The Belfast Induced Natural Emotion Database

For many years psychological research on facial expression of emotion has relied heavily on a recognition paradigm based on posed static photographs. There is growing evidence that there may be fundamental differences between the expressions depicted in such stimuli and the emotional expressions present in everyday life. Affective computing, with its pragmatic emphasis on realism, needs examples of natural emotion. This paper describes a unique database containing recordings of mild to moderate emotionally coloured responses to a series of laboratory based emotion induction tasks. The recordings are accompanied by information on self-report of emotion and intensity, continuous trace-style ratings of valence and intensity, the sex of the participant, the sex of the experimenter, the active or passive nature of the induction task and it gives researchers the opportunity to compare expressions from people from more than one culture.

Illumination invariant facial recognition using a piecewise-constant lighting model

In this paper we demonstrate a simple and novel illumination model that can be used for illumination invariant facial recognition. This model requires no prior knowledge of the illumination conditions and can be used when there is only a single training image per-person. The proposed illumination model separates the effects of illumination over a small area of the face into two components; an additive component modelling the mean illumination and a multiplicative component, modelling the variance within the facial area. Illumination invariant facial recognition is performed in a piecewise manner, by splitting the face image into blocks, then normalizing the illumination within each block based on the new lighting model. The assumptions underlying this novel lighting model have been verified on the YaleB face database. We show that magnitude 2D Fourier features can be used as robust facial descriptors within the new lighting model. Using only a single training image per-person, our new method achieves high (in most cases 100%) identification accuracy on the YaleB, extended YaleB and CMU-PIE face databases.

Neonatal Facial Coding System for assessing postoperative pain in infants:item reduction is valid and feasible

The objectives of this study were to: (1). evaluate the validity of the Neonatal Facial Coding System (NFCS) for assessment of postoperative pain and (2). explore whether the number of NFCS facial actions could be reduced for assessing postoperative pain.

Bedside application of the Neonatal Facial Coding System in pain assessment of premature neonates

Assessment of infant pain is a pressing concern, especially within the context of neonatal intensive care where infants may be exposed to prolonged and repeated pain during lengthy hospitalization. In the present study the feasibility of carrying out the complete Neonatal Facial Coding System (NFCS) in real time at bedside, specifically reliability, construct and concurrent validity, was evaluated in a tertiary level Neonatal Intensive Care Unit (NICU). Heel lance was used as a model of procedural pain, and observed with n = 40 infants at 32 weeks gestational age. Infant sleep/wake state, NFCS facial activity and specific hand movements were coded during baseline, unwrap, swab, heel lance, squeezing and recovery events. Heart rate was recorded continuously and digitally sampled using a custom designed computer system. Repeated measures analysis of variance (ANOVA) showed statistically significant differences across events for facial activity (P <0.0001) and heart rate (P <0.0001). Planned comparisons showed facial activity unchanged during baseline, swab and unwrap, then increased significantly during heel lance (P <0.0001), increased further during squeezing (P <0.003), then decreased during recovery (P <0.0001). Systematic shifts in sleep/wake state were apparent. Rise in facial activity was consistent with increased heart rate, except that facial activity more closely paralleled initiation of the invasive event. Thus facial display was more specific to tissue damage compared with heart rate. Inter-observer reliability was high. Construct validity of the NFCS at bedside was demonstrated as invasive procedures were distinguished from tactile. While bedside coding of behavior does not permit raters to be blind to events, mechanical recording of heart rate allowed for an independent source of concurrent validation for bedside application of the NFCS scale.

The expression of pain in infants and toddlers:developmental changes in facial action

Age-related changes in the facial expression of pain during the first 18 months of life have important implications for our understanding of pain and pain assessment. We examined facial reactions video recorded during routine immunization injections in 75 infants stratified into 2-, 4-, 6-, 12-, and 18-month age groups. Two facial coding systems differing in the amount of detail extracted were applied to the records. In addition, parents completed a brief questionnaire that assessed child temperament and provided background information. Parents' efforts to soothe the children also were described. While there were consistencies in facial displays over the age groups, there also were differences on both measures of facial activity, indicating systematic variation in the nature and severity of distress. The least pain was expressed by the 4-month age group. Temperament was not related to the degree of pain expressed. Systematic variations in parental soothing behaviour indicated accommodation to the age of the child. Reasons for the differing patterns of facial activity are examined, with attention paid to the development of inhibitory mechanisms and the role of negative emotions such as anger and anxiety.

Judging pain in newborns:facial and cry determinants

Explored the facial and cry characteristics that adults use when judging an infant's pain. Sixteen women viewed videotaped reactions of 36 newborns subjected to noninvasive thigh rubs and vitamin K injections in the course of routine care and rated discomfort. The group mean interrater reliability was high. Detailed descriptions of the infants' facial reactions and cry sounds permitted specification of the determinants of distress judgments. Several facial variables (a brow bulge, eyes squeezed shut, and deepened nasolabial fold constellation, and taut tongue) accounted for 49% of the variance in ratings of affective discomfort after controlling for ratings of discomfort during a noninvasive event. In a separate analysis not including facial activity, several cry variables (formant frequency, latency to cry) also accounted for variance (38%) in ratings. When the facial and cry variables were considered together, cry variables added little to the prediction of ratings in comparison to facial variables. Cry would seem to command attention, but facial activity, rather than cry, can account for the major variations in adults' judgments of neonatal pain.

Neonatal facial and cry responses to invasive and non-invasive procedures

Evaluation of pain in neonates is difficult due to their limited means of communication. The aim was to determine whether behavioural reactions of cry and facial activity provoked by an invasive procedure could be discriminated from responses to non-invasive tactile events. Thirty-six healthy full-term infants (mean age 2.2 h) received 3 procedures in counterbalanced order: intramuscular injection, application of triple dye to the umbilical stub, and rubbing thigh with alcohol. Significant effects of procedure were found for total face activity and latency to face movement. A cluster of facial actions comprised of brow bulging, eyes squeezed shut, deepening of the naso-labial furrow and open mouth was associated most frequently with the invasive procedure. Comparisons between the 2 non-invasive procedures showed more facial activity to thigh swabbing and least to application of triple dye to the umbilical cord. Acoustic analysis of cry showed statistically significant differences across procedures only for latency to cry and cry duration for the group as a whole. However, babies who cried to two procedures showed higher pitch and greater intensity to the injection. There were no significant differences in melody, dysphonation, or jitter. Methodological difficulties for investigators in this area were examined, including criteria for the selection of cries for analysis, and the logical and statistical challenges of contrasting cries induced by different conditions when some babies do not always cry. It was concluded that facial expression, in combination with short latency to onset of cry and long duration of first cry cycle typifies reaction to acute invasive procedures.

Pain expression in neonates:facial action and cry

Pain expression in neonates instigated by heel-lance for blood sampling purposes was systematically described using measures of facial expression and cry and compared across sleep/waking states and sex. From gate-control theory it was hypothesized that pain behavior would vary with the ongoing functional state of the infant, rather than solely reflecting tissue insult. Awake-alert but inactive infants responded with the most facial activity, consistent with current views that infants in this state are most receptive to environmental stimulation. Infants in quiet sleep showed the least facial reaction and the longest latency to cry. Fundamental frequency of cry was not related to sleep/waking state. This suggested that findings from the cry literature on qualities of pain cry as a reflection of nervous system 'stress', in unwell newborns, do not generalize directly to healthy infants as a function of state. Sex differences were apparent in speed of response, with boys showing shorter time to cry and to display facial action following heel-lance. The findings of facial action variation across sleep/waking state were interpreted as indicating that the biological and behavioral context of pain events affects behavioral expression, even at the earliest time developmentally, before the opportunity for learned response patterns occurs. Issues raised by the study include the importance of using measurement techniques which are independent of preconceived categories of affective response.

Politeness and honesty contribute additively to the interpretation of scalar expressions

Scalar terms have been the focus of much recent attention. People can interpret such terms narrowly, for example, interpreting A or B to convey A or B but not both, on the grounds that a speaker would have explicitly used a more informative term (i.e., and) had he or she been in a position to do so; or they can interpret such terms broadly (A or B or both). Examined here are the effects of politeness contexts and self-rated honesty on people’s interpretation of the scalar connective or. In two experiments, it is shown that participants are less likely to adopt the narrow interpretation when the communicative context is face threatening, and that regardless of context, participants high in self-rated honesty adopt the narrow interpretation to a greater extent than those low in self-rated honesty. These results are consistent with the claim that an assumption of honesty underlies certain pragmatic inferences and suggest that personality may be an important source of individual differences in language interpretation.

The significance of combining VEGFA, FLT1, and KDR expressions in colon cancer patient prognosis and predicting response to bevacizumab

Targeting angiogenesis through inhibition of the vascular endothelial growth factor (VEGF) pathway has been successful in the treatment of late stage colorectal cancer. However, not all patients benefit from inhibition of VEGF. Ras status is a powerful biomarker for response to anti-epidermal growth factor receptor therapy; however, an appropriate biomarker for response to anti-VEGF therapy is yet to be identified. VEGF and its receptors, FLT1 and KDR, play a crucial role in colon cancer progression; individually, these factors have been shown to be prognostic in colon cancer; however, expression of none of these factors alone was predictive of tumor response to anti-VEGF therapy. In the present study, we analyzed the expression levels of VEGFA, FLT1, and KDR in two independent colon cancer datasets and found that high expression levels of all three factors afforded a very poor prognosis. The observation was further confirmed in another independent colon cancer dataset, wherein high levels of expression of this three-gene signature was predictive of poor prognosis in patients with proficient mismatch repair a wild-type KRas status, or mutant p53 status. Most importantly, this signature also predicted tumor response to bevacizumab, an antibody targeting VEGFA, in a cohort of bevacizumab-treated patients. Since bevacizumab has been proven to be an important drug in the treatment of advanced stage colon cancer, our results suggest that the three-gene signature approach is valuable in terms of its prognostic value, and that it should be further evaluated in a prospective clinical trial to investigate its predictive value to anti-VEGF treatment.

Privacy-Protected Facial Biometric Verification via Fuzzy Forest Learning

Although visual surveillance has emerged as an effective technolody for public security, privacy has become an issue of great concern in the transmission and distribution of surveillance videos. For example, personal facial images should not be browsed without permission. To cope with this issue, face image scrambling has emerged as a simple solution for privacyrelated applications. Consequently, online facial biometric verification needs to be carried out in the scrambled domain thus bringing a new challenge to face classification. In this paper, we investigate face verification issues in the scrambled domain and propose a novel scheme to handle this challenge. In our proposed method, to make feature extraction from scrambled face images robust, a biased random subspace sampling scheme is applied to construct fuzzy decision trees from randomly selected features, and fuzzy forest decision using fuzzy memberships is then obtained from combining all fuzzy tree decisions. In our experiment, we first estimated the optimal parameters for the construction of the random forest, and then applied the optimized model to the benchmark tests using three publically available face datasets. The experimental results validated that our proposed scheme can robustly cope with the challenging tests in the scrambled domain, and achieved an improved accuracy over all tests, making our method a promising candidate for the emerging privacy-related facial biometric applications.

The Prognostic Significance of Combining VEGFA, FLT1 and KDR mRNA Expressions in Brain Tumors

Tumor cells require angiogenesis to deliver nutrients and oxygen to support their fast growth and metabolism. The vascular endothelial growth factor (VEGF) pathway plays an important role in promoting angiogenesis, including tumor-induced angiogenesis. Recent clinical trials have demonstrated the benefit of targeting VEGF in the treatment of glioblastoma. However, the prognostic significance of the expression of VEGFA and its receptors VEGFR1 (FLT1) and VEGFR2 (KDR) are still largely elusive. In the present study, we aimed to investigate the prognostic significance of these three factors, alone or in combination, in glioma patients. Gene mRNA expression was extracted from three independent brain tumor cohorts totaling 242 patients and the association between gene expression and survival was tested. We found that when VEGFA, FLT1 and KDR expressions were considered alone, only VEGFA demonstrated a significant association with patient survival. Patients with high expression of both VEGFA and either receptor had significantly worse survival than patients expressing both factors at a low level. Importantly, we found that those patients whose tumors overexpressed all three genes had a significantly shorter survival compared to those patients with a low level expression of these genes. Our results suggest that a high level expression of VEGFA and its receptors, both FLT1 and KDR, may be required for brain tumor progression, and that these three factors should be considered together as a prognostic indicator for brain tumor patients.

Improving Recall of Regular Expressions for Information Extraction

Learning or writing regular expressions to identify instances of a specific
concept within text documents with a high precision and recall is challenging.
It is relatively easy to improve the precision of an initial regular expression
by identifying false positives covered and tweaking the expression to avoid the
false positives. However, modifying the expression to improve recall is difficult
since false negatives can only be identified by manually analyzing all documents,
in the absence of any tools to identify the missing instances. We focus on partially
automating the discovery of missing instances by soliciting minimal user
feedback. We present a technique to identify good generalizations of a regular
expression that have improved recall while retaining high precision. We empirically
demonstrate the effectiveness of the proposed technique as compared to
existing methods and show results for a variety of tasks such as identification of
dates, phone numbers, product names, and course numbers on real world datasets

Facial cleanliness and risk of trachoma in families

Trachoma is the leading infectious cause of blindness worldwide, and epidemiologic studies of factors that may increase the transmission of ocular Chlamydia trachomatis are needed. In two villages in a hyperendemic area of Central Tanzania, 472 (90%) of 527 preschool-aged children were examined for specific signs of unclean faces and presence of trachoma. The odds of trachoma were 70% higher in children with flies and nasal discharge on their faces. Other facial signs were not important. In large families, the odds of trachoma increased 4.8-fold if a sibling had trachoma and 6.8-fold if a sibling had trachoma and an unclean face. Health education strategies aimed at improving face washing need to target cleaning nasal discharge and keeping flies off children's faces.