Coding infant engagement in the Face-to-Face Still-Face paradigm using deep neural networks

BackgroundThe Face-to-Face Still-Face (FFSF) task is a validated and commonly used observational measure of mother-infant socio-emotional interactions. With the ascendence of deep learning-based facial emotion recognition, it is possible that common complex tasks, such as the coding of FFSF videos, could be coded with a high degree of accuracy by deep neural networks (DNNs). The primary objective of this study was to test the accuracy of four DNN image classification models against the coding of infant engagement conducted by two trained independent manual raters.Methods68 mother-infant dyads completed the FFSF task at three timepoints. Two trained independent raters undertook second-by-second manual coding of infant engagement into one of four classes: 1) positive affect, 2) neutral affect, 3) object/environment engagement, and 4) negative affect.ResultsTraining four different DNN models on 40,000 images, we achieved a maximum accuracy of 99.5% on image classification of infant frames taken from recordings of the FFSF task with a maximum inter-rater reliability (Cohen's κ-value) of 0.993.LimitationsThis study inherits all sampling and experimental limitations of the original study from which the data was taken, namely a relatively small and primarily White sample.ConclusionsBased on the extremely high classification accuracy, these findings suggest that DNNs could be used to code infant engagement in FFSF recordings. DNN image classification models may also have the potential to improve the efficiency of coding all observational tasks with applications across multiple fields of human behavior research.     

Identifying lesions on structural brain images--validation of the method and application to neuropsychological patients

The study of neuropsychological disorders has been greatly facilitated by the localization of brain lesions on MRI scans. Current popular approaches for the assessment of MRI brain scans mostly depend on the successful segmentation of the brain into grey and white matter. These methods cannot be used effectively with large lesions because lesions usually impair segmentation. We propose a novel, fully automated approach for the delineation of brain lesions on MR scans. This method involves comparing a skull stripped, smoothed, unsegmented T1 images to a control group using the general linear model. We tested this method by using images with simulated lesions of different sizes and images containing real lesions from patients with language deficits. We also tested how varying the size of the Gaussian smoothing kernel affects detection. The simulation was informed by findings of a lesion morphological study also presented here. The proposed method detected simulated lesions effectively in the range of 30--90%相似文献   

Using segmentation to support the learning from animated soccer scenes: An effect of prior knowledge

ObjectivesWe used a cognitive load perspective to investigate the effects of levels of learner expertise and different forms of segmentation in learning from animated soccer scenes.MethodExpert and novice players (N = 48) completed a recall reconstruction-test and rated their invested mental effort after studying a continuous animation, a macro-step and a micro-step segmented animation.ResultsFindings demonstrated an expertise reversal effect for segmentation. It positively affected learning outcomes of novices but not experts (even though they still invested less mental effort and repeated the animation less often in the two segmented conditions). Additionally, novices benefited more from micro-step segmentation than from macro-step segmentation, while experts performed at the same level with both forms of segmentation.ConclusionsStudy results suggested that adapting instructional animation formats to players with different levels of expertise should be a crucial part of successful training.     

Automatic skin lesions segmentation based on a new morphological approach via geodesic active contour

Automatic disease classification has been one of the most intensively searched in recent years due to the possibility of quickly providing a diagnosis to the patient. In this process, the segmentation of regions of interest of these diseases has a fundamental role in their subsequent classification. With skin lesions segmentation it is no different and in recent years many studies have achieved interesting results, becoming an important tool in aiding the medical diagnosis of skin diseases. In this work, a morphological geodesic active contour segmentation (MGAC) method is proposed with automatic initialization, using mathematical morphology which is a great partial differential equation approximation, with lower computational cost, no stability problems and fully automatic. The proposed method was tested in a stable and well-known dermoscopic images database provided by Pedro Hispano Hospital (PH2) and was compared with both methods that make use of machine learning or deep learning techniques such as fully convolutional networks (FCN), full resolution convolutional networks (FrCN), deep class-specific learning with probability based step-wise integration (DCL-PSI), and others, and also traditional methods like JSEG, statistical region merging (SRM), Level Set, ASLM and others. The MGAC showed good results in all similarity metrics compared in this work like Jaccard Index (86.16%), Dice coefficient (92.09%) and Matthew correlation coefficient (87.52%), and also achieves good results in sensitivity (91.72%), specificity (97.99%), accuracy (94.59%) and F-measure (93.82%). Thus, the proposed method presented better results in relation to all these metrics when compared to the traditional methods and still presented better results in relation to the methods that use machine learning or deep learning techniques in Jaccard Index, Dice coefficient and specificity. This confirm that the MGAC can efficiently segment skin lesions, presenting great potential to be applied in the aid of the medical diagnosis.     

A performance comparison between shallow and deeper neural networks supervised classification of tomosynthesis breast lesions images

Computer Aided Decision (CAD) systems, based on 3D tomosynthesis imaging, could support radiologists in classifying different kinds of breast lesions and then improve the diagnosis of breast cancer (BC) with a lower X-ray dose than in Computer Tomography (CT) systems.In previous work, several Convolutional Neural Network (CNN) architectures were evaluated to discriminate four different classes of lesions considering high-resolution images automatically segmented: (a) irregular opacity lesions, (b) regular opacity lesions, (c) stellar opacity lesions and (d) no-lesions. In this paper, instead, we use the same previously extracted relevant Regions of Interest (ROIs) containing the lesions, but we propose and evaluate two different approaches to better discriminate among the four classes.In this work, we evaluate and compare the performance of two different frameworks both considering supervised classifiers topologies. The first framework is feature-based, and consider morphological and textural hand-crafted features, extracted from each ROI, as input to optimised Artificial Neural Network (ANN) classifiers. The second framework, instead, considers non-neural classifiers based on automatically computed features evaluating the classification performance extracting several sets of features using different Convolutional Neural Network models.Final results show that the second framework, based on features computed automatically by CNN architectures performs better than the first approach, in terms of accuracy, specificity, and sensitivity.     

An efficient cervical disease diagnosis approach using segmented images and cytology reporting

Cervical cancer is the second most common cancer in women globally. A computer aided cervical disease diagnosis system that can relieve pressure on medical experts and save the cost is proposed. To implement our approach in the reality of cervical diseases diagnosis, a multi-modal framework is designed for three kinds of cervical diseases diagnosis that integrates uterine cervix images, Thinprep Cytology Test, human papillomavirus test, and patients’ age. However, too many features increase memory storage costs and computational costs, and it affects the spread of this system in poor areas. Feature selection not only eliminates redundant or irrelevant features but also finds the factors that influence the disease most first is performed in multi-modal frameworks for cervical diseases diagnosis. The detailed process of the method is as follows: first, according the representative color, an efficient image segmentation algorithm is developed; then from three different types of segmented images, we extract color features and texture features for interpreting uterine cervix images; next, Boruta algorithm is applied to feature selection; finally, the performance of Random Forests that utilizes selected features for cervical disease diagnosis is investigated. In the experiment, the proposed multi-modal diagnostic approach gives the final diagnosis for three different kinds of cervical diseases with 83.1% accuracy, which significantly outperforms methods using any single source of information alone. The validation cohort is applied to validate the efficiency of our method, and the performance of random forest obtained by using only 1.2% of features is like or even better than using 100% of features.     

Human age classification using facial skin aging features and artificial neural network

In this paper a novel method based on facial skin aging features and Artificial Neural Network (ANN) is proposed to classify the human face images into four age groups. The facial skin aging features are extracted by using Local Gabor Binary Pattern Histogram (LGBPH) and wrinkle analysis. The ANN classifier is designed by using two layer feedforward backpropagation neural networks. The proposed age classification framework is trained and tested with face images from PAL face database and shown considerable improvement in the age classification accuracy up to 94.17% and 93.75% for male and female respectively.     

Convolutional neural network based Alzheimer’s disease classification from magnetic resonance brain images

Alzheimer’s disease, the most common form of dementia is a neurodegenerative brain order that has currently no cure for it. Hence, early diagnosis of such disease using computer-aided systems is a subject of great importance and extensive research amongst researchers. Nowadays, deep learning or particularly convolutional neural network (CNN) is getting more attention due to its state-of-the-art performances in variety of computer vision tasks such as visual object classification, detection and segmentation. Several recent studies, that have used brain MRI scans and deep learning have shown promising results for diagnosis of Alzheimer’s disease. However, most common issue with deep learning architectures such as CNN is that they require large amount of data for training. In this paper, a mathematical model P_FS_EC_TL based on transfer learning is used in which a CNN architecture, VGG-16 trained on ImageNet dataset is used as a feature extractor for the classification task. Experimentation is performed on data collected from Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The accuracy of the 3-way classification using the described method is 95.73% for the validation set.     

An intelligent facial expression recognition system with emotion intensity classification

Facial expressions play a crucial role in emotion recognition as compared to other modalities. In this work, an integrated network, which is capable of recognizing emotion intensity levels from facial images in real time using deep learning technique is proposed. The cognitive study of facial expressions based on expression intensity levels are useful in applications such as healthcare, coboting, Industry 4.0 etc. This work proposes to augment emotion recognition with 2 other important parameters, valence and emotion intensity. This helps in better automated responses by a machine to an emotion. The valence model helps in classifying emotion as positive and negative emotions and discrete model classifies emotions as happy, anger, disgust, surprise and neutral state using Convolution Neural Network (CNN). Feature extraction and classification are carried out using CMU Multi-PIE database. The proposed architecture achieves 99.1% and 99.11% accuracy for valence model and discrete model respectively for offline image data with 5-fold cross validation. The average accuracy achieved in real time for valance model and discrete model is 95% & 95.6% respectively. Also, this work contributes to build a new database using facial landmarks, with three intensity levels of facial expressions which helps to classify expressions into low, mild and high intensities. The performance is also tested for different classifiers. The proposed integrated system is configured for real time Human Robot Interaction (HRI) applications on a test bed consisting of Raspberry Pi and RPA platform to assess its performance.     

时间维度在记叙文理解中的作用

采用事件分割范式探讨了中文条件下时间维度在记叙文理解中的作用。实验1在中文条件下重复了Speer和Zacks(2005)年的研究,结果发现读者更多将时间短语所在位置作为分割边界,表明时间转换在情景模型更新中发挥了重要作用。实验2探讨了在没有时间短语条件下读者对文本分割的情况,结果发现读者主要是按照事件单元进行分割;实验3a和3b在文本的事件单元中插入时间短语,形成时间转换与事件转换分离的条件,探讨读者在这种时间转换与事件单元转换不一致的条件下所采用的分割策略,结果表明,读者更多仍然按照事件单元转换进行分割,而且对事件单元转换的依赖强于时间转换,但同时时间短语仍对文本的分割有一定影响。上述结果表明,事件单元作为建构记叙文心理表征的核心单元,时间维度作为事件单元转换的线索,只有在标识事件转换的情况下,才能引发读者情景模型的更新。     

“Do I Know You?” Altering hairstyle affects facial recognition

Background: Research has demonstrated that both internal features (e.g., eyes) and external features (e.g., hair) are important for recognizing unfamiliar faces; however, the impact of altering hairstyle on the recognition of unfamiliar faces has yet to be isolated and investigated in the absence of deep processing. Objectives: We sought to examine the extent to which altering hair impacts the recognition of a previously viewed face. Methods: Participants were presented with a series of face images followed by a recognition probe of either a new face or a face that was among the previously presented images with either the same hairstyle (identical face) or a different hairstyle (disguised face). Results: Participants showed significantly less accuracy in the disguised condition compared to the identical condition. Conclusions: Our results provide evidence that hairstyle plays a role in recognizing unfamiliar faces. This appears to hold true across race and sex, as well as across deep and shallow processing.     

What Is Unique About Supervising Couple Therapists?

Abstract

What is unique about supervising couple therapists? To answer this question I highlight three important therapeutic processes in CT and their accompanying supervisory implications. The first process, the attending to values and beliefs about the meaning of coupling to couples and therapists and its influence on CT, is facilitated by supervisors who help supervisees uncover values and beliefs about coupling. The second process, developing the therapeutic alliance which has a unique complexity in CT, is facilitated by the processing of the therapeutic alliance in supervision and discovering ways of strengthening it. The final process, attending to emotion prevalent in CT, is facilitated by supervisors who assist supervisees in becoming comfortable with the expression of emotion and work with it constructively in CT. After briefly describing each process and why it is viewed as important in CT, I suggest ways supervisors can assist supervisees' becoming more proficient in them. An abbreviated supervision illustration ends each section.     

Lights,camera, action: the role of editing and framing on the processing of filmed events

ABSTRACT

Filmmakers use various cinematic techniques in an effort to guide attention to certain aspects of these events. The present study was conducted to investigate how framing and editing can guide viewers’ attention toward character actions during event segmentation. Participants watched and segmented a movie that simultaneously showed two actors engaged in two related activities. Participants watched one of three versions of the movie: Static center version that did not foreground any character; Static off-center version that foregrounding one of the characters, and an edited version with a mix of shots that foregrounding both characters. Participants engaged in an event partonomy task in which they were asked to identify the boundaries between the events that were depicted in the movie. After watching the movie, they were asked to recall the events. The results showed converging evidence between the event segmentation and recall data, which both indicated that cinematic devices affect the perception and memory of the event structure depicted in the film.     

Identifying developmental stuttering and associated comorbidities in electronic health records and creating a phenome risk classifier

PurposeThis study aimed to identify cases of developmental stuttering and associated comorbidities in de-identified electronic health records (EHRs) at Vanderbilt University Medical Center, and, in turn, build and test a stuttering prediction model.MethodsA multi-step process including a keyword search of medical notes, a text-mining algorithm, and manual review was employed to identify stuttering cases in the EHR. Confirmed cases were compared to matched controls in a phenotype code (phecode) enrichment analysis to reveal conditions associated with stuttering (i.e., comorbidities). These associated phenotypes were used as proxy variables to phenotypically predict stuttering in subjects within the EHR that were not otherwise identifiable using the multi-step identification process described above.ResultsThe multi-step process resulted in the manually reviewed identification of 1,143 stuttering cases in the EHR. Highly enriched phecodes included codes related to childhood onset fluency disorder, adult-onset fluency disorder, hearing loss, sleep disorders, atopy, a multitude of codes for infections, neurological deficits, and body weight. These phecodes were used as variables to create a phenome risk classifier (PheRC) prediction model to identify additional high likelihood stuttering cases. The PheRC prediction model resulted in a positive predictive value of 83 %.ConclusionsThis study demonstrates the feasibility of using EHRs in the study of stuttering and found phenotypic associations. The creation of the PheRC has the potential to enable future studies of stuttering using existing EHR data, including investigations into the genetic etiology.     

iMap: a novel method for statistical fixation mapping of eye movement data

Eye movement data analyses are commonly based on the probability of occurrence of saccades and fixations (and their characteristics) in given regions of interest (ROIs). In this article, we introduce an alternative method for computing statistical fixation maps of eye movements—iMap—based on an approach inspired by methods used in functional magnetic resonance imaging. Importantly, iMap does not require the a priori segmentation of the experimental images into ROIs. With iMap, fixation data are first smoothed by convolving Gaussian kernels to generate three-dimensional fixation maps. This procedure embodies eyetracker accuracy, but the Gaussian kernel can also be flexibly set to represent acuity or attentional constraints. In addition, the smoothed fixation data generated by iMap conform to the assumptions of the robust statistical random field theory (RFT) approach, which is applied thereafter to assess significant fixation spots and differences across the three-dimensional fixation maps. The RFT corrects for the multiple statistical comparisons generated by the numerous pixels constituting the digital images. To illustrate the processing steps of iMap, we provide sample analyses of real eye movement data from face, visual scene, and memory processing. The iMap MATLAB toolbox is editable and freely available for download online ().     

Positive psychology,the classification of character strengths and virtues,and issues of measurement

ABSTRACT

This essay raises concerns about positive psychology’s classification of character strengths and virtues and issues of measurement. Part I examines the process whereby the classification was compiled. Part II turns to issues of measurement and questions about positive psychologists’ sensitivity to variations in the meanings of the constructs they purport to measure, both within and across cultures. I argue that attempts to find a ‘deep structure’ of the character strengths and virtues should proceed hand in hand with efforts to render positive psychology and its measurement tools more sensitive to variability in character strengths and virtues across and within cultures. The essay concludes with suggestions for future research.