Lightweight Internet Traffic Classification - A Subject Based Solution with Word Embeddings

Internet traffic classification is a relevant and mature research field, anyway of growing importance and with still open technical challenges, also due to the pervasive presence of Internet-connected devices into everyday life. We claim the need for innovative traffic classification solutions capable of being lightweight, of adopting a domain-based approach, of not only concentrating on application-level protocol categorization but also classifying Internet traffic by subject. To this purpose, this paper originally proposes a classification solution that leverages domain name information extracted from IPFIX summaries, DNS logs, and DHCP leases, with the possibility to be applied to any kind of traffic. Our proposed solution is based on an extension of Word2vec unsupervised learning techniques running on a specialized Apache Spark cluster. In particular, learning techniques are leveraged to generate word-embeddings from a mixed dataset composed by domain names and natural language corpuses in a lightweight way and with general applicability. The paper also reports lessons learnt from our implementation and deployment experience that demonstrates that our solution can process 5500 IPFIX summaries per second on an Apache Spark cluster with 1 slave instance in Amazon EC2 at a cost of $ 3860 year. Reported experimental results about Precision, Recall, F-Measure, Accuracy, and Cohen's Kappa show the feasibility and effectiveness of the proposal. The experiments prove that words contained in domain names do have a relation with the kind of traffic directed towards them, therefore using specifically trained word embeddings we are able to classify them in customizable categories. We also show that training word embeddings on larger natural language corpuses leads improvements in terms of precision up to 180%.

One Approach to the Problem Solution of Specialized Software Development for Subject Search

In the article relevance of system development for subject search using computational linguistics is considered. The basic principles of system functioning are defined. The principle of grammar development for information retrieval from the partially structured text in a natural language is considered. The ranging principle of results of information search is defined.

Patenting Systems, Patentable Subject Matter, and Prior Art

The International School of Solid State Physics presented the 56th Course"Materials for Renewable Energy” in Erice (Italy), from July 18th to 28th 2012. This course was sponsored by the Italian Ministry of Education, University and Scientific Research, the Materials Research Society and the European Materials Research Society. The event was hosted at the "Ettore Majorana Foundation and Centre for Scientific Culture”. The school reviewed critical materials issues for the production and storage of renewable and sustainable energy. The aim of the School was to present the state-of-the-art and future perspectives in this critical area. It was to bring together the international community of students, young scientists, and experts in a unique atmosphere for reciprocal benefits in terms of enthusiasm, knowledge and new ideas.

Diplomatic history of the Panama Canal. Correspondence relating to the negotiation and application of certain treaties on the subject of the construction of an interoceanic canal, and accompanying papers.

Includes a report of the secretary of state, with papers relative to the construction of the Panama Canal.

Claims upon Mexico. Message from the President of the United States, upon the subject of the claims of the United States upon the United Mexican States.

"Referred to the Committee on Foreign Affairs."

Debate on the subject of confederation with Canada.

"Reprinted from the Government Gazette Extraordinary of March, 1870."to 1870."

Index to subject bibliographies in library bulletins to December 31, 1897.

Mode of access: Internet.

Subject headings for the aeronautical index /

Mimeographed.

A bibliography of philosophy : being the sections relating to that subject in the Best books and the Reader's guide /

Mode of access: Internet.

The manner of securing all sorts of buildings from fire, or, A treatise upon the construction of arches made with bricks and plaister, called flat-arches, and of a roof without timber called a bricked-roof : with the addition of some letters that have passed between the Count of Espie and Peter Wyche Esq. on this subject : adorned with two copper-plates serving to illustrate the whole work /

Publication date from ESTC.