Search Results (15)

With the increasing complexity of human–computer interaction scenarios, conventional digital human facial expression systems show notable limitations in handling multi-emotion co-occurrence, dynamic expression, and semantic responsiveness. This paper proposes a digital human system framework that integrates multimodal emotion recognition and compound facial expression generation. The system establishes a complete pipeline for real-time interaction and compound emotional expression, following a sequence of “speech semantic parsing—multimodal emotion recognition—Action Unit (AU)-level 3D facial expression control.” First, a ResNet18-based model is employed for robust emotion classification using the AffectNet dataset. Then, an AU motion curve driving module is constructed on the Unreal Engine platform, where dynamic synthesis of basic emotions is achieved via a state-machine mechanism. Finally, Generative Pre-trained Transformer (GPT) is utilized for semantic analysis, generating structured emotional weight vectors that are mapped to the AU layer to enable language-driven facial responses. Experimental results demonstrate that the proposed system significantly improves facial animation quality, with naturalness increasing from 3.54 to 3.94 and semantic congruence from 3.44 to 3.80. These results validate the system’s capability to generate realistic and emotionally coherent expressions in real time. This research provides a complete technical framework and practical foundation for high-fidelity digital humans with affective interaction capabilities. Full article

Background/Objectives: Chronic craniofacial inflammation is recognized as a factor in anxiety-like behaviors, yet effective therapeutic options remain limited. Agmatine, a dietary bioactive compound found in fermented foods such as sake lees, exhibits modulatory effects on neural functions, alleviating psychological distress like anxiety associated with local inflammation. Methods: We investigated both the therapeutic and preventive effects of agmatine on anxiety-like behaviors and the related neural basis in a mouse model of persistent craniofacial inflammation induced by complete Freund’s adjuvant (CFA). Results: Comprehensive behavioral assessments, including the elevated plus maze, open field, dark–light box, social interaction, and novel object recognition tests, revealed that therapeutic agmatine administration (1.0 and 30 mg/kg) significantly reduced CFA-induced anxiety-like behaviors, with the higher dose showing more robust and sustained effects across multiple time points. These behavioral improvements were paralleled by reductions in acetylated histone H3, FosB, and c-Fos expression in key anxiety-related brain regions, suggesting a reversal of craniofacial inflammation-associated neural changes. In contrast, preventive agmatine treatment exerted modest and time-dependent behavioral benefits with minimal molecular normalization. Notably, preventive agmatine did not affect general locomotor activity (indicated by total movement distance), indicating that its anxiolytic effects were not confounded by altered locomotor activity. Metabolomic analysis confirmed the presence of agmatine in sake lees (~0.37 mM), supporting the hypothesis that fermented food products might offer dietary routes to emotional resilience. Conclusions: These findings underscore agmatine’s promise as a context-specific epigenetic modulator capable of mitigating anxiety-like behaviors by normalizing inflammation-driven molecular dysregulation in the brain. Full article

Aboriginal and Torres Strait Islander ways of knowing, being and doing have fostered physical, social, and emotional wellbeing for millenia, forming a foundation of strength and resilience. However, colonisation, systemic violence and discrimination—including the forced removal of Aboriginal and Torres Strait Islander children, which continues today—have disrupted this foundation, leading to compounding cycles of intergenerational and complex trauma. The enduring impact of intergenerational and complex trauma is exemplified in increasing proportions of Aboriginal and Torres Strait Islander children being removed from their families and involved in the child protection and youth justice system—which represents a national crisis. Despite this crisis, the national response remains insufficient. To address these urgent issues, over 200 predominantly Aboriginal and Torres Strait Islander stakeholders, participated in Gathering the Seeds Symposium, the inaugural meeting for the Replanting the Birthing Trees project held in Perth in April 2023. This meeting marked the beginning of a public dialogue aimed at Closing the Gap by advancing community-led strategies to break cycles of trauma and foster cycles of nurturing, recovery, and wellbeing for Aboriginal and Torres Strait Islander parents and children across the first 2000 days. We outline critical shortcomings in the current child protection and youth justice systems, and the urgent need for child wellbeing reform. Importantly we highlight recommendations made in submissions in 2023 to two key Australian inquiries—the National Early Years Strategy and the Human Rights Commission inquiry into out of home care and youth justice systems. We argue that structural reforms and culturally safe and skillful care for parents experiencing trauma and violence is a serious gap, and a national priority. The first 2000 days represents a critical window of opportunity to transform cycles of trauma into cycles of healing. It is time to ‘replant the birthing trees’ and ensure that all Aboriginal and Torres Strait Islander babies and families can have the best possible start to life through comprehensive models of care grounded in recognition of the right to self-determination and culture. Full article

Facial expression recognition (FER) is essential for discerning human emotions and is applied extensively in big data analytics, healthcare, security, and user experience enhancement. This study presents a comprehensive evaluation of ten state-of-the-art deep learning models—VGG16, VGG19, ResNet50, ResNet101, DenseNet, GoogLeNet V1, MobileNet V1, EfficientNet V2, ShuffleNet V2, and RepVGG—on the task of facial expression recognition using the FER2013 dataset. Key performance metrics, including test accuracy, training time, and weight file size, were analyzed to assess the learning efficiency, generalization capabilities, and architectural innovations of each model. EfficientNet V2 and ResNet50 emerged as top performers, achieving high accuracy and stable convergence using compound scaling and residual connections, enabling them to capture complex emotional features with minimal overfitting. DenseNet, GoogLeNet V1, and RepVGG also demonstrated strong performance, leveraging dense connectivity, inception modules, and re-parameterization techniques, though they exhibited slower initial convergence. In contrast, lightweight models such as MobileNet V1 and ShuffleNet V2, while excelling in computational efficiency, faced limitations in accuracy, particularly in challenging emotion categories like “fear” and “disgust”. The results highlight the critical trade-offs between computational efficiency and predictive accuracy, emphasizing the importance of selecting appropriate architecture based on application-specific requirements. This research contributes to ongoing advancements in deep learning, particularly in domains such as facial expression recognition, where capturing subtle and complex patterns is essential for high-performance outcomes. Full article

Hearing loss represents a multifaceted and pervasive challenge that deeply impacts various aspects of an individual’s life, spanning psychological, emotional, social, and economic realms. Understanding the molecular underpinnings that orchestrate hearing loss remains paramount in the quest for effective therapeutic strategies. This review aims to expound upon the physiological, biochemical, and molecular aspects of hearing loss, with a specific focus on its correlation with diabetes. Within this context, phytochemicals have surfaced as prospective contenders in the pursuit of potential adjuvant therapies. These compounds exhibit noteworthy antioxidant and anti-inflammatory properties, which hold the potential to counteract the detrimental effects induced by oxidative stress and inflammation—prominent contributors to hearing impairment. Furthermore, this review offers an up-to-date exploration of the diverse molecular pathways modulated by these compounds. However, the dynamic landscape of their efficacy warrants recognition as an ongoing investigative topic, inherently contingent upon specific experimental models. Ultimately, to ascertain the genuine potential of phytochemicals as agents in hearing loss treatment, a comprehensive grasp of the molecular mechanisms at play, coupled with rigorous clinical investigations, stands as an imperative quest. Full article

Several lines of evidence suggest that scarcity of the gaseous molecule nitric oxide (NO) is associated with the pathogenesis of schizophrenia. Therefore, compounds, such as NO donors, that can normalize NO levels might be of utility for the treatment of this pathology. It has been previously shown that the NO donor molsidomine attenuated schizophrenia-like behavioral deficits caused by glutamate hypofunction in rats. The aim of the current study was to investigate the efficacy of molsidomine and that of the joint administration of this NO donor with sub-effective doses of the non-typical antipsychotics clozapine and risperidone to counteract memory deficits associated with dysregulation of the brain dopaminergic system in rats. Molsidomine (2 and 4 mg/kg) attenuated spatial recognition and emotional memory deficits induced by the mixed dopamine (DA) D₁/D₂ receptor agonist apomorphine (0.5 mg/kg). Further, the joint administration of sub-effective doses of molsidomine (1 mg/kg) with those of clozapine (0.1 mg/kg) or risperidone (0.03 mg/kg) counteracted non-spatial recognition memory impairments caused by apomorphine. The present findings propose that molsidomine is sensitive to DA dysregulation since it attenuates memory deficits induced by apomorphine. Further, the current findings reinforce the potential of molsidomine as a complementary molecule for the treatment of schizophrenia. Full article

Human emotion label prediction is crucial to Artificial Intelligent in the Internet of Things (IoT). Facial expression recognition is the main technique to predict human emotion labels. Existing facial expression recognition methods do not consider the compound emotion and the fuzziness of emotion labels. Fuzzy learning is a mathematical tool for dealing with fuzziness and uncertainty information. The advantage of using fuzzy learning for human emotion recognition is that multiple fuzzy sentiment labels can be processed simultaneously. This paper proposes a fuzzy learning-based expression recognition method for human emotion label prediction. First, a fuzzy label distribution system is constructed using fuzzy sets for representing facial expressions. Then, two fuzzy label distribution prediction methods based on fuzzy rough sets are proposed to solve the compound emotion prediction. The probability that a sample is likely and definitely belongs to an emotion is obtained by calculating the upper and lower approximations. Experiments show the proposed algorithm not only performs well on human emotion label prediction but can also be used for other label distribution prediction tasks. The proposed method is more accurate and more general than other methods. The improvement of the method on the effect of emotion recognition extends the application scope of artificial intelligence in IoT. Full article

Memory impairments constitute a significant problem worldwide, and the COVID-19 pandemic dramatically increased the prevalence of cognitive deficits. Patients with cognitive deficits, specifically memory disturbances, have underlying comorbid conditions such as schizophrenia, anxiety, or depression. Moreover, the available treatment options have unsatisfactory effectiveness. Therefore, there is a need to search for novel procognitive and anti-amnesic drugs with additional pharmacological activity. One of the important therapeutic targets involved in the modulation of learning and memory processes are serotonin receptors, including 5-HT_1A, 5-HT₆, and 5-HT₇, which also play a role in the pathophysiology of depression. Therefore, this study aimed to assess the anti-amnesic and antidepressant-like potential of JJGW08, a novel arylpiperazine alkyl derivative of salicylamide with strong antagonistic properties at 5-HT_1A and D₂ receptors and weak at 5-HT_2A and 5-HT₇ receptors in rodents. First, we investigated the compound’s affinity for 5-HT₆ receptors using the radioligand assays. Next, we assessed the influence of the compound on long-term emotional and recognition memory. Further, we evaluated whether the compound could protect against MK-801-induced cognitive impairments. Finally, we determined the potential antidepressant-like activity of the tested compound. We found that JJGW08 possessed no affinity for 5-HT₆ receptors. Furthermore, JJGW08 protected mice against MK-801-induced recognition and emotional memory deficits but showed no antidepressant-like effects in rodents. Therefore, our preliminary study may suggest that blocking serotonin receptors, especially 5-HT_1A and 5-HT₇, might be beneficial in treating cognitive impairments, but it requires further investigation. Full article

Depression, anxiety, and schizophrenia may coexist in psychiatric patients. Moreover, these disorders are very often associated with cognitive impairments. However, pharmacotherapy of these conditions remains challenging due to limited drug effectiveness or numerous side effects. Therefore, there is an urgent need to develop novel multimodal compounds that can be used to treat depression, anxiety, and schizophrenia, as well as memory deficits. Thus, this study aimed to evaluate the potential antidepressant-like, anxiolytic-like, antipsychotic-like effects, and anti-amnesic properties, of the novel arylpiperazine derivative of salicylamide, JJGW07, with an affinity towards serotonin 5-HT_1A, 5-HT_2A, and 5-HT₇ and dopamine D₂ receptors. Firstly, we investigated the compound’s affinity for 5-HT₆ receptors and its functional activity by using in vitro assays. JJGW07 did not bind to 5-HT₆ receptors and showed antagonistic properties for 5-HT_1A, 5-HT_2A, 5-HT₇, and D₂ receptors. Based on the receptor profile, we performed behavioral studies in mice to evaluate the antidepressant-like, anxiolytic-like, and antipsychotic-like activity of the tested compound using forced swim and tail suspension tests; four-plate, marble-burying, and elevated plus maze tests; and MK-801- and amphetamine-induced hyperlocomotion tests, respectively. JJGW07 revealed antidepressant-like properties in the tail suspension test, anxiolytic-like effects in the four-plate and marble-burying tests, and antipsychotic-like activity in the MK-801-induced hyperlocomotion test. Importantly, the tested compound did not induce catalepsy and motor impairments or influence locomotor activity in rodents. Finally, to assess the potential procognitive and anti-amnesic properties of JJGW07, we used passive avoidance and object recognition tests in mice. JJGW07 demonstrated positive effects on long-term emotional memory and also ameliorated MK-801-induced emotional memory impairments in mice, but showed no procognitive properties in the case of recognition memory. Our results encourage the search for new compounds among salicylamide derivatives, which could be model structures with multitarget mechanisms of action that could be used in psychiatric disorder therapy. Full article

Human behavior is stimulated by the outside world, and the emotional response caused by it is a subjective response expressed by the body. Humans generally behave in common ways, such as lying, sitting, standing, walking, and running. In real life of human beings, there are more and more dangerous behaviors in human beings due to negative emotions in family and work. With the transformation of the information age, human beings can use Industry 4.0 smart devices to realize intelligent behavior monitoring, remote operation, and other means to effectively understand and identify human behavior characteristics. According to the literature survey, researchers at this stage analyze the characteristics of human behavior and cannot achieve the classification learning algorithm of single characteristics and composite characteristics in the process of identifying and judging human behavior. For example, the characteristic analysis of changes in the sitting and sitting process cannot be for classification and identification, and the overall detection rate also needs to be improved. In order to solve this situation, this paper develops an improved machine learning method to identify single and compound features. In this paper, the HATP algorithm is first used for sample collection and learning, which is divided into 12 categories by single and composite features; secondly, the CNN convolutional neural network algorithm dimension, recurrent neural network RNN algorithm, long- and short-term extreme value network LSTM algorithm, and gate control is used. The ring unit GRU algorithm uses the existing algorithm to design the model graph and the existing algorithm for the whole process; thirdly, the machine learning algorithm and the main control algorithm using the proposed fusion feature are used for HATP and human beings under the action of wearable sensors. The output features of each stage of behavior are fused; finally, by using SPSS data analysis and re-optimization of the fusion feature algorithm, the detection mechanism achieves an overall target sample recognition rate of about 83.6%. Finally, the research on the algorithm mechanism of machine learning for human behavior feature classification under the new algorithm is realized. Full article

At present, food quality is of utmost importance, not only to comply with commercial regulations, but also to meet the expectations of consumers; this aspect includes sensory features capable of triggering emotions through the citizen’s perception. To date, key parameters for food quality assessment have been sought through analytical methods alone or in combination with a panel test, but the evaluation of panelists’ reactions via psychophysiological markers is now becoming increasingly popular. As such, the present review investigates recent applications of traditional and novel methods to the specific field. These include electronic senses (e-nose, e-tongue, and e-eye), sensory analysis, and wearables for emotion recognition. Given the advantages and limitations highlighted throughout the review for each approach (both traditional and innovative ones), it was possible to conclude that a synergy between traditional and innovative approaches could be the best way to optimally manage the trade-off between the accuracy of the information and feasibility of the investigation. This evidence could help in better planning future investigations in the field of food sciences, providing more reliable, objective, and unbiased results, but it also has important implications in the field of neuromarketing related to edible compounds. Full article

Facial emotion recognition is an inherently complex problem due to individual diversity in facial features and racial and cultural differences. Moreover, facial expressions typically reflect the mixture of people’s emotional statuses, which can be expressed using compound emotions. Compound facial emotion recognition makes the problem even more difficult because the discrimination between dominant and complementary emotions is usually weak. We have created a database that includes 31,250 facial images with different emotions of 115 subjects whose gender distribution is almost uniform to address compound emotion recognition. In addition, we have organized a competition based on the proposed dataset, held at FG workshop 2020. This paper analyzes the winner’s approach—a two-stage recognition method (1st stage, coarse recognition; 2nd stage, fine recognition), which enhances the classification of symmetrical emotion labels. Full article

Understanding animal emotions is a key to unlocking methods for improving animal welfare. Currently there are no ‘benchmarks’ or any scientific assessments available for measuring and quantifying the emotional responses of farm animals. Using sensors to collect biometric data as a means of measuring animal emotions is a topic of growing interest in agricultural technology. Here we reviewed several aspects of the use of sensor-based approaches in monitoring animal emotions, beginning with an introduction on animal emotions. Then we reviewed some of the available technological systems for analyzing animal emotions. These systems include a variety of sensors, the algorithms used to process biometric data taken from these sensors, facial expression, and sound analysis. We conclude that a single emotional expression measurement based on either the facial feature of animals or the physiological functions cannot show accurately the farm animal’s emotional changes, and hence compound expression recognition measurement is required. We propose some novel ways to combine sensor technologies through sensor fusion into efficient systems for monitoring and measuring the animals’ compound expression of emotions. Finally, we explore future perspectives in the field, including challenges and opportunities. Full article

For a long time, expressions have been something that human beings are proud of. That is an essential difference between us and machines. With the development of computers, we are more eager to develop communication between humans and machines, especially communication with emotions. The emotional growth of computers is similar to the growth process of each of us, starting with a natural, intimate, and vivid interaction by observing and discerning emotions. Since the basic emotions, angry, disgusted, fearful, happy, neutral, sad and surprised are put forward, there are many researches based on basic emotions at present, but few on compound emotions. However, in real life, people’s emotions are complex. Single expressions cannot fully and accurately show people’s inner emotional changes, thus, exploration of compound expression recognition is very essential to daily life. In this paper, we recommend a scheme of combining spatial and frequency domain transform to implement end-to-end joint training based on model ensembling between models for appearance and geometric representations learning for the recognition of compound expressions in the wild. We are mainly devoted to digging the appearance and geometric information based on deep learning models. For appearance feature acquisition, we adopt the idea of transfer learning, introducing the ResNet50 model pretrained on VGGFace2 for face recognition to implement the fine-tuning process. Here, we try and compare two minds, one is that we utilize two static expression databases FER2013 and RAF Basic for basic emotion recognition to fine tune, the other is that we fine tune the model on the input three channels composed of images generated by DWT2 and WAVEDEC2 wavelet transforms based on rbio3.1 and sym1 wavelet bases respectively. For geometric feature acquisition, we firstly introduce a densesift operator to extract facial key points and their histogram descriptions. After that, we introduce deep SAE with a softmax function, stacked LSTM and Sequence-to-Sequence with stacked LSTM and define their structures by ourselves. Then, we feed the salient key points and their descriptions into three models to train respectively and compare their performances. When the model training for appearance and geometric features learning is completed, we combine the two models with category labels to achieve further end-to-end joint training, considering that ensembling models, which describe different information, can further improve recognition results. Finally, we validate the performance of our proposed framework on an RAF Compound database and achieve a recognition rate of 66.97%. Experiments show that integrating different models, which express different information, and achieving end-to-end training can quickly and effectively improve the performance of the recognition. Full article

Human beings are particularly inclined to express real emotions through micro-expressions with subtle amplitude and short duration. Though people regularly recognize many distinct emotions, for the most part, research studies have been limited to six basic categories: happiness, surprise, sadness, anger, fear, and disgust. Like normal expressions (i.e., macro-expressions), most current research into micro-expression recognition focuses on these six basic emotions. This paper describes an important group of micro-expressions, which we call compound emotion categories. Compound micro-expressions are constructed by combining two basic micro-expressions but reflect more complex mental states and more abundant human facial emotions. In this study, we firstly synthesized a Compound Micro-expression Database (CMED) based on existing spontaneous micro-expression datasets. These subtle feature of micro-expression makes it difficult to observe its motion track and characteristics. Consequently, there are many challenges and limitations to synthetic compound micro-expression images. The proposed method firstly implemented Eulerian Video Magnification (EVM) method to enhance facial motion features of basic micro-expressions for generating compound images. The consistent and differential facial muscle articulations (typically referred to as action units) associated with each emotion category have been labeled to become the foundation of generating compound micro-expression. Secondly, we extracted the apex frames of CMED by 3D Fast Fourier Transform (3D-FFT). Moreover, the proposed method calculated the optical flow information between the onset frame and apex frame to produce an optical flow feature map. Finally, we designed a shallow network to extract high-level features of these optical flow maps. In this study, we synthesized four existing databases of spontaneous micro-expressions (CASME I, CASME II, CAS(ME)², SAMM) to generate the CMED and test the validity of our network. Therefore, the deep network framework designed in this study can well recognize the emotional information of basic micro-expressions and compound micro-expressions. Full article