Individual Video Training iVT - Development of a National Infrastructure for Video-Supported Learning

Introduction: Video‐Supported Learning is particularly effective when it comes to skills and behaviors. Video registration of patient‐physician interviews, class room instruction or practical skills allow it to learners themselves, their peers, and their tutors to assess the quality of the learner's performance, to give specific feedback, and to make suggestions for improvement. Methods: In Switzerland, four pedagogical universities and two medical faculties joined to initiate the development of a national infrastructure for Video Supported Learning. The goal was to have a system that is simple to use, has most steps automated, provides the videos over the Internet, and has a sophisticated access control. Together with SWITCH, the national IT‐Support‐Organisation for Swiss Universities, the program iVT (Individual Video Training) was developed by integrating two preexisting technologies. The first technology is SWITCHcast, a podcast system. With SWITCHcast, videos are automatically uploaded to a server as soon as the registration is over. There the videos are processed and converted to different formats. The second technology is the national Single Logon System AAI (Authentification and Authorization Infrastructure) that enables iVT to link each video with the corresponding learner. The learner starts the registration with his Single Logon. Thus, the video can unambiguously be assigned. Via his institution's Learning Management System (LMS), the learner can access his video and give access to his video to peers and tutors. Results: iVT is now used at all involved institutions. The system works flawlessly. In Bern, we use iVT for the communications skills training in the forth and sixth year. Since students meet with patient actors alone, iVT is also used to certify attendance. Students are encouraged to watch the videos of the interview and the feedback of the patient actor. The offer to discuss a video with a tutor was not used by the students. Discussion: We plan to expand the use of iVT by making peer assessment compulsory. To support this, annotation capabilities are currently added to iVT. We also want to use iVT in training of practical skills, again for self as well as for peer assessment.  At present, we use iVT for quality control of patient actor's performance.

The Role of Infrared Thermography as a Non-Invasive Tool for the Detection of Lameness in Cattle

The use of infrared thermography for the identification of lameness in cattle has increased in recent years largely because of its non-invasive properties, ease of automation and continued cost reductions. Thermography can be used to identify and determine thermal abnormalities in animals by characterizing an increase or decrease in the surface temperature of their skin. The variation in superficial thermal patterns resulting from changes in blood flow in particular can be used to detect inflammation or injury associated with conditions such as foot lesions. Thermography has been used not only as a diagnostic tool, but also to evaluate routine farm management. Since 2000, 14 peer reviewed papers which discuss the assessment of thermography to identify and manage lameness in cattle have been published. There was a large difference in thermography performance in these reported studies. However, thermography was demonstrated to have utility for the detection of contralateral temperature difference and maximum foot temperature on areas of interest. Also apparent in these publications was that a controlled environment is an important issue that should be considered before image scanning.

Subjective quality study of adaptive streaming of monoscopic and stereoscopic video

Nowadays, HTTP adaptive streaming (HAS) has become a reliable distribution technology offering significant advantages in terms of both user perceived Quality of Experience (QoE) and resource utilization for content and network service providers. By trading-off the video quality, HAS is able to adapt to the available bandwidth and display requirements so that it can deliver the video content to a variety of devices over the Internet. However, until now there is not enough knowledge of how the adaptation techniques affect the end user's visual experience. Therefore, this paper presents a comparative analysis of different bitrate adaptation strategies in adaptive streaming of monoscopic and stereoscopic video. This has been done through a subjective experiment of testing the end-user response to the video quality variations, considering the visual comfort issue. The experimental outcomes have made a good insight into the factors that can influence on the QoE of different adaptation strategies.

Now Streaming: A Consortial PDA Video Pilot Project

In 2014, eight academic libraries in the state of New York collaborated on a group patron driven acquisition (PDA) pilot program with Kanopy, a video streaming service for libraries. The institutions, despite vast differences in size and profile, each launched Kanopy’s streaming solution on their campuses under a program where they would jointly contribute to and acquire films based on group usage. The pilot ran for seven months and led to some fascinating insights into the differences in demand for film across campuses, the possibility of PDA as a model for library acquisition, and the feasibility of a group approach to acquisition. This paper presents the background to, results of, and reflections on the pilot program from the three unique perspectives of the consortium, the vendor, and one of the libraries involved, providing a holistic view of the success of the pilot and the lessons learned.

Monitoring Infants By Automatic Video Processing

This work has, as its objective, the development of non-invasive and low-cost systems for monitoring and automatic diagnosing specific neonatal diseases by means of the analysis of suitable video signals. We focus on monitoring infants potentially at risk of diseases characterized by the presence or absence of rhythmic movements of one or more body parts. Seizures and respiratory diseases are specifically considered, but the approach is general. Seizures are defined as sudden neurological and behavioural alterations. They are age-dependent phenomena and the most common sign of central nervous system dysfunction. Neonatal seizures have onset within the 28th day of life in newborns at term and within the 44th week of conceptional age in preterm infants. Their main causes are hypoxic-ischaemic encephalopathy, intracranial haemorrhage, and sepsis. Studies indicate an incidence rate of neonatal seizures of 0.2% live births, 1.1% for preterm neonates, and 1.3% for infants weighing less than 2500 g at birth. Neonatal seizures can be classified into four main categories: clonic, tonic, myoclonic, and subtle. Seizures in newborns have to be promptly and accurately recognized in order to establish timely treatments that could avoid an increase of the underlying brain damage. Respiratory diseases related to the occurrence of apnoea episodes may be caused by cerebrovascular events. Among the wide range of causes of apnoea, besides seizures, a relevant one is Congenital Central Hypoventilation Syndrome (CCHS) \cite{Healy}. With a reported prevalence of 1 in 200,000 live births, CCHS, formerly known as Ondine's curse, is a rare life-threatening disorder characterized by a failure of the automatic control of breathing, caused by mutations in a gene classified as PHOX2B. CCHS manifests itself, in the neonatal period, with episodes of cyanosis or apnoea, especially during quiet sleep. The reported mortality rates range from 8% to 38% of newborn with genetically confirmed CCHS. Nowadays, CCHS is considered a disorder of autonomic regulation, with related risk of sudden infant death syndrome (SIDS). Currently, the standard method of diagnosis, for both diseases, is based on polysomnography, a set of sensors such as ElectroEncephaloGram (EEG) sensors, ElectroMyoGraphy (EMG) sensors, ElectroCardioGraphy (ECG) sensors, elastic belt sensors, pulse-oximeter and nasal flow-meters. This monitoring system is very expensive, time-consuming, moderately invasive and requires particularly skilled medical personnel, not always available in a Neonatal Intensive Care Unit (NICU). Therefore, automatic, real-time and non-invasive monitoring equipments able to reliably recognize these diseases would be of significant value in the NICU. A very appealing monitoring tool to automatically detect neonatal seizures or breathing disorders may be based on acquiring, through a network of sensors, e.g., a set of video cameras, the movements of the newborn's body (e.g., limbs, chest) and properly processing the relevant signals. An automatic multi-sensor system could be used to permanently monitor every patient in the NICU or specific patients at home. Furthermore, a wire-free technique may be more user-friendly and highly desirable when used with infants, in particular with newborns. This work has focused on a reliable method to estimate the periodicity in pathological movements based on the use of the Maximum Likelihood (ML) criterion. In particular, average differential luminance signals from multiple Red, Green and Blue (RGB) cameras or depth-sensor devices are extracted and the presence or absence of a significant periodicity is analysed in order to detect possible pathological conditions. The efficacy of this monitoring system has been measured on the basis of video recordings provided by the Department of Neurosciences of the University of Parma. Concerning clonic seizures, a kinematic analysis was performed to establish a relationship between neonatal seizures and human inborn pattern of quadrupedal locomotion. Moreover, we have decided to realize simulators able to replicate the symptomatic movements characteristic of the diseases under consideration. The reasons is, essentially, the opportunity to have, at any time, a 'subject' on which to test the continuously evolving detection algorithms. Finally, we have developed a smartphone App, called 'Smartphone based contactless epilepsy detector' (SmartCED), able to detect neonatal clonic seizures and warn the user about the occurrence in real-time.

Improving the scientific reliability of biological detection of explosives by Canis familiaris: Active odour signatures and their implications

The use of canines as a method of detection of explosives is well established worldwide and those applying this technology range from police forces and law enforcement to humanitarian agencies in the developing world. Despite the recent surge in publication of novel instrumental sensors for explosives detection, canines are still regarded by many to be the most effective real-time field method of explosives detection. However, unlike instrumental methods, currently it is difficult to determine detection levels, perform calibration of the canines' ability or produce scientifically valid quality control checks. Accordingly, amongst increasingly strict requirements regarding forensic evidence admission such as Frye and Daubert, there is a need for better scientific understanding of the process of canine detection. ^ When translated to the field of canine detection, just like any instrumental technique, peer reviewed publication of the reliability, success and error rates, is required for admissibility. Commonly training is focussed towards high explosives such as TNT and Composition 4, and the low explosives such as Black and Smokeless Powders are added often only for completeness. ^ Headspace analyses of explosive samples, performed by Solid Phase Microextraction (SPME) paired with Gas Chromatography - Mass Spectrometry (GC-MS), and Gas Chromatography - Electron Capture Detection (GC-ECD) was conducted, highlighting common odour chemicals. The odour chemicals detected were then presented to previously trained and certified explosives detection canines, and the activity/inactivity of the odour determined through field trials and experiments. ^ It was demonstrated that TNT and cast explosives share a common odour signature, and the same may be said for plasticized explosives such as Composition C-4 and Deta Sheet. Conversely, smokeless powders were demonstrated not to share common odours. An evaluation of the effectiveness of commercially available pseudo aids reported limited success. The implications of the explosive odour studies upon canine training then led to the development of novel inert training aids based upon the active odours determined. ^

Systems Modeling of Lung Cancer Screening Programs to Improve Quality

Thesis (Master's)--University of Washington, 2016-08

A performance evaluation of machine learning-based streaming spam tweets detection

The popularity of Twitter attracts more and more spammers. Spammers send unwanted tweets to Twitter users to promote websites or services, which are harmful to normal users. In order to stop spammers, researchers have proposed a number of mechanisms. The focus of recent works is on the application of machine learning techniques into Twitter spam detection. However, tweets are retrieved in a streaming way, and Twitter provides the Streaming API for developers and researchers to access public tweets in real time. There lacks a performance evaluation of existing machine learning-based streaming spam detection methods. In this paper, we bridged the gap by carrying out a performance evaluation, which was from three different aspects of data, feature, and model. A big ground-truth of over 600 million public tweets was created by using a commercial URL-based security tool. For real-time spam detection, we further extracted 12 lightweight features for tweet representation. Spam detection was then transformed to a binary classification problem in the feature space and can be solved by conventional machine learning algorithms. We evaluated the impact of different factors to the spam detection performance, which included spam to nonspam ratio, feature discretization, training data size, data sampling, time-related data, and machine learning algorithms. The results show the streaming spam tweet detection is still a big challenge and a robust detection technique should take into account the three aspects of data, feature, and model.

Analysis of the failure of cracked biscuits

Cracks or checks in biscuits weaken the material and cause the product to break at low load levels that are perceived as injurious to product quality. In this work, the structural response of circular digestive biscuits, with diameter 72 mm and thickness 7.2 mm, simply supported around the circumference and loaded by a central concentrated force was investigated by experiment and theory. Tests were conducted to quantify the distribution in breakage strength for structurally sound biscuits, biscuits with natural checks and biscuits with a single known part-through crack. For sound biscuits the breakage force is Normally distributed with a mean of 12.5 N and standard deviation of 1.2 N. For biscuits with checks, the corresponding statistics are 9.6 N ± 2.62 N respectively. The presence of a crack weakens the biscuit and strength, as measured by breakage force falls almost linearly with crack length and crack depth. The orientation of the crack, whether radial or tangential, and its location (i.e. position of the crack mid-point on the biscuit surface) are also important. Deep, radial, cracks located close to the biscuit centre can reduce the strength by up to 50%. Two separate failure criteria were examined for sound and cracked biscuits respectively. The results from these tests were in good accord with theory. For a biscuit without defects, breakage occurred when maximum biscuit stress reached or exceeded the failure stress of 420 kPa. For a biscuit with cracks, breakage occurred as above or alternatively when its critical stress intensity factor of 18 kPam0.5 was reached.

Automatic tracking, super-resolution and recognition of human faces from surveillance video

Identifying an individual from surveillance video is a difficult, time consuming and labour intensive process. The proposed system aims to streamline this process by filtering out unwanted scenes and enhancing an individual's face through super-resolution. An automatic face recognition system is then used to identify the subject or present the human operator with likely matches from a database. A person tracker is used to speed up the subject detection and super-resolution process by tracking moving subjects and cropping a region of interest around the subject's face to reduce the number and size of the image frames to be super-resolved respectively. In this paper, experiments have been conducted to demonstrate how the optical flow super-resolution method used improves surveillance imagery for visual inspection as well as automatic face recognition on an Eigenface and Elastic Bunch Graph Matching system. The optical flow based method has also been benchmarked against the ``hallucination'' algorithm, interpolation methods and the original low-resolution images. Results show that both super-resolution algorithms improved recognition rates significantly. Although the hallucination method resulted in slightly higher recognition rates, the optical flow method produced less artifacts and more visually correct images suitable for human consumption.

Impact of zooming and enhancing Region of Interests for optimizing user experience on mobile sports video

In mobile videos, small viewing size and bitrate limitation often cause unpleasant viewing experiences, which is particularly important for fast-moving sports videos. For optimizing the overall user experience of viewing sports videos on mobile phones, this paper explores the benefits of emphasizing Region of Interest (ROI) by 1) zooming in and 2) enhancing the quality. The main goal is to measure the effectiveness of these two approaches and determine which one is more effective. To obtain a more comprehensive understanding of the overall user experience, the study considers user’s interest in video content and user’s acceptance of the perceived video quality, and compares the user experience in sports videos with other content types such as talk shows. The results from a user study with 40 subjects demonstrate that zooming and ROI-enhancement are both effective in improving the overall user experience with talk show and mid-shot soccer videos. However, for the full-shot scenes in soccer videos, only zooming is effective while ROI-enhancement has a negative effect. Moreover, user’s interest in video content directly affects not only the user experience and the acceptance of video quality, but also the effect of content type on the user experience. Finally, the overall user experience is closely related to the degree of the acceptance of video quality and the degree of the interest in video content. This study is valuable in exploiting effective approaches to improve user experience, especially in mobile sports video streaming contexts, whereby the available bandwidth is usually low or limited. It also provides further understanding of the influencing factors of user experience.

Robust suspicious behaviour detection for smart surveillance systems

Video surveillance technology, based on Closed Circuit Television (CCTV) cameras, is one of the fastest growing markets in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. To overcome this limitation, it is necessary to have “intelligent” processes which are able to highlight the salient data and filter out normal conditions that do not pose a threat to security. In order to create such intelligent systems, an understanding of human behaviour, specifically, suspicious behaviour is required. One of the challenges in achieving this is that human behaviour can only be understood correctly in the context in which it appears. Although context has been exploited in the general computer vision domain, it has not been widely used in the automatic suspicious behaviour detection domain. So, it is essential that context has to be formulated, stored and used by the system in order to understand human behaviour. Finally, since surveillance systems could be modeled as largescale data stream systems, it is difficult to have a complete knowledge base. In this case, the systems need to not only continuously update their knowledge but also be able to retrieve the extracted information which is related to the given context. To address these issues, a context-based approach for detecting suspicious behaviour is proposed. In this approach, contextual information is exploited in order to make a better detection. The proposed approach utilises a data stream clustering algorithm in order to discover the behaviour classes and their frequency of occurrences from the incoming behaviour instances. Contextual information is then used in addition to the above information to detect suspicious behaviour. The proposed approach is able to detect observed, unobserved and contextual suspicious behaviour. Two case studies using video feeds taken from CAVIAR dataset and Z-block building, Queensland University of Technology are presented in order to test the proposed approach. From these experiments, it is shown that by using information about context, the proposed system is able to make a more accurate detection, especially those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information give critical feedback to the system designers to refine the system. Finally, the proposed modified Clustream algorithm enables the system to both continuously update the system’s knowledge and to effectively retrieve the information learned in a given context. The outcomes from this research are: (a) A context-based framework for automatic detecting suspicious behaviour which can be used by an intelligent video surveillance in making decisions; (b) A modified Clustream data stream clustering algorithm which continuously updates the system knowledge and is able to retrieve contextually related information effectively; and (c) An update-describe approach which extends the capability of the existing human local motion features called interest points based features to the data stream environment.

DNA technology for the detection of common genetic variants that predispose to thrombophilia

With the identification of common single locus point mutations as risk factors for thrombophilia, many DNA testing methodologies have been described for detecting these variations. Traditionally, functional or immunological testing methods have been used to investigate quantitative anticoagulant deficiencies. However, with the emergence of the genetic variations, factor V Leiden, prothrombin 20210 and, to a lesser extent, the methylene tetrahydrofolate reductase (MTHFR677) and factor V HR2 haplotype, traditional testing methodologies have proved to be less useful and instead DNA technology is more commonly employed in diagnostics. This review considers many of the DNA techniques that have proved to be useful in the detection of common genetic variants that predispose to thrombophilia. Techniques involving gel analysis are used to detect the presence or absence of restriction sites, electrophoretic mobility shifts, as in single strand conformation polymorphism or denaturing gradient gel electrophoresis, and product formation in allele-specific amplification. Such techniques may be sensitive, but are unwielding and often need to be validated objectively. In order to overcome some of the limitations of gel analysis, especially when dealing with larger sample numbers, many alternative detection formats, such as closed tube systems, microplates and microarrays (minisequencing, real-time polymerase chain reaction, and oligonucleotide ligation assays) have been developed. In addition, many of the emerging technologies take advantage of colourimetric or fluorescence detection (including energy transfer) that allows qualitative and quantitative interpretation of results. With the large variety of DNA technologies available, the choice of methodology will depend on several factors including cost and the need for speed, simplicity and robustness. © 2000 Lippincott Williams & Wilkins.

Hand-held monocular SLAM in thermal-infrared

Thermal-infrared imagery is relatively robust to many of the failure conditions of visual and laser-based SLAM systems, such as fog, dust and smoke. The ability to use thermal-infrared video for localization is therefore highly appealing for many applications. However, operating in thermal-infrared is beyond the capacity of existing SLAM implementations. This paper presents the first known monocular SLAM system designed and tested for hand-held use in the thermal-infrared modality. The implementation includes a flexible feature detection layer able to achieve robust feature tracking in high-noise, low-texture thermal images. A novel approach for structure initialization is also presented. The system is robust to irregular motion and capable of handling the unique mechanical shutter interruptions common to thermal-infrared cameras. The evaluation demonstrates promising performance of the algorithm in several environments.

Impairment of simulated motorcycle riding performance under low dose alcohol

Crash statistics that include the blood alcohol concentration (BAC) of vehicle operators reveal that crash involved motorcyclists are over represented at low BACs (e.g., ≤0.05%). This riding simulator study compared riding performance and hazard response under three low dose alcohol conditions (sober, 0.02% BAC, 0.05% BAC). Forty participants (20 novice, 20 experienced) completed simulated rides in urban and rural scenarios while responding to a safety-critical peripheral detection task (PDT). Results showed a significant increase in the standard deviation of lateral position in the urban scenario and PDT reaction time in the rural scenario under 0.05% BAC compared with zero alcohol. Participants were most likely to collide with an unexpected pedestrian in the urban scenario at 0.02% BAC, with novice participants at a greater relative risk than experienced riders. Novices chose to ride faster than experienced participants in the rural scenario regardless of BAC. Not all results were significant, emphasising the complex situation of the effects of low dose BAC on riding performance, which needs further research. The results of this simulator study provide some support for a legal BAC for motorcyclists below 0.05%.