Hierarchical recognition of intentional human gestures for sports video annotation

We present a novel technique for the recognition of complex human gestures for video annotation using accelerometers and the hidden Markov model. Our extension to the standard hidden Markov model allows us to consider gestures at different levels of abstraction through a hierarchy of hidden states. Accelerometers in the form of wrist bands are attached to humans performing intentional gestures, such as umpires in sports. Video annotation is then performed by populating the video with time stamps indicating significant events, where a particular gesture occurs. The novelty of the technique lies in the development of a probabilistic hierarchical framework for complex gesture recognition and the use of accelerometers to extract gestures and significant events for video annotation.

Automatic labeling of sports video using umpire gesture recognition

We present results on an extension to our approach for automatic sports video annotation. Sports video is augmented with accelerometer data from wrist bands worn by umpires in the game. We solve the problem of automatic segmentation and robust gesture classification using a hierarchical hidden Markov model in conjunction with a filler model. The hierarchical model allows us to consider gestures at different levels of abstraction and the filler model allows us to handle extraneous umpire movements. Results are presented for labeling video for a game of Cricket.

Learning discriminative sequence models from partially labelled data for activity recognition

Recognising daily activity patterns of people from low-level sensory data is an important problem. Traditional approaches typically rely on generative models such as the hidden Markov models and training on fully labelled data. While activity data can be readily acquired from pervasive sensors, e.g. in smart environments, providing manual labels to support fully supervised learning is often expensive. In this paper, we propose a new approach based on partially-supervised training of discriminative sequence models such as the conditional random field (CRF) and the maximum entropy Markov model (MEMM). We show that the approach can reduce labelling effort, and at the same time, provides us with the flexibility and accuracy of the discriminative framework. Our experimental results in the video surveillance domain illustrate that these models can perform better than their generative counterpart (i.e. the partially hidden Markov model), even when a substantial amount of labels are unavailable.

Human activity learning and segmentation using partially hidden discriminative models

Learning and understanding the typical patterns in the daily activities and routines of people from low-level sensory data is an important problem in many application domains such as building smart environments, or providing intelligent assistance. Traditional approaches to this problem typically rely on supervised learning and generative models such as the hidden Markov models and its extensions. While activity data can be readily acquired from pervasive sensors, e.g. in smart environments, providing manual labels to support supervised training is often extremely expensive. In this paper, we propose a new approach based on semi-supervised training of partially hidden discriminative models such as the conditional random field (CRF) and the maximum entropy Markov model (MEMM). We show that these models allow us to incorporate both labeled and unlabeled data for learning, and at the same time, provide us with the flexibility and accuracy of the discriminative framework. Our experimental results in the video surveillance domain illustrate that these models can perform better than their generative counterpart, the partially hidden Markov model, even when a substantial amount of labels are unavailable.

Improving the cost-effectiveness of cardiovascular disease prevention in Australia : a modelling study

Background : Cardiovascular disease is the leading cause of death worldwide. Like many countries, Australia is currently changing its guidelines for cardiovascular disease prevention from drug treatment for everyone with 'high blood pressure' or 'high cholesterol', to prevention based on a patient's absolute risk. In this research, we model cost-effectiveness of cardiovascular disease prevention with blood pressure and lipid drugs in Australia under three different scenarios: (1) the true current practice in Australia; (2) prevention as intended under the current guidelines; and (3) prevention according to proposed absolute risk levels. We consider the implications of changing to absolute risk-based cardiovascular disease prevention, for the health of the Australian people and for Government health sector expenditure over the long term.

Methods : We evaluate cost-effectiveness of statins, diuretics, ACE inhibitors, calcium channel blockers and beta-blockers, for Australian men and women, aged 35 to 84 years, who have never experienced a heart disease or stroke event. Epidemiological changes and health care costs are simulated by age and sex in a discrete time Markov model, to determine total impacts on population health and health sector costs over the lifetime, from which we derive cost-effectiveness ratios in 2008 Australian dollars per quality-adjusted life year.

Results : Cardiovascular disease prevention based on absolute risk is more cost-effective than prevention under the current guidelines based on single risk factor thresholds, and is more cost-effective than the current practice, which does not follow current clinical guidelines. Recommending blood pressure-lowering drugs to everyone with at least 5% absolute risk and statin drugs to everyone with at least 10% absolute risk, can achieve current levels of population health, while saving $5.4 billion for the Australian Government over the lifetime of the population. But savings could be as high as $7.1 billion if Australia could match the cheaper price of statin drugs in New Zealand.

Conclusions : Changing to absolute risk-based cardiovascular disease prevention is highly recommended for reducing health sector spending, but the Australian Government must also consider measures to reduce the cost of statin drugs, over and above the legislated price cuts of November 2010.

Which interventions offer best value for money in primary prevention of cardiovascular disease?

Background
Despite many decades of declining mortality rates in the Western world, cardiovascular disease remains the leading cause of death worldwide. In this research we evaluate the optimal mix of lifestyle, pharmaceutical and population-wide interventions for primary prevention of cardiovascular disease.

Methods and Findings
In a discrete time Markov model we simulate the ischaemic heart disease and stroke outcomes and cost impacts of intervention over the lifetime of all Australian men and women, aged 35 to 84 years, who have never experienced a heart disease or stroke event. Best value for money is achieved by mandating moderate limits on salt in the manufacture of bread, margarine and cereal. A combination of diuretic, calcium channel blocker, ACE inhibitor and low-cost statin, for everyone with at least 5% five-year risk of cardiovascular disease, is also cost-effective, but lifestyle interventions aiming to change risky dietary and exercise behaviours are extremely poor value for money and have little population health benefit.

Conclusions
There is huge potential for improving efficiency in cardiovascular disease prevention in Australia. A tougher approach from Government to mandating limits on salt in processed foods and reducing excessive statin prices, and a shift away from lifestyle counselling to more efficient absolute risk-based prescription of preventive drugs, could cut health care costs while improving population health.

Generative models for automatic recognition of human daily activities from a single triaxial accelerometer

In this work, we compare two generative models including Gaussian Mixture Model (GMM) and Hidden Markov Model (HMM) with Support Vector Machine (SVM) classifier for the recognition of six human daily activity (i.e., standing, walking, running, jumping, falling, sitting-down) from a single waist-worn tri-axial accelerometer signals through 4-fold cross-validation and testing on a total of thirteen subjects, achieving an average recognition accuracy of 96.43% and 98.21% in the first experiment and 95.51% and 98.72% in the second, respectively. The results demonstrate that both HMM and GMM are not only able to learn but also capable of generalization while the former outperformed the latter in the recognition of daily activities from a single waist worn tri-axial accelerometer. In addition, these two generative models enable the assessment of human activities based on acceleration signals with varying lengths.

Resisting web proxy-based HTTP attacks by temporal and spatial locality behavior

A novel server-side defense scheme is proposed to resist the Web proxy-based distributed denial of service attack. The approach utilizes the temporal and spatial locality to extract the behavior features of the proxy-to-server traffic, which makes the scheme independent of the traffic intensity and frequently varying Web contents. A nonlinear mapping function is introduced to protect weak signals from the interference of infrequent large values. Then, a new hidden semi-Markov model parameterized by Gaussian-mixture and Gamma distributions is proposed to describe the time-varying traffic behavior of Web proxies. The new method reduces the number of parameters to be estimated, and can characterize the dynamic evolution of the proxy-to-server traffic rather than the static statistics. Two diagnosis approaches at different scales are introduced to meet the requirement of both fine-grained and coarse-grained detection. Soft control is a novel attack response method proposed in this work. It converts a suspicious traffic into a relatively normal one by behavior reshaping rather than rudely discarding. This measure can protect the quality of services of legitimate users. The experiments confirm the effectiveness of the proposed scheme.

Link between vertical and horizontal movement patterns of cod in the North Sea

We used a geolocation method based on tidal amplitude and water depth to assess the horizontal movements of 14 cod Gadus morhua equipped with time-depth recorders (TDR) in the North Sea and English Channel. Tracks ranged from 40 to 468 d and showed horizontal movements of up to 455 km and periods of continuous localised residence of up to 360 d. Cod spent time both in midwater (43% of total time) and near the seabed (57% of total time). A variety of common vertical movement patterns were seen within periods of both residence and directed horizontal movement. Hence particular patterns of vertical movement could not unequivocally define periods of migration or localised residence. After long horizontal movements, cod tended to adopt resident behaviour for several months and then return to broadly the same location where they were tagged, indicating a geospatial instinct. The results suggest that residence and homing behaviour are important features of Atlantic cod behaviour.

Adefovir dipivoxil and pegylated interferon alpha for the treatment of chronic hepatitis B: an updated systematic review and economic evaluation

To update and extend a 2006 report on the clinical effectiveness and cost-effectiveness of adefovir dipivoxil (ADV) and pegylated interferon alpha (PEG-alpha) for the treatment of chronic hepatitis B (CHB). Thirteen bibliographic databases were searched including MEDLINE, EMBASE and the Cochrane Library. Searches were run from the beginning of 2005 to September 2007. For the clinical effectiveness review, randomised controlled trials (RCTs) comparing ADV, PEG-alpha-2a and PEG-alpha-2b with currently licensed treatments for CHB, including non-pegylated interferon alpha (IFN-alpha) and lamivudine (LAM), were included. Outcomes included biochemical, histological and virological response to treatment, drug resistance and adverse effects. A systematic review of economic evaluations of antiviral treatments for CHB was conducted. The economic Markov model used in the 2006 report was updated in terms of utility values, discount rates and costs. `

Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method

In this paper, we address the problems of fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images. We propose a learning-based, unified random forest regression and classification framework to tackle these two problems. More specifically, in the first stage, the localization of 3D vertebral bodies is solved with random forest regression where we aggregate the votes from a set of randomly sampled image patches to get a probability map of the center of a target vertebral body in a given image. The resultant probability map is then further regularized by Hidden Markov Model (HMM) to eliminate potential ambiguity caused by the neighboring vertebral bodies. The output from the first stage allows us to define a region of interest (ROI) for the segmentation step, where we use random forest classification to estimate the likelihood of a voxel in the ROI being foreground or background. The estimated likelihood is combined with the prior probability, which is learned from a set of training data, to get the posterior probability of the voxel. The segmentation of the target vertebral body is then done by a binary thresholding of the estimated probability. We evaluated the present approach on two openly available datasets: 1) 3D T2-weighted spine MR images from 23 patients and 2) 3D spine CT images from 10 patients. Taking manual segmentation as the ground truth (each MR image contains at least 7 vertebral bodies from T11 to L5 and each CT image contains 5 vertebral bodies from L1 to L5), we evaluated the present approach with leave-one-out experiments. Specifically, for the T2-weighted MR images, we achieved for localization a mean error of 1.6 mm, and for segmentation a mean Dice metric of 88.7% and a mean surface distance of 1.5 mm, respectively. For the CT images we achieved for localization a mean error of 1.9 mm, and for segmentation a mean Dice metric of 91.0% and a mean surface distance of 0.9 mm, respectively.

Fool me if you can: mimicking attacks and anti-attacks in cyberspace

Botnets have become major engines for malicious activities in cyberspace nowadays. To sustain their botnets and disguise their malicious actions, botnet owners are mimicking legitimate cyber behavior to fly under the radar. This poses a critical challenge in anomaly detection. In this paper, we use web browsing on popular web sites as an example to tackle this problem. First of all, we establish a semi-Markov model for browsing behavior. Based on this model, we find that it is impossible to detect mimicking attacks based on statistics if the number of active bots of the attacking botnet is sufficiently large (no less than the number of active legitimate users). However, we also find it is hard for botnet owners to satisfy the condition to carry out a mimicking attack most of the time. With this new finding, we conclude that mimicking attacks can be discriminated from genuine flash crowds using second order statistical metrics. We define a new fine correntropy metrics and show its effectiveness compared to others. Our real world data set experiments and simulations confirm our theoretical claims. Furthermore, the findings can be widely applied to similar situations in other research fields.

Bayesian nonparametric approaches to abnormality detection in video surveillance

In data science, anomaly detection is the process of identifying the items, events or observations which do not conform to expected patterns in a dataset. As widely acknowledged in the computer vision community and security management, discovering suspicious events is the key issue for abnormal detection in video surveil-lance. The important steps in identifying such events include stream data segmentation and hidden patterns discovery. However, the crucial challenge in stream data segmenta-tion and hidden patterns discovery are the number of coherent segments in surveillance stream and the number of traffic patterns are unknown and hard to specify. Therefore, in this paper we revisit the abnormality detection problem through the lens of Bayesian nonparametric (BNP) and develop a novel usage of BNP methods for this problem. In particular, we employ the Infinite Hidden Markov Model and Bayesian Nonparamet-ric Factor Analysis for stream data segmentation and pattern discovery. In addition, we introduce an interactive system allowing users to inspect and browse suspicious events.