Effect of intraoperative cell salvage on coagulation function outcomes in patients with massive post-Cesarean section hemorrhage.

OBJECTIVE: To examine the impact of using intraoperative cell salvage (ICS) for the restoration of coagulation function in cases of massive Post-Cesarean Section Hemorrhage (PCSH). METHODS: A retrospective analysis was conducted on 60 cases of massive PCSH meeting inclusion criteria at Suqian Maternity and Children's Hospital from January 2020 to July 2022. Patients were divided into two groups: allogeneic blood transfusion group (Group A, n = 30) and ICS group (Group B, n = 30), based on transfusion methods. Blood parameters, coagulation function, and adverse reactions were assessed before (T0) and after (T1) transfusion. Patients were categorized into good prognosis (GP) and poor prognosis (PP) groups based on adverse reaction occurrence. Clinical profiles were compared between groups, and multivariate binary logistic regression analysis was employed to evaluate the factors that may affect the prognosis in women with PCSH. RESULTS: No significant differences in routine blood parameters were observed between groups at T0 and T1 (P>0.05). At T0, no significant differences in PT, APTT, TT, or FIB were found between groups (P>0.05). Both groups showed a reduction in PT, APTT, and TT values at T1 compared to T0, with Group B experiencing a more significant decrease than Group A (P<0.05). FIB increased in both groups at T1 compared to T0, with Group B demonstrating a higher increase than Group A (P<0.05). Both groups showed increased blood pressure at T1 compared to T0, with Group B showing a more pronounced elevation than Group A (P<0.05). The occurrence of adverse reactions was significantly lower in Group B (1/30, 3.33%) compared to Group A (7/30, 23.33%) (P<0.05). Logistic regression analysis identified FIB<1.52 g/L and HR<45.35 times/min as factors associated with increased risk of unfavorable outcome in women with PCSH. CONCLUSION: In patients experiencing significant PCSH, ICS may lead to better postoperative recovery of blood parameters, faster restoration of coagulation function, and reduced risk of adverse events compared to ABT. Moreover, early detection of coagulation function and blood gas indexes is crucial for clinicians to implement timely prevention and treatment measures.

Photorewriting, Time-Resolved Encryption, and Unclonable Anticounterfeiting with Artificial Intelligence Authentication via a Reversible Photoswitchable System.

In the fields of photolithographic patterning, optical anticounterfeiting, and information encryption, reversible photochromic materials with solid-state fluorescence are emerging as a potential class of systems. A design strategy for reversible photochromic materials has been proposed and synthesized through the introduction of photoactive thiophene groups into the molecular backbone of aryl vinyls, compounds with unique aggregation-induced emission properties, and solid-state reversible photocontrollable fluorescence and color-changing properties. This work develops novel photochromic inks, films, and cellulose hydrogels for enhancing the security of information encryption and anticounterfeiting technologies. They achieve rapid and reversible color change under ultraviolet light irradiation. Dependent upon the rate of color change, higher levels of time-resolved security can be achieved. This feature is important for enhancing the confidentiality of encrypted information and the reliability of security labels. Color-changing cellulose hydrogels, inks, and films consisting of three photochromic fluorescent molecules have quick photoactivity, great photoreversibility and photostability, and good processability, making them ideal for time-delayed anticounterfeiting and smart encryption. Furthermore, specialized algorithms are used to construct convolutional neural networks, and image analysis is performed on these systems, thus solving the current problem of the time-consuming information decryption process. This artificial intelligence method offers new opportunities for enhanced data encryption.

Loss of FoxO1 activates an alternate mechanism of mitochondrial quality control for healthy adipose browning.

Browning of white adipose tissue is hallmarked by increased mitochondrial density and metabolic improvements. However, it remains largely unknown how mitochondrial turnover and quality control are regulated during adipose browning. In the present study, we found that mice lacking adipocyte FoxO1, a transcription factor that regulates autophagy, adopted an alternate mechanism of mitophagy to maintain mitochondrial turnover and quality control during adipose browning. Post-developmental deletion of adipocyte FoxO1 (adO1KO) suppressed Bnip3 but activated Fundc1/Drp1/OPA1 cascade, concurrent with up-regulation of Atg7 and CTSL. In addition, mitochondrial biogenesis was stimulated via the Pgc1α/Tfam pathway in adO1KO mice. These changes were associated with enhanced mitochondrial homeostasis and metabolic health (e.g., improved glucose tolerance and insulin sensitivity). By contrast, silencing Fundc1 or Pgc1α reversed the changes induced by silencing FoxO1, which impaired mitochondrial quality control and function. Ablation of Atg7 suppressed mitochondrial turnover and function, causing metabolic disorder (e.g., impaired glucose tolerance and insulin sensitivity), regardless of elevated markers of adipose browning. Consistently, suppression of autophagy via CTSL by high-fat diet was associated with a reversal of adO1KO-induced benefits. Our data reveal a unique role of FoxO1 in coordinating mitophagy receptors (Bnip3 and Fundc1) for a fine-tuned mitochondrial turnover and quality control, underscoring autophagic clearance of mitochondria as a prerequisite for healthy browning of adipose tissue.

A wireless fluorescent sensing device for on-site closed-loop detection of hydrazine levels in the environment.

Given the extensive need for the detection of hydrazine (N2H4) in the biomedical and chemical-pharmaceutical sectors, there is a necessity to devise a fast, sensitive, specific, and portable technique for precisely quantifying hydrazine at environmental levels. In our work, an "OFF-ON" type fluorescent probe namely 2-(4-(10-(naphthalen-2-yl)anthracen-9-yl)phenyl)isoindole-1,3-dione (NAP), which was inspired by the "Gabriel" reaction, was synthesized. The NAP fluorescent cellulose film successfully achieved the detection of hydrazine vapor with a LOD = 0.658 ppm. Compared to previous qualitative methods for detecting hydrazine, this study successfully achieved quantitative identification of hydrazine at low concentrations. In addition, a portable sensor device based on NAP cellulose film was successfully integrated, enabling ultra-sensitive, wireless, remote, and real-time detection of N2H4 vapor. It was determined that the probe (NAP) exhibited excellent detection performance when applied to various environmental samples including distilled water, tap water, creek water, soil and plants. This study introduces a potentially effective approach for detecting hydrazine in real-world settings.

Therapeutically targeting type I interferon directly to XCR1+ dendritic cells reveals the role of cDC1s in anti-drug antibodies.

Conventional type 1 dendritic cells (cDC1s) are superior in antigen cross-presentation and priming CD8+ T cell anti-tumor immunity and thus, are a target of high interest for cancer immunotherapy. Type I interferon (IFN) is a potent inducer of antigen cross-presentation, but, unfortunately, shows only modest results in the clinic given the short half-life and high toxicity of current type I IFN therapies, which limit IFN exposure in the tumor. CD8+ T cell immunity is dependent on IFN signaling in cDC1s and preclinical studies suggest targeting IFN directly to cDC1s may be sufficient to drive anti-tumor immunity. Here, we engineered an anti-XCR1 antibody (Ab) and IFN mutein (IFNmut) fusion protein (XCR1Ab-IFNmut) to determine whether systemic delivery could drive selective and sustained type I IFN signaling in cDC1s leading to anti-tumor activity and, in parallel, reduced systemic toxicity. We found that the XCR1Ab-IFNmut fusion specifically enhanced cDC1 activation in the tumor and spleen compared to an untargeted control IFN. However, multiple treatments with the XCR1Ab-IFNmut fusion resulted in robust anti-drug antibodies (ADA) and loss of drug exposure. Using other cDC1-targeting Ab-IFNmut fusions, we found that localizing IFN directly to cDC1s activates their ability to promote ADA responses, regardless of the cDC1 targeting antigen. The development of ADA remains a major hurdle in immunotherapy drug development and the cellular and molecular mechanisms governing the development of ADA responses in humans is not well understood. Our results reveal a role of cDC1s in ADA generation and highlight the potential ADA challenges with targeting immunostimulatory agents to this cellular compartment.

Research Progress and Prospect of Stimuli-Responsive Lignin Functional Materials.

As the world's second most abundant renewable natural phenolic polymer after cellulose, lignin is an extremely complex, amorphous, highly cross-linked class of aromatic polyphenolic macromolecules. Due to its special aromatic structure, lignin is considered to be one of the most suitable candidates to replace fossil materials, thus the research on lignin functional materials has received extensive attention. Because lignin has stimuli-sensitive groups such as phenolic hydroxyl, hydroxyl, and carboxyl, the preparation of stimuli-responsive lignin-based functional materials by combining lignin with some stimuli-responsive polymers is a current research hotspot. Therefore, this article will review the research progress of stimuli-responsive lignin-based functional materials in order to guide the subsequent work. Firstly, we elaborate the source and preparation of lignin and various types of lignin pretreatment methods. We then sort out and discuss the preparation of lignin stimulus-responsive functional materials according to different stimuli (pH, light, temperature, ions, etc.). Finally, we further envision the scope and potential value of lignin stimulus-responsive functional materials for applications in actuators, optical coding, optical switches, solar photothermal converters, tissue engineering, and biomedicine.

FoxO1 regulates adipose transdifferentiation and iron influx by mediating Tgfß1 signaling pathway.

Adipose plasticity is critical for metabolic homeostasis. Adipocyte transdifferentiation plays an important role in adipose plasticity, but the molecular mechanism of transdifferentiation remains incompletely understood. Here we show that the transcription factor FoxO1 regulates adipose transdifferentiation by mediating Tgfß1 signaling pathway. Tgfß1 treatment induced whitening phenotype in beige adipocytes, reducing UCP1 and mitochondrial capacity and enlarging lipid droplets. Deletion of adipose FoxO1 (adO1KO) dampened Tgfß1 signaling by downregulating Tgfbr2 and Smad3 and induced browning of adipose tissue in mice, increasing UCP1 and mitochondrial content and activating metabolic pathways. Silencing FoxO1 also abolished the whitening effect of Tgfß1 on beige adipocytes. The adO1KO mice exhibited a significantly higher energy expenditure, lower fat mass, and smaller adipocytes than the control mice. The browning phenotype in adO1KO mice was associated with an increased iron content in adipose tissue, concurrent with upregulation of proteins that facilitate iron uptake (DMT1 and TfR1) and iron import into mitochondria (Mfrn1). Analysis of hepatic and serum iron along with hepatic iron-regulatory proteins (ferritin and ferroportin) in the adO1KO mice revealed an adipose tissue-liver crosstalk that meets the increased iron requirement for adipose browning. The FoxO1-Tgfß1 signaling cascade also underlay adipose browning induced by ß3-AR agonist CL316243. Our study provides the first evidence of a FoxO1-Tgfß1 axis in the regulation of adipose browning-whitening transdifferentiation and iron influx, which sheds light on the compromised adipose plasticity in conditions of dysregulated FoxO1 and Tgfß1 signaling.

Hormonal regulation of metabolism-recent lessons learned from insulin and estrogen.

Hormonal signaling plays key roles in tissue and metabolic homeostasis. Accumulated evidence has revealed a great deal of insulin and estrogen signaling pathways and their interplays in the regulation of mitochondrial, cellular remodeling, and macronutrient metabolism. Insulin signaling regulates nutrient and mitochondrial metabolism by targeting the IRS-PI3K-Akt-FoxOs signaling cascade and PGC1α. Estrogen signaling fine-tunes protein turnover and mitochondrial metabolism through its receptors (ERα, ERß, and GPER). Insulin and estrogen signaling converge on Sirt1, mTOR, and PI3K in the joint regulation of autophagy and mitochondrial metabolism. Dysregulated insulin and estrogen signaling lead to metabolic diseases. This article reviews the up-to-date evidence that depicts the pathways of insulin signaling and estrogen-ER signaling in the regulation of metabolism. In addition, we discuss the cross-talk between estrogen signaling and insulin signaling via Sirt1, mTOR, and PI3K, as well as new therapeutic options such as agonists of GLP1 receptor, GIP receptor, and ß3-AR. Mapping the molecular pathways of insulin signaling, estrogen signaling, and their interplays advances our understanding of metabolism and discovery of new therapeutic options for metabolic disorders.

Effects of Ruxolitinib on Myeloproliferative Neoplasms via the Negative Regulators.

BACKGROUND: We evaluated the JAK2V617F mutation and p-JAK2, SOCS-1, SHP-1 expression in JAK2V617F positive myeloproliferative neoplasms (MPNs) patients and the role of JAK/STAT pathway in human erythroleukemia (HEL) cells, which had JAK2V617F mutation. METHODS: Protein expression of p-JAK2, SOCS-1, SHP-1 in bone marrow biopsies (BMBs) were detected by immunohistochemical staining methods. Cell apoptosis and cell cycle were detected by flow cytometry and Caspase 3/7 assay kits. RESULTS: 1. The p-JAK2, SOCS-1, and SHP-1 expressions were significantly different between JAK2V617F positive MPN and control patients (p < 0.01); 2. After being treated for 3 months, the p-JAK2, SOCS-1, and SHP-1 expressions were significantly different compared with newly diagnosed patients (p < 0.01). 3. HEL cell viabilities were significantly different after being treated with different concentrations of ruxolitinib. Ruxolitinib had a significant effect on the cell apoptosis, viability, and the protein activity of caspase-3 and -7 of HEL cells. 3. The mRNA and protein expressions of JAK2 and the protein expression of p-JAK2 were gradually decreased (p ＜ 0.01, p ＜ 0.05), while the mRNA and protein expressions of SOCS1 and SHP1 were gradually increased (all p ＜ 0.01).

Flexible Multiview Spectral Clustering With Self-Adaptation.

Multiview spectral clustering (MVSC) has achieved state-of-the-art clustering performance on multiview data. Most existing approaches first simply concatenate multiview features or combine multiple view-specific graphs to construct a unified fusion graph and then perform spectral embedding and cluster label discretization with k -means to obtain the final clustering results. They suffer from an important drawback: all views are treated as fixed when fusing multiple graphs and equal when handling the out-of-sample extension. They cannot adaptively differentiate the discriminative capabilities of multiview features. To alleviate these problems, we propose a flexible MVSC with self-adaptation (FMSCS) method in this article. A self-adaptive learning scheme is designed for structured graph construction, multiview graph fusion, and out-of-sample extension. Specifically, we learn a fusion graph with a desirable clustering structure by adaptively exploiting the complementarity of different view features under the guidance of a proper rank constraint. Meanwhile, we flexibly learn multiple projection matrices to handle the out-of-sample extension by adaptively adjusting the view combination weights according to the specific contents of unseen data. Finally, we derive an alternate optimization strategy that guarantees desirable convergence to iteratively solve the formulated unified learning model. Extensive experiments demonstrate the superiority of our proposed method compared with state-of-the-art MVSC approaches. For the purpose of reproducibility, we provide the code and testing datasets at https://github.com/shidan0122/FMICS.

Assessing the Activity of Transcription Factor FoxO1.

The transcription factor FoxO1 (forkhead box O1) regulates genes that are involved in development, metabolism, cellular innovation, longevity, and stress responses. Assessment of FoxO1 activity is therefore critical to understand the regulatory network of this transcription factor. FoxO1 transactivation activity relies on its ability to bind to the promoters of target genes, which is controlled by posttranslational modifications (e.g., dephosphorylation or phosphorylation) that may promote nuclear translocation or exclusion of FoxO1. In this chapter we describe the protocols for FoxO1 activity assessment using Western blotting analysis of the posttranslational modification of FoxO1 in whole cell lysates and ELISA of DNA binding activity of FoxO1 in nuclear extracts.

Effect of Weight-Adjusted Phenylephrine, Norepinephrine, and Metaraminol for Elective Cesarean Delivery on Neonatal Acid-Base Status: A Randomized Controlled Trial.

Purpose: Many previous trials have compared the effects of different vasoactive drugs on cesarean section patients, but their infusion rate is based on experience rather than high-quality evidence. It is difficult to judge whether the effect of vasoactive drug comes from the better choice or a more appropriate at rates of vasoactive drugs. The effect of vasoactive drugs at the rates of the 90% effective dose needs to be verified and compared. Patients and Methods: Women undergoing elective caesarean delivery under combined spinal-epidural anaesthesia were randomized to receive phenylephrine or norepinephrine or metaraminol infusion at the rate that was assumed to be the 90% effective dose. Anesthetic management was standardized and included fluid loading with 10 mL/kg of Ringer. The primary outcome was the umbilical artery pH. Results: 78 patients were included. The umbilical artery pH was not significantly different among the three groups (phenylephrine group: 7.33 ± 0.03 vs norepinephrine group: 7.33 ± 0.04 vs metaraminol group: 7.33 ± 0.04, P = 0.99). There were no significant differences in the incidence of hypotension, hypertension, bradycardia, and nausea and vomiting among the three groups. The SBP of the phenylephrine group was significantly higher than that of the metaraminol group (adjustive P value = 0.005). Conclusion: Phenylephrine (0.54 µg/kg/min) or metaraminol (2 µg/kg/min) or norepinephrine (0.08 µg/kg/min) administered to healthy patients with elective cesarean section after spinal anesthesia has no significant effect on the acid-base balance of the fetus.

Controllable synthesis of conjugated microporous polymer films for ultrasensitive detection of chemical warfare agents.

Nerve agents, one of the most toxic chemical warfare agents, seriously threaten human life and public security. The high toxicity of nerve agents makes the development of fluorescence sensors with suitable limit of detection challenging. Here, we propose a sensor design based on a conjugated microporous polymer film for the detection of diethyl chlorophosphate, a substitute of Sarin, with low detection limit of 2.5 ppt. This is due to the synergy of the susceptible on-off effect of hybridization and de-hybridization of hybrid local and charge transfer (HLCT) materials and the microporous structure of CMP films facilitating the inward diffusion of DCP vapors, and the extended π-conjugated structure. This strategy provides a new idea for the future development of gas sensors. In addition, a portable sensor is successfully integrated based on TCzP-CMP films that enables wireless, remote, ultrasensitive, and real-time detection of DCP vapors.

Mechanisms of autophagic responses to altered nutritional status.

Autophagy is a dynamic process and critical for cellular remodeling and organelle quality control. In response to altered nutritional status (e.g., fasting and feeding), autophagic activity is finely tuned by transcriptional, posttranslational, and epigenetic regulations via various signaling pathways, including energy sensors (e.g., mechanistic target of rapamycin (mTOR)/ AMP-activated protein kinase - Unc-51 Like Autophagy Activating Kinase 1, mTORC1- WD Repeat Domain, Phosphoinositide Interacting 2, mTORC1- transcription factor EB, perilipin 5- Sirtuin 1, and Sirtuin 1-mediated deacetylation of autophagy proteins), fasting or feeding induced hormones (e.g., fibroblast growth factor [FGF21]- protein kinase A - Jumonji domain-containing protein D3, FGF21- downstream regulatory element antagonist modulator - E3 ligase Midline-1- transcription factor EB, FGF19-SHP- lysine-specific demethylase, insulin- insulin receptor substrate - protein kinase B - forkhead box O, glucagon- protein kinase A - cAMP response binding protein), and lysosomal enzymes (e.g., cathepsin B and cathepsin L). In contrast to fasting that induces autophagy and health benefits, nutrient oversupply (overfeeding or feeding on high energy diets) dysregulates autophagy, which has been increasingly observed in animal models of human chronic diseases such as obesity, diabetes, non-alcoholic fatty liver disease, and cardiovascular disease. Studies have revealed multifaceted effects of high energy diets on autophagy, being either an inhibitor or enhancer of autophagy. The conundrum may arise from the variations in methods for autophagy analysis, components of high energy diets and control diets for treatments, treatment durations, and the ages of genetic backgrounds of laboratory animals. In this article, we reviewed the evidence from both human and animal studies, presenting the molecular mechanism of autophagic response to altered nutritional status and discussing the contributing factors of and possible solution to the current conundrum concerning the exact role of high energy diets in autophagic regulation.

FoxO transcription factors in mitochondrial homeostasis.

Mitochondria play essential roles in cellular energetics, biosynthesis, and signaling transduction. Dysfunctional mitochondria have been implicated in different diseases such as obesity, diabetes, cardiovascular disease, nonalcoholic fatty liver disease, neurodegenerative disease, and cancer. Mitochondrial homeostasis is controlled by a triad of mitochondrial biogenesis, dynamics (fusion and fission), and autophagy (mitophagy). Studies have underscored FoxO transcription factors as key mitochondrial regulators. Specifically, FoxOs regulate mitochondrial biogenesis by dampening NRF1-Tfam and c-Myc-Tfam cascades directly, and inhibiting NAD-Sirt1-Pgc1α cascade indirectly by inducing Hmox1 or repressing Fxn and Urod. In addition, FoxOs mediate mitochondrial fusion (via Mfn1 and Mfn2) and fission (via Drp1, Fis1, and MIEF2), during which FoxOs elicit regulatory mechanisms at transcriptional, posttranscriptional (e.g. via miR-484/Fis1), and posttranslational (e.g. via Bnip3-calcineurin mediated Drp1 dephosphorylation) levels. Furthermore, FoxOs control mitochondrial autophagy in the stages of autophagosome formation and maturation (e.g. initiation, nucleation, and elongation), mitochondria connected to and engulfed by autophagosome (e.g. via PINK1 and Bnip3 pathways), and autophagosome-lysosome fusion to form autolysosome for cargo degradation (e.g. via Tfeb and cathepsin proteins). This article provides an up-to-date view of FoxOs regulating mitochondrial homeostasis and discusses the potential of targeting FoxOs for therapeutics.

Loss Re-Scaling VQA: Revisiting the Language Prior Problem From a Class-Imbalance View.

Recent studies have pointed out that many well-developed Visual Question Answering (VQA) models are heavily affected by the language prior problem. It refers to making predictions based on the co-occurrence pattern between textual questions and answers instead of reasoning upon visual contents. To tackle this problem, most existing methods focus on strengthening the visual feature learning capability to reduce this text shortcut influence on model decisions. However, few efforts have been devoted to analyzing its inherent cause and providing an explicit interpretation. It thus lacks a good guidance for the research community to move forward in a purposeful way, resulting in model construction perplexity towards overcoming this non-trivial problem. In this paper, we propose to interpret the language prior problem in VQA from a class-imbalance view. Concretely, we design a novel interpretation scheme whereby the loss of mis-predicted frequent and sparse answers from the same question type is distinctly exhibited during the late training phase. It explicitly reveals why the VQA model tends to produce a frequent yet obviously wrong answer, to a given question whose right answer is sparse in the training set. Based upon this observation, we further propose a novel loss re-scaling approach to assign different weights to each answer according to the training data statistics for estimating the final loss. We apply our approach into six strong baselines and the experimental results on two VQA-CP benchmark datasets evidently demonstrate its effectiveness. In addition, we also justify the validity of the class imbalance interpretation scheme on other computer vision tasks, such as face recognition and image classification.

Pairwise Two-Stream ConvNets for Cross-Domain Action Recognition With Small Data.

In this work, we target cross-domain action recognition (CDAR) in the video domain and propose a novel end-to-end pairwise two-stream ConvNets (PTC) algorithm for real-life conditions, in which only a few labeled samples are available. To cope with the limited training sample problem, we employ pairwise network architecture that can leverage training samples from a source domain and, thus, requires only a few labeled samples per category from the target domain. In particular, a frame self-attention mechanism and an adaptive weight scheme are embedded into the PTC network to adaptively combine the RGB and flow features. This design can effectively learn domain-invariant features for both the source and target domains. In addition, we propose a sphere boundary sample-selecting scheme that selects the training samples at the boundary of a class (in the feature space) to train the PTC model. In this way, a well-enhanced generalization capability can be achieved. To validate the effectiveness of our PTC model, we construct two CDAR data sets (SDAI Action I and SDAI Action II) that include indoor and outdoor environments; all actions and samples in these data sets were carefully collected from public action data sets. To the best of our knowledge, these are the first data sets specifically designed for the CDAR task. Extensive experiments were conducted on these two data sets. The results show that PTC outperforms state-of-the-art video action recognition methods in terms of both accuracy and training efficiency. It is noteworthy that when only two labeled training samples per category are used in the SDAI Action I data set, PTC achieves 21.9% and 6.8% improvement in accuracy over two-stream and temporal segment networks models, respectively. As an added contribution, the SDAI Action I and SDAI Action II data sets will be released to facilitate future research on the CDAR task.

Assessing learning engagement based on facial expression recognition in MOOC's scenario.

Online learning has become one of the most important learning styles, yet with the need of supervisors to consistently keep the learners motivated and on-task. Some learners could be supervised by outer factors, and distance learners have to be motivated by themselves. However, online learning engagement is hardly to be assessed by supervisors in real time. With the rapid development of information technology, it is able to remedy the above problem by using intelligent video surveillance techniques. In this paper, we propose a novel framework of learning engagement assessment which introduces facial expression recognition to timely acquire the emotional changes of the learners. Moreover, a new facial expression recognition method is proposed based on domain adaptation, which is suitable for the MOOC scenario. The experiments show the effectiveness of our proposed framework on assessing learners' learning engagement. The comparisons with the state-of-the-art methods also demonstrate the superiority of our proposed facial emotion recognition method.