Novel application of a discrete choice experiment to identify preferences for a national healthcare-associated infection surveillance programme: A cross-sectional study

Objective: To identify key stakeholder preferences and priorities when considering a national healthcare-associated infection (HAI) surveillance programme through the use of a discrete choice experiment (DCE). Setting: Australia does not have a national HAI surveillance programme. An online web-based DCE was developed and made available to participants in Australia. Participants: A sample of 184 purposively selected healthcare workers based on their senior leadership role in infection prevention in Australia. Primary and secondary outcomes: A DCE requiring respondents to select 1 HAI surveillance programme over another based on 5 different characteristics (or attributes) in repeated hypothetical scenarios. Data were analysed using a mixed logit model to evaluate preferences and identify the relative importance of each attribute. Results: A total of 122 participants completed the survey (response rate 66%) over a 5-week period. Excluding 22 who mismatched a duplicate choice scenario, analysis was conducted on 100 responses. The key findings included: 72% of stakeholders exhibited a preference for a surveillance programme with continuous mandatory core components (mean coefficient 0.640 (p<0.01)), 65% for a standard surveillance protocol where patient-level data are collected on infected and non-infected patients (mean coefficient 0.641 (p<0.01)), and 92% for hospital-level data that are publicly reported on a website and not associated with financial penalties (mean coefficient 1.663 (p<0.01)). Conclusions: The use of the DCE has provided a unique insight to key stakeholder priorities when considering a national HAI surveillance programme. The application of a DCE offers a meaningful method to explore and quantify preferences in this setting.

A design methodology for selecting and placement of sensors in multimedia surveillance systems

This paper addresses the problem of how to select the optimal number of sensors and how to determine their placement in a given monitored area for multimedia surveillance systems. We propose to solve this problem by obtaining a novel performance metric in terms of a probability measure for accomplishing the task as a function of set of sensors and their placement. This measure is then used to find the optimal set. The same measure can be used to analyze the degradation in system 's performance with respect to the failure of various sensors. We also build a surveillance system using the optimal set of sensors obtained based on the proposed design methodology. Experimental results show the effectiveness of the proposed design methodology in selecting the optimal set of sensors and their placement.

Boosting-based transfer learning for multi-view head-pose classification from surveillance videos

This work proposes a boosting-based transfer learning approach for head-pose classification from multiple, low-resolution views. Head-pose classification performance is adversely affected when the source (training) and target (test) data arise from different distributions (due to change in face appearance, lighting, etc). Under such conditions, we employ Xferboost, a Logitboost-based transfer learning framework that integrates knowledge from a few labeled target samples with the source model to effectively minimize misclassifications on the target data. Experiments confirm that the Xferboost framework can improve classification performance by up to 6%, when knowledge is transferred between the CLEAR and FBK four-view headpose datasets.

RAPID HUMAN ACTION RECOGNITION IN H.264/AVC COMPRESSED DOMAIN FOR VIDEO SURVEILLANCE

This paper discusses a novel high-speed approach for human action recognition in H. 264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of our work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can effect in reduced hardware utilization and fast recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust in outdoor as well as indoor testing scenarios. We have tested our method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed (>2000 fps) approximately 100 times more than existing state-of-the-art pixel-domain algorithms.

Exploring Transfer Learning Approaches for Head Pose Classification from Multi-view Surveillance Images

Head pose classification from surveillance images acquired with distant, large field-of-view cameras is difficult as faces are captured at low-resolution and have a blurred appearance. Domain adaptation approaches are useful for transferring knowledge from the training (source) to the test (target) data when they have different attributes, minimizing target data labeling efforts in the process. This paper examines the use of transfer learning for efficient multi-view head pose classification with minimal target training data under three challenging situations: (i) where the range of head poses in the source and target images is different, (ii) where source images capture a stationary person while target images capture a moving person whose facial appearance varies under motion due to changing perspective, scale and (iii) a combination of (i) and (ii). On the whole, the presented methods represent novel transfer learning solutions employed in the context of multi-view head pose classification. We demonstrate that the proposed solutions considerably outperform the state-of-the-art through extensive experimental validation. Finally, the DPOSE dataset compiled for benchmarking head pose classification performance with moving persons, and to aid behavioral understanding applications is presented in this work.

Skip Decision and Reference Frame Selection for Low-Complexity H.264/AVC Surveillance Video Coding

H. 264/advanced video coding surveillance video encoders use the Skip mode specified by the standard to reduce bandwidth. They also use multiple frames as reference for motion-compensated prediction. In this paper, we propose two techniques to reduce the bandwidth and computational cost of static camera surveillance video encoders without affecting detection and recognition performance. A spatial sampler is proposed to sample pixels that are segmented using a Gaussian mixture model. Modified weight updates are derived for the parameters of the mixture model to reduce floating point computations. A storage pattern of the parameters in memory is also modified to improve cache performance. Skip selection is performed using the segmentation results of the sampled pixels. The second contribution is a low computational cost algorithm to choose the reference frames. The proposed reference frame selection algorithm reduces the cost of coding uncovered background regions. We also study the number of reference frames required to achieve good coding efficiency. Distortion over foreground pixels is measured to quantify the performance of the proposed techniques. Experimental results show bit rate savings of up to 94.5% over methods proposed in literature on video surveillance data sets. The proposed techniques also provide up to 74.5% reduction in compression complexity without increasing the distortion over the foreground regions in the video sequence.

INTERPOL's surveillance network in curbing transnational terrorism

This paper investigates the role that INTERPOL surveillance – the Mobile INTERPOL Network Database (MIND) and the Fixed INTERPOL Network Database (FIND) – played in the War on Terror since its inception in 2005. MIND/FIND surveillance allows countries to screen people and documents systematically at border crossings against INTERPOL databases on terrorists, fugitives, and stolen and lost travel documents. Such documents have been used in the past by terrorists to transit borders. By applying methods developed in the treatment-effects literature, this paper establishes that countries adopting MIND/FIND experienced fewer transnational terrorist attacks than had they not adopted MIND/FIND. Our estimates indicate that, on average, during 2008–2011, adopting and using MIND/FIND results in 1.23 fewer transnational terrorist incidents each year per 100 million people. Thus, a country like France with a population just above 64 million people in 2008 would have 0.79 fewer transnational terrorist incidents per year owing to its use of INTERPOL surveillance. For most treatment countries, this amounts to a sizeable proportional reduction of about 60 per cent.

Biological surveillance of chalk-streams

An article reviewing the methods of biological surveillance of chalk-streams developed and commonly used at that time, with a focus on their application to the River Frome catchment in Dorset. In evaluating the surveillance methods, the author looks at sampling methods (including cores and kick-sampling), the level of identification of macroinvertebrates, and temporal and spatial variations. Responses of indices to organic pollution are also discussed. A number of accompanying figures are also included.

Joint Anglo-Soviet biological surveillance exercise on River Dnieper

As one part of an on-going programme concerned with environmental protection as provided for under the terms of a UK/USSR Joint Environmental Protection Agreement signed in London, 21 May 1974, a seminar — ”The elaboration of the scientific basis for monitoring the quality of surface water by hydrobiological indices” was held at Valdai in Russia 12—14 July, 1976. As a continuation of this theme it was agreed that delegations of hydrobiologists from each side should carry out reciprocal visits to carry out comparative field tests on selected systems of biological surveillance in use in the respective countries. In May 1978 a team of British hydrobiologists visited the USSR, under the auspices of the Department of Environment, to carry out joint exercises on the River Dnieper and some tributaries. This paper reports the results of selected methods used by the British side when applied to the conditions found in the River Dnieper.

A surveillance strategy for invasive species of concern in deepwater habitats of the Northwestern Hawaiian Islands

This report describes a surveillance strategy to detect deepwater invasive species in the Northwestern Hawaiian Islands. A need for this strategy was identified in the Papahānaumokuākea Marine National Monument Management Plan and the Monument’s Draft Natural Resources Science Plan. This strategy focuses on detecting two species of concern, the octocoral Carijoa riisei and the red alga Hypnea musciformis. Most research on invasive species in the Hawaiian archipelago has focused on shallow water habitats within the limits of conventional SCUBA (0-30 m). Deeper habitats such as mesophotic reefs are much more difficult to access and consequently little is known about the distribution of deepwater invasive species or their impacts. Recent deepwater (>30 m) sightings of H. musciformis and C. riisei, in and near NWHI, respectively, have prompted a call for further research and surveillance of invasive species in deepwater habitats. This report compiles the most up to date information about these two species of concern in deepwater habitats. A literature search and conversations with subject matter experts was used to identify their current distribution, preferred habitat types, optimal detection methods and ways to efficiently sample the vast extent of NWHI. The proposed sampling strategy prioritizes survey effort where C. riisei and H. musciformis are most likely to be found. At coarse spatial scales (tens to hundreds of kilometers), opportunistic observations and distance from the Main Hawaiian Islands, a principal propagule source, are used to identify high-risk islands and banks. At fine spatial scales (meters to tens of kilometers) a habitat suitability model was developed to identify high-risk habitats. The habitat suitability model focused on habitat preferences of C. riisei, since the species is well studied and adequate data exists to map habitats. There was insufficient information to identify suitable habitat for H. muscifomis. Habitat preferences for the algae are poorly understood and there is a lack of data at relevant spatial scales to map those preferences which are known. The principal habitats identified by the habitat suitability model were ledges and the edges of rugose coral reefs, where the shade loving octocoral would likely be found. Habitat suitability maps were developed for seven atolls and banks to aid in survey site selection. The protocol relied on technical divers to conduct visual surveys of benthic habitats. It was developed to increase the efficiency of surveys, maximize the probability of detection, identify important information relevant to future surveys and standardize results. The strategy, model and protocol were tested during a field mission in 2009 at several atolls and islands in NWHI. The field mission did not detect any invasive species among deepwater habitats and much was learned to improve future surveys. Data gaps and improvements are discussed.