Robust network traffic classification

As a fundamental tool for network management and security, traffic classification has attracted increasing attention in recent years. A significant challenge to the robustness of classification performance comes from zero-day applications previously unknown in traffic classification systems. In this paper, we propose a new scheme of Robust statistical Traffic Classification (RTC) by combining supervised and unsupervised machine learning techniques to meet this challenge. The proposed RTC scheme has the capability of identifying the traffic of zero-day applications as well as accurately discriminating predefined application classes. In addition, we develop a new method for automating the RTC scheme parameters optimization process. The empirical study on real-world traffic data confirms the effectiveness of the proposed scheme. When zero-day applications are present, the classification performance of the new scheme is significantly better than four state-of-the-art methods: random forest, correlation-based classification, semi-supervised clustering, and one-class SVM.

A review of methods and tools to assess the implementation of government policies to create healthy food environments for preventing obesity and diet-related non-communicable diseases

BACKGROUND: Policies to create healthy food environments are recognized as critical components of efforts to prevent obesity and diet-related non-communicable diseases. There has not been a systematic review of existing methods and tools used to assess the implementation of these government policies. The purpose of this study was to review methods and tools used for assessing the implementation of government policies to create healthy food environments. The study conducted a systematic literature search. Multiple databases as well as the grey literature were searched. All study designs and review papers on assessing the implementation of government policies to create healthy food environments were included. A quality assessment of the methods and tools identified from relevant studies was carried out using the following four criteria: comprehensiveness, relevance, generalizability and feasibility. This quality assessment was completed by two independent reviewers. RESULTS: The review identified 52 studies across different policy areas, levels and settings. Self-administered questionnaires and policy checklists were most commonly applied to assess the extent of policy implementation, whereas semi-structured interviews were most commonly used to evaluate the implementation process. Measures varied widely, with the existence of policy implementation the aspect most commonly assessed. The most frequently identified barriers and facilitators for policy implementation were infrastructure support, resources and stakeholder engagement. The assessment of policy implementation on food environments was usually undertaken in combination with other policy areas, particularly nutrition education and physical activity. Three tools/methods were rated 'high' quality and 13 tools/methods received 'medium' quality ratings. CONCLUSIONS: Harmonization of the available high-quality methods and tools is needed to ensure that assessment of government policy implementation can be compared across different countries and settings and over time. This will contribute to efforts to increase government accountability for their actions to improve the healthiness of food environments.