredictionanautoencoderapproachwithclustering AT jiashungwang videopopularitypredictionanautoencoderapproachwithclustering |
_version_ |
1724181493318680576 |