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%.

Graft preservation solutions in cardiovascular surgery.

Vein grafts are still the most commonly used graft material in cardiovascular surgery and much effort has been spent in recent years on investigating the optimal harvesting technique. One other related topic of similar importance remained more or less an incidental one. The storage solutions of vein grafts following procurement and prior to implantation are, despite their assumed impact, a relatively neglected theme. There is no doubt that the endothelium plays a key role in long-term patency of vein grafts, but the effects of the different storage solutions on the endothelium remain unclear : In a review of the literature, we could find 20 specific papers that addressed the question, of which the currently available preservation solutions are superior, harmless, damaging or ineffective. The focus lies on saline and autologous whole blood. Besides these two storage media, novel or alternative solutions have been investigated with surprising findings. In addition, a few words will be spent on potential alternatives and novel solutions on the market. As there is currently no randomized clinical trial regarding saline versus autologous whole blood available, this review compares all previous studies and methods of analysis to provide a certain level of evidence on this topic. In summary, saline has negative effects on the endothelial layers and therefore may compromise graft patency. Related factors, such as distension pressure, may outbalance the initial benefit of autologous whole blood or storage solutions and intensify the harmful effects of warm saline. In addition, there is no uniform consent on the superiority of autologous whole blood for vein graft storage. This may open the door to alternatives such as the University of Wisconsin solution or one of the specific designed storage solutions like TiProtec™ or Somaluthion™. Whether these preservation solutions are superior or advantageous remains the subject of further studies.