Removal policies in network caches for World-Wide Web documents
Conference proceedings on Applications, technologies, architectures, and protocols for computer communications
Replacement policies for a proxy cache
IEEE/ACM Transactions on Networking (TON)
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Logistic Regression in an Adaptive Web Cache
IEEE Internet Computing
Rate of change and other metrics: a live study of the world wide web
USITS'97 Proceedings of the USENIX Symposium on Internet Technologies and Systems on USENIX Symposium on Internet Technologies and Systems
Cost-aware WWW proxy caching algorithms
USITS'97 Proceedings of the USENIX Symposium on Internet Technologies and Systems on USENIX Symposium on Internet Technologies and Systems
Hi-index | 0.00 |
In this paper Web cache optimization using document features is proposed. The problem in Web cache optimization is to decide which strategy to use in replacement of cache objects. While commonly used policies use heuristic rules, proposed model predicts the value of each Web object by using features collected from the HTTP responses and from the HTML structure of the document. In a case study, generalized linear model and multilayer perceptron committee model are used to classify about 50000 Web documents according to their popularity. Results show that linear model does not find any correlation between the features and document popularity. MLP model gives better results, yielding mean classification percentages of 64 and 74 for the documents to be left or to be removed from the Web cache, respectively.