Multi-scale discrepancy adversarial network for cross-corpus speech emotion recognition

Background One of the most critical issues in human-computer interaction applications is recognizing human emotions based on speech.In recent years,the challenging problem of cross-corpus speech emotion recognition(SER)has generated extensive research.Nevertheless,the domain discrepancy between training data and testing data remains a major challenge to achieving improved system performance.Methods This paper introduces a novel multi-scale discrepancy adversarial(MSDA)network for conducting multiple timescales domain adaptation for cross-corpus SER,i.e.,integrating domain discriminators of hierarchical levels into the emotion recognition framework to mitigate the gap between the source and target domains.Specifically,we extract two kinds of speech features,i.e.,handcraft features and deep features,from three timescales of global,local,and hybrid levels.In each timescale,the domain discriminator and the feature extrator compete against each other to learn features that minimize the discrepancy between the two domains by fooling the discriminator.Results Extensive experiments on cross-corpus and cross-language SER were conducted on a combination dataset that combines one Chinese dataset and two English datasets commonly used in SER.The MSDA is affected by the strong discriminate power provided by the adversarial process,where three discriminators are working in tandem with an emotion classifier.Accordingly,the MSDA achieves the best performance over all other baseline methods.Conclusions The proposed architecture was tested on a combination of one Chinese and two English datasets.The experimental results demonstrate the superiority of our powerful discriminative model for solving cross-corpus SER.

Adaptive spatio-temporal attention neural network for cross-database micro-expression recognition

Background The use of micro-expression recognition to recognize human emotions is one of the most critical challenges in human-computer interaction applications. In recent years, cross-database micro-expression recognition(CDMER) has emerged as a significant challenge in micro-expression recognition and analysis. Because the training and testing data in CDMER come from different micro-expression databases, CDMER is more challenging than conventional micro-expression recognition. Methods In this paper, an adaptive spatio-temporal attention neural network(ASTANN) using an attention mechanism is presented to address this challenge. To this end, the micro-expression databases SMIC and CASME II are first preprocessed using an optical flow approach,which extracts motion information among video frames that represent discriminative features of micro-expression.After preprocessing, a novel adaptive framework with a spatiotemporal attention module was designed to assign spatial and temporal weights to enhance the most discriminative features. The deep neural network then extracts the cross-domain feature, in which the second-order statistics of the sample features in the source domain are aligned with those in the target domain by minimizing the correlation alignment(CORAL) loss such that the source and target databases share similar distributions. Results To evaluate the performance of ASTANN, experiments were conducted based on the SMIC and CASME II databases under the standard experimental evaluation protocol of CDMER. The experimental results demonstrate that ASTANN outperformed other methods in relevant crossdatabase tasks. Conclusions Extensive experiments were conducted on benchmark tasks, and the results show that ASTANN has superior performance compared with other approaches. This demonstrates the superiority of our method in solving the CDMER problem.

On Self-adjustment of Social Conventions to Small Perturbations

We present a model for self-adjustment of social conventions to small perturbations, and investigate how perturbations can influence the convergence of social convention in different situations. The experimental results show that the sensitivity of social conventions is determined by not only the perturbations themselves but also the agent adjustment functions for the perturbations; and social conventions are more sensitive to the outlier agent number than to the strategy fluctuation magnitudes and localities of perturbations.

Alzheimer’s disease classification based on sparse functional connectivity and non-negative matrix factorization

A novel framework is proposed to obtain physiologically meaningful features for Alzheimer's disease(AD)classification based on sparse functional connectivity and non-negative matrix factorization.Specifically,the non-negative adaptive sparse representation(NASR)method is applied to compute the sparse functional connectivity among brain regions based on functional magnetic resonance imaging(fMRI)data for feature extraction.Afterwards,the sparse non-negative matrix factorization(sNMF)method is adopted for dimensionality reduction to obtain low-dimensional features with straightforward physical meaning.The experimental results show that the proposed framework outperforms the competing frameworks in terms of classification accuracy,sensitivity and specificity.Furthermore,three sub-networks,including the default mode network,the basal ganglia-thalamus-limbic network and the temporal-insular network,are found to have notable differences between the AD patients and the healthy subjects.The proposed framework can effectively identify AD patients and has potentials for extending the understanding of the pathological changes of AD.

A Case Study on Primary Problem Student in Yemen

Nowadays,problem student is a common phenomenon exiting in primary and secondary school,Yemen.However,current unknown is why problem students appear and how to make an effective intervention way for reducing the problem behaviors.Although there have been many researches about problem student's problem behaviors researches on causes,developmental mechanism and educational strategies of problem students mainly stay on the theoretical research stage.This study aimed to investigate main reason for the formation of problem students and then make an effective intervention way and examine the invention effect.Firstly,combining existing research literature and teaching experience,this study sums up that problem behavior of problem students is mainly learning problem,interpersonal problem and willpower problem.Secondly,this study selected ten"problem students"of primary school as the participants.They are simply classified into three categories in accordance with the severity of the problem behaviors of problem students.I summarized various causes and affecting factors of problem behaviors through observing their performances and behaviors,and conduct in-depth interviews and explorations throughout the whole research process.Thirdly,on the basis of kind and severity of problems,various flexibly methods were used for the intervention study of problem behaviors.After that,I conducted interviews with the study cases,parents and teachers once again and made tracked records for the intervention effect.The intervention achieves marked improvement.For example,most students greatly improve their behaviors in class.Finally,I reflect the research process itself,considering that the case study is necessary method for the issue of"problem students".The use of qualitative research method is more conducive to enter the inner world of the studying cases,and better understand their true conditions as well.And on this basis,it is easier to find a breakthrough in the problem to improve the"problem students"and make a closer link between theoretical research and practical application.

Preoperative serum cortisone levels are associated with cognition in preschool‑aged children with tetralogy of Fallot after corrective surgery:new evidence from human populations and mice

Background Tetralogy of Fallot(TOF)is the most common cyanotic congenital heart disease.Children with TOF would be confronted with neurological impairment across their lifetime.Our study aimed to identify the risk factors for cerebral morphology changes and cognition in postoperative preschool-aged children with TOF.Methods We used mass spectrometry(MS)technology to assess the levels of serum metabolites,Wechsler preschool and primary scale of intelligence-Fourth edition(WPPSI-Ⅳ)index scores to evaluate neurodevelopmental levels and multimodal magnetic resonance imaging(MRI)to detect cortical morphological changes.Results Multiple linear regression showed that preoperative levels of serum cortisone were positively correlated with the gyrification index of the left inferior parietal gyrus in children with TOF and negatively related to their lower visual spaces index and nonverbal index.Meanwhile,preoperative SpO_(2) was negatively correlated with levels of serum cortisone after adjusting for all covariates.Furthermore,after intervening levels of cortisone in chronic hypoxic model mice,total brain volumes were reduced at both postnatal(P)11.5 and P30 days.Conclusions Our results suggest that preoperative serum cortisone levels could be used as a biomarker of neurodevelopmental impairment in children with TOF.Our study findings emphasized that preoperative levels of cortisone could influence cerebral development and cognition abilities in children with TOF.

A Fiber Tractography Study of Social-Emotional Related Fiber Tracts in Children and Adolescents with Autism Spectrum Disorder

The symptoms of autism spectrum disorder（ASD） have been hypothesized to be caused by changes in brain connectivity. From the clinical perspective, the‘‘disconnectivity＇＇ hypothesis has been used to explain characteristic impairments in ‘‘socio-emotional＇＇ function.Therefore, in this study we compared the facial emotional recognition（FER） feature and the integrity of socialemotional-related white-matter tracts between children and adolescents with high-functioning ASD（HFA） and their typically developing（TD） counterparts. The correlation between the two factors was explored to find out if impairment of the white-matter tracts is the neural basis of social-emotional disorders. Compared with the TD group,FER was significantly impaired and the fractional anisotropy value of the right cingulate fasciculus was increased in the HFA group（P ／ 0.01）. In conclusion, the FER function of children and adolescents with HFA was impaired and the microstructure of the cingulate fasciculus had abnormalities.

ReDB:A meiotic homologous recombination rate database

Meiotic recombination occurs preferentially at certain regions in the genome referred to as hot spots which are important for generating genetic diversity and proper segregation of chromosomes during meiosis.Although observations concerning individual hotspots have given clues as to the mechanism of recombination initiation,the nature and causes of recombination rate variation in the genome are still little known.A rational solution is to estimate and rank recombination rates along the genome.Therefore,it is a high demand for a database that deposits and integrates those data to provide a systematical repository of genome-wide recombination rates.Homologous recombination hotspots database is a web-based database of meiotic recombination rates,which comprises enormous data and information of human,mouse,rat,D.melanogaster,C.elegans and yeast.Users can query the database in several alternative ways.The database stores various details for every sequence,such as chromosome number,hyperlinks to the respective reference,and the sequence in FASTA format.