An effective network traffic classification method with unknown flow detection

Traffic classification technique is an essential tool for network and system security in the complex environments such as cloud computing based environment. The state-of-the-art traffic classification methods aim to take the advantages of flow statistical features and machine learning techniques, however the classification performance is severely affected by limited supervised information and unknown applications. To achieve effective network traffic classification, we propose a new method to tackle the problem of unknown applications in the crucial situation of a small supervised training set. The proposed method possesses the superior capability of detecting unknown flows generated by unknown applications and utilizing the correlation information among real-world network traffic to boost the classification performance. A theoretical analysis is provided to confirm performance benefit of the proposed method. Moreover, the comprehensive performance evaluation conducted on two real-world network traffic datasets shows that the proposed scheme outperforms the existing methods in the critical network environment.

Improving renal patient care without compromising safety: interactive simulated e-learning

The nephrology educators network [NEN] recognised in 2007 that inequities existed in the access and delivery of evidence based renal education programs particularly to nurses in regional and remote areas. To address this, a web-based approach to learning, through the development of peer reviewed, interactive nephrology e-learning programs was adopted. These programs aligned with the tenets of e-learning instructional design and afforded more effective and consistent clinical support and induction for nurses in the renal specialty. The e-learning programs promote a standardised evidence-based approach to nephrology education and were developed by content experts from across Australia and New Zealand. The design methodology avoided the duplication of resources while also encouraging knowledge transfer between participating health organisations.

This paper will discuss the development and successful implementation of these e-learning programs across renal healthcare units in Australasia. Implemented packages include: Introduction to Buttonhole Cannulation – featuring an interactive ultrasound and cannulation application; Introduction to Haemodialysis; Introduction to Peritoneal Dialysis [PD], featuring simulated PD machines, allowing for the teaching of troubleshooting without compromising patient safety. E-learning programs are further supported through interactive case scenarios that present unfolding real world simulations and enable learners to meet different patients and manage their care while learning about key messages relating to renal health. Modules currently in development include; Acute Kidney Injury; Fluid Assessment, Water Quality and Vascular Access. The implementation of these programs assist the facilitation of positive change in teaching and learning practices in nephrology nursing aimed at improving patient outcomes.

Supporting athlete selection and strategic planning in track cycling omnium: A statistical and machine learning approach

This article describes the implementation of machine learning techniques that assist cycling experts in the crucial decision-making processes for athlete selection and strategic planning in the track cycling omnium. The omnium is a multi-event competition that was included in the Olympic Games for the first time in 2012. Presently, selectors and cycling coaches make decisions based on experience and opinion. They rarely have access to knowledge that helps predict athletic performances. The omnium presents a unique and complex decision-making challenge as it is not clear what type of athlete is best suited to the omnium (e.g., sprint or endurance specialist) and tactical decisions made by the coach and athlete during the event will have significant effects on the overall performance of the athlete. In the present work, a variety of machine learning techniques were used to analyze omnium competition data from the World Championships since 2007. The analysis indicates that sprint events have slightly more influence in determining the medalists, than endurance-based events. Using a probabilistic analysis, we created a model of performance prediction that provides an unprecedented level of supporting information that assists coaches with strategic and tactical decisions during the omnium.

Bayesian model averaging of load demand forecasts from neural network models

Creating a set of a number of neural network (NN) models in an ensemble and accumulating them can achieve better overview capability as compared to single neural network. Neural network ensembles are designed to provide solutions to particular problems. Many researchers and academicians have adopted this NN ensemble technique, especially in machine learning, and has been applied in various fields of engineering, medicine and information technology. This paper present a robust aggregation methodology for load demand forecasting based on Bayesian Model Averaging of a set of neural network models in an ensemble. This paper estimate a vector of coefficient for individual NN models' forecasts using validation data-set. These coefficients, also known as weights, are equal to posterior probabilities of the models generating the forecasts. These BMA weights are then used in combining forecasts generated from NN models with test data-set. By comparing the Bayesian results with the Simple Averaging method, it was observed that benefits are obtained by utilizing an advanced method like BMA for forecast combinations.

Artificial neural network analysis of twin tunnelling-induced ground settlements

In this paper, we apply a computational intelligence method for tunnelling settlement prediction. A supervised feed forward back propagation neural network is used to predict the surface settlement during twin-tunnelling while surface buildings are considered in the models. The performance of the statistical neural network structure is tested on a dataset provided by numerical parametric studies conducted by ABAQUS software based on Shiraz line 1 metro data. Six input variables are fed to neural network model for predicting the surface settlement. These include tunnel center depth, distance between centerlines of twin tunnels, buildings width and building bending stiffness, and building weight and distance to tunnel centerline. Simulation results indicate that the proposed NN models are able to accurately predict the surface settlement.

Intelligent traffic light control of isolated intersections using machine learning methods

Traffic congestion is one of the major problems in modern cities. This study applies machine learning methods to determine green times in order to minimize in an isolated intersection. Q-learning and neural networks are applied here to set signal light times and minimize total delays. It is assumed that an intersection behaves in a similar fashion to an intelligent agent learning how to set green times in each cycle based on traffic information. Here, a comparison between Q-learning and neural network is presented. In Q-learning, considering continuous green time requires a large state space, making the learning process practically impossible. In contrast to Q-learning methods, the neural network model can easily set the appropriate green time to fit the traffic demand. The performance of the proposed neural network is compared with two traditional alternatives for controlling traffic lights. Simulation results indicate that the application of the proposed method greatly reduces the total delay in the network compared to the alternative methods.

Exploring distributed leadership for the quality management of online learning environments

Online learning environments (OLEs) are complex information technology (IT) systems that intersect with many areas of university organisation. Distributed models of leadership have been proposed as appropriate for the good governance of OLEs. Based on theoretical and empirical research, a group of Australian universities proposed a framework for the quality management of OLEs, and sought to validate the model via a survey of Australasian university representatives with OLE leadership responsibility. For the framework elements: Planning and Resourcing were rated most important; Organisational structure was rated least important; Technologies were rated low in importance and high in satisfaction; Resourcing and Evaluation were rated low in satisfaction; and Resourcing had the highest rating of importance coupled with low satisfaction. Considering distributed leadership in their institution, respondents reported that the organisational alignments represented by 'official' reporting and peer relationships were significantly more important and more effective than the organisational alignments linking the formal and informal leaders. From a range of desirable characteristics of distributed leadership, 'continuity and sustainability' received the highest rating of importance and a low rating of 'in evidence' - there are concerns about the sustainability of distributed leadership for the governance of OLEs in universities.

Bend me, shape me, anyway you want me: constructing teacher identities across different learning paradigms

This article discusses one key finding from a qualitative study that investigated the experiences of overseas-born, ethnic minority early childhood pre-service teachers in New Zealand. Data were collected through interviews with recently graduated Bachelor of Teaching (Early Childhood Education) teachers and early childhood lecturers. Until they were supported to incorporate their cultural knowledges into their new learning, most graduate participants found there was little to which they could relate in the pedagogies and content of their teacher education courses. This article makes recommendations for the planning, preparation and delivery of early childhood teacher education.

Learning to dance with a human

Artificial neural networks are an effective means of allowing software agents to learn about and filter aspects of their domain. In this paper we explore the use of artificial neural networks in the context of dance performance. The software agent’s neural network is presented with movement in the form of motion capture streams, both pre-recorded and live. Learning can be viewed as analogous to rehearsal, recognition and response to performance. The interrelationship between the software agent and dancer throughout the process is considered as a potential means of allowing the agent to function beyond its limited self-contained capability.

Remix the social: remix the learning

This paper reports on how the findings from an eighteen month secondary school action research study, in which social media was integrated into face-to-face classroom practice, was used to inform a fourth year undergraduate teacher-education unit at Deakin University in Australia. The school action research study was conducted in an Australian public secondary school. Students were aged between 13 and 16 years of age and a total of thirteen classes were involved. In each of the three semesters of data collection, one online social network was shared with up to seven classes and each class had approximately 25 students. Blogs, Groups, Chats, Discussion Forums, Web 2.0 tools and a wide range of student-generated content were shared online, within a class and between classes. Students were encouraged to interact and to share their thoughts and ideas about planning as well as using their out-of-school skills and knowledge. Each topic, within each class, was one action research cycle, using Armstrong and Moore’s (2004) framework. By following Graham Nuthall’s lens on learning, the researcher was able to focus on teaching as being about sensitivity and adaptation: adjusting to the here-and-now circumstances of particular students (Nuthall 2007). Elements of self organisation with spontaneous and strange attractors were identified throughout the study and these made links to Doll’s (1993) post-modern perspective of chaotic behaviour and the complexity of Hayles’ (1990) ‘disorderly order’.

Network traffic clustering using random forest proximities

The recent years have seen extensive work on statistics-based network traffic classification using machine learning (ML) techniques. In the particular scenario of learning from unlabeled traffic data, some classic unsupervised clustering algorithms (e.g. K-Means and EM) have been applied but the reported results are unsatisfactory in terms of low accuracy. This paper presents a novel approach for the task, which performs clustering based on Random Forest (RF) proximities instead of Euclidean distances. The approach consists of two steps. In the first step, we derive a proximity measure for each pair of data points by performing a RF classification on the original data and a set of synthetic data. In the next step, we perform a K-Medoids clustering to partition the data points into K groups based on the proximity matrix. Evaluations have been conducted on real-world Internet traffic traces and the experimental results indicate that the proposed approach is more accurate than the previous methods.

Classifying network traffic in the big data era

With the arrival of Big Data Era, properly utilizing the power of big data is becoming increasingly essential for the strength and competitiveness of businesses and organizations. We are facing grand challenges from big data from different perspectives, such as processing, communication, security, and privacy. In this talk, we discuss the big data challenges in network traffic classification and our solutions to the challenges. The significance of the research lies in the fact that each year the network traffic increase exponentially on the current Internet. Traffic classification has wide applications in network management, from security monitoring to quality of service measurements. Recent research tends to apply machine-learning techniques to flow statistical feature based classification methods. In this talk, we propose a series of novel approaches for traffic classification, which can improve the classification performance effectively by incorporating correlated information into the classification process. We analyze the new classification approaches and their performance benefit from both theoretical and empirical perspectives. A large number of experiments are carried out on two real-world traffic datasets to validate the proposed approach. The results show the traffic classification performance can be improved significantly even under the extreme difficult circumstance of very few training samples. Our work has significant impact on security applications.

A review of online learning in supervised neural networks

Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feedforward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented.