Comparison of automated classification techniques for predicting benthic biological communities using hydroacoustics and video observations

The effective management of our marine ecosystems requires the capability to identify, characterise and predict the distribution of benthic biological communities within the overall seascape architecture. The rapid expansion of seabed mapping studies has seen an increase in the application of automated classification techniques to efficiently map benthic habitats, and the need of techniques to assess confidence of model outputs. We use towed video observations and 11 seafloor complexity variables derived from multibeam echosounder (MBES) bathymetry and backscatter to predict the distribution of 8 dominant benthic biological communities in a 54 km² site, off the central coast of Victoria, Australia. The same training and evaluation datasets were used to compare the accuracies of a Maximum Likelihood Classifier (MLC) and two new generation decision tree methods, QUEST (Quick Unbiased Efficient Statistical Tree) and CRUISE (Classification Rule with Unbiased Interaction Selection and Estimation), for predicting dominant biological communities. The QUEST classifier produced significantly better results than CRUISE and MLC model runs, with an overall accuracy of 80% (Kappa 0.75). We found that the level of accuracy with the size of training set varies for different algorithms. The QUEST results generally increased in a linear fashion, CRUISE performed well with smaller training data sets, and MLC performed least favourably overall, generating anomalous results with changes to training size. We also demonstrate how predicted habitat maps can provide insights into habitat spatial complexity on the continental shelf. Significant variation between patch-size and habitat types and significant correlations between patch size and depth were also observed.

Trauma and holocaust video testimony : the intersection of history, memory, and judgment in the interview process

This article analyzes video testimonies recorded at the Jewish Holocaust Museum and Research Centre in Melbourne,Australia, which address the highly complex and sensitive issue of “privileged” Jews. The so-called privileged Jews include prisoners in the Nazi-operated camps and ghettos who held positions that gave them access to material and other benefits, while compelling them to act in ways that have been judged detrimental to fellow inmates. Although the issue of “privileged” Jews has been largely neglected, it relates to a crucial facet of the Holocaust and has vast implications for its aftermath. The ethical dilemmas facing these victims may be closely linked to what Lawrence Langer has termed choiceless choices, which challenge conventional notions of “judgment” and “responsibility.” This problem is also the primary subject of Auschwitz survivor Primo Levi’s essay titled “The Grey Zone,” which is arguably the most influential essay ever written on the Holocaust. Levi argues that one should abstain from judging individuals who confronted such extreme circumstances, positioning prisoners with “privileged” positions at the threshold of representation and understanding. However, moral evaluations of “privileged” Jews have a strong impact on Holocaust testimonies, whether these were constructed during the war or recorded long after the survivors’ experiences. The examples of video testimonies explored in this article reveal that this is particularly the case when interviewees are former “privileged” Jews and interviewers are themselves Holocaust survivors. The article argues that when confronted with such an emotionally and morally fraught issue, judgment may itself be seen as a “limit of representation.”

Video streaming: Implementation and evaluation in an undergraduate nursing program

Video streaming technology enables video content, held on the web sites, to be streamed via the web. We report the implementation and evaluation of video streaming in an undergraduate nursing program in a metropolitan university in Australia. Students (n = 703) were emailed a survey with a 15% response rate. We found that 91% (n = 74) of respondents stated that video streaming assisted their learning. Forty-six percent(n = 50) of students had difficulty accessing video streaming (particularly at the beginning of the study period). Over a 97-day period there were 8440 “hits” to the site from 1039 different internet protocol (IP) addresses. There were 4475 video streaming sessions undertaken by users. Video streaming was used for reviewing previously attended lectures (52%, n = 56), examination preparation (34%, n = 37), viewing missed lectures (27%, n = 29) and class preparation (9%, n = 10). Our experience with the introduction of video streaming has met with general enthusiasm from both students and teaching staff. Video streaming has particular relevance for rural students.

The effects of playing violent video games on adolescents : should parents be quaking in their boots?

Debate regarding the psychological and behavioural effects of playing violent video games has recently led to claims that violent video games increase aggression effects in adolescents, and that this issue has now been settled. However, other researchers have found either no detrimental effects from game playing or even positive (cathartic) effects. In this research we demonstrate that these different conclusions are not mutually exclusive and can be explained by the method of assessment and analytic techniques utilised. We had adolescents play a violent video game (Quake II) and took measurements of anger both before, during and after game play. The results demonstrated that some people increase, some decrease and the majority show no change in anger ratings. Unlike past research, we also demonstrate that these changes are mediated by the player's feelings immediately prior to game play and a labile temperament - one predisposed to aggression - and that these variables predict people's reactions with an average 73% concordance rate.

The development of a generic framework for the implementation of a cheap, component-based virtual video-conferencing system

We address the problem of virtual-videoconferencing. The proposed solution is effected in terms of a generic framework based on an in-house Virtual Reality system. The framework is composed of a number of distinct components: model acquisition, head tracking, expression analysis, network transmission and avatar reconstruction. The framework promises to provide a unique, cheap, and fast system for avatar construction, transmission and animation. This approach affords a conversion from the traditional video stream approach to the management of an avatar remotely and consequently makes minimal demands on network resources.

Understanding fish-habitat associations using video observations and sonar imaging

This thesis was motivated by the increasing role of species distribution models in managing marine fishes and their habitats. These models provided new information about fish-habitat associations. However, models are potentially influenced by fish behaviour towards underwater video systems.

Comparing towed and baited underwater video techniques for assessing temperate marine fishes

Accurate estimates of fish species occurrence are important to any species’ assessments and distribution model. With increasing emphasis on nondestructive sampling, underwater video techniques are commonly used without a thorough understanding of their advantages and disadvantages. This study compared data collected from baited remote underwater stereo-video systems (stereo BRUVS) and towed-video systems to determine; (1) the differences between these video techniques in terms of fish assemblages, functional groups (i.e. pelagic carnivore, epibenthic carnivore/omnivore or herbivore) and observability (i.e. conspicuous or cryptic), and (2) what impact do these two techniques have on the interpretation of spatially-explicit, predictive models. We found stereo BRUVS and towedvideo techniques recorded very different assemblages, functional groups and observability categories across structurally complex benthic biological habitats (i.e. macroalgae dominated habitats). However, as the habitat complexity became less (e.g. seagrass and areas with no visible macro-biota) both techniques appeared to provide similar fish assemblage information. We also found considerable differences in the predicted extents of habitat suitability between the two video techniques.