Random Gabor based templates for facial expression recognition in images with facial occlusion

Robust facial expression recognition (FER) under occluded face conditions is challenging. It requires robust algorithms of feature extraction and investigations into the effects of different types of occlusion on the recognition performance to gain insight. Previous FER studies in this area have been limited. They have spanned recovery strategies for loss of local texture information and testing limited to only a few types of occlusion and predominantly a matched train-test strategy. This paper proposes a robust approach that employs a Monte Carlo algorithm to extract a set of Gabor based part-face templates from gallery images and converts these templates into template match distance features. The resulting feature vectors are robust to occlusion because occluded parts are covered by some but not all of the random templates. The method is evaluated using facial images with occluded regions around the eyes and the mouth, randomly placed occlusion patches of different sizes, and near-realistic occlusion of eyes with clear and solid glasses. Both matched and mis-matched train and test strategies are adopted to analyze the effects of such occlusion. Overall recognition performance and the performance for each facial expression are investigated. Experimental results on the Cohn-Kanade and JAFFE databases demonstrate the high robustness and fast processing speed of our approach, and provide useful insight into the effects of occlusion on FER. The results on the parameter sensitivity demonstrate a certain level of robustness of the approach to changes in the orientation and scale of Gabor filters, the size of templates, and occlusions ratios. Performance comparisons with previous approaches show that the proposed method is more robust to occlusion with lower reductions in accuracy from occlusion of eyes or mouth.

Inpatient facial expression recognition with SMS alert

Facial expression recognition (FER) has been dramatically developed in recent years, thanks to the advancements in related fields, especially machine learning, image processing and human recognition. Accordingly, the impact and potential usage of automatic FER have been growing in a wide range of applications, including human-computer interaction, robot control and driver state surveillance. However, to date, robust recognition of facial expressions from images and videos is still a challenging task due to the difficulty in accurately extracting the useful emotional features. These features are often represented in different forms, such as static, dynamic, point-based geometric or region-based appearance. Facial movement features, which include feature position and shape changes, are generally caused by the movements of facial elements and muscles during the course of emotional expression. The facial elements, especially key elements, will constantly change their positions when subjects are expressing emotions. As a consequence, the same feature in different images usually has different positions. In some cases, the shape of the feature may also be distorted due to the subtle facial muscle movements. Therefore, for any feature representing a certain emotion, the geometric-based position and appearance-based shape normally changes from one image to another image in image databases, as well as in videos. This kind of movement features represents a rich pool of both static and dynamic characteristics of expressions, which playa critical role for FER. The vast majority of the past work on FER does not take the dynamics of facial expressions into account. Some efforts have been made on capturing and utilizing facial movement features, and almost all of them are static based. These efforts try to adopt either geometric features of the tracked facial points, or appearance difference between holistic facial regions in consequent frames or texture and motion changes in loca- facial regions. Although achieved promising results, these approaches often require accurate location and tracking of facial points, which remains problematic.

Determinants of physical activity in middle school children

Objective To evaluate the theory of reasoned action (TRA) and planned behavior (TPB) in predicting moderate-to-vigorous physical activity (MVPA) in sixth-grade youth. Methods One hundred ninety-eight students completed a questionnaire measuring attitudes, subjective norms, perceived behavioral control, and intentions to be active. MVPA was measured using the CSA 7,164 accelerometer. Results Although demonstrating an acceptable fit, the TRA and TPB accounted for only a small percentage of the variance in MVPA. In support of the TPB: the addition: of control perceptions to the reasoned! action model! added to the prediction of intentions and MVPA. Conclusion Within our sample of sixth graders, the utility of the, TRA or TPB;as a framework for activity interventions appears to be limited.

Root caries patterns and risk factors of middle-aged and elderly people in China

The objectives of this study were to describe root caries patterns of Chinese adults and to analyze the effect of selected demographic and socioeconomic factors on these patterns. A total sample of 1080 residents aged 35-44-years-old and 1080 residents aged 65-74-years-old from three urban and three rural survey sites in Hubei Province participated in both an oral health interview and a clinical oral health examination. Root surface caries prevalence rates were 13.1% in the middle-aged group and 43.9% in the elderly group. The mean number of teeth affected by caries in the middle-aged group was reported at 0.21 and 1.0 in the elderly group. Mean Root Caries Index (RCI) scores of the middle-aged were reported at 6.29 and elderly subjects were reported at 11.95. Elderly people living in rural areas reported a higher RCI score (13.24) than those living in urban areas (10.70). A significantly higher frequency of root surface caries was observed in elderly participants (P < 0.001, OR = 3.80) and ethnic minorities (P < 0.001, OR = 1.93). In addition, smokers, nontea drinkers, and those with an annual household income of 10,000 yuan or less tended to have higher caries prevalence. RCI figures for the different tooth types ranged from 1% to 16%, indicating a wide variation in attack rates. In conclusion, our study suggests that root surface caries occurrence is high among the Chinese adult population, especially older adults. With an increasing number of retained teeth in both middle-aged and elderly people, root caries is a growing disease in the People's Republic of China which deserves more attention in future research.

A pilot study on affective classification of facial images for emerging news topics

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from real-world resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.

Third harmonic generation of the surface wave in the semiconductor-metal slowing-down structure

A nonlinear process is considered of the surface wave third harmonics generation in a slowing-down semiconductor-metal structure. The process is conditioned by non-parabolicity of the charge carrier dispersion law. It is shown that in narrow-gap semiconducting materials it is necessary to account for the process together with the surface wave second harmonics generation conditioned by nonlinearity of quasi-hydrodynamics and the Maxwell equations. The conclusion is made that the third harmonies amplitude in narrow-gap semiconductors may exceed substantially the signal amplitude at the 3w frequency in a gas plasma and be of the same order with the surface waves second harmonies amplitude.

Clinical impacts of mammalian target of rapamycin expression in human colorectal cancers

This study investigated the clinicopathologic roles of mammalian target of rapamycin (mTOR) expression and its relationship to carcinogenesis and tumor progression in a colorectal adenoma-adenocarcinoma model. Two colon cancer cell lines with different pathologic stages (SW480 and SW48) and 1 normal colonic epithelial cell line (FHC) were used, in addition to 119 colorectal adenocarcinomas and 32 adenomas. mTOR expression profiles at messenger RNA (mRNA) and protein levels were investigated in the cells and tissues using real-time quantification polymerase chain reaction and immunohistochemistry. The findings were correlated with the clinicopathologic features of the tumors. The colon cell line from stage III cancer (SW48) showed higher expression of mTOR mRNA than that from stage II cancer (SW480). At the tissue level, mTOR showed higher mRNA and protein expression in colorectal carcinoma than in adenoma. The mRNA and protein expression was correlated with each other in approximately one-third of the carcinomas and adenomas. High levels of mTOR mRNA expression were noted more in carcinoma or adenoma arising from the distal portion of the large intestine (P = .025 and .019, respectively). Within the colorectal cancer population, a high level of expression of mTOR mRNA was related to the presence of lymph node metastases (P = .031), advanced pathologic stage (P = .05), and presence of persistent disease or tumor recurrence (P = .035). To conclude, the study has indicated that mTOR is likely to be involved in the development and progression of colorectal cancer and is linked to cancer initiation, invasiveness, and progression.

Studying upper-limb kinematic using inertial sensors embedded in smartphones

Background: In recent years, there have been investigations concerning upper-limbs kinematics by various devices. The latest generation of smartphones often includes inertial sensors with subunits which can detect inertial kinematics. The use of smartphones is presented as a convenient and portable analysis method for studying kinematics in terms of angular mobility and linear acceleration Objective: The aim of this study was to study humerus kinematics through six physical properties that correspond to angular mobility and acceleration in the three axes of space, obtained by a smartphone. Methods: This cross-sectional study recruited healthy young adult subjects. Descriptive and anthropometric independent variables related to age, gender, weight, size, and BMI were included. Six physical properties were included corresponding to two dependent variables for each of three special axes: mobility angle (degrees) and lineal acceleration (meters/seconds2), which were obtained thought the inertial measurement sensor embedded in the iPhone4 smartphone equipped with three two elements for the detection of kinematic variables: a gyroscope and an accelerometer. Apple uses an LIS302DL accelerometer in the iPhone4. The application used to obtain kinematic data was xSensor Pro, Crossbow Technology, Inc., available at the Apple AppStore. The iPhone4 has storage capacity of 20MB. The data-sampling rate was set to 32 Hz, and the data for each analytical task was transmitted as email for analysis and postprocessing The iPhone4 was placed in the right half of the body of each subject located in the middle third of the humerus slightly posterior snugly secured by a neoprene fixation belt. Tasks were explained concisely and clearly. The beginning and the end were decided by a verbal order by the researcher. Participants were placed standing, starting from neutral position, performing the following analytical tasks: 180º right shoulder abduction (eight repetitions) and, after a break of about 3 minutes, 180º right shoulder flexion (eight repetitions). Both tasks were performed with the elbow extended, wrist in neutral position and the palmar area of the hand toward the midline at the beginning and end of the movement. Results: A total of 11 subjects (8 men, 3 woman) were measured, whose mean of age was 24.7 years (SD = 4.22 years) and their average BMI was 22.64 Kg/m2 (SD = 2.29 Kg/m2). The mean of angular mobility collected by the smartphone was bigger in pitch axis for flexion (= 157.28°, SD= 12.35°) and abduction (= 151.71°, SD= 9.70°). With regard to acceleration, the highest peak mean value was shown in the Y motion axis during flexion (= 19.5°/s2, SD = 0.8°/s2) and abduction (= 19.4°/s2, SD = 0.8°/s2). Also, descriptive graphics of analytical tasks performed were obtained. Conclusions: This study shows how humerus contributes to upper-limb motion and it identified movement patterns. Therefore, it supports smartphone as a useful device to analyze upper-limb kinematics. Thanks to this study it´s possible to develop a simple application that facilitates the evaluation of the patient.

Progress and challenges of disaster health management in China : a scoping review

Background Despite the importance of an effective health system response to various disasters, relevant research is still in its infancy, especially in middle- and low-income countries. Objective This paper provides an overview of the status of disaster health management in China, with its aim to promote the effectiveness of the health response for reducing disaster-related mortality and morbidity. Design A scoping review method was used to address the recent progress of and challenges to disaster health management in China. Major health electronic databases were searched to identify English and Chinese literature that were relevant to the research aims. Results The review found that since 2003 considerable progress has been achieved in the health disaster response system in China. However, there remain challenges that hinder effective health disaster responses, including low standards of disaster-resistant infrastructure safety, the lack of specific disaster plans, poor emergency coordination between hospitals, lack of portable diagnostic equipment and underdeveloped triage skills, surge capacity, and psychological interventions. Additional challenges include the fragmentation of the emergency health service system, a lack of specific legislation for emergencies, disparities in the distribution of funding, and inadequate cost-effective considerations for disaster rescue. Conclusions One solution identified to address these challenges appears to be through corresponding policy strategies at multiple levels (e.g. community, hospital, and healthcare system level).

Proceedings of the Third International Workshop on Theory and Applications of Process Visualization

This is the third TAProViz workshop being run at BPM. The intention this year is to consolidate on the results of the previous successful workshops by further developing this important topic, identifying the key research topics of interest to the BPM visualization community. We note this year the continuing interest in the visualisation of process mining data and resultant process models. More info at: http://wst.univie.ac.at/topics/taproviz14/

Psychological health of medical and dental students in Saudi Arabia : a longitudinal study

Introduction: Many studies have indicated the poor psychological health of medical and dental students. However, few studies have assessed the longitudinal trajectory of that psychological health at different times in an academic year. Aim: To evaluate the positive and negative aspects of psychological health among preclinical medical and dental students in Saudi Arabia prospectively. Methods: A total of 317 preclinical medical and dental students were recruited for a longitudinal study design from second and third-year students at Umm Al-Qura University in the 2012-2013 academic year. The students were assessed at the middle of the first term and followed up after 3-monthes at the beginning of the second term. Questionnaires included assessment of depression, anxiety, stress, self-efficacy, and satisfaction with life. Results: Depression, anxiety, stress, and satisfaction with life were improved significantly at the beginning of the second term, whereas self-efficacy did not change significantly. The medical, female, and third-year student subgroups had the most significant changes. Depression and stress were significantly changed at the beginning of the second term in most demographic subgroups. Conclusion: Preclinical medical and dental students have different psychological health levels at different times of the same academic year. It is recommended to consider time of data collection when analyzing the results of such studies.

Facial motion engages predictive visual mechanisms

We employed a novel cuing paradigm to assess whether dynamically versus statically presented facial expressions differentially engaged predictive visual mechanisms. Participants were presented with a cueing stimulus that was either the static depiction of a low intensity expressed emotion; or a dynamic sequence evolving from a neutral expression to the low intensity expressed emotion. Following this cue and a backwards mask, participants were presented with a probe face that displayed either the same emotion (congruent) or a different emotion (incongruent) with respect to that displayed by the cue although expressed at a high intensity. The probe face had either the same or different identity from the cued face. The participants' task was to indicate whether or not the probe face showed the same emotion as the cue. Dynamic cues and same identity cues both led to a greater tendency towards congruent responding, although these factors did not interact. Facial motion also led to faster responding when the probe face was emotionally congruent to the cue. We interpret these results as indicating that dynamic facial displays preferentially invoke predictive visual mechanisms, and suggest that motoric simulation may provide an important basis for the generation of predictions in the visual system.

Facial emotion modulates the neural mechanisms responsible for short interval time perception

Emotionally arousing events can distort our sense of time. We used mixed block/event-related fMRI design to establish the neural basis for this effect. Nineteen participants were asked to judge whether angry, happy and neutral facial expressions that varied in duration (from 400 to 1,600 ms) were closer in duration to either a short or long duration they learnt previously. Time was overestimated for both angry and happy expressions compared to neutral expressions. For faces presented for 700 ms, facial emotion modulated activity in regions of the timing network Wiener et al. (NeuroImage 49(2):1728–1740, 2010) namely the right supplementary motor area (SMA) and the junction of the right inferior frontal gyrus and anterior insula (IFG/AI). Reaction times were slowest when faces were displayed for 700 ms indicating increased decision making difficulty. Taken together with existing electrophysiological evidence Ng et al. (Neuroscience, doi: 10.3389/fnint.2011.00077, 2011), the effects are consistent with the idea that facial emotion moderates temporal decision making and that the right SMA and right IFG/AI are key neural structures responsible for this effect.

Brain networks subserving the evaluation of static and dynamic facial expressions

Because moving depictions of face emotion have greater ecological validity than their static counterparts, it has been suggested that still photographs may not engage ‘authentic’ mechanisms used to recognize facial expressions in everyday life. To date, however, no neuroimaging studies have adequately addressed the question of whether the processing of static and dynamic expressions rely upon different brain substrates. To address this, we performed an functional magnetic resonance imaging (fMRI) experiment wherein participants made emotional expression discrimination and Sex discrimination judgements to static and moving face images. Compared to Sex discrimination, Emotion discrimination was associated with widespread increased activation in regions of occipito-temporal, parietal and frontal cortex. These regions were activated both by moving and by static emotional stimuli, indicating a general role in the interpretation of emotion. However, portions of the inferior frontal gyri and supplementary/pre-supplementary motor area showed task by motion interaction. These regions were most active during emotion judgements to static faces. Our results demonstrate a common neural substrate for recognizing static and moving facial expressions, but suggest a role for the inferior frontal gyrus in supporting simulation processes that are invoked more strongly to disambiguate static emotional cues.