High level data fusion

We address the question of how to obtain effective fusion of identification information such that it is robust to the quality of this information. As well as technical issues data fusion is encumbered with a collection of (potentially confusing) practical considerations. These considerations are described during the early chapters in which a framework for data fusion is developed. Following this process of diversification it becomes clear that the original question is not well posed and requires more precise specification. We use the framework to focus on some of the technical issues relevant to the question being addressed. We show that fusion of hard decisions through use of an adaptive version of the maximum a posteriori decision rule yields acceptable performance. Better performance is possible using probability level fusion as long as the probabilities are accurate. Of particular interest is the prevalence of overconfidence and the effect it has on fused performance. The production of accurate probabilities from poor quality data forms the latter part of the thesis. Two approaches are taken. Firstly the probabilities may be moderated at source (either analytically or numerically). Secondly, the probabilities may be transformed at the fusion centre. In each case an improvement in fused performance is demonstrated. We therefore conclude that in order to obtain robust fusion care should be taken to model the probabilities accurately; either at the source or centrally.

Cognitive neuroscience and (very) high level vision

THE PURPOSE OF THIS ARTICLE is two-fold, first to provide a general overview of two of the main cognitive neuroscientific techniques available, specifically functional magnetic resonance imaging (fMRI) and transcranial magnetic stimulation (TMS); and secondly to apply these techniques to elaborate a discussion of an aspect of higher level vision, namely implied motion, that is the perception of movement from a static image.

Learning higher-level features with convolutional restricted Boltzmann machines for sentiment analysis

In recent years, learning word vector representations has attracted much interest in Natural Language Processing. Word representations or embeddings learned using unsupervised methods help addressing the problem of traditional bag-of-word approaches which fail to capture contextual semantics. In this paper we go beyond the vector representations at the word level and propose a novel framework that learns higher-level feature representations of n-grams, phrases and sentences using a deep neural network built from stacked Convolutional Restricted Boltzmann Machines (CRBMs). These representations have been shown to map syntactically and semantically related n-grams to closeby locations in the hidden feature space. We have experimented to additionally incorporate these higher-level features into supervised classifier training for two sentiment analysis tasks: subjectivity classification and sentiment classification. Our results have demonstrated the success of our proposed framework with 4% improvement in accuracy observed for subjectivity classification and improved the results achieved for sentiment classification over models trained without our higher level features.

Handling high level of censoring for endovascular aortic repair risk prediction

Feature selection is important in medical field for many reasons. However, selecting important variables is a difficult task with the presence of censoring that is a unique feature in survival data analysis. This paper proposed an approach to deal with the censoring problem in endovascular aortic repair survival data through Bayesian networks. It was merged and embedded with a hybrid feature selection process that combines cox's univariate analysis with machine learning approaches such as ensemble artificial neural networks to select the most relevant predictive variables. The proposed algorithm was compared with common survival variable selection approaches such as; least absolute shrinkage and selection operator LASSO, and Akaike information criterion AIC methods. The results showed that it was capable of dealing with high censoring in the datasets. Moreover, ensemble classifiers increased the area under the roc curves of the two datasets collected from two centers located in United Kingdom separately. Furthermore, ensembles constructed with center 1 enhanced the concordance index of center 2 prediction compared to the model built with a single network. Although the size of the final reduced model using the neural networks and its ensembles is greater than other methods, the model outperformed the others in both concordance index and sensitivity for center 2 prediction. This indicates the reduced model is more powerful for cross center prediction.

Comparing sentence-level features for authorship analysis in Portuguese

In this paper we compare the robustness of several types of stylistic markers to help discriminate authorship at sentence level. We train a SVM-based classifier using each set of features separately and perform sentence-level authorship analysis over corpus of editorials published in a Portuguese quality newspaper. Results show that features based on POS information, punctuation and word / sentence length contribute to a more robust sentence-level authorship analysis. © Springer-Verlag Berlin Heidelberg 2010.

Clinical evaluation of the Grand Seiko Auto Ref/Keratometer WAM-5500

Purpose: A clinical evaluation of the Grand Seiko Auto Ref/Keratometer WAM-5500 (Japan) was performed to evaluate validity and repeatability compared with non-cycloplegic subjective refraction and Javal–Schiotz keratometry. An investigation into the dynamic recording capabilities of the instrument was also conducted. Methods: Refractive error measurements were obtained from 150 eyes of 75 subjects (aged 25.12 ± 9.03 years), subjectively by a masked optometrist, and objectively with the WAM-5500 at a second session. Keratometry measurements from the WAM-5500 were compared to Javal–Schiotz readings. Intratest variability was examined on all subjects, whilst intertest variability was assessed on a subgroup of 44 eyes 7–14 days after the initial objective measures. The accuracy of the dynamic recording mode of the instrument and its tolerance to longitudinal movement was evaluated using a model eye. An additional evaluation of the dynamic mode was performed using a human eye in relaxed and accommodated states. Results: Refractive error determined by the WAM-5500 was found to be very similar (p = 0.77) to subjective refraction (difference, -0.01 ± 0.38 D). The instrument was accurate and reliable over a wide range of refractive errors (-6.38 to +4.88 D). WAM-5500 keratometry values were steeper by approximately 0.05 mm in both the vertical and horizontal meridians. High intertest repeatability was demonstrated for all parameters measured: for sphere, cylinder power and MSE, over 90% of retest values fell within ±0.50 D of initial testing. In dynamic (high-speed) mode, the root-mean-square of the fluctuations was 0.005 ± 0.0005 D and a high level of recording accuracy was maintained when the measurement ring was significantly blurred by longitudinal movement of the instrument head. Conclusion: The WAM-5500 Auto Ref/Keratometer represents a reliable and valid objective refraction tool for general optometric practice, with important additional features allowing pupil size determination and easy conversion into high-speed mode, increasing its usefulness post-surgically following accommodating intra-ocular lens implantation, and as a research tool in the study of accommodation.

The discourse of biology lectures : aspects of its mode and text structure

The present thesis investigates mode related aspects in biology lecture discourse and attempts to identify the position of this variety along the spontaneous spoken versus planned written language continuum. Nine lectures (of 43,000 words) consisting of three sets of three lectures each, given by the three lecturers at Aston University, make up the corpus. The indeterminacy of the results obtained from the investigation of grammatical complexity as measured in subordination motivates the need to take the analysis beyond sentence level to the study of mode related aspects in the use of sentence-initial connectives, sub-topic shifting and paraphrase. It is found that biology lecture discourse combines features typical of speech and writing at sentence as well as discourse level: thus, subordination is more used than co-ordination, but one degree complexity sentence is favoured; some sentence initial connectives are only found in uses typical of spoken language but sub-topic shift signalling (generally introduced by a connective) typical of planned written language is a major feature of the lectures; syntactic and lexical revision and repetition, interrupted structures are found in the sub-topic shift signalling utterance and paraphrase, but the text is also amenable to analysis into sentence like units. On the other hand, it is also found that: (1) while there are some differences in the use of a given feature, inter-speaker variation is on the whole not significant; (2) mode related aspects are often motivated by the didactic function of the variety; and (3) the structuring of the text follows a sequencing whose boundaries are marked by sub-topic shifting and the summary paraphrase. This study enables us to draw four theoretical conclusions: (1) mode related aspects cannot be approached as a simple dichotomy since a combination of aspects of both speech and writing are found in a given feature. It is necessary to go to the level of textual features to identify mode related aspects; (2) homogeneity is dominant in this sample of lectures which suggests that there is a high level of standardization in this variety; (3) the didactic function of the variety is manifested in some mode related aspects; (4) the features studied play a role in the structuring of the text.

Do simple intransitive finger movements consistently activate frontoparietal mirror neuron areas in humans?

The posterior inferior frontal gyrus (pIFG) and anterior inferior parietal lobule (aIPL) form the core regions of the human “mirror neuron system” that matches an observed movement onto its internal motor representation. We used event-related functional MRI to examine whether simple intransitive finger movements evoke “mirror activity” in the pIFG and aIPL. In separate sessions, participants either merely observed visuospatial stimuli or responded to them as quickly as possible with a spatially compatible finger movement. A picture of a relaxed hand with static dots on the tip of the index and little finger was continuously presented as high-level baseline. Four types of stimuli were presented in a pseudorandom order: a color change of a dot, a moving finger, a moving dot, or a simultaneous finger-dot movement. Dot movements were spatially and kinematically matched to finger movements. Participants were faster at imitating a finger movement than performing the same movement in response to a moving dot or a color change of a dot. Though imitative responses were facilitated, fMRI revealed no additional “mirror activity” in the pIFG and aIPL during the observation or imitation of finger movements as opposed to observing or responding to a moving dot. Mere observation of a finger movement alone failed to induce significant activation of the pIFG and aIPL. The lack of a signature of “mirror neuron activity” in the inferior frontoparietal cortex is presumably due to specific features of the task which may have favored stimulus–response mapping based on common spatial coding. We propose that the responsiveness of human frontoparietal mirror neuron areas to simple intransitive movements critically depends on the experimental context.

Towards a multilevel model of the high performance work systems–workplace safety relationship

Human Resource (HR) systems and practices generally referred to as High Performance Work Practices (HPWPs), (Huselid, 1995) (sometimes termed High Commitment Work Practices or High Involvement Work Practices) have attracted much research attention in past decades. Although many conceptualizations of the construct have been proposed, there is general agreement that HPWPs encompass a bundle or set of HR practices including sophisticated staffing, intensive training and development, incentive-based compensation, performance management, initiatives aimed at increasing employee participation and involvement, job safety and security, and work design (e.g. Pfeffer, 1998). It is argued that these practices either directly and indirectly influence the extent to which employees’ knowledge, skills, abilities, and other characteristics are utilized in the organization. Research spanning nearly 20 years has provided considerable empirical evidence for relationships between HPWPs and various measures of performance including increased productivity, improved customer service, and reduced turnover (e.g. Guthrie, 2001; Belt & Giles, 2009). With the exception of a few papers (e.g., Laursen &Foss, 2003), this literature appears to lack focus on how HPWPs influence or foster more innovative-related attitudes and behaviours, extra role behaviors, and performance. This situation exists despite the vast evidence demonstrating the importance of innovation, proactivity, and creativity in its various forms to individual, group, and organizational performance outcomes. Several pertinent issues arise when considering HPWPs and their relationship to innovation and performance outcomes. At a broad level is the issue of which HPWPs are related to which innovation-related variables. Another issue not well identified in research relates to employees’ perceptions of HPWPs: does an employee actually perceive the HPWP –outcomes relationship? No matter how well HPWPs are designed, if they are not perceived and experienced by employees to be effective or worthwhile then their likely success in achieving positive outcomes is limited. At another level, research needs to consider the mechanisms through which HPWPs influence –innovation and performance. The research question here relates to what possible mediating variables are important to the success or failure of HPWPs in impacting innovative behaviours and attitudes and what are the potential process considerations? These questions call for theory refinement and the development of more comprehensive models of the HPWP-innovation/performance relationship that include intermediate linkages and boundary conditions (Ferris, Hochwarter, Buckley, Harrell-Cook, & Frink, 1999). While there are many calls for this type of research to be made a high priority, to date, researchers have made few inroads into answering these questions. This symposium brings together researchers from Australia, Europe, Asia and Africa to examine these various questions relating to the HPWP-innovation-performance relationship. Each paper discusses a HPWP and potential variables that can facilitate or hinder the effects of these practices on innovation- and performance- related outcomes. The first paper by Johnston and Becker explores the HPWPs in relation to work design in a disaster response organization that shifts quickly from business as usual to rapid response. The researchers examine how the enactment of the organizational response is devolved to groups and individuals. Moreover, they assess motivational characteristics that exist in dual work designs (normal operations and periods of disaster activation) and the implications for innovation. The second paper by Jørgensen reports the results of an investigation into training and development practices and innovative work behaviors (IWBs) in Danish organizations. Research on how to design and implement training and development initiatives to support IWBs and innovation in general is surprisingly scant and often vague. This research investigates the mechanisms by which training and development initiatives influence employee behaviors associated with innovation, and provides insights into how training and development can be used effectively by firms to attract and retain valuable human capital in knowledge-intensive firms. The next two papers in this symposium consider the role of employee perceptions of HPWPs and their relationships to innovation-related variables and performance. First, Bish and Newton examine perceptions of the characteristics and awareness of occupational health and safety (OHS) practices and their relationship to individual level adaptability and proactivity in an Australian public service organization. The authors explore the role of perceived supportive and visionary leadership and its impact on the OHS policy-adaptability/proactivity relationship. The study highlights the positive main effects of awareness and characteristics of OHS polices, and supportive and visionary leadership on individual adaptability and proactivity. It also highlights the important moderating effects of leadership in the OHS policy-adaptability/proactivity relationship. Okhawere and Davis present a conceptual model developed for a Nigerian study in the safety-critical oil and gas industry that takes a multi-level approach to the HPWP-safety relationship. Adopting a social exchange perspective, they propose that at the organizational level, organizational climate for safety mediates the relationship between enacted HPWS’s and organizational safety performance (prescribed and extra role performance). At the individual level, the experience of HPWP impacts on individual behaviors and attitudes in organizations, here operationalized as safety knowledge, skills and motivation, and these influence individual safety performance. However these latter relationships are moderated by organizational climate for safety. A positive organizational climate for safety strengthens the relationship between individual safety behaviors and attitudes and individual-level safety performance, therefore suggesting a cross-level boundary condition. The model includes both safety performance (behaviors) and organizational level safety outcomes, operationalized as accidents, injuries, and fatalities. The final paper of this symposium by Zhang and Liu explores leader development and relationship between transformational leadership and employee creativity and innovation in China. The authors further develop a model that incorporates the effects of extrinsic motivation (pay for performance: PFP) and employee collectivism in the leader-employee creativity relationship. The papers’ contributions include the incorporation of a PFP effect on creativity as moderator, rather than predictor in most studies; the exploration of the PFP effect from both fairness and strength perspectives; the advancement of knowledge on the impact of collectivism on the leader- employee creativity link. Last, this is the first study to examine three-way interactional effects among leader-member exchange (LMX), PFP and collectivism, thus, enriches our understanding of promoting employee creativity. In conclusion, this symposium draws upon the findings of four empirical studies and one conceptual study to provide an insight into understanding how different variables facilitate or potentially hinder the influence various HPWPs on innovation and performance. We will propose a number of questions for further consideration and discussion. The symposium will address the Conference Theme of ‘Capitalism in Question' by highlighting how HPWPs can promote financial health and performance of organizations while maintaining a high level of regard and respect for employees and organizational stakeholders. Furthermore, the focus on different countries and cultures explores the overall research question in relation to different modes or stages of development of capitalism.

Predicting answering behaviour in online question answering communities

The value of Question Answering (Q&A) communities is dependent on members of the community finding the questions they are most willing and able to answer. This can be difficult in communities with a high volume of questions. Much previous has work attempted to address this problem by recommending questions similar to those already answered. However, this approach disregards the question selection behaviour of the answers and how it is affected by factors such as question recency and reputation. In this paper, we identify the parameters that correlate with such a behaviour by analysing the users' answering patterns in a Q&A community. We then generate a model to predict which question a user is most likely to answer next. We train Learning to Rank (LTR) models to predict question selections using various user, question and thread feature sets. We show that answering behaviour can be predicted with a high level of success, and highlight the particular features that inuence users' question selections.

The design and validation of an optical coherence tomography-based classification system for focal vitreomacular traction

PurposeTo develop and validate a classification system for focal vitreomacular traction (VMT) with and without macular hole based on spectral domain optical coherence tomography (SD-OCT), intended to aid in decision-making and prognostication.MethodsA panel of retinal specialists convened to develop this system. A literature review followed by discussion on a wide range of cases formed the basis for the proposed classification. Key features on OCT were identified and analysed for their utility in clinical practice. A final classification was devised based on two sequential, independent validation exercises to improve interobserver variability.ResultsThis classification tool pertains to idiopathic focal VMT assessed by a horizontal line scan using SD-OCT. The system uses width (W), interface features (I), foveal shape (S), retinal pigment epithelial changes (P), elevation of vitreous attachment (E), and inner and outer retinal changes (R) to give the acronym WISPERR. Each category is scored hierarchically. Results from the second independent validation exercise indicated a high level of agreement between graders: intraclass correlation ranged from 0.84 to 0.99 for continuous variables and Fleiss' kappa values ranged from 0.76 to 0.95 for categorical variables.ConclusionsWe present an OCT-based classification system for focal VMT that allows anatomical detail to be scrutinised and scored qualitatively and quantitatively using a simple, pragmatic algorithm, which may be of value in clinical practice as well as in future research studies.