High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning

High-dimensional problem domains pose significant challenges for anomaly detection. The presence of irrelevant features can conceal the presence of anomalies. This problem, known as the '. curse of dimensionality', is an obstacle for many anomaly detection techniques. Building a robust anomaly detection model for use in high-dimensional spaces requires the combination of an unsupervised feature extractor and an anomaly detector. While one-class support vector machines are effective at producing decision surfaces from well-behaved feature vectors, they can be inefficient at modelling the variation in large, high-dimensional datasets. Architectures such as deep belief networks (DBNs) are a promising technique for learning robust features. We present a hybrid model where an unsupervised DBN is trained to extract generic underlying features, and a one-class SVM is trained from the features learned by the DBN. Since a linear kernel can be substituted for nonlinear ones in our hybrid model without loss of accuracy, our model is scalable and computationally efficient. The experimental results show that our proposed model yields comparable anomaly detection performance with a deep autoencoder, while reducing its training and testing time by a factor of 3 and 1000, respectively.

Traffic matrix prediction and estimation based on deep learning in large-scale IP backbone networks

Network traffic analysis has been one of the most crucial techniques for preserving a large-scale IP backbone network. Despite its importance, large-scale network traffic monitoring techniques suffer from some technical and mercantile issues to obtain precise network traffic data. Though the network traffic estimation method has been the most prevalent technique for acquiring network traffic, it still has a great number of problems that need solving. With the development of the scale of our networks, the level of the ill-posed property of the network traffic estimation problem is more deteriorated. Besides, the statistical features of network traffic have changed greatly in terms of current network architectures and applications. Motivated by that, in this paper, we propose a network traffic prediction and estimation method respectively. We first use a deep learning architecture to explore the dynamic properties of network traffic, and then propose a novel network traffic prediction approach based on a deep belief network. We further propose a network traffic estimation method utilizing the deep belief network via link counts and routing information. We validate the effectiveness of our methodologies by real data sets from the Abilene and GÉANT backbone networks.

Approaches to learning accounting : a cross-cultural study

Purpose – The purpose of this study is to examine the relationship between the cultural background of students and their learning approaches in a first year undergraduate accounting program.

Design/methodology/approach – While prior research in this area has more generally focused on the investigation of the approaches to learning by accounting students, there appears to have been little investigation into the learning approaches of students from different cultures who are studying accounting together at the same institution. The paper presents the results of a study of 550 students enrolled in an undergraduate accounting program at a multi-campus university in Victoria, Australia, which used Biggs' study process questionnaire (SPQ) to assess the approaches to learning utilised by local and Chinese students.

Findings – The results showed that, while there were no significant differences in the use of surface and deep learning strategies by the Chinese and Australian students, there were significant differences in the learning motives of the two groups. Furthermore, the results contradict prior claims that Asian students rely principally on the memorisation and reproduction of factual information as a means of achieving academic success.

Originality/value – The study provides support for the notion that Chinese students may in fact have a culturally induced bias towards seeking understanding through deeper approaches to study.

Student learning orientations : are there differences between age and gender?

The increasing diversity and mobility of students have challenged universities, world over, to review educational courses and delivery to provide a more satisfying learning environment to students. The continuous improvement of the 'quality' of teaching and learning is one of the key goals of universities endeavouring to fulfil their obligations as learning institutions. Using a revised SPQ2F instrument (Biggs, 2003, Biggs and Leung, 2001), this exploratory study undertakes a comparative analysis of the age and gender differences in the learning orientations of two groups of tertiary students in an Australian University. The results indicate that there are no significant differences in the learning orientations of students but on average they seem to demonstrate deep learning than surface learning although they may differ in terms of the learning contexts.

How group composition can influence opportunities for spontaneous learning

Classroom video, and video-stimulated interviews of small group work, in a Grade 5/6 classroom are used to show ways group composition can influence learning opportunities. Vygotsky’s (1933/1966; 1978) learning theory on the spontaneous creation of knowledge as compared to the guidance of an expert other frames this group analysis. Illustrations from two groups show how opportunities to spontaneously create new knowledge can be limited or enhanced by psychological factors associated with the inclination to explore that have been linked to resilience in the form of optimism (Seligman, 1995, Williams, 2003). This study contributes to our knowledge on forming groups to promote deep learning. It raises questions about other ways in which learning may be influenced by optimistic orientation and about building this personal characteristic to enable deep learning.

Scaffolding students' learning in EME150 introduction to learners and learning theory : on looking back

This is a reflective article on the importance scaffolding in the EME 150 unit taught in collaboration with Deakin University Australia. Being the first unit introduced in the second semester of the first academic year, students were given a lot of support to enhance their understanding and learning since this curriculum was solely developed by Deakin University and introduced for the first time in teachers education curriculum. The scaffolding tools discussed in this article enabled students to a) establish deep learning of the theory. b) engage in collaborative and engaged learning which established good ethical relations between students c) transfer learning by applying theory into practice.

Approaches to learning across cultures : The role of assessment

In the context of a broader research study on the intercultural understanding of teachers in Australia, Japan and Thailand, this paper focuses on approaches to learning and the role of assessment in shaping such approaches. Popular contrasts portray Asian learners as compliant and favouring rote memorisation and Western learners as independent and favouring deep, conceptual learning. Yet Asian students frequently outperform their Western counterparts in competitive tests purported to measure higher cognitive skills. Biggs and his associates have challenged the stereotypical view of Asian students as rote learners as a Western misperception. But data from the present cross-cultural study suggest it is more than a Western misperception, being shared by teachers in Japan and Thailand. With this background, this paper then explores the role of assessment through an analysis of examination papers in the three countries at the high stakes, year 12 level. This analysis of the ways in which knowledge and comprehension are assessed identifies different practices across cultures but not ones corresponding to the rhetoric on contrasting approaches to learning. Rather it concludes that assessment tasks classified superficially as comprehension can be approached through memorisation and conversely, those often classified as memorisation can require careful reading, thought and interpretation, while drawing from an extensive knowledge base. A shared understanding of the nature of assessment tasks in different cultures thus has the potential to dissolve the demarcation of culturally embedded learning styles and to enhance deep learning grounded in specialist knowledge for scholars, be they students or teachers, in all cultures.

Student perception of learning approach and teamwork benefits in accounting : a qualitative study

Accounting academics have heeded the call to incorporate team learning activities into the curricula, yet little is known of student perception of teamwork and whether they view it as beneficial to them. This study addresses the gap by utilising qualitative techniques to examine student perception of the benefits of teamwork and what aspects of the teamwork will contribute to their future professional work. Results indicate that students perceive teamwork enables the use of deep learning and, further, that teamwork at the undergraduate level contributes to their future abilities in the profession. The paper ends by presenting implications for accounting educators.

Learning cultures of problem-based learning teams

The learning experiences of first-year engineering students to a newly implemented engineering problem-based learning (PBL) curriculum is reported here, with an emphasis on student approaches to learning. Ethnographic approaches were used for data collection and analysis. This study found that student learning in a PBL team in this setting was mainly influenced by the attitudes, behaviour and learning approaches of the student members in that team. Three different learning cultures that emerged from the analysis of eight PBL teams are reported here. They are the finishing culture, the performing culture and the collaborative learning culture. It was found that the team that used a collaborative approach to learning benefited the most in this PBL setting. Students in this team approached learning at a deep level. The findings of this study imply that students in a problem-based, or project-based, learning setting may not automatically adopt a collaborative learning culture. Hence, it is important for institutions and teachers to identify and consider the factors that influence student learning in their particular setting, provide students with necessary tools and ongoing coaching to nurture deep learning approaches in PBL teams.

The social network virtual design studio : integrated design learning using blended learning environments

Online communications, multimedia, mobile computing and face-to-face learning create blended learning environments to which some Virtual Design Studios (VDS) have reacted to. Social Networks (SN), as instruments for communication, have provided a potentially fruitful operative base for VDS. These technologies transfer communication, leadership, democratic interaction, teamwork, social engagement and responsibility away from the design tutors to the participants. The implementation of Social Network VDS (SNVDS) moved the VDS beyond its conventional realm and enabled students to develop architectural design that is embedded into a community of learners and expertise both online and offline. Problem-based learning (PBL) becomes an iterative and reflexive process facilitating deep learning. The paper discusses details of the SNVDS, its pedagogical implications to PBL, and presents how the SNVDS is successful in enabling architectural students to collaborate and communicate design proposals that integrate a variety of skills, deep learning, knowledge and construction with a rich learning experience.

The challenges of blended learning using a media annotation tool

Blended learning has been evolving as an important approach to learning and teaching in tertiary education. This approach incorporates learning in both online and face-to-face modes and promotes deep learning by incorporating the best of both approaches. An innovation in blended learning is the use of an online media annotation tool (MAT) in combination with face-to-face classes. This tool allows students to annotate their own or teacher-uploaded video adding to their understanding of professional skills in various disciplines in tertiary education. Examination of MAT occurred in 2011 and included nine cohorts of students using the tool. This article canvasses selected data relating to MAT including insights into the use of blended learning focussing on the challenges of combining face-to-face and online learning using a relatively new online tool.

Relationships between vocational interests and learning approaches to advance the quality of student learning in accounting

This study investigates the influence of vocational interests on the learning approach of accounting students at the undergraduate level. It brings together two theoretical models: vocational interests and approaches to learning, to investigate student learning in the accounting discipline. The research focus is supported by more general findings from the education literature which suggest that interest-oriented learning leads to superior approaches to learning. The research was tested using 917 tertiary accounting students across two universities. The associations between vocational interests and learning approaches provide support for the theoretical model linking vocational interests (e.g. conventional) with deep learning approaches in a tertiary accounting environment. There are practical implications for the teaching of accounting with particular reference to whether the current curriculum reinforces the values of those individuals with conventional interests.

DeepSoft: a vision for a deep model of software

Although software analytics has experienced rapid growth as a research area, it has not yet reached its full potential for wide industrial adoption. Most of the existing work in software analytics still relies heavily on costly manual feature engineering processes, and they mainly address the traditional classification problems, as opposed to predicting future events. We present a vision for \emph{DeepSoft}, an \emph{end-to-end} generic framework for modeling software and its development process to predict future risks and recommend interventions. DeepSoft, partly inspired by human memory, is built upon the powerful deep learning-based Long Short Term Memory architecture that is capable of learning long-term temporal dependencies that occur in software evolution. Such deep learned patterns of software can be used to address a range of challenging problems such as code and task recommendation and prediction. DeepSoft provides a new approach for research into modeling of source code, risk prediction and mitigation, developer modeling, and automatically generating code patches from bug reports.

Responding to the learner diversity : an inquiry into the delivery of a second year marketing unit

This paper reports on the outcome of an inquiry into the learner diversity and the delivery of a second year marketing subject in an Australian university. Using Biggs’s revised SPQ2F instrument (Biggs, 2003), it analyses the learning approaches of students and the opportunities for developing teaching strategies for better learning outcomes. The results suggest that overall students seem to adopt deep learning than surface learning though they differ in terms of the learning contexts. Moreover, no significant differences among students in regard to the study approach domains except for minor variation related to specific items in the instrument.

Second life first hand: a teacher perspective

The professional landscape in public relations is changing as new communication and social networking technologies are integrated into day-to-day professional practice. Whilst adoption of such technologies by public relations practitioners is certainly on the increase, their use can still be regarded as limited and application experimental to some degree. However, few could argue that these technologies will be increasingly important to public relations practice in coming years.
In this context, public relations educators must strive to deliver a contemporary curriculum reflective of industry expectations and best practice principles but which also provides students with exposure to new communication contexts and technologies.

The advent of persistent virtual worlds generated by Massively Multiplayer Online Role Playing Games (MMORPGs) and Collaborative Virtual Environments (CVEs) offer new realms for public relations practitioners and educators alike. Virtual worlds potentially provide public relations educators with novel but relevant training grounds for their students. These 3D worlds offer dynamic and authentic learning environments which have the capability to foster deep learning and engender a sense of community within a student cohort in a way that many computer-mediated classrooms sadly lack.

This paper will present the experiences of two tertiary educators’ journey towards a conceptual understanding of the persistent virtual world, Second Life, from a teacher perspective. The paper argues that the successful adoption of new online technologies like Second Life need not be inhibited by preferences for technology or prior ICT skills as long as teaching staff are given the necessary support and training by their institutions coupled with opportunity for familiarisation and experimentation.