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.

Semi-supervised classification based on subspace sparse representation

Graph plays an important role in graph-based semi-supervised classification. However, due to noisy and redundant features in high-dimensional data, it is not a trivial job to construct a well-structured graph on high-dimensional samples. In this paper, we take advantage of sparse representation in random subspaces for graph construction and propose a method called Semi-Supervised Classification based on Subspace Sparse Representation, SSC-SSR in short. SSC-SSR first generates several random subspaces from the original space and then seeks sparse representation coefficients in these subspaces. Next, it trains semi-supervised linear classifiers on graphs that are constructed by these coefficients. Finally, it combines these classifiers into an ensemble classifier by minimizing a linear regression problem. Unlike traditional graph-based semi-supervised classification methods, the graphs of SSC-SSR are data-driven instead of man-made in advance. Empirical study on face images classification tasks demonstrates that SSC-SSR not only has superior recognition performance with respect to competitive methods, but also has wide ranges of effective input parameters.

Secure universal designated verifier signature without random oracles

In Asiacrypt 2003, the concept of universal designated verifier signature (UDVS) was introduced by Steinfeld, Bull, Wang and Pieprzyk. In the new paradigm, any signature holder (not necessarily the signer) can designate the publicly verifiable signature to any desired designated verifier (using the verifier’s public key), such that only the designated verifier can believe that the signature holder does have a valid publicly verifiable signature, and hence, believes that the signer has signed the message. Any other third party cannot believe this fact because this verifier can use his secret key to create a valid UDVS which is designated to himself. In ACNS 2005, Zhang, Furukawa and Imai proposed the first UDVS scheme without random oracles. In this paper, we give a security analysis to the scheme of Zhang et al. and propose a novel UDVS scheme without random oracles based on Waters’ signature scheme, and prove that our scheme is secure under the Gap Bilinear Diffie Hellman assumption

Thinking with the body: Mind and movement in the work of Wayne McGregor | Random Dance

Thinking with the Body was an exhibition at London's Wellcome Collection, offering a glimpse into Wayne McGregor | Random Dance's interdisciplinary research and the impact it has in the rehearsal studio. Staged in the run-up to the first performances of Atomos at Sadler's Wells (Oct 2013), the exhibition featured the results of over a decade of interdisciplinary research into choreographic creativity which has been applied in the studio, in dance education, and to increase public understanding.

Wellcome Collection is a free visitor destination exploring the connections between medicine, life and art in the past, present and future. Wellcome Collection is part of the Wellcome Trust, a global charitable foundation dedicated to achieving improvements in human and animal health.

The exhibition finished on 27 October 2013, but the film exhibits are still available to view online.

Efficient mining of top-k breaker emerging subgraph patterns from graph datasets

This paper introduces a new type of discriminative subgraph pattern called breaker emerging subgraph pattern by introducing three constraints and two new concepts: base and breaker. A breaker emerging sub-graph pattern consists of three subpatterns: a con-strained emerging subgraph pattern, a set of bases and a set of breakers. An efficient approach is pro-posed for the discovery of top-k breaker emerging sub-graph patterns from graph datasets. Experimental re-sults show that the approach is capable of efficiently discovering top-k breaker emerging subgraph patterns from given datasets, is more efficient than two previ-ous methods for mining discriminative subgraph pat-terns. The discovered top-k breaker emerging sub-graph patterns are more informative, more discrim-inative, more accurate and more compact than the minimal distinguishing subgraph patterns. The top-k breaker emerging patterns are more useful for sub-structure analysis, such as molecular fragment analy-sis. © 2009, Australian Computer Society, Inc.

Stabilized sparse ordinal regression for medical risk stratification

The recent wide adoption of electronic medical records (EMRs) presents great opportunities and challenges for data mining. The EMR data are largely temporal, often noisy, irregular and high dimensional. This paper constructs a novel ordinal regression framework for predicting medical risk stratification from EMR. First, a conceptual view of EMR as a temporal image is constructed to extract a diverse set of features. Second, ordinal modeling is applied for predicting cumulative or progressive risk. The challenges are building a transparent predictive model that works with a large number of weakly predictive features, and at the same time, is stable against resampling variations. Our solution employs sparsity methods that are stabilized through domain-specific feature interaction networks. We introduces two indices that measure the model stability against data resampling. Feature networks are used to generate two multivariate Gaussian priors with sparse precision matrices (the Laplacian and Random Walk). We apply the framework on a large short-term suicide risk prediction problem and demonstrate that our methods outperform clinicians to a large margin, discover suicide risk factors that conform with mental health knowledge, and produce models with enhanced stability. © 2014 Springer-Verlag London.

Salt intake assessed by 24 h urinary sodium excretion in a random and opportunistic sample in Australia

The gold standard method for measuring population sodium intake is based on a 24 h urine collection carried out in a random population sample. However, because participant burden is high, response rates are typically low with less than one in four agreeing to provide specimens. At this low level of response it is possible that simply asking for volunteers would produce the same results.

Detection on application layer DDoS using random walk model

Application Layer Distributed Denial of Service (ALDDoS) attacks have been increasing rapidly with the growth of Botnets and Ubiquitous computing. Differentiate to the former DDoS attacks, ALDDoS attacks cannot be efficiently detected, as attackers always adopt legitimate requests with real IP address, and the traffic has high similarity to legitimate traffic. In spite of that, we think, the attackers' browsing behavior will have great disparity from that of the legitimate users'. In this paper, we put forward a novel user behavior-based method to detect the application layer asymmetric DDoS attack. We introduce an extended random walk model to describe user browsing behavior and establish the legitimate pattern of browsing sequences. For each incoming browser, we observe his page request sequence and predict subsequent page request sequence based on random walk model. The similarity between the predicted and the observed page request sequence is used as a criterion to measure the legality of the user, and then attacker would be detected based on it. Evaluation results based on real collected data set has demonstrated that our method is very effective in detecting asymmetric ALDDoS attacks. © 2014 IEEE.

The prevalence of vitamin B12 deficiency in a random sample from the Australian population

 Objective: Vitamin B12 deficiency is common in older adults, and may increase the risk of cognitive impairment. The distribution of vitamin B12 insufficiency in younger age groups is less studied. This study aims to assess the prevalence of vitamin B12 deficiency (<156ρmol/L) and subclinical low-normal levels (156-250ρmol/L) in a large, random sample of the Australian population across the adult life span.
Methods: We examined serum vitamin B12 levels in a random sample of 1,085 men and 1,125 women aged 20-97 years between 1994 and 2006; in the Barwon Statistical Division, a regional area in south eastern Australia that is representative of the socioeconomic status of the Australian population.
Results: The age-standardised prevalence of vitamin B12 deficiency in this cohort of men and women was 3.6%. Subclinical low-normal vitamin B12 levels (156-250ρmol/L) were found in 26%. Serum vitamin B12 levels declined with age among men (p-value <0.001) and were lower in men than women (p-value <0.001). Vitamin B12 levels were higher among supplement users (8.0% of the cohort).
Conclusions: Vitamin B12 levels decline with age, and have been associated with neurodegenerative diseases and cognitive decline. Early intervention by diet education or supplement use to address this age-associated decline in vitamin levels may be an effective strategy to prevent decline in a significant segment of the population. Such intervention may need to start in mid-life (from 50-years of age) before the onset age-related decline in vitamin B12 levels.

On the definition of an kinematic hardening effect graph for sheet metal forming process simulations

The objective of this work is to develop a kinematic hardening effect graph (KHEG) which can be used to evaluate the effect of kinematic hardening on the model accuracy of numerical sheet metal forming simulations and this without the need of complex material characterisation. The virtual manufacturing process design and optimisation depends on the accuracy of the constitutive models used to represent material behaviour. Under reverse strain paths the Bauschinger effect phenomenon is modelled using kinematic hardening models. However, due to the complexity of the experimental testing required to characterise this phenomenon in this work the KHEG is presented as an indicator to evaluate the potential benefit of carrying out these tests. The tool is validated with the classic three point bending process and the U-channel width drawbead process. In the same way, the capability of the KHEG to identify effects in forming processes that do not include forming strain reversals is identified.

Gambling participation and problem gambling severity in a stratified random survey : Findings from the second social and economic impact study of gambling in Tasmania

Demographic characteristics associated with gambling participation and problem gambling severity were investigated in a stratified random survey in Tasmania, Australia. Computer-assisted telephone interviews were conducted in March 2011 resulting in a representative sample of 4,303 Tasmanian residents aged 18 years or older. Overall, 64.8 % of Tasmanian adults reported participating in some form of gambling in the previous 12 months. The most common forms of gambling were lotteries (46.5 %), keno (24.3 %), instant scratch tickets (24.3 %), and electronic gaming machines (20.5 %). Gambling severity rates were estimated at non-gambling (34.8 %), non-problem gambling (57.4 %), low risk gambling (5.3 %), moderate risk (1.8 %), and problem gambling (.7 %). Compared to Tasmanian gamblers as a whole significantly higher annual participation rates were reported by couples with no children, those in full time paid employment, and people who did not complete secondary school. Compared to Tasmanian gamblers as a whole significantly higher gambling frequencies were reported by males, people aged 65 or older, and people who were on pensions or were unable to work. Compared to Tasmanian gamblers as a whole significantly higher gambling expenditure was reported by males. The highest average expenditure was for horse and greyhound racing ($AUD 1,556), double the next highest gambling activity electronic gaming machines ($AUD 767). Compared to Tasmanian gamblers as a whole problem gamblers were significantly younger, in paid employment, reported lower incomes, and were born in Australia. Although gambling participation rates appear to be falling, problem gambling severity rates remain stable. These changes appear to reflect a maturing gambling market and the need for population specific harm minimisation strategies. © 2014 Springer Science+Business Media New York.

Hydrologic landscape regionalisation using deductive classification and random forests

Landscape classification and hydrological regionalisation studies are being increasingly used in ecohydrology to aid in the management and research of aquatic resources. We present a methodology for classifying hydrologic landscapes based on spatial environmental variables by employing non-parametric statistics and hybrid image classification. Our approach differed from previous classifications which have required the use of an a priori spatial unit (e.g. a catchment) which necessarily results in the loss of variability that is known to exist within those units. The use of a simple statistical approach to identify an appropriate number of classes eliminated the need for large amounts of post-hoc testing with different number of groups, or the selection and justification of an arbitrary number. Using statistical clustering, we identified 23 distinct groups within our training dataset. The use of a hybrid classification employing random forests extended this statistical clustering to an area of approximately 228,000 km2 of south-eastern Australia without the need to rely on catchments, landscape units or stream sections. This extension resulted in a highly accurate regionalisation at both 30-m and 2.5-km resolution, and a less-accurate 10-km classification that would be more appropriate for use at a continental scale. A smaller case study, of an area covering 27,000 km2, demonstrated that the method preserved the intra- and inter-catchment variability that is known to exist in local hydrology, based on previous research. Preliminary analysis linking the regionalisation to streamflow indices is promising suggesting that the method could be used to predict streamflow behaviour in ungauged catchments. Our work therefore simplifies current classification frameworks that are becoming more popular in ecohydrology, while better retaining small-scale variability in hydrology, thus enabling future attempts to explain and visualise broad-scale hydrologic trends at the scale of catchments and continents.