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%.

Modeling of Self-similar Traffic

Modeling of self-similar traffic is performed for the queuing system of G/M/1/K type using Weibull distribution. To study the self-similar traffic the simulation model is developed by using SIMULINK software package in MATLAB environment. Approximation of self-similar traffic on the basis of spline functions. Modeling self-similar traffic is carried outfor QS of W/M/1/K type using the Weibull distribution. Initial data are: the value of Hurst parameter H=0,65, the shape parameter of the distribution curve α≈0,7 and distribution parameter β≈0,0099. Considering that the self-similar traffic is characterized by the presence of "splashes" and long-termdependence between the moments of requests arrival in this study under given initial data it is reasonable to use linear interpolation splines.

Heat flow and heat conductivity coefficient measured in bottom sediments collected in Cruise 13 of R/V Akademik Sergey Vavilov in the Pechora Sea

In Cruise 13 of R/V Akademik Sergey Vavilov in the Pechora Sea, six heat flow varied from 50 to 75 mW/m**2. Deep heat flow in the Pechora Sea was calculated equal to 45 mW/m**2, which is confirmed by results of geological and geophysical studies and corresponds to Middle Baikal age of the basement. A model of structure of the lithosphere in the Pechora Sea is suggested. Total thickness of the lithosphere in the basin (190 km) determined from geothermal data agrees well with that in transition zones from the continent to the ocean. According to estimates of deep heat flow in the region obtained, thickness of the mantle (160 km), of the basaltic (15 km), and of the granitic (15 km) layers of the lithosphere were also evaluated. Temperature values at boundaries of the sedimentary layers were calculated over a geological and geophysical profile crossing the Pechora Sea basin. Temperatures obtained agree with the temperature interval of hydrocarbon generation and correspond to Permian-Triassic sedimentary sequences, which are the most productive ones in the Pechora Sea region from the point of view of oil and gas potential.

(Table 1) Magnetic viscosity coefficient, VRM and NRM of DSDP Hole 6-57

THE magnetic properties of the basalts which form layer 2 of the oceanic lithosphere are important because of their relevance to the hypothesis (Vine and Matthews, 1963, doi:10.1038/199947a0) of seafloor spreading. Most studies of these magnetic properties have been carried out on basalts obtained from dredge hauls taken predominantly from ocean ridge systems and fracture zones. These constitute special areas of the oceanic crust where the sediment cover is negligible. It is of interest to compare the magnetic properties of the dredged basalts with samples recovered from holes drilled through the overlying sediments into the basaltic layer at places distant from ridge axes. Samples obtained from the abandoned Mohole project and, more recently, from the Deep Sea Drilling Project (DSDP) possessed magnetic properties similar to those of dredged basalts (Cox and Doell, 1962, doi:10.1029/JZ067i010p03997; Lowrie et al., 1973, doi:10.1016/0012-821X(73)90198-2). Here I describe highly unstable magnetic characteristics found in basalts from DSDP hole 57.

Additional traffic assignment options for the TASSIM model. Phase I. Final report.

Transportation Department, Washington, D.C.

Alcohol highway-traffic safety workshop for the judiciary.

National Highway Traffic Safety Administration, Washington, D.C.

Preliminary human factors guidelines for traffic management centers.

Federal Highway Administration, ITS Joint Program Office, Washington, D. C.