Social signal processing for pain monitoring using a hidden conditional random field

utomatic pain monitoring has the potential to greatly improve patient diagnosis and outcomes by providing a continuous objective measure. One of the most promising methods is to do this via automatically detecting facial expressions. However, current approaches have failed due to their inability to: 1) integrate the rigid and non-rigid head motion into a single feature representation, and 2) incorporate the salient temporal patterns into the classification stage. In this paper, we tackle the first problem by developing a “histogram of facial action units” representation using Active Appearance Model (AAM) face features, and then utilize a Hidden Conditional Random Field (HCRF) to overcome the second issue. We show that both of these methods improve the performance on the task of pain detection in sequence level compared to current state-of-the-art-methods on the UNBC-McMaster Shoulder Pain Archive.

Business planning, innovation and performance in nascent firms

Debate about the relationships between business planning and performance has been active for decades (Bhidé, 2000; Mintzberg, 1994). While results have been inconclusive, this topic still strongly divides the research community (Brinckmann et al., 2010; Chwolka & Raith, 2011; Delmar & Shane, 2004; Frese, 2009; Gruber, 2007; Honig & Karlsson, 2004). Previous research explored the relationships between innovation and the venture creation process (Amason et al., 2006, Dewar & Dutton, 1986; Jennings et al., 2009). However, the relationships between business planning and innovation have mostly been invoked indirectly in the strategy and entrepreneurship literatures through the notion of uncertainty surrounding the development of innovation. Some posited that planning may be irrelevant due to the iterative process, the numerous changes innovation development entails and the need to be flexible (Brews & Hunt, 1999). Others suggested that planning may facilitate the achievement of goals and overcoming of obstacles (Locke and Latham, 2000), guide the venture in its allocation of resources (Delmar and Shane, 2003) and help to foster the communication about the innovation being developed (Liao & Welsh, 2008). However, the nature and extents of the relationships between business planning, innovation and performance are still largely unknown. Moreover, if the reasons why ventures should engage (Frese, 2009) –or not- (Honig, 2004) in business planning have been investigated quite extensively (Brinckmann et al., 2010), the specific value of business planning for nascent firms developing innovation is still unclear. The objective of this paper is to shed some light on these important aspects by investigating the two following questions on a large sample of random nascent firms: 1) how is business planning use over time by new ventures developing different types and degrees of innovation? 2) how do business planning and innovation impact the performance of the nascent firms? Methods & Key propositions This PSED-type study draws its data from the first three waves of the CAUSEE project where 30,105 Australian households were randomly contacted by phone using a methodology to capture emerging firms (Davidsson, Steffens, Gordon, Reynolds, 2008). This screening led to the identification of 594 nascent ventures (i.e., firms that were not operating yet at the time of the identification) that were willing to participate in the study. Comprehensive phone interviews were conducted with these 594 ventures. Likewise, two comprehensive follow-ups were organised 12 months and 24 months later where 80% of the eligible cases of the previous wave completed the interview. The questionnaire contains specific sections investigating business plans such as: presence or absence, degree of formality and updates of the plan. Four types of innovation are measured along three degrees of intensity to produce a comprehensive continuous measure ranging from 0 to 12 (Dahlqvist & Wiklund, 2011). Other sections informing on the gestation activities, industry and different types of experiences will be used as controls to measure the relationships and the impacts of business planning and innovation on the performance of nascent firms overtime. Results from two rounds of pre-testing informed the design of the instrument included in the main survey. The three waves of data are used to first test and compare the use of planning amongst nascent firms by their degrees of innovation and then to examine their impact on performance overtime through regression analyses. Results and Implications Three waves of data collection have been completed. Preliminary results show that on average, innovative firms are more likely to have a business plans than their low innovative counterpart. They are also most likely to update their plan suggesting a more continuous use of the plan over time than previously thought. Further analyses regarding the relationships between business planning, innovation and performance are undergoing. This paper is expected to contribute to the literature on business planning and innovation by measuring quantitatively their impact on nascent firms activities and performance at different stages of their development. In addition, this study will shed a new light on the business planning-performance relationship by disentangling plans, types of nascent firms regarding their innovation degres and their performance over time. Finally, we expect to increase the understanding of the venture creation process by analysing those questions on nascent firms from a large longitudinal sample of randomly selected ventures. We acknowledge the results from this study will be preliminary and will have to be interpreted with caution as the business planning-performance is not a straightforward relationship (Brinckmann et al., 2010). Meanwhile, we believe that this study is important to the field of entrepreneurship as it provides some much needed insights on the processes used by nascent firms during their creation and early operating stages.

Sunlight and other determinants of circulating 25-hydroxyvitamin D levels in black and white participants in a nationwide U.S. study

Circulating 25-hydroxyvitamin D (25(OH)D), a marker for vitamin D status, is associated with bone health and possibly cancers and other diseases; yet, the determinants of 25(OH)D status, particularly ultraviolet radiation (UVR) exposure, are poorly understood. Determinants of 25(OH)D were analyzed in a subcohort of 1,500 participants of the US Radiologic Technologists (USRT) Study that included whites (n 842), blacks (n 646), and people of other races/ethnicities (n 12). Participants were recruited monthly (20082009) across age, sex, race, and ambient UVR level groups. Questionnaires addressing UVR and other exposures were generally completed within 9 days of blood collection. The relation between potential determinants and 25(OH)D levels was examined through regression analysis in a random two-thirds sample and validated in the remaining one third. In the regression model for the full study population, age, race, body mass index, some seasons, hours outdoors being physically active, and vitamin D supplement use were associated with 25(OH)D levels. In whites, generally, the same factors were explanatory. In blacks, only age and vitamin D supplement use predicted 25(OH)D concentrations. In the full population, determinants accounted for 25 of circulating 25(OH)D variability, with similar correlations for subgroups. Despite detailed data on UVR and other factors near the time of blood collection, the ability to explain 25(OH)D was modest.

Self-regulated learning and executive function : exploring the relationships in a sample of adolescent males

This study investigated relationships between SRL and EF in a sample of 254 school-aged adolescent males. Two hypotheses were tested: that self-reported measures of SRL and EF are closely related and that as different aspects of EF mature during adolescence, the corresponding components of SRL should also improve, leading to an age-related increase in the correlation between EF and SRL. Two self-report instruments were used: the strategies for self-regulated learning survey (SSRLS) and the behavioural rating instrument of executive function (BRIEF). Strong correlations between the measures of EF and SRL were found, especially in areas associated with metacognitive processes. Correlations between EF and SRL were found, with weaker correlations between behavioural regulation and SRL were found to be weaker for the younger participants in the sample while the relationship between EF and SRL appears to grow stronger during the initial years of high school even though self-reported levels of EF along with motivation for SRL and important components of SRL such as goal setting and planning were found to decrease with age. Decreasing levels of motivation for learning during adolescence are speculated to moderate the deployment of SRL and EF in a school context.

Sample size considerations and augmentation of computer experiments

Computer Experiments, consisting of a number of runs of a computer model with different inputs, are now common-place in scientific research. Using a simple fire model for illustration some guidelines are given for the size of a computer experiment. A graph is provided relating the error of prediction to the sample size which should be of use when designing computer experiments. Methods for augmenting computer experiments with extra runs are also described and illustrated. The simplest method involves adding one point at a time choosing that point with the maximum prediction variance. Another method that appears to work well is to choose points from a candidate set with maximum determinant of the variance covariance matrix of predictions.

Iris based identity verification robust to sample presentation security attacks

Iris based identity verification is highly reliable but it can also be subject to attacks. Pupil dilation or constriction stimulated by the application of drugs are examples of sample presentation security attacks which can lead to higher false rejection rates. Suspects on a watch list can potentially circumvent the iris based system using such methods. This paper investigates a new approach using multiple parts of the iris (instances) and multiple iris samples in a sequential decision fusion framework that can yield robust performance. Results are presented and compared with the standard full iris based approach for a number of iris degradations. An advantage of the proposed fusion scheme is that the trade-off between detection errors can be controlled by setting parameters such as the number of instances and the number of samples used in the system. The system can then be operated to match security threat levels. It is shown that for optimal values of these parameters, the fused system also has a lower total error rate.

Student's experiences with traditional bullying and cyberbullying : findings from a Romanian sample

The field of cyberbullying is relatively new and there is no universal consensus on its definition, measurement and intervention. Authors agree that bullying has entered into the digital domain and professionals require the skills to help identify and prevent these behaviours. Ninety two students were surveyed to determine their experience with different types of bullying behaviors (face-to-face, cyberbullying or both), as bully, victim or witness. Our objective was to explore the association between those types of bullying and anxiety. The results suggest a significant association between face-to-face bullying and anxiety. Similarly, there was significant association between experiencing both types of bullying and anxiety. Further studies are required with larger and more diverse samples in order to verify current findings and to test for additional associations.

Classifier selection using sequential error ratio criterion for multi-instance and multi-sample fusion

Classifier selection is a problem encountered by multi-biometric systems that aim to improve performance through fusion of decisions. A particular decision fusion architecture that combines multiple instances (n classifiers) and multiple samples (m attempts at each classifier) has been proposed in previous work to achieve controlled trade-off between false alarms and false rejects. Although analysis on text-dependent speaker verification has demonstrated better performance for fusion of decisions with favourable dependence compared to statistically independent decisions, the performance is not always optimal. Given a pool of instances, best performance with this architecture is obtained for certain combination of instances. Heuristic rules and diversity measures have been commonly used for classifier selection but it is shown that optimal performance is achieved for the `best combination performance' rule. As the search complexity for this rule increases exponentially with the addition of classifiers, a measure - the sequential error ratio (SER) - is proposed in this work that is specifically adapted to the characteristics of sequential fusion architecture. The proposed measure can be used to select a classifier that is most likely to produce a correct decision at each stage. Error rates for fusion of text-dependent HMM based speaker models using SER are compared with other classifier selection methodologies. SER is shown to achieve near optimal performance for sequential fusion of multiple instances with or without the use of multiple samples. The methodology applies to multiple speech utterances for telephone or internet based access control and to other systems such as multiple finger print and multiple handwriting sample based identity verification systems.

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Purpose: Flat-detector, cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. Methods: The rich sources of prior information in IGRT are incorporated into a hidden Markov random field (MRF) model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk (OAR). The voxel labels are estimated using the iterated conditional modes (ICM) algorithm. Results: The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom (CIRS, Inc. model 062). The mean voxel-wise misclassification rate was 6.2%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. Conclusions: By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Random Breath Testing in Australia: Is there an Optimum Level of Intensity?

Background: Random Breath Testing (RBT) is the main drink driving law enforcement tool used throughout Australia. International comparative research considers Australia to have the most successful RBT program compared to other countries in terms of crash reductions (Erke, Goldenbeld, & Vaa, 2009). This success is attributed to the programs high intensity (Erke et al., 2009). Our review of the extant literature suggests that there is no research evidence that indicates an optimal level of alcohol breath testing. That is, we suggest that no research exists to guide policy regarding whether or not there is a point at which alcohol related crashes reach a point of diminishing returns as a result of either saturated or targeted RBT testing. Aims: In this paper we first provide an examination of RBTs and alcohol related crashes across Australian jurisdictions. We then address the question of whether or not an optimal level of random breath testing exists by examining the relationship between the number of RBTs conducted and the occurrence of alcohol-related crashes over time, across all Australian states. Method: To examine the association between RBT rates and alcohol related crashes and to assess whether an optimal ratio of RBT tests per licenced drivers can be determined we draw on three administrative data sources form each jurisdiction. Where possible data collected spans January 1st 2000 to September 30th 2012. The RBT administrative dataset includes the number of Random Breath Tests (RBTs) conducted per month. The traffic crash administrative dataset contains aggregated monthly count of the number of traffic crashes where an individual’s recorded BAC reaches or exceeds 0.05g/ml of alcohol in blood. The licenced driver data were the monthly number of registered licenced drivers spanning January 2000 to December 2011. Results: The data highlights that the Australian story does not reflective of all States and territories. The stable RBT to licenced driver ratio in Queensland (of 1:1) suggests a stable rate of alcohol related crash data of 5.5 per 100,000 licenced drivers. Yet, in South Australia were a relative stable rate of RBT to licenced driver ratio of 1:2 is maintained the rate of alcohol related traffic crashes is substantially less at 3.7 per 100,000. We use joinpoint regression techniques and varying regression models to fit the data and compare the different patterns between jurisdictions. Discussion: The results of this study provide an updated review and evaluation of RBTs conducted in Australia and examines the association between RBTs and alcohol related traffic crashes. We also present an evidence base to guide policy decisions for RBT operations.

Harmonic quality of multilevel cascade inverters with random carrier phase pulse width modulation

The output harmonic quality of N series connected full-bridge dc-ac inverters is investigated. The inverters are pulse width modulated using a common reference signal but randomly phased carrier signals. Through analysis and simulation, probability distributions for inverter output harmonics and vector representations of N carrier phases are combined and assessed. It is concluded that a low total harmonic distortion is most likely to occur and will decrease further as N increases.

Are more city dwellers caught drink driving than country folk? An analysis by random breath testing apprehension rates

Background Random Breath Testing (RBT) remains a central enforcement strategy to deter and apprehend drink drivers in Queensland (Australia). Despite this, there is little published research regarding the exact drink driving apprehension rates across the state as measured through RBT activities. Aims The aim of the current study was to examine the prevalence of apprehending drink drivers in urban versus rural areas. Methods The Queensland Police Service provided data relating to the number of RBT conducted and apprehensions for the period 1 January 2000 to 31 December 2011. Results In the period, 35,082,386 random breath tests (both mobile and stationary) were conducted in Queensland which resulted in 248,173 individuals being apprehended for drink driving offences. Overall drink driving apprehension rates appear to have decreased across time. Close examination of the data revealed that the highest proportion of drink driving apprehensions (when compared with RBT testing rates) was in the Northern and Far Northern regions of Queensland (e.g., rural areas). In contrast, the lowest proportions were observed within the two Brisbane metropolitan regions (e.g., urban areas). However, differences in enforcement styles across the urban and rural regions need to be considered. Discussion and conclusions The research presentation will further outline the major findings of the study in regards to maximising the efficiency of RBT operations both within urban and rural areas of Queensland, Australia.

Child-related factors that influence teacher-child relationships using an Australian national sample

This study assessed the extent to which child-related factors had an impact on teacher-child relationships in Australian childcare settings. Analyses used data from Growing Up in Australia: The Longitudinal Study of Australian Children (LSAC). The sample consisted of 1577 two to three year old children (M= 33.9 months, SD=2.93; 51.5% male). Two separate hierarchical multiple regression analyses were conducted to examine the relation between teachers’ perceptions of their relationships with children and (a) gender, (b), indigenous status, (c), language background other than English, (d), socio-economic position, (e) special health care needs, (f) expression and receptive language concerns, (g) psychosocial competence and problems and (h) temperament factors (approach, persistence and reactivity). Results indicated that special health care needs, receptive language concerns and all three temperament scales (approach, persistence and reactivity) significantly predicted conflict in teacher-child relationships. Close relationships were predicted by being female, indigenous status, higher socio-economic position, not having a special health care need and no expressive language concerns.

Identify disorders in health records using Conditional Random Fields and Metamap: AEHRC at ShARe/CLEF 2013 eHealth Evaluation Lab Task 1

The Australian e-Health Research Centre (AEHRC) recently participated in the ShARe/CLEF eHealth Evaluation Lab Task 1. The goal of this task is to individuate mentions of disorders in free-text electronic health records and map disorders to SNOMED CT concepts in the UMLS metathesaurus. This paper details our participation to this ShARe/CLEF task. Our approaches are based on using the clinical natural language processing tool Metamap and Conditional Random Fields (CRF) to individuate mentions of disorders and then to map those to SNOMED CT concepts. Empirical results obtained on the 2013 ShARe/CLEF task highlight that our instance of Metamap (after ltering irrelevant semantic types), although achieving a high level of precision, is only able to identify a small amount of disorders (about 21% to 28%) from free-text health records. On the other hand, the addition of the CRF models allows for a much higher recall (57% to 79%) of disorders from free-text, without sensible detriment in precision. When evaluating the accuracy of the mapping of disorders to SNOMED CT concepts in the UMLS, we observe that the mapping obtained by our ltered instance of Metamap delivers state-of-the-art e ectiveness if only spans individuated by our system are considered (`relaxed' accuracy).