Towards bio-inspired place recognition over multiple spatial scales

This paper presents a new multi-scale place recognition system inspired by the recent discovery of overlapping, multi-scale spatial maps stored in the rodent brain. By training a set of Support Vector Machines to recognize places at varying levels of spatial specificity, we are able to validate spatially specific place recognition hypotheses against broader place recognition hypotheses without sacrificing localization accuracy. We evaluate the system in a range of experiments using cameras mounted on a motorbike and a human in two different environments. At 100% precision, the multiscale approach results in a 56% average improvement in recall rate across both datasets. We analyse the results and then discuss future work that may lead to improvements in both robotic mapping and our understanding of sensory processing and encoding in the mammalian brain.

Towards condition-invariant, top-down visual place recognition

In this paper we present a novel place recognition algorithm inspired by recent discoveries in human visual neuroscience. The algorithm combines intolerant but fast low resolution whole image matching with highly tolerant, sub-image patch matching processes. The approach does not require prior training and works on single images (although we use a cohort normalization score to exploit temporal frame information), alleviating the need for either a velocity signal or image sequence, differentiating it from current state of the art methods. We demonstrate the algorithm on the challenging Alderley sunny day – rainy night dataset, which has only been previously solved by integrating over 320 frame long image sequences. The system is able to achieve 21.24% recall at 100% precision, matching drastically different day and night-time images of places while successfully rejecting match hypotheses between highly aliased images of different places. The results provide a new benchmark for single image, condition-invariant place recognition.

Predicting fault-prone software modules with rank sum classification

The detection and correction of defects remains among the most time consuming and expensive aspects of software development. Extensive automated testing and code inspections may mitigate their effect, but some code fragments are necessarily more likely to be faulty than others, and automated identification of fault prone modules helps to focus testing and inspections, thus limiting wasted effort and potentially improving detection rates. However, software metrics data is often extremely noisy, with enormous imbalances in the size of the positive and negative classes. In this work, we present a new approach to predictive modelling of fault proneness in software modules, introducing a new feature representation to overcome some of these issues. This rank sum representation offers improved or at worst comparable performance to earlier approaches for standard data sets, and readily allows the user to choose an appropriate trade-off between precision and recall to optimise inspection effort to suit different testing environments. The method is evaluated using the NASA Metrics Data Program (MDP) data sets, and performance is compared with existing studies based on the Support Vector Machine (SVM) and Naïve Bayes (NB) Classifiers, and with our own comprehensive evaluation of these methods.

High dietary diversity is associated with obesity in Sri Lankan adults : an evaluation of three dietary scores

Background Dietary diversity is recognized as a key element of a high quality diet. However, diets that offer a greater variety of energy-dense foods could increase food intake and body weight. The aim of this study was to explore association of diet diversity with obesity in Sri Lankan adults. Methods Six hundred adults aged > 18 years were randomly selected by using multi-stage stratified sample. Dietary intake assessment was undertaken by a 24 hour dietary recall. Three dietary scores, Dietary Diversity Score (DDS), Dietary Diversity Score with Portions (DDSP) and Food Variety Score (FVS) were calculated. Body mass index (BMI) ≥ 25 kg.m-2 is defined as obese and Asian waist circumference cut-offs were used diagnosed abdominal obesity. Results Mean of DDS for men and women were 6.23 and 6.50 (p=0.06), while DDSP was 3.26 and 3.17 respectively (p=0.24). FVS values were significantly different between men and women 9.55 and 10.24 (p=0.002). Dietary diversity among Sri Lankan adults was significantly associated with gender, residency, ethnicity, education level but not with diabetes status. As dietary scores increased, the percentage consumption was increased in most of food groups except starches. Obese and abdominal obese adults had the highest DDS compared to non obese groups (p<0.05). With increased dietary diversity the level of BMI, waist circumference and energy consumption was significantly increased in this population. Conclusion Our data suggests that dietary diversity is positively associated with several socio-demographic characteristics and obesity among Sri Lankan adults. Although high dietary diversity is widely recommended, public health messages should emphasize to improve dietary diversity in selective food items.

Lesions in the bed nucleus of the stria terminalis disrupt corticosterone and freezing responses elicited by a contextual but not by a specific cue-conditioned fear stimulus

The bed nucleus of the stria terminalis (BNST) is believed to be a critical relay between the central nucleus of the amygdala (CE) and the paraventricular nucleus of the hypothalamus in the control of hypothalamic–pituitary– adrenal (HPA) responses elicited by conditioned fear stimuli. If correct, lesions of CE or BNST should block expression of HPA responses elicited by either a specific conditioned fear cue or a conditioned context. To test this, rats were subjected to cued (tone) or contextual classical fear conditioning. Two days later, electrolytic or sham lesions were placed in CE or BNST. After 5 days, the rats were tested for both behavioral (freezing) and neuroendocrine (corticosterone) responses to tone or contextual cues. CE lesions attenuated conditioned freezing and corticosterone responses to both tone and con- text. In contrast, BNST lesions attenuated these responses to contextual but not tone stimuli. These results suggest CE is indeed an essential output of the amygdala for the expres- sion of conditioned fear responses, including HPA re- sponses, regardless of the nature of the conditioned stimu- lus. However, because lesions of BNST only affected behav- ioral and endocrine responses to contextual stimuli, the results do not support the notion that BNST is critical for HPA responses elicited by conditioned fear stimuli in general. Instead, the BNST may be essential specifically for contex- tual conditioned fear responses, including both behavioral and HPA responses, by virtue of its connections with the hippocampus, a structure essential to contextual condition- ing. The results are also not consistent with the hypothesis that BNST is only involved in unconditioned aspects of fear and anxiety.

Online self-supervised multi-instance segmentation of dynamic objects

This paper presents a method for the continuous segmentation of dynamic objects using only a vehicle mounted monocular camera without any prior knowledge of the object’s appearance. Prior work in online static/dynamic segmentation is extended to identify multiple instances of dynamic objects by introducing an unsupervised motion clustering step. These clusters are then used to update a multi-class classifier within a self-supervised framework. In contrast to many tracking-by-detection based methods, our system is able to detect dynamic objects without any prior knowledge of their visual appearance shape or location. Furthermore, the classifier is used to propagate labels of the same object in previous frames, which facilitates the continuous tracking of individual objects based on motion. The proposed system is evaluated using recall and false alarm metrics in addition to a new multi-instance labelled dataset to evaluate the performance of segmenting multiple instances of objects.

De-Identification of health records using Anonym: Effectiveness and robustness across datasets

Objective Evaluate the effectiveness and robustness of Anonym, a tool for de-identifying free-text health records based on conditional random fields classifiers informed by linguistic and lexical features, as well as features extracted by pattern matching techniques. De-identification of personal health information in electronic health records is essential for the sharing and secondary usage of clinical data. De-identification tools that adapt to different sources of clinical data are attractive as they would require minimal intervention to guarantee high effectiveness. Methods and Materials The effectiveness and robustness of Anonym are evaluated across multiple datasets, including the widely adopted Integrating Biology and the Bedside (i2b2) dataset, used for evaluation in a de-identification challenge. The datasets used here vary in type of health records, source of data, and their quality, with one of the datasets containing optical character recognition errors. Results Anonym identifies and removes up to 96.6% of personal health identifiers (recall) with a precision of up to 98.2% on the i2b2 dataset, outperforming the best system proposed in the i2b2 challenge. The effectiveness of Anonym across datasets is found to depend on the amount of information available for training. Conclusion Findings show that Anonym compares to the best approach from the 2006 i2b2 shared task. It is easy to retrain Anonym with new datasets; if retrained, the system is robust to variations of training size, data type and quality in presence of sufficient training data.

Process compliance analysis based on behavioural profiles

Process compliance measurement is getting increasing attention in companies due to stricter legal requirements and market pressure for operational excellence. In order to judge on compliance of the business processing, the degree of behavioural deviation of a case, i.e., an observed execution sequence, is quantified with respect to a process model (referred to as fitness, or recall). Recently, different compliance measures have been proposed. Still, nearly all of them are grounded on state-based techniques and the trace equivalence criterion, in particular. As a consequence, these approaches have to deal with the state explosion problem. In this paper, we argue that a behavioural abstraction may be leveraged to measure the compliance of a process log – a collection of cases. To this end, we utilise causal behavioural profiles that capture the behavioural characteristics of process models and cases, and can be computed efficiently. We propose different compliance measures based on these profiles, discuss the impact of noise in process logs on our measures, and show how diagnostic information on non-compliance is derived. As a validation, we report on findings of applying our approach in a case study with an international service provider.

Teaching and using analogy in law

Analogy plays a central role in legal reasoning, yet how to analogize is poorly taught and poorly practiced. We all recognize when legal analogies are being made: when a law professor suggests a difficult hypothetical in class and a student tentatively guesses at the answer based on the cases she read the night before, when an attorney advises a client to settle because a previous case goes against him, or when a judge adopts one precedent over another on the basis that it better fits the present case. However, when it comes to explaining why certain analogies are compelling, persuasive, or better than the alternative, lawyers usually draw a blank. The purpose of this article is to provide a simple model that can be used to teach and to learn how analogy actually works, and what makes one analogy superior to a competing analogy. The model is drawn from a number of theories of analogy making in cognitive science. Cognitive science is the “long-term enterprise to understand the mind scientifically.” The field studies the mechanisms that are involved in cognitive processes like thinking, memory, learning, and recall; and one of its main foci has been on how people construct analogies. The lessons from cognitive science theories of analogy can be applied to legal analogies to give students and lawyers a better understanding of this fundamental process in legal reasoning.

Clinical use of objective measures of physical activity

With measurement of physical activity becoming more common in clinical practice, it is imperative that healthcare professionals become more knowledgeable about the different methods available to objectively measure physical activity behaviour. Objective measures do not rely on information provided by the patient, but instead measure and record the biomechanical or physiological consequences of performing physical activity, often in real time. As such, objective measures are not subject to the reporting bias or recall problems associated with self-report methods. The purpose of this article was to provide an overview of the different methods used to objectively measure physical activity in clinical practice. The review was delimited to heart rate monitoring, accelerometers and pedometers since their small size, low participant burden and relatively low cost make these objective measures appropriate for use in clinical practice settings. For each measure, strengths and weakness were discussed; and whenever possible, literature-based examples of implementation were provided.

Comparison of 3 accelerometer data reduction approaches, step counts, and 2 self-report measures for estimating physical activity in free-living adults

Background Accelerometers have become one of the most common methods of measuring physical activity (PA). Thus, validity of accelerometer data reduction approaches remains an important research area. Yet, few studies directly compare data reduction approaches and other PA measures in free-living samples. Objective To compare PA estimates provided by 3 accelerometer data reduction approaches, steps, and 2 self-reported estimates: Crouter's 2-regression model, Crouter's refined 2-regression model, the weighted cut-point method adopted in the National Health and Nutrition Examination Survey (NHANES; 2003-2004 and 2005-2006 cycles), steps, IPAQ, and 7-day PA recall. Methods A worksite sample (N = 87) completed online-surveys and wore ActiGraph GT1M accelerometers and pedometers (SW-200) during waking hours for 7 consecutive days. Daily time spent in sedentary, light, moderate, and vigorous intensity activity and percentage of participants meeting PA recommendations were calculated and compared. Results Crouter's 2-regression (161.8 +/- 52.3 minutes/day) and refined 2-regression (137.6 +/- 40.3 minutes/day) models provided significantly higher estimates of moderate and vigorous PA and proportions of those meeting PA recommendations (91% and 92%, respectively) as compared with the NHANES weighted cut-point method (39.5 +/- 20.2 minutes/day, 18%). Differences between other measures were also significant. Conclusions When comparing 3 accelerometer cut-point methods, steps, and self-report measures, estimates of PA participation vary substantially.

Neurological consequences of diabetic ketoacidosis at initial presentation of type 1 diabetes in a prospective cohort study of children

OBJECTIVE To investigate the impact of new-onset diabetic ketoacidosis (DKA) during child- hood on brain morphology and function. RESEARCH DESIGN AND METHODS Patients aged 6–18 years with and without DKA at diagnosis were studied at four time points: <48 h, 5 days, 28 days, and 6 months postdiagnosis. Patients under- went magnetic resonance imaging (MRI) and spectroscopy with cognitive assess- ment at each time point. Relationships between clinical characteristics at presentation and MRI and neurologic outcomes were examined using multiple linear regression, repeated-measures, and ANCOVA analyses. RESULTS Thirty-six DKA and 59 non-DKA patients were recruited between 2004 and 2009. With DKA, cerebral white matter showed the greatest alterations with increased total white matter volume and higher mean diffusivity in the frontal, temporal, and parietal white matter. Total white matter volume decreased over the first 6 months. For gray matter in DKA patients, total volume was lower at baseline and increased over 6 months. Lower levels of N-acetylaspartate were noted at base- line in the frontal gray matter and basal ganglia. Mental state scores were lower at baseline and at 5 days. Of note, although changes in total and regional brain volumes over the first 5 days resolved, they were associated with poorer delayed memory recall and poorer sustained and divided attention at 6 months. Age at time of presentation and pH level were predictors of neuroimaging and functional outcomes. CONCLUSIONS DKA at type 1 diabetes diagnosis results in morphologic and functional brain changes. These changes are associated with adverse neurocognitive outcomes in the medium term.

Correlates of physical activity in male and female youth

This study examined associations between psychosocial factors and physical activity in a group of youth (n = 520). Students completed the Previous Day Physical Activity Recall and a survey of potential determinants of physical activity. Regression analyses of intentions to be physically active revealed that enjoyment and self-efficacy predicted intentions for both males and females. Attitudes predicted moderate to vigorous activity (MVPA), and enjoyment and self-efficacy predicted vigorous activity (VPA) for males. Self-efficacy predicted both MVPA and VPA for females. The findings suggest that intervention programs targeted at youth should include developmentally appropriate activities that are fun and promote physical activity self-efficacy.

Physical activity patterns of Singaporean adolescents

The purpose of this study was to document the level of physical activity and sedentary behavior in a representative sample of Singaporean adolescents. A random sample of 1,827 secondary school students from six secondary schools (929 boys, 898 girls, mean age 14.9 +/- 1.2 yr) completed the Three-Day Physical Activity Recall (3DPAR) self-report instrument. Approximately 63% of Singaporean high school students met current guidelines requiring 60 min of moderate to vigorous physical activity daily. Just over half (51.6%) met the guideline calling for regular vigorous physical activity. Across all grade levels, boys were consistently more active than girls. More than 70% of Singaporean high school students exceeded the recommended 2 hours per day of electronic media use. Collectively, these findings suggest that a significant proportion of Singaporean adolescents are not sufficiently active and are in need of programs to promote physical activity and decrease sedentary behavior.

Tracking of physical activity, physical inactivity, and health-related physical fitness in rural youth

This study examined the tracking of selected measures of physical activity, inactivity, and fitness in a cohort of rural youth. Students (N = 181, 54.7% female, 63.5% African American) completed test batteries during their fifth-(age = 10.7 +/- 0.7 years), sixth-, and seventh-grade years. The Previous Day Physical Activity Recall (PDPAR) was used to assess 30-min blocks of vigorous physical activity (VPA), moderate-to-vigorous physical activity (MVPA), TV watching and other sedentary activities, and estimated energy expenditure (EE). Fitness measures included the PWC 170 cycle ergometer test, strength tests, triceps skinfold thickness, and BMI. Intraclass correlation coefficients (ICCs) for VPA, MVPA, and after-school EE ranged from 0.63 to 0.78. ICCs ranged from 0.49 to 0.71 for measures of inactivity and from 0.78 to 0.82 for the fitness measures. These results indicate that measures of physical activity, inactivity, and physical fitness tend to track during the transition from elementary to middle school.