Automatic network traffic classification

The thesis addresses a number of critical problems in regard to fully automating the process of network traffic classification and protocol identification. Several effective solutions based on statistical analysis and machine learning techniques are proposed, which significantly reduce the requirements for human interventions in network traffic classification systems.

2Loud?: Community mapping of exposure to traffic noise with mobile phones

Abstract: Despite ample medical evidence of the adverse impacts of traffic noise on health, most policies for traffic noise management are arbitrary or incomplete, resulting in serious social and economic impacts. Surprisingly, there is limited information about citizen’s exposure to traffic noise worldwide. This paper presents the 2Loud? mobile phone application, developed and tested as a methodology to monitor, assess and map the level of exposure to traffic noise of citizens with focus on the night period and indoor locations, since sleep disturbance is one of the major triggers for ill health related to traffic noise. Based on a community participation experiment using the 2Loud? mobile phone application in a region close to freeways in Australia, the results of this research indicates a good level of accuracy for the noise monitoring by mobile phones and also demonstrates significant levels of indoor night exposure to traffic noise in the study area. The proposed methodology, through the data produced and the participatory process involved, can potentially assist in planning and management towards healthier urban environments.

Participatory sensing and education: helping the community mitigate sleep disturbance from traffic noise

Purpose – This paper aims to present a project in Australia, where participants use smartphones to measure the level of traffic noise in their homes. Through the data collected, participants learn if they are subjected to sleep disturbances and, if so, understand how they can manage the issue to protect their health. The project also has a secondary purpose: the local council would like to engage its community through the exercise and be seen as acting on the community’s problems.

ANFIS traffic signal controller for an isolated intersection

Traffic signal controlling is one of the solutions to reduce the traffic congestion in cities. To set appropriate green times for traffic signal lights, we have applied Adaptive Neuro-Fuzzy Inference System (ANFIS) method in traffic signal controllers. ANFIS traffic signal controller is used for controlling traffic congestion of a single intersection with the purpose of minimizing travel delay time. The ANFIS traffic controller is an intelligent controller that learns to set an appropriate green time for each phase of traffic signal lights at the start of the phase and based on the traffic information. The controller uses genetic algorithm to tune ANFIS parameters during learning time. The results of the experiments show higher performance of the ANFIS traffic signal controller compared to three other traffic controllers that are developed as benchmarks. One of the benchmarks is GA-FLC (Araghi et al., 2014), next one is a fixed-FLC, and a fixed-time controller with three different values for green phase. Results show the higher performance of ANFIS controller.

Detection and defense of application-layer DDoS attacks in backbone web traffic

Web servers are usually located in a well-organized data center where these servers connect with the outside Internet directly through backbones. Meanwhile, the application-layer distributed denials of service (AL-DDoS) attacks are critical threats to the Internet, particularly to those business web servers. Currently, there are some methods designed to handle the AL-DDoS attacks, but most of them cannot be used in heavy backbones. In this paper, we propose a new method to detect AL-DDoS attacks. Our work distinguishes itself from previous methods by considering AL-DDoS attack detection in heavy backbone traffic. Besides, the detection of AL-DDoS attacks is easily misled by flash crowd traffic. In order to overcome this problem, our proposed method constructs a Real-time Frequency Vector (RFV) and real-timely characterizes the traffic as a set of models. By examining the entropy of AL-DDoS attacks and flash crowds, these models can be used to recognize the real AL-DDoS attacks. We integrate the above detection principles into a modularized defense architecture, which consists of a head-end sensor, a detection module and a traffic filter. With a swift AL-DDoS detection speed, the filter is capable of letting the legitimate requests through but the attack traffic is stopped. In the experiment, we adopt certain episodes of real traffic from Sina and Taobao to evaluate our AL-DDoS detection method and architecture. Compared with previous methods, the results show that our approach is very effective in defending AL-DDoS attacks at backbones. © 2013 Elsevier B.V. All rights reserved.

Optimal design of traffic signal controller using neural networks and fuzzy logic systems

This paper aims at optimally adjusting a set of green times for traffic lights in a single intersection with the purpose of minimizing travel delay time and traffic congestion. Neural network (NN) and fuzzy logic system (FLS) are two methods applied to develop intelligent traffic timing controller. For this purpose, an intersection is considered and simulated as an intelligent agent that learns how to set green times in each cycle based on the traffic information. The training approach and data for both these learning methods are similar. Both methods use genetic algorithm to tune their parameters during learning. Finally, The performance of the two intelligent learning methods is compared with the performance of simple fixed-time method. Simulation results indicate that both intelligent methods significantly reduce the total delay in the network compared to the fixed-time method.

Optimal fuzzy traffic signal controller for an isolated intersection

  This paper aims at optimally adjusting a set of green times for traffic lights in a single intersection with the purpose of minimizing travel delay time and traffic congestion. Fuzzy logic system (FLS) is the method applied to develop the intelligent traffic timing controller. For this purpose, an intersection is considered and simulated as an intelligent agent that learns how to set green times in each cycle based on the traffic information. The FLS controller (FLC) uses genetic algorithm to tune its parameters during learning phase. Finally, The performance of the intelligent FLC is compared with the performance of a FLC with predefined parameters and three simple fixed-time controller. Simulation results indicate that intelligent FLC significantly reduces the total delay in the network compared to the fixed-time method and FLC with manual parameter setting.

Internet traffic classification using constrained clustering

Statistics-based Internet traffic classification using machine learning techniques has attracted extensive research interest lately, because of the increasing ineffectiveness of traditional port-based and payload-based approaches. In particular, unsupervised learning, that is, traffic clustering, is very important in real-life applications, where labeled training data are difficult to obtain and new patterns keep emerging. Although previous studies have applied some classic clustering algorithms such as K-Means and EM for the task, the quality of resultant traffic clusters was far from satisfactory. In order to improve the accuracy of traffic clustering, we propose a constrained clustering scheme that makes decisions with consideration of some background information in addition to the observed traffic statistics. Specifically, we make use of equivalence set constraints indicating that particular sets of flows are using the same application layer protocols, which can be efficiently inferred from packet headers according to the background knowledge of TCP/IP networking. We model the observed data and constraints using Gaussian mixture density and adapt an approximate algorithm for the maximum likelihood estimation of model parameters. Moreover, we study the effects of unsupervised feature discretization on traffic clustering by using a fundamental binning method. A number of real-world Internet traffic traces have been used in our evaluation, and the results show that the proposed approach not only improves the quality of traffic clusters in terms of overall accuracy and per-class metrics, but also speeds up the convergence.

Dividing traffic sub-areas based on a parallel K-means algorithm

In order to alleviate the traffic congestion and reduce the complexity of traffic control and management, it is necessary to exploit traffic sub-areas division which should be effective in planing traffic. Some researchers applied the K-Means algorithm to divide traffic sub-areas on the taxi trajectories. However, the traditional K-Means algorithms faced difficulties in processing large-scale Global Position System(GPS) trajectories of taxicabs with the restrictions of memory, I/O, computing performance. This paper proposes a Parallel Traffic Sub-Areas Division(PTSD) method which consists of two stages, on the basis of the Parallel K-Means(PKM) algorithm. During the first stage, we develop a process to cluster traffic sub-areas based on the PKM algorithm. Then, the second stage, we identify boundary of traffic sub-areas on the base of cluster result. According to this method, we divide traffic sub-areas of Beijing on the real-word (GPS) trajectories of taxicabs. The experiment and discussion show that the method is effective in dividing traffic sub-areas.

On addressing the imbalance problem : A correlated KNN approach for network traffic classification

With the arrival of big data era, the Internet traffic is growing exponentially. A wide variety of applications arise on the Internet and traffic classification is introduced to help people manage the massive applications on the Internet for security monitoring and quality of service purposes. A large number of Machine Learning (ML) algorithms are introduced to deal with traffic classification. A significant challenge to the classification performance comes from imbalanced distribution of data in traffic classification system. In this paper, we proposed an Optimised Distance-based Nearest Neighbor (ODNN), which has the capability of improving the classification performance of imbalanced traffic data. We analyzed the proposed ODNN approach and its performance benefit from both theoretical and empirical perspectives. A large number of experiments were implemented on the real-world traffic dataset. The results show that the performance of “small classes” can be improved significantly even only with small number of training data and the performance of “large classes” remains stable.

Internet traffic clustering with side information

Internet traffic classification is a critical and essential functionality for network management and security systems. Due to the limitations of traditional port-based and payload-based classification approaches, the past several years have seen extensive research on utilizing machine learning techniques to classify Internet traffic based on packet and flow level characteristics. For the purpose of learning from unlabeled traffic data, some classic clustering methods have been applied in previous studies but the reported accuracy results are unsatisfactory. In this paper, we propose a semi-supervised approach for accurate Internet traffic clustering, which is motivated by the observation of widely existing partial equivalence relationships among Internet traffic flows. In particular, we formulate the problem using a Gaussian Mixture Model (GMM) with set-based equivalence constraint and propose a constrained Expectation Maximization (EM) algorithm for clustering. Experiments with real-world packet traces show that the proposed approach can significantly improve the quality of resultant traffic clusters. © 2014 Elsevier Inc.

Breakdown in central motor control can be attenuated by motor practice and neuro-modulation of the primary motor cortex

The performance of a repetitive index finger flexion–extension task at maximal voluntary rate (MVR) begins to decline just a few seconds into the task and we have previously postulated that this breakdown has a central origin. To test this hypothesis, we have combined two objectives; to determine whether motor practice can lessen the performance deterioration in an MVR task, and whether further gains can be achieved with a transcranial magnetic stimulation (TMS) protocol that increases corticomotor excitability (CME). Eleven right-handed subjects participated in a randomized crossover study design that consisted of a 15-min interventional TMS at I-wave periodicity (ITMS) and single-pulsed Sham intervention prior to six 10-s practice sets of a repetitive finger flexion–extension task at MVR. Motor-evoked potentials (MEPs) were recorded from the first dorsal interosseous muscle. The starting movement rate, and the percentage decline in rate by the end of the MVR were quantitated. Training of the MVR task improved the sustainability of the task by reducing the decline in movement rate. CME increased steadily after each training bout, and this increase was maintained up to 20 min after the last bout. ITMS further increased CME, and was associated with an increase in both the starting rate of the MVR task and its sustainability, when compared to Sham. The results implicate central motor processes in the performance and sustainability of the MVR task, and indicate that MVR kinematics can improve with short-term training and with non-invasive neuro-modulation.

A review on computational intelligence methods for controlling traffic signal timing

Urban traffic as one of the most important challenges in modern city life needs practically effective and efficient solutions. Artificial intelligence methods have gained popularity for optimal traffic light control. In this paper, a review of most important works in the field of controlling traffic signal timing, in particular studies focusing on Q-learning, neural network, and fuzzy logic system are presented. As per existing literature, the intelligent methods show a higher performance compared to traditional controlling methods. However, a study that compares the performance of different learning methods is not published yet. In this paper, the aforementioned computational intelligence methods and a fixed-time method are implemented to set signals times and minimize total delays for an isolated intersection. These methods are developed and compared on a same platform. The intersection is treated as an intelligent agent that learns to propose an appropriate green time for each phase. The appropriate green time for all the intelligent controllers are estimated based on the received traffic information. A comprehensive comparison is made between the performance of Q-learning, neural network, and fuzzy logic system controller for two different scenarios. The three intelligent learning controllers present close performances with multiple replication orders in two scenarios. On average Q-learning has 66%, neural network 71%, and fuzzy logic has 74% higher performance compared to the fixed-time controller.

High breakdown bundle adjustment

Identifying the parameters of a model such that it best fits an observed set of data points is fundamental to the majority of problems in computer vision. This task is particularly demanding when portions of the data has been corrupted by gross outliers, measurements that are not explained by the assumed distributions. In this paper we present a novel method that uses the Least Quantile of Squares (LQS) estimator, a well known but computationally demanding high-breakdown estimator with several appealing theoretical properties. The proposed method is a meta-algorithm, based on the well established principles of proximal splitting, that allows for the use of LQS estimators while still retaining computational efficiency. Implementing the method is straight-forward as the majority of the resulting sub-problems can be solved using existing standard bundle-adjustment packages. Preliminary experiments on synthetic and real image data demonstrate the impressive practical performance of our method as compared to existing robust estimators used in computer vision.