W
Wei Li
Researcher at University of Cambridge
Publications - 11
Citations - 490
Wei Li is an academic researcher from University of Cambridge. The author has contributed to research in topics: Traffic classification & Statistical classification. The author has an hindex of 7, co-authored 11 publications receiving 444 citations. Previous affiliations of Wei Li include Queen Mary University of London.
Papers
More filters
Journal ArticleDOI
Efficient application identification and the temporal and spatial stability of classification schema
TL;DR: This paper compares and contrasts the effective and efficient classification of network-based applications using behavioral observations of network -traffic and those using deep-packet inspection, and documents the accuracy of spatial classification without training data possessing spatial diversity.
Proceedings ArticleDOI
A Machine Learning Approach for Efficient Traffic Classification
Wei Li,Andrew W. Moore +1 more
TL;DR: A machine-learning approach that accurately classifies live traffic using C4.5 decision tree by collecting 12 features at the start of the flows, without inspecting the packet payload, can identify live traffic of different types of applications with 99.8% total accuracy.
Book ChapterDOI
GTVS: Boosting the Collection of Application Traffic Ground Truth
TL;DR: This paper proposes a methodology and details the design of a technical framework that significantly boosts the efficiency in compiling the application traffic ground truth and a case study on a 30 minute real data trace is presented.
Proceedings ArticleDOI
Experience with high-speed automated application-identification for network-management
TL;DR: Deployment experience is discussed and real traffic is used to illustrate how such an architecture enables several distinct features: high accuracy, high throughput, minimal delay, and efficient packet labeling --- all in a low-cost, robust configuration that works alongside the enterprise access-router.
Proceedings Article
Classifying HTTP Traffic in the New Age
TL;DR: Using full-payload data, HTTP has been a great success, used by many applications and provided a useful request / response paradigm and a historical context over a multi-year period is shown.