Content structure discovery in educational videos using shared structures in the hierarchical hidden Markov models

In this paper, we present an application of the hierarchical HMM for structure discovery in educational videos. The HHMM has recently been extended to accommodate the concept of shared structure, ie: a state might multiply inherit from more than one parents. Utilising the expressiveness of this model, we concentrate on a specific class of video -educational videos - in which the hierarchy of semantic units is simpler and clearly defined in terms of topics and its subunits. We model the hierarchy of topical structures by an HHMM and demonstrate the usefulness of the model in detecting topic transitions.

Topic transition detection using hierarchical hidden Markov and semi-Markov models

In this paper we introduce a probabilistic framework to exploit hierarchy, structure sharing and duration information for topic transition detection in videos. Our probabilistic detection framework is a combination of a shot classification step and a detection phase using hierarchical probabilistic models. We consider two models in this paper: the extended Hierarchical Hidden Markov Model (HHMM) and the Coxian Switching Hidden semi-Markov Model (S-HSMM) because they allow the natural decomposition of semantics in videos, including shared structures, to be modeled directly, and thus enabling efficient inference and reducing the sample complexity in learning. Additionally, the S-HSMM allows the duration information to be incorporated, consequently the modeling of long-term dependencies in videos is enriched through both hierarchical and duration modeling. Furthermore, the use of the Coxian distribution in the S-HSMM makes it tractable to deal with long sequences in video. Our experimentation of the proposed framework on twelve educational and training videos shows that both models outperform the baseline cases (flat HMM and HSMM) and performances reported in earlier work in topic detection. The superior performance of the S-HSMM over the HHMM verifies our belief that duration information is an important factor in video content modeling.

Discovery of activity structures using the hierarchical hidden Markov model

In building a surveillance system for monitoring people behaviours, it is important to understand the typical patterns of people's movement in the environment. This task is difficult when dealing with high-level behaviours. The flat model such as the hidden Markov model (HMM) is inefficient in differentiating between signatures of such behaviours. This paper examines structure learning for high-level behaviours using the hierarchical hidden Markov model (HHMM).We propose a two-phase learning algorithm in which the parameters of the behaviours at low levels are estimated first and then the structures and parameters of the behaviours at high levels are learned from multi-camera training data. Our algorithm is then evaluated using data from a real environment, demonstrating the robustness of the learned structure in recognising people's behaviour.

Efficient Coxian duration modelling for activity recognition in smart environment with the hidden semi-Markov model

In this paper, we exploit the discrete Coxian distribution and propose a novel form of stochastic model, termed as the Coxian hidden semi-Makov model (Cox-HSMM), and apply it to the task of recognising activities of daily living (ADLs) in a smart house environment. The use of the Coxian has several advantages over traditional parameterization (e.g. multinomial or continuous distributions) including the low number of free parameters needed, its computational efficiency, and the existing of closed-form solution. To further enrich the model in real-world applications, we also address the problem of handling missing observation for the proposed Cox-HSMM. In the domain of ADLs, we emphasize the importance of the duration information and model it via the Cox-HSMM. Our experimental results have shown the superiority of the Cox-HSMM in all cases when compared with the standard HMM. Our results have further shown that outstanding recognition accuracy can be achieved with relatively low number of phases required in the Coxian, thus making the Cox-HSMM particularly suitable in recognizing ADLs whose movement trajectories are typically very long in nature.

Long-term species, sexual and individual variations in foraging strategies of fur seals revealed by stable isotopes in whiskers

Background: Individual variations in the use of the species niche are an important component of diversity in trophic interactions. A challenge in testing consistency of individual foraging strategy is the repeated collection of information on the same individuals.

Methodology/Principal Findings: The foraging strategies of sympatric fur seals (Arctocephalus gazella and A. tropicalis) were examined using the stable isotope signature of serially sampled whiskers. Most whiskers exhibited synchronous delta C-13 and delta N-15 oscillations that correspond to the seal annual movements over the long term (up to 8 years). delta C-13 and delta N-15 values were spread over large ranges, with differences between species, sexes and individuals. The main segregating mechanism operates at the spatial scale. Most seals favored foraging in subantarctic waters (where the Crozet Islands are located) where they fed on myctophids. However, A. gazella dispersed in the Antarctic Zone and A. tropicalis more in the subtropics. Gender differences in annual time budget shape the seal movements. Males that do not perform any parental care exhibited large isotopic oscillations reflecting broad annual migrations, while isotopic values of females confined to a limited foraging range during lactation exhibited smaller changes. Limited inter-individual isotopic variations occurred in female seals and in male A. tropicalis. In contrast, male A. gazella showed large inter-individual variations, with some males migrating repeatedly to high-Antarctic waters where they fed on krill, thus meaning that individual specialization occurred over years.

Conclusions/Significance: Whisker isotopic signature yields unique long-term information on individual behaviour that integrates the spatial, trophic and temporal dimensions of the ecological niche. The method allows depicting the entire realized niche of the species, including some of its less well-known components such as age-, sex-, individual- and migration-related changes. It highlights intrapopulation heterogeneity in foraging strategies that could have important implications for likely demographic responses to environmental variability.

A generic classifier-ensemble approach for biomedical named entity recognition

In named entity recognition (NER) for biomedical literature, approaches based on combined classifiers have demonstrated great performance improvement compared to a single (best) classifier. This is mainly owed to sufficient level of diversity exhibited among classifiers, which is a selective property of classifier set. Given a large number of classifiers, how to select different classifiers to put into a classifier-ensemble is a crucial issue of multiple classifier-ensemble design. With this observation in mind, we proposed a generic genetic classifier-ensemble method for the classifier selection in biomedical NER. Various diversity measures and majority voting are considered, and disjoint feature subsets are selected to construct individual classifiers. A basic type of individual classifier – Support Vector Machine (SVM) classifier is adopted as SVM-classifier committee. A multi-objective Genetic algorithm (GA) is employed as the classifier selector to facilitate the ensemble classifier to improve the overall sample classification accuracy. The proposed approach is tested on the benchmark dataset – GENIA version 3.02 corpus, and compared with both individual best SVM classifier and SVM-classifier ensemble algorithm as well as other machine learning methods such as CRF, HMM and MEMM. The results show that the proposed approach outperforms other classification algorithms and can be a useful method for the biomedical NER problem.

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.

Preparing for WIL : online career development for IT students

This paper reports on an online unit that enhances IT students’ generic skills. Frequently IT students, even those with a strong technical background and a high academic record, can be unsuccessful at obtaining work placements as they stumble at the interview stage due to a lack of social or professional skills. A simulation was created that enables students to enhance their employability and to prepare for transition to work integrated learning (WIL) through realistic interview preparation. The simulation utilizes a synchronous communication tool to conduct behavioural group interviews with expert careers advisors. The impact of this new initiative is explored and feedback received from faculty, careers advisors and students during three trimesters is discussed. The findings suggest that incorporating WIL through the simulation has been a success by at least raising students’ awareness of the importance and significance of being well prepared for job interviews.

Multi-modal abnormality detection in video with unknown data segmentation

This paper examines a new problem in large scale stream data: abnormality detection which is localized to a data segmentation process. Unlike traditional abnormality detection methods which typically build one unified model across data stream, we propose that building multiple detection models focused on different coherent sections of the video stream would result in better detection performance. One key challenge is to segment the data into coherent sections as the number of segments is not known in advance and can vary greatly across cameras; and a principled way approach is required. To this end, we first employ the recently proposed infinite HMM and collapsed Gibbs inference to automatically infer data segmentation followed by constructing abnormality detection models which are localized to each segmentation. We demonstrate the superior performance of the proposed framework in a real-world surveillance camera data over 14 days.

Uplink power control via adaptive Hidden-Markov-Model-Based pathloss estimation

Dynamic variations in channel behavior is considered in transmission power control design for cellular radio systems. It is well known that power control increases system capacity, improves Quality of Service (QoS), and reduces multiuser interference. In this paper, an adaptive power control design based on the identification of the underlying pathloss dynamics of the fading channel is presented. Formulating power control decisions based on the measured received power levels allows modeling the fading channel pathloss dynamics in terms of a Hidden Markov Model (HMM). Applying the online HMM identification algorithm enables accurate estimation of the real pathloss ensuring efficient performance of the suggested power control scheme.

Web-based counseling for problem gambling: exploring motivations and recommendations

Background:

The best of all worlds: Immersive interfaces for art education in virtual and real world teaching and learning environments

A narrative interpretative research methodology was used to investigate collaboration between higher education students and an art educator with the aim of establishing a community of learners. Located, Cloud based and graphically built 3D virtual, socially networked, e-learning environments were used to encourage synchronous and asynchronous student participation in authentic learning and collaborative art practice. Discussion focuses on art educator observations, student visual journal entries, their virtual exhibition of artworks on Deakin Art Education Island in Second Life and student evaluations of the unit Navigating the Visual World. It was concluded that immersion in an e-technology rich blended learning environment resulted in the establishment of an effective e-learning community of art.