Frontiers in Computational Neuroscience · مجلد 18 · 1485121-1485121
Facial emotion recognition (FER) can serve as a valuable tool for assessing emotional states, which are often linked to mental health. However, mental health encompasses a broad range of factors that go beyond facial expressions. While FER provides insights into certain aspects of emotional well-being, it can be used in conjunction with other assessments to form a more comprehensive understanding of an individual's mental health. This research work proposes a framework for human FER using UNet image segmentation and transfer learning with the EfficientNetB4 model (called FacialNet). The proposed model demonstrates promising results, achieving an accuracy of 90% for six emotion classes (happy, sad, fear, pain, anger, and disgust) and 96.39% for binary classification (happy and sad). The significance of FacialNet is judged by extensive experiments conducted against various machine learning and deep learning models, as well as state-of-the-art previous research works in FER. The significance of FacialNet is further validated using a cross-validation technique, ensuring reliable performance across different data splits. The findings highlight the effectiveness of leveraging UNet image segmentation and EfficientNetB4 transfer learning for accurate and efficient human facial emotion recognition, offering promising avenues for real-world applications in emotion-aware systems and effective computing platforms. Experimental findings reveal that the proposed approach performs substantially better than existing works with an improved accuracy of 96.39% compared to existing 94.26%.
facial emotion recognitionmental health assessmentEfficientNet-B4transfer learning
Substituting sugar with noncaloric sweeteners prevents overweight and diabetes development. They come in two types: artificial, like aspartame and sucralose, and natural, such as sorbitol. This research aimed to assess the effects of sucrose and these sweeteners on nutritional parameters, hematological parameters, hormones, and anti- and pro-inflammatory cytokines in male rats. Thirty rats had been separated into five groups. The results showed the highest significant increase in body weight gain, total food intake, and feed efficiency noticed in the aspartame group followed by sucralose, sucrose, and sorbitol, respectively. In contrast to RBCs and platelets, all sweeteners significantly reduced the hemoglobin level, Hct %, and WBC count. The aspartame group showed the highest decline in glycoproteins, steroids, and T3, and T4 hormones and a dramatic elevation in thyroid stimulating hormone, eicosanoid, and amine hormones compared with the control group. A vigorous elevation in anti- and proinflammatory cytokine levels was observed in the aspartame group, followed by sucralose, sucrose, and sorbitol groups. Aspartame has the highest docking scores when studying the interactions of sweeteners and a target protein associated with hormones or cytokines using in silico molecular docking, with the best absorption, distribution, metabolism, elimination, and toxicity properties compared to the remaining sweeteners.
In wireless sensor networks, the existing clustering head selection protocol is unworkable, leading to uneven network loads and a shorter network lifetime. To improve energy-effective wireless sensor networks (WSN) for e-commerce applications, a cluster head selection technique called CIBOA (Cluster Head Selection using Integrated Butterfly Optimization technique) has been created to address this problem. The current clustering head selection mechanism in wireless sensor networks is ineffective, which results in unequal network loads and a shorter network lifetime. The Butterfly Optimization Algorithm (BOA) has undergone significant modifications to enhance performance. These enhancements significantly boost the optimization speed and accuracy of BOA, thereby strengthening its search capabilities. During the process of selecting cluster heads (CH), a novel fitness function has been developed. This function considers variables such as remaining energy levels, the distance between nodes and base stations, and the average distance between neighboring nodes. The results show that CIBOA comprehensively considers factors like node energy and distance. This holistic approach results in a reduction in overall network operational time, making it particularly suitable for Energy-efficient networks of wireless sensors, especially in the context of e-commerce applications.
cluster head selectionwireless sensor networksbutterfly optimization algorithme-commerce applications
In the realm of medical imaging, the early detection of kidney issues, particularly renal cell hydronephrosis, holds immense importance. Traditionally, the identification of such conditions within ultrasound images has relied on manual analysis, a labor-intensive and error-prone process. However, in recent years, the emergence of deep learning-based algorithms has paved the way for automation in this domain. This study aims to harness the power of deep learning models to autonomously detect renal cell hydronephrosis in ultrasound images taken in close proximity to the kidneys. State-of-the-art architectures, including VGG16, ResNet50, InceptionV3, and the innovative Novel DCNN, were put to the test and subjected to rigorous comparisons. The performance of each model was meticulously evaluated, employing metrics such as F1 score, accuracy, precision, and recall. The results paint a compelling picture. The Novel DCNN model outshines its peers, boasting an impressive accuracy rate of 99.8%. In the same arena, InceptionV3 achieved a notable 90% accuracy, ResNet50 secured 89%, and VGG16 reached 85%. These outcomes underscore the Novel DCNN's prowess in the realm of renal cell hydronephrosis detection within ultrasound images. Moreover, this study offers a detailed view of each model's performance through confusion matrices, shedding light on their abilities to categorize true positives, true negatives, false positives, and false negatives. In this regard, the Novel DCNN model exhibits remarkable proficiency, minimizing both false positives and false negatives. In conclusion, this research underscores the Novel DCNN model's supremacy in automating the detection of renal cell hydronephrosis in ultrasound images. With its exceptional accuracy and minimal error rates, this model stands as a promising tool for healthcare professionals, facilitating early-stage diagnosis and treatment. Furthermore, the model's convergence rate and accuracy hold potential for enhancement through further exploration, including testing on larger and more diverse datasets and investigating diverse optimization strategies.
International Immunopharmacology · مجلد 141 · 112934-112934
Hepatic fibrosis is a common pathology present in most chronic liver diseases. Autophagy is a lysosome-mediated intracellular catabolic and recycling process that plays an essential role in maintaining normal hepatic functions. Nuclear factor erythroid 2-like 2 (Nrf2) is a transcription factor responsible for the regulation of cellular anti-oxidative stress response. This study was designed to assess the cytoprotective effect of mesenchymal stem cell-derived exosomes (MSC-exos) on endothelial-mesenchymal transition (EMT) in Carbon Tetrachloride (CCL4) induced liver fibrosis. Rats were treated with 0.1 ml of CCL4 twice weekly for 8 weeks, followed by administration of a single dose of MSC-exos. Rats were then sacrificed after 4 weeks, and liver samples were collected for gene expression analyses, Western blot, histological studies, immunohistochemistry, and transmission electron microscopy. Our results showed that MSC-exos administration decreased collagen deposition, apoptosis, and inflammation. Exosomes modulate the Nrf2/Keap1/p62 pathway, restoring autophagy and Nrf2 levels through modulation of the non-canonical pathway of Nrf2/Keap1/p62. Additionally, MSC-exos regulated miR-153-3p, miR-27a, miR-144 and miRNA-34a expression. In conclusion, the present study shed light on MSC-exos as a cytoprotective agent against EMT and tumorigenesis in chronic liver inflammation.
This study aimed to investigate the potential of patuletin, a rare natural flavonoid, as a virulence and LasR inhibitor against Pseudomonas aeruginosa. Various computational studies were utilized to explore the binding of Patuletin and LasR at a molecular level. Molecular docking revealed that Patuletin strongly interacted with the active pocket of LasR, with a high binding affinity value of −20.96 kcal/mol. Further molecular dynamics simulations, molecular mechanics generalized Born surface area (MM/GBSA), protein-ligand interaction profile (PLIP), and essential dynamics analyses confirmed the stability of the patuletin-LasR complex, and no significant structural changes were observed in the LasR protein upon binding. Key amino acids involved in binding were identified, along with a free energy value of −26.9 kcal/mol. In vitro assays were performed to assess patuletin’s effects on P. aeruginosa. At a sub-inhibitory concentration (1/4 MIC), patuletin significantly reduced biofilm formation by 48% and 42%, decreased pyocyanin production by 24% and 14%, and decreased proteolytic activities by 42% and 20% in P. aeruginosa isolate ATCC 27853 (PA27853) and P. aeruginosa clinical isolate (PA1), respectively. In summary, this study demonstrated that patuletin effectively inhibited LasR activity in silico and attenuated virulence factors in vitro, including biofilm formation, pyocyanin production, and proteolytic activity. These findings suggest that patuletin holds promise as a potential therapeutic agent in combination with antibiotics to combat antibiotic-tolerant P. aeruginosa infections.