Cross database training of audio-visual hidden Markov models for phone recognition

Speech recognition can be improved by using visual information in the form of lip movements of the speaker in addition to audio information. To date, state-of-the-art techniques for audio-visual speech recognition continue to use audio and visual data of the same database for training their models. In this paper, we present a new approach to make use of one modality of an external dataset in addition to a given audio-visual dataset. By so doing, it is possible to create more powerful models from other extensive audio-only databases and adapt them on our comparatively smaller multi-stream databases. Results show that the presented approach outperforms the widely adopted synchronous hidden Markov models (HMM) trained jointly on audio and visual data of a given audio-visual database for phone recognition by 29% relative. It also outperforms the external audio models trained on extensive external audio datasets and also internal audio models by 5.5% and 46% relative respectively. We also show that the proposed approach is beneficial in noisy environments where the audio source is affected by the environmental noise.

Improving Near-Miss Event Detection Rate at Railway Level Crossings

Even though crashes between trains and road users are rare events at railway level crossings, they are one of the major safety concerns for the Australian railway industry. Nearmiss events at level crossings occur more frequently, and can provide more information about factors leading to level crossing incidents. In this paper we introduce a video analytic approach for automatically detecting and localizing vehicles from cameras mounted on trains for detecting near-miss events. To detect and localize vehicles at level crossings we extract patches from an image and classify each patch for detecting vehicles. We developed a region proposals algorithm for generating patches, and we use a Convolutional Neural Network (CNN) for classifying each patch. To localize vehicles in images we combine the patches that are classified as vehicles according to their CNN scores and positions. We compared our system with the Deformable Part Models (DPM) and Regions with CNN features (R-CNN) object detectors. Experimental results on a railway dataset show that the recall rate of our proposed system is 29% higher than what can be achieved with DPM or R-CNN detectors.

Exploring accuracy factors in cost estimating practice towards implementing Building Information Modelling (BIM)

Cost estimating has been acknowledged as a crucial component of construction projects. Depending on available information and project requirements, cost estimates evolve in tandem with project lifecycle stages; conceptualisation, design development, execution and facility management. The premium placed on the accuracy of cost estimates is crucial to producing project tenders and eventually in budget management. Notwithstanding the initial slow pace of its adoption, Building Information Modelling (BIM) has successfully addressed a number of challenges previously characteristic of traditional approaches in the AEC, including poor communication, the prevalence of islands of information and frequent reworks. Therefore, it is conceivable that BIM can be leveraged to address specific shortcomings of cost estimation. The impetus for leveraging BIM models for accurate cost estimation is to align budgeted and actual cost. This paper hypothesises that the accuracy of BIM-based estimation, as more efficient, process-mirrors of traditional cost estimation methods, can be enhanced by simulating traditional cost estimation factors variables. Through literature reviews and preliminary expert interviews, this paper explores the factors that could potentially lead to more accurate cost estimates for construction projects. The findings show numerous factors that affect the cost estimates ranging from project information and its characteristic, project team, clients, contractual matters, and other external influences. This paper will make a particular contribution to the early phase of BIM-based project estimation.

The root locus method: application to linear stability analysis and design of cooperative car-following models

A global framework for linear stability analyses of traffic models, based on the dispersion relation root locus method, is presented and is applied taking the example of a broad class of car-following (CF) models. This approach is able to analyse all aspects of the dynamics: long waves and short wave behaviours, phase velocities and stability features. The methodology is applied to investigate the potential benefits of connected vehicles, i.e. V2V communication enabling a vehicle to send and receive information to and from surrounding vehicles. We choose to focus on the design of the coefficients of cooperation which weights the information from downstream vehicles. The coefficients tuning is performed and different ways of implementing an efficient cooperative strategy are discussed. Hence, this paper brings design methods in order to obtain robust stability of traffic models, with application on cooperative CF models

Comparing multilevel and Bayesian spatial random effects survival models to assess geographical inequalities in colorectal cancer survival: a case study

Background Multilevel and spatial models are being increasingly used to obtain substantive information on area-level inequalities in cancer survival. Multilevel models assume independent geographical areas, whereas spatial models explicitly incorporate geographical correlation, often via a conditional autoregressive prior. However the relative merits of these methods for large population-based studies have not been explored. Using a case-study approach, we report on the implications of using multilevel and spatial survival models to study geographical inequalities in all-cause survival. Methods Multilevel discrete-time and Bayesian spatial survival models were used to study geographical inequalities in all-cause survival for a population-based colorectal cancer cohort of 22,727 cases aged 20–84 years diagnosed during 1997–2007 from Queensland, Australia. Results Both approaches were viable on this large dataset, and produced similar estimates of the fixed effects. After adding area-level covariates, the between-area variability in survival using multilevel discrete-time models was no longer significant. Spatial inequalities in survival were also markedly reduced after adjusting for aggregated area-level covariates. Only the multilevel approach however, provided an estimation of the contribution of geographical variation to the total variation in survival between individual patients. Conclusions With little difference observed between the two approaches in the estimation of fixed effects, multilevel models should be favored if there is a clear hierarchical data structure and measuring the independent impact of individual- and area-level effects on survival differences is of primary interest. Bayesian spatial analyses may be preferred if spatial correlation between areas is important and if the priority is to assess small-area variations in survival and map spatial patterns. Both approaches can be readily fitted to geographically enabled survival data from international settings

Optimal management of the critically Ill: Anaesthesia, monitoring, data capture, and point-of-care technological practices in ovine models of critical care

Animal models of critical illness are vital in biomedical research. They provide possibilities for the investigation of pathophysiological processes that may not otherwise be possible in humans. In order to be clinically applicable, the model should simulate the critical care situation realistically, including anaesthesia, monitoring, sampling, utilising appropriate personnel skill mix, and therapeutic interventions. There are limited data documenting the constitution of ideal technologically advanced large animal critical care practices and all the processes of the animal model. In this paper, we describe the procedure of animal preparation, anaesthesia induction and maintenance, physiologic monitoring, data capture, point-of-care technology, and animal aftercare that has been successfully used to study several novel ovine models of critical illness. The relevant investigations are on respiratory failure due to smoke inhalation, transfusion related acute lung injury, endotoxin-induced proteogenomic alterations, haemorrhagic shock, septic shock, brain death, cerebral microcirculation, and artificial heart studies. We have demonstrated the functionality of monitoring practices during anaesthesia required to provide a platform for undertaking systematic investigations in complex ovine models of critical illness.

Linear and weakly nonlinear stability analyses of cooperative car-following models

Stability analyses have been widely used to better understand the mechanism of traffic jam formation. In this paper, we consider the impact of cooperative systems (a.k.a. connected vehicles) on traffic dynamics and, more precisely, on flow stability. Cooperative systems are emerging technologies enabling communication between vehicles and/or with the infrastructure. In a distributed communication framework, equipped vehicles are able to send and receive information to/from other equipped vehicles. Here, the effects of cooperative traffic are modeled through a general bilateral multianticipative car-following law that improves cooperative drivers' perception of their surrounding traffic conditions within a given communication range. Linear stability analyses are performed for a broad class of car-following models. They point out different stability conditions in both multianticipative and nonmultianticipative situations. To better understand what happens in unstable conditions, information on the shock wave structure is studied in the weakly nonlinear regime by the mean of the reductive perturbation method. The shock wave equation is obtained for generic car-following models by deriving the Korteweg de Vries equations. We then derive traffic-state-dependent conditions for the sign of the solitary wave (soliton) amplitude. This analytical result is verified through simulations. Simulation results confirm the validity of the speed estimate. The variation of the soliton amplitude as a function of the communication range is provided. The performed linear and weakly nonlinear analyses help justify the potential benefits of vehicle-integrated communication systems and provide new insights supporting the future implementation of cooperative systems.

Finding within-organisation spatial information on the web

Information available on company websites can help people navigate to the offices of groups and individuals within the company. Automatically retrieving this within-organisation spatial information is a challenging AI problem This paper introduces a novel unsupervised pattern-based method to extract within-organisation spatial information by taking advantage of HTML structure patterns, together with a novel Conditional Random Fields (CRF) based method to identify different categories of within-organisation spatial information. The results show that the proposed method can achieve a high performance in terms of F-Score, indicating that this purely syntactic method based on web search and an analysis of HTML structure is well-suited for retrieving within-organisation spatial information.

Leveraging of software as a service by small and medium enterprises: Information systems capabilities and organisational complementarities

This research explored how small and medium enterprises can achieve success with software as a service (SaaS) applications from cloud. Based upon an empirical investigation of six growth oriented and early technology adopting small and medium enterprises, this study proposes a SaaS for small and medium enterprise success model with two approaches: one for basic and one for advanced benefits. The basic model explains the effective use of SaaS for achieving informational and transactional benefits. The advanced model explains the enhanced use of software as a service for achieving strategic and transformational benefits. Both models explicate the information systems capabilities and organizational complementarities needed for achieving success with SaaS.

Analysis of word embeddings and sequence features for clinical information extraction

This study investigates the use of unsupervised features derived from word embedding approaches and novel sequence representation approaches for improving clinical information extraction systems. Our results corroborate previous findings that indicate that the use of word embeddings significantly improve the effectiveness of concept extraction models; however, we further determine the influence that the corpora used to generate such features have. We also demonstrate the promise of sequence-based unsupervised features for further improving concept extraction.

An account and analysis of the implementation of various ebook business models at QUT, Australia

QUT (Queensland University of Technology) is a leading university based in the city of Brisbane, Queensland, Australia and is a selectively research intensive university with 2,500 higher degree research students and an overall student population of 45,000 students. The transition from print to online resources is largely completed and the library now provides access to 450,000 print books, 1,000 print journals, 600,000 ebooks, 120,000 ejournals and 100,000 online videos. The ebook collection is now used three times as much as the print book collection. This paper focuses on QUT Library’s ebook strategy and the challenges of building and managing a rapidly growing collection of ebooks using a range of publishers, platforms, and business and financial models. The paper provides an account of QUT Library’s experiences in using Patron Driven Acquisition (PDA) using eBook Library (EBL); the strategic procurement of publisher and subject collections by lease and outright purchase models, the more recent transition to Evidence Based Selection (EBS) options provided by some publishers, and its piloting of etextbook models. The paper provides an in-depth analysis of each of these business models at QUT, focusing on access verses collection development, usage, cost per use, and value for money.

Voice, deliberation, resistance and persuasion through participatory journalism business models

The pervasive use of the World Wide Web by the general population has created a cultural shift throughout the world. It has enabled more people to share more information about more events and issues than was possible before its general use. As a consequence, it has transformed traditional news media’s approach to almost every aspect of journalism, with many organisations restructuring their philosophy and practice to include a variety of participatory spaces/forums where people are free to engage in deliberative dialogue about matters of public importance. This paper draws from an international collective case study that showcases various approaches to participatory online news journalism during the period 1997–2011 (Adams, 2013). The research finds differences in the ways in which public service, commercial, and independent news media give voice to the public, and ultimately in their approach to journalism’s role as the Fourth Estate––one of the key institutions of democracy. The work is framed by the notion that journalism in democratic societies has a crucial role in ensuring citizens are informed and engaged with public affairs. An examination of four media models, OhmyNews International, News Corp Australia (formerly News Limited), the Guardian and the British Broadcasting Corporation (BBC), showcases the various approaches to participatory online news journalism and how each provides different avenues for citizen engagement. Semistructured in-depth interviews with some of the key senior journalists and editors provide specific information on comparisons between the distinctive practices in each of their employer organisations.

Combining propensity and influence models for product adoption prediction

This paper studies the problem of selecting users in an online social network for targeted advertising so as to maximize the adoption of a given product. In previous work, two families of models have been considered to address this problem: direct targeting and network-based targeting. The former approach targets users with the highest propensity to adopt the product, while the latter approach targets users with the highest influence potential – that is users whose adoption is most likely to be followed by subsequent adoptions by peers. This paper proposes a hybrid approach that combines a notion of propensity and a notion of influence into a single utility function. We show that targeting a fixed number of high-utility users results in more adoptions than targeting either highly influential users or users with high propensity.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

Integrating and evaluating neural word embeddings in information retrieval

Recent advances in neural language models have contributed new methods for learning distributed vector representations of words (also called word embeddings). Two such methods are the continuous bag-of-words model and the skipgram model. These methods have been shown to produce embeddings that capture higher order relationships between words that are highly effective in natural language processing tasks involving the use of word similarity and word analogy. Despite these promising results, there has been little analysis of the use of these word embeddings for retrieval. Motivated by these observations, in this paper, we set out to determine how these word embeddings can be used within a retrieval model and what the benefit might be. To this aim, we use neural word embeddings within the well known translation language model for information retrieval. This language model captures implicit semantic relations between the words in queries and those in relevant documents, thus producing more accurate estimations of document relevance. The word embeddings used to estimate neural language models produce translations that differ from previous translation language model approaches; differences that deliver improvements in retrieval effectiveness. The models are robust to choices made in building word embeddings and, even more so, our results show that embeddings do not even need to be produced from the same corpus being used for retrieval.