Implementation of a network flow lookup circuit for next-generation packet classifiers

This paper presents a lookup circuit with advanced memory techniques and algorithms that examines network packet headers at high throughput rates. Hardware solutions and test scenarios are introduced to evaluate the proposed approach. The experimental results show that the proposed lookup circuit is able to achieve at least 39 million packet header lookups per second, which facilitates the application of next-generation stateful packet classifications at beyond 20Gbps internet traffic throughput rates.

A sequential algorithm for sparse support vector classifiers

Support vector machines (SVMs), though accurate, are not preferred in applications requiring high classification speed or when deployed in systems of limited computational resources, due to the large number of support vectors involved in the model. To overcome this problem we have devised a primal SVM method with the following properties: (1) it solves for the SVM representation without the need to invoke the representer theorem, (2) forward and backward selections are combined to approach the final globally optimal solution, and (3) a criterion is introduced for identification of support vectors leading to a much reduced support vector set. In addition to introducing this method the paper analyzes the complexity of the algorithm and presents test results on three public benchmark problems and a human activity recognition application. These applications demonstrate the effectiveness and efficiency of the proposed algorithm.


--------------------------------------------------------------------------------

Android Malware Detection Using Parallel Machine Learning Classifiers

Mobile malware has continued to grow at an alarming rate despite on-going mitigation efforts. This has been much more prevalent on Android due to being an open platform that is rapidly overtaking other competing platforms in the mobile smart devices market. Recently, a new generation of Android malware families has emerged with advanced evasion capabilities which make them much more difficult to detect using conventional methods. This paper proposes and investigates a parallel machine learning based classification approach for early detection of Android malware. Using real malware samples and benign applications, a composite classification model is developed from parallel combination of heterogeneous classifiers. The empirical evaluation of the model under different combination schemes demonstrates its efficacy and potential to improve detection accuracy. More importantly, by utilizing several classifiers with diverse characteristics, their strengths can be harnessed not only for enhanced Android malware detection but also quicker white box analysis by means of the more interpretable constituent classifiers.

Learning from time series:Supervised Aggregative Feature Extraction

Many modeling problems require to estimate a scalar output from one or more time series. Such problems are usually tackled by extracting a fixed number of features from the time series (like their statistical moments), with a consequent loss in information that leads to suboptimal predictive models. Moreover, feature extraction techniques usually make assumptions that are not met by real world settings (e.g. uniformly sampled time series of constant length), and fail to deliver a thorough methodology to deal with noisy data. In this paper a methodology based on functional learning is proposed to overcome the aforementioned problems; the proposed Supervised Aggregative Feature Extraction (SAFE) approach allows to derive continuous, smooth estimates of time series data (yielding aggregate local information), while simultaneously estimating a continuous shape function yielding optimal predictions. The SAFE paradigm enjoys several properties like closed form solution, incorporation of first and second order derivative information into the regressor matrix, interpretability of the generated functional predictor and the possibility to exploit Reproducing Kernel Hilbert Spaces setting to yield nonlinear predictive models. Simulation studies are provided to highlight the strengths of the new methodology w.r.t. standard unsupervised feature selection approaches. © 2012 IEEE.

Machine Learning for Predictive Maintenance: A Multiple Classifiers Approach

In this paper a multiple classifier machine learning methodology for Predictive Maintenance (PdM) is presented. PdM is a prominent strategy for dealing with maintenance issues given the increasing need to minimize downtime and associated costs. One of the challenges with PdM is generating so called ’health factors’ or quantitative indicators of the status of a system associated with a given maintenance issue, and determining their relationship to operating costs and failure risk. The proposed PdM methodology allows dynamical decision rules to be adopted for maintenance management and can be used with high-dimensional and censored data problems. This is achieved by training multiple classification modules with different prediction horizons to provide different performance trade-offs in terms of frequency of unexpected breaks and unexploited lifetime and then employing this information in an operating cost based maintenance decision system to minimise expected costs. The effectiveness of the methodology is demonstrated using a simulated example and a benchmark semiconductor manufacturing maintenance problem.

Supervised walking in comparison with fitness training for chronic back pain in physiotherapy: results of the SWIFT single-blinded randomized controlled trial (ISRCTN17592092)

Effectiveness of brief/minimal contact self-activation interventions that encourage participation in physical activity (PA) for chronic low back pain (CLBP >12 weeks) is unproven. The primary objective of this assessor-blinded randomized controlled trial was to investigate the difference between an individualized walking programme (WP), group exercise class (EC), and usual physiotherapy (UP, control) in mean change in functional disability at 6 months. A sample of 246 participants with CLBP aged 18 to 65 years (79 men and 167 women; mean age ± SD: 45.4 ± 11.4 years) were recruited from 5 outpatient physiotherapy departments in Dublin, Ireland. Consenting participants completed self-report measures of functional disability, pain, quality of life, psychosocial beliefs, and PA were randomly allocated to the WP (n = 82), EC (n = 83), or UP (n = 81) and followed up at 3 (81%; n = 200), 6 (80.1%; n = 197), and 12 months (76.4%; n = 188). Cost diaries were completed at all follow-ups. An intention-to-treat analysis using a mixed between-within repeated-measures analysis of covariance found significant improvements over time on the Oswestry Disability Index (Primary Outcome), the Numerical Rating Scale, Fear Avoidance-PA scale, and the EuroQol EQ-5D-3L Weighted Health Index (P < 0.05), but no significant between-group differences and small between-group effect sizes (WP: mean difference at 6 months, 6.89 Oswestry Disability Index points, 95% confidence interval [CI] -3.64 to -10.15; EC: -5.91, CI: -2.68 to -9.15; UP: -5.09, CI: -1.93 to -8.24). The WP had the lowest mean costs and the highest level of adherence. Supervised walking provides an effective alternative to current forms of CLBP management.

Tele-Supervised FES-Assisted Exercise for Hemiplegic Upper Limb

Stroke survivors often have upper limb (UL) hemiparesis, limiting their ability to perform activities of daily life (ADLs). Intensive, task-oriented exercise therapy (ET) can improve UL function, but motivation to perform sufficient ET is difficult to maintain. Here we report on a trial in which a workstation was deployed in the homes of chronic stroke survivors to enable tele-coaching of ET in the guise of computer games. Participants performed 6 weeks of 1 hour/day, 5 days/week ET. Hand opening and grasp were assisted with functional electrical stimulation (FES). The primary outcome measure was the Action Research Arm Test (ARAT). Secondary outcome measures included a quantitative test of UL function performed on the workstation, grasp force measurements and transcranial magnetic stimulation (TMS). Improvements were seen in the functional tests, but surprisingly, not in the TMS responses. An important finding was that participants commencing with intermediate functional scores improved the most.

CONCLUSIONS: 1) Daily, tele-supervised FES-ET in chronic stroke survivors is feasible with commercially-available technology. 2) The intervention can significantly improve UL function, particularly in people who start with an intermediate level of function. 3) Significant improvements in UL function can occur in the absence of changes in TMS responses.

Predictive molecular classifiers in colorectal cancer

The introduction of predictive molecular markers has radically enhanced the identification of which patients may benefit from a given treatment. Despite recent controversies, KRAS mutation is currently the most recognized molecular predictive marker in colorectal cancer (CRC), predicting efficacy of anti-epidermal growth factor receptor (anti-EGFR) antibodies. However, other relevant markers have been reported and claimed to identify patients that will benefit from anti-EGFR therapies. This group of markers includes BRAF mutations, PI3KCA mutations, and loss of PTEN expression. Similarly, molecular markers for cytotoxic agents' efficacy also may predict outcome in patients with CRC. This review aims to summarize the most important predictive molecular classifiers in patients with CRC and further discuss any inconsistent or conflicting findings for these molecular classifiers.

Supervised Aggregative Feature Extraction for Big Data Time Series Regression

In many applications, and especially those where batch processes are involved, a target scalar output of interest is often dependent on one or more time series of data. With the exponential growth in data logging in modern industries such time series are increasingly available for statistical modeling in soft sensing applications. In order to exploit time series data for predictive modelling, it is necessary to summarise the information they contain as a set of features to use as model regressors. Typically this is done in an unsupervised fashion using simple techniques such as computing statistical moments, principal components or wavelet decompositions, often leading to significant information loss and hence suboptimal predictive models. In this paper, a functional learning paradigm is exploited in a supervised fashion to derive continuous, smooth estimates of time series data (yielding aggregated local information), while simultaneously estimating a continuous shape function yielding optimal predictions. The proposed Supervised Aggregative Feature Extraction (SAFE) methodology can be extended to support nonlinear predictive models by embedding the functional learning framework in a Reproducing Kernel Hilbert Spaces setting. SAFE has a number of attractive features including closed form solution and the ability to explicitly incorporate first and second order derivative information. Using simulation studies and a practical semiconductor manufacturing case study we highlight the strengths of the new methodology with respect to standard unsupervised feature extraction approaches.

Clustering-Based Ensemble Method as an Alternative to Stacking

One of the most popular techniques of generating classifier ensembles is known as stacking which is based on a meta-learning approach. In this paper, we introduce an alternative method to stacking which is based on cluster analysis. Similar to stacking, instances from a validation set are initially classified by all base classifiers. The output of each classifier is subsequently considered as a new attribute of the instance. Following this, a validation set is divided into clusters according to the new attributes and a small subset of the original attributes of the instances. For each cluster, we find its centroid and calculate its class label. The collection of centroids is considered as a meta-classifier. Experimental results show that the new method outperformed all benchmark methods, namely Majority Voting, Stacking J48, Stacking LR, AdaBoost J48, and Random Forest, in 12 out of 22 data sets. The proposed method has two advantageous properties: it is very robust to relatively small training sets and it can be applied in semi-supervised learning problems. We provide a theoretical investigation regarding the proposed method. This demonstrates that for the method to be successful, the base classifiers applied in the ensemble should have greater than 50% accuracy levels.

Visual outcomes of cataract surgery performed by supervised novice surgeons during training in rural China

To assess the outcomes of cataract surgery performed by novice surgeons during training in a rural programme. Design: Retrospective study. Participants: Three hundred thirty-four patients operated by two trainees under supervision at rural Chinese county hospitals. Methods: Two trainees performed surgeries under supervision. Visual acuity, refraction and examinations were carried out 3 months postoperatively. Main Outcome Measures: Postoperative uncorrected visual acuity, pinhole visual acuity, causes of visual impairment (postoperative uncorrected visual acuity<6/18) Results: Among 518 operated patients, 426 (82.2%) could be contacted and 334 (64.4% of operated patients) completed the examinations. The mean age was 74.1±8.8 years and 62.9% were women. Postoperative uncorrected visual acuity was available in 372 eyes. Among them, uncorrected visual acuity was ≥6/18 in 278 eyes (74.7%) and <6/60 in 60 eyes (16.1%), and 323 eyes (86.8%) had pinhole visual acuity≥6/18 and 38 eyes (10.2%) had pinhole visual acuity<6/60. Main causes of visual impairment were uncorrected refractive error (63.9%) and comorbid eye disease (24.5%). Comorbid eye diseases associated with pinhole visual acuity<6/60 (n=23, 6.2%) included glaucoma, other optic nerve atrophy, vitreous haemorrhage and retinal detachment. Conclusions: The findings suggest that hands-on training remains safe and effective even when not implemented in centralized training centres. Further refinement of the training protocol, providing postoperative refractive services and more accurate preoperative intraocular lens calculations, can help optimize outcomes. © 2012 The Authors Clinical and Experimental Ophthalmology © 2012 Royal Australian and New Zealand College of Ophthalmologists.

Completely supervised training algorithms for B-spline neural networks and neuro-fuzzy systems

Complete supervised training algorithms for B-spline neural networks and fuzzy rule-based systems are discussed. By interducing the relationship between B-spline neural networks and certain types of fuzzy models, training algorithms developed initially for neural networks can be adapted by fuzzy systems.

Supervised training approach using spiking neural networks

One of the basic aspects of some neural networks is their attempt to approximate as much as possible their biological counterparts. The goal is to achieve a simple and robust network, easy to understand and able of simulating the human brain at a computational level. Recently a third generation of neural networks (NN) [1], called Spiking Neural Networks(SNN) was appeared. This new kind of networks use the time of a electrical pulse, or spike, to encode the information. In the first and second generation of NN analog values are used in the communication between neurons.

Classificação de atividades físicas através do uso do acelerómetro do smartphone

Dissertação de natureza científica realizada para a obtenção do grau de Mestre em Engenharia de redes de comunicação e Multimédia