Modification Of Architecture Research Articles

An Enhanced LSTM-based Sales Forecasting Model for Functional Beverages in Cross-Cultural Markets

This paper proposes an enhanced Long Short-Term Memory (LSTM) based forecasting model explicitly designed for functional beverage sales prediction in cross-cultural markets. Traditional forecasting methods often struggle with capturing the complex interplay between cultural factors and sales patterns, leading to suboptimal prediction accuracy in diverse market environments. The proposed model incorporates innovative architectural modifications to the standard LSTM structure, integrating cultural-aware gates and specialized feature engineering techniques to capture market-specific characteristics. The research utilizes comprehensive sales data from six major markets across North America, Asia, and Europe from 2019 to 2023. The enhanced model demonstrates superior performance with a 28.4% improvement in prediction accuracy compared to traditional methods, achieving an average RMSE of 0.134 across all tested markets. The model's effectiveness is particularly evident in markets with high cultural diversity, where it achieved a 31.5% reduction in prediction error compared to conventional approaches. The research findings establish that cultural dimensions account for approximately 37.5% of sales variation across markets, highlighting the critical importance of cultural feature integration in sales forecasting. The practical implementation of the model resulted in a 23.7% reduction in inventory holding costs and improved resource allocation efficiency. This research contributes to the theoretical understanding of cross-cultural market dynamics and practical applications in global business operations.

Research on the cascade modulation method for star position simulation in a weak starlight simulator

In order to surmount the challenge wherein the gray-scale resolution of liquid crystal on silicon (LCOS) imaging within a faint starlight simulator acts as a limiting factor for the precision of stellar position correction, this paper introduces a design approach for a cascaded architecture tailored to faint starlight simulators. Through the implementation of an isometric mapping technique that maps the dimming LCOS onto the surface of the imaging LCOS, the dimensionality of gray-scale adjustment for the imaging LCOS is augmented, thereby enhancing the accuracy of simulated stellar position correction. Initially, a stellar position cascaded modulation architecture is meticulously constructed to investigate the pivotal factors that impact the gray-scale resolution of the imaging LCOS within the framework of the cascaded modulation architecture. Subsequently, the optimization protocol for the concentrator system embedded within the cascaded modulation architecture is formulated. Leveraging the simulated annealing algorithm, the multi-parameter freeform surface of the concentrator system undergoes synchronous optimization. Finally, the simulation outcomes derived from the cascaded modulation architecture both prior to and subsequent to optimization clearly demonstrate that upon the implementation of the novel architecture, the accuracy of simulated stellar position correction experiences a notable enhancement of 62%.

Enhancing perovskite solar cell efficiency and stability through architectural modifications and additives

Enhancing perovskite solar cell efficiency and stability through architectural modifications and additives

Plasticity of Root System Architecture and Whole Transcriptome Responses Underlying Nitrogen Deficiency Tolerance Conferred by a Wild Emmer Wheat QTL.

Our aim was to elucidate mechanisms underlying nitrogen (N)-deficiency tolerance in bread wheat (cultivar Ruta), conferred by a wild emmer wheat QTL (WEW; IL99). We hypothesised that the tolerance in IL99 is driven by enhanced N-uptake through modification of root system architecture (RSA) underscored by transcriptome modifications. Severe N-deficiency (0.1 N for 26 days) triggered significantly higher plasticity in IL99 compared to Ruta by modifying 16 RSA traits; nine of which were IL99-specific. The change in root growth in IL99 was collectively characterised by a transition in root orientation from shallow to steep, increased root number and length, and denser networks, enabling nutrient acquisition from a larger volume and deeper soil layers. Gene ontology and KEGG-enrichment analyses highlighted IL99-specific pathways and candidate genes elevated under N-deficiency. This included Jasmonic acid metabolism, a key hormone mediating RSA plasticity (AOS1, TIFY, MTB2, MYC2), and lignification-mediated root strengthening (CYP73A, 4CL). 'N-metabolism' was identified as a main shared pathway to IL99 and Ruta, with enhanced nitrate uptake predominant in IL99 (NRT2.4), while remobilisation was the main strategy in Ruta (NRT2.3). These findings provide novel insights into wheat plasticity response underlying tolerance to N-deficiency and demonstrate the potential of WEW for improving N-uptake under suboptimal conditions.

The impact of architectural modifications on relative resistance to fluid flow in ventricular catheters

IntroductionAlthough many ventricular catheter designs exist for hydrocephalus treatment, few standardized studies assess outflow resistance and the impact of design modifications on shunt drainage. This study represents the in-vitro assessment of various architectural modifications on catheter flow rate and pressure, focusing on bulk outflow dynamics and occlusion with whole blood-inoculated cerebrospinal fluid.MethodsCatheters were manufactured utilizing a novel catheter production setup with 16 variations from standard catheters, including but not limited to changes in: hole number, hole dimensions, catheter lumen dimension, and catheter lumen impingement. These catheters were tested in a portable custom-made ventricular catheter testing device to analyze relative resistance to flow between catheter designs. A subset of catheters with varying lumen diameters was tested in 0.30 mL/min saline flow with 2.5% blood to simulate early blood exposure.ResultsWith increasing hole and lumen diameter, we found a significant decrease in overall catheter relative resistance using DIH20 (P < 0.001 and P < 0.002 respectively, n = 5). With increasing lumen diameters, blood assays showed a significant increase in the time to complete obstruction (P = 0.027, n = 5). Lumen impingement, representing one obstruction-based pinch point in the lumen, showed a considerable increase in relative resistance as obstruction diameter increased and lumen diameter at the pinch point decreased (P = 0.001, n = 5). Removal of specific catheter hole rows trended toward an increase relative resistance after 75% of catheter holes were blocked, but the effect in relative outflow resistance is otherwise minimal (P > 0.05, n = 5) and no effect was observed with blocking segments.ConclusionThis study implemented a novel method of rapid catheter manufacturing to systematically produce ventricular catheters with specific catheter architecture. By testing variables independently, we found that catheters with changes to the lumen diameter had the most dramatic shifts in overall relative resistance between catheter designs. Similarly, testing in the acute in-vitro blood assay demonstrated that smaller diameter catheters have a higher propensity to obstruct with blood compared to catheters with larger diameter. Relative resistance impacts fluid outflow efficiency, which may translate to clinical outcomes for hydrocephalus patients. These findings help us understand catheter architectural effects on resistance and inform future designs for specific ventricle morphologies.

The Small Key to the Treasure Chest: Endogenous Plant Peptides Involved in Symbiotic Interactions

Plant growth and development are inextricably connected with rhizosphere organisms. Plants have to balance between strong defenses against pathogens while modulating their immune responses to recruit beneficial organisms such as bacteria and fungi. In recent years, there has been increasing evidence that regulatory peptides are essential in establishing these symbiotic relationships, orchestrating processes that include nutrient acquisition, root architecture modification, and immune modulation. In this review, we provide a comprehensive summary of the peptide families that facilitate beneficial relationships between plants and rhizosphere organisms.

Construction of an Experimental Device for Military Communication Using Binary Amplitude Shift Keying

Aims: To address the core requirement for military communication systems—ensuring "timely, accurate, confidential, and secure" communication—this study aims to overcome the limitations of traditional amplitude modulation (AM) methods by developing a modern experimental device using Binary Amplitude Shift Keying (BASK) modulation. Study Design: Traditional military communication systems rely on AM modulation due to its simplicity and ease of implementation. However, AM is susceptible to noise, suitable only for long-wave transmissions (e.g., AM radio), and struggles to integrate with modern technologies like 4G and 5G. To address these challenges, this study explores the mathematical foundation and system design of BASK modulation and demodulation. Methodology: The research investigates the mathematical principles of BASK, designs the system architecture for BASK modulation and demodulation, and develops an experimental device to validate the performance of the BASK-based communication model. Results: The study successfully developed an experimental device that demonstrates the feasibility of using BASK modulation for military communication. The device provides a platform for practical testing and verification of the BASK model, laying the groundwork for further advancements. Conclusion: This research provides a foundation for modernizing military communication devices. By overcoming the limitations of traditional methods and facilitating the integration of advanced technologies, the proposed device meets the stringent requirements of military environments.

Enhancing plant disease detection through deep learning: a Depthwise CNN with squeeze and excitation integration and residual skip connections

This study proposes an advanced method for plant disease detection utilizing a modified depthwise convolutional neural network (CNN) integrated with squeeze-and-excitation (SE) blocks and improved residual skip connections. In light of increasing global challenges related to food security and sustainable agriculture, this research focuses on developing a highly efficient and accurate automated system for identifying plant diseases, thereby contributing to enhanced crop protection and yield optimization. The proposed model is trained on a comprehensive dataset encompassing various plant species and disease categories, ensuring robust performance and adaptability. By evaluating the model with online random images, demonstrate its significant adaptability and effectiveness in overcoming key challenges, such as achieving high accuracy and meeting the practical demands of agricultural applications. The architectural modifications are specifically designed to enhance feature extraction and classification performance, all while maintaining computational efficiency. The evaluation results further highlight the model’s effectiveness, achieving an accuracy of 98% and an F1 score of 98.2%. These findings emphasize the model’s potential as a practical tool for disease identification in agricultural applications, supporting timely and informed decision-making for crop protection.

Hybrid Modular Redundancy: Exploring Modular Redundancy Approaches in RISC-V Multi-core Computing Clusters for Reliable Processing in Space

Space Cyber-Physical Systems such as spacecraft and satellites strongly rely on the reliability of onboard computers to guarantee the success of their missions. Relying solely on radiation-hardened technologies is extremely expensive, and developing inflexible architectural and microarchitectural modifications to introduce modular redundancy within a system leads to significant area increase and performance degradation. To mitigate the overheads of traditional radiation hardening and modular redundancy approaches, we present a novel Hybrid Modular Redundancy approach, a redundancy scheme that features a cluster of RISC-V processors with a flexible on-demand dual-core and triple-core lockstep grouping of computing cores with runtime split-lock capabilities. Further, we propose two recovery approaches, software-based and hardware-based, trading off performance and area overhead. Running at 430 MHz, our fault-tolerant cluster achieves up to 1,160 MOPS on a matrix multiplication benchmark when configured in non-redundant mode and 617 and 414 MOPS in dual and triple mode, respectively. A software-based recovery in triple mode requires 363 clock cycles and occupies 0.612 mm 2 , representing a 1.3% area overhead over a non-redundant 12-core RISC-V cluster. As a high-performance alternative, a new hardware-based method provides rapid fault recovery in just 24 clock cycles and occupies 0.660 mm 2 , namely, ∼9.4% area overhead over the baseline non-redundant RISC-V cluster. The cluster is also enhanced with split-lock capabilities to enter one of the available redundant modes with minimum performance loss, allowing execution of a mission-critical portion of code when in independent mode, or a performance section when in a reliability mode, with <400 clock cycles overhead for entry and exit. The proposed system is the first to integrate these functionalities on an open-source RISC-V-based compute device, enabling finely tunable reliability versus performance trade-offs.

A trigger-inducible split-Csy4 architecture for programmable RNA modulation.

The CRISPR-derived endoribonuclease Csy4 is a popular tool for controlling transgene expression in various therapeutically relevant settings, but adverse effects potentially arising from non-specific RNA cleavage remains largely unexplored. Here, we report a split-Csy4 architecture that was carefully optimized for in vivo usage. First, we separated Csy4 into two independent protein moieties whose full catalytic activity can be restored via various constitutive or conditional protein dimerization systems. Next, we show that introduction of split-Csy4 into human cells caused a substantially reduced extent in perturbation of the endogenous transcriptome when directly compared to full-length Csy4. Inspired by these results, we went on to use such split-Csy4 module to engineer inducible CRISPR- and translation-level gene switches regulated by the FDA-approved drug grazoprevir. This work provides valuable resource for Csy4-related biomedical research and discusses important issues for the development of clinically eligible regulation tools.

Internal structural changes in age-related curved hair due to cyclical extension: An IR spectroscopy study.

This study aimed to identify structural changes in age-related curved hair (referred to as "YUGAMI" hair in Japanese) induced by cyclical extension using infrared (IR) spectroscopy coupled with chemometrics, such as multivariate curve resolution (MCR) and two-dimensional correlation spectroscopy (2DCOS). The hair fibres were stretched at a strain level of 0.3-N, and this operation was counted as one cycle and was repeated 500 cycles. Every 25 cycles, IR spectra were obtained using an attenuated total reflection IR (ATR-IR) microscope. The spectra were analysed by MCR to investigate the structural changes of keratin protein inside of the hair. 2DCOS was conducted to investigate the genesis pathway of SO3H in the 1000-1150 cm-1 range and the change in the secondary structure of keratin protein of hair in the 1600-1700 cm-1 range. For age-related curved hair, 0.3-N strain levels increased the CH2 and C=O signals after 125 cycles and the SO3H signal after 225 cycles, but no architectural modifications were observed in straight hair. Two results were obtained from 2DCOS. One was cyclical extension increased the S-SO3H signal, followed by SO3H signal. The other in the 1600-1700 cm-1 range indicated an increase in the secondary structural motif and β-structure after the formation of SO3H. This study shows that the process of internal transformations can be split into three steps in age-related curved hair caused by cyclical extension. The first step is the surface transfer of internal lipids, and the second step is two distinct patterns of disulfide bond cleavage: C-S and S-S fission. The final step is further transformation of the unravelled α-helices into β-structures which occurs above roughly 225 stretched. Our findings can be an effective factor in care the increase of curvature by cyclical extension such as everyday grooming.

Performance Evaluation of Deep Learning Image Classification Modules in the MUN-ABSAI Ice Risk Management Architecture.

The retreat of Arctic sea ice has opened new maritime routes, offering faster shipping opportunities; however, these routes present significant navigational challenges due to the harsh ice conditions. To address these challenges, this paper proposes a deep learning-based Arctic ice risk management architecture with multiple modules, including ice classification, risk assessment, ice floe tracking, and ice load calculations. A comprehensive dataset of 15,000 ice images was created using public sources and contributions from the Canadian Coast Guard, and it was used to support the development and evaluation of the system. The performance of the YOLOv8n-cls model was assessed for the ice classification modules due to its fast inference speed, making it suitable for resource-constrained onboard systems. The training and evaluation were conducted across multiple platforms, including Roboflow, Google Colab, and Compute Canada, allowing for a detailed comparison of their capabilities in image preprocessing, model training, and real-time inference generation. The results demonstrate that Image Classification Module I achieved a validation accuracy of 99.4%, while Module II attained 98.6%. Inference times were found to be less than 1 s in Colab and under 3 s on a stand-alone system, confirming the architecture's efficiency in real-time ice condition monitoring.

Detection and recognition of foreign objects in Pu-erh Sun-dried green tea using an improved YOLOv8 based on deep learning.

The quality and safety of tea food production is of paramount importance. In traditional processing techniques, there is a risk of small foreign objects being mixed into Pu-erh sun-dried green tea, which directly affects the quality and safety of the food. To rapidly detect and accurately identify these small foreign objects in Pu-erh sun-dried green tea, this study proposes an improved YOLOv8 network model for foreign object detection. The method employs an MPDIoU optimized loss function to enhance target detection performance, thereby increasing the model's precision in targeting. It incorporates the EfficientDet high-efficiency target detection network architecture module, which utilizes compound scale-centered anchor boxes and an adaptive feature pyramid to achieve efficient detection of targets of various sizes. The BiFormer bidirectional attention mechanism is introduced, allowing the model to consider both forward and backward dependencies in sequence data, significantly enhancing the model's understanding of the context of targets in images. The model is further integrated with sliced auxiliary super-inference technology and YOLOv8, which subdivides the image and conducts in-depth analysis of local features, significantly improving the model's recognition accuracy and robustness for small targets and multi-scale objects. Experimental results demonstrate that, compared to the original YOLOv8 model, the improved model has seen increases of 4.50% in Precision, 5.30% in Recall, 3.63% in mAP, and 4.9% in F1 score. When compared with the YOLOv7, YOLOv5, Faster-RCNN, and SSD network models, its accuracy has improved by 3.92%, 7.26%, 14.03%, and 11.30%, respectively. This research provides new technological means for the intelligent transformation of automated color sorters, foreign object detection equipment, and intelligent sorting systems in the high-quality production of Yunnan Pu-erh sun-dried green tea. It also provides strong technical support for the automation and intelligent development of the tea industry.

Computational Fluid Dynamics Simulation and Experimental Study of The Airflow in a Traditional Courtyard House

Traditional courtyard houses, common in Mediterranean and Middle Eastern regions, are recognized for their ability to provide aerodynamic comfort in hot and arid climates. In the face of escalating climate change effects and health challenges amplified by the COVID-19 pandemic, there is an urgent need for sustainable architectural solutions. Courtyards, as central elements of these dwellings, play a crucial role in managing natural ventilation and creating favourable microclimates. This study specifically examines courtyard houses that have undergone significant transformations over time. Originally characterized by low courtyard heights, these houses have seen increases in elevation to accommodate growing housing needs, fundamentally altering their interaction with airflow and environmental factors. The study addresses how these architectural modifications, alongside courtyard orientation relative to prevailing winds, influence aerodynamic comfort. The primary objective of this research is to assess how the shape, height, and orientation of courtyards affect air quality and user comfort. By analyzing these parameters, the study seeks to offer architectural solutions that respond to contemporary challenges, both climatic and health-related. To achieve these objectives, the research employs a methodology combining numerical simulations using the ANSYS Fluent software, wind tunnel experiments, and a parametric analysis of morphological and climatic indicators. The case study focuses on the old town of Annaba, which has a rich heritage of courtyard houses that have been preserved since 2013.The results show that optimal courtyard orientation can improve air circulation by 25 to 45%, depending on prevailing winds and seasonal variations. Lower courtyards allow for better evacuation of hot air, while higher courtyards—introduced due to historical transformations—tend to retain more heat. These configurations, adapted to local climatic conditions, also contribute to a reduction in energy consumption by up to 30%. Furthermore, increased natural ventilation in open courtyards helps limit the transmission of airborne viruses, thereby improving indoor air quality.

Enhanced Growth of Cucumber (Cucumis sativus L.) Through Amino Acids and Seaweed Extracts for the Use in Organic Agriculture

AbstractThe increasing consumer interest in organic products is driving the rise of the agricultural sector. However, organic farming productivity was lower than conventional due to the reduction of external inputs, synthetic fertilizers, and pesticides. In this context, the use of organic biostimulant emerged as a promising solution. The aim of this study was to evaluate the efficacy of three doses (0.1, 0.2, 0.3 mL per plant) of an innovative organic biostimulant based on amino acids and seaweed extract (Lombrico® ARREL), on cucumber (Cucumis sativus L.) under hydroponic conditions in a plant growth chamber. The results demonstrated that the root application of the biostimulant promoted plant growth development. In the shoot, there was an increase in height, number of leaves, fresh and dry weight and leaf area compared to the control. In the root, there was an increase in volume (66.2, 83.2, and 165%), fresh weight (45.0, 61.0 and 97.3%) and dry weight (7.0, 23.0 and 53.7%) as escalating the product dose (low, medium and high, respectively) compared to the control. Furthermore, the root length decreased, triggering a significant modification of the root system architecture. Transcriptome analysis in the root revelated that this biostimulant induced change in the gene expression. Gene ontology and Kyoto Encyclopedia of Genes and Genomes (KEEG) analysis showed stimulation of the cell division, biosynthesis and remodeling of the cell wall, increasing plant metabolism and hormone signal transduction, as well as activating the phenylpropanoid biosynthesis. This study showed the benefit of integrating the biostimulant uses in organic agriculture management to improve plant development, thereby enhancing crop productivity.

Модификация архитектуры сверточной нейронной сети для определения категории земельного участка со спутниковых снимков

Correct classification of land plots by their types, for example, such as forest, agricultural, urbanized, water bodies, and others, is relevant for remote sensing of the Earth and the development of geoinformation technologies. The accuracy and reliability of the results of such categorization are of paramount importance for the efficient use of natural resources, rational land use, and environmental monitoring. The article presents an approach to solving the problem of categorizing land plots based on satellite images by applying a modified standard model of a convolutional neural network. The main attention is paid to the modification of the network architecture in order to improve the accuracy of land plot classification. The authors propose an approach to training and optimizing the network in order to solve this problem. The stages of data preparation are discussed in detail, including preprocessing satellite images, annotating them, and creating high-quality training samples. The presented approaches to network training and optimization include the use of modern regularization techniques, adaptive learning methods, and class balancing strategies, which allows efficient processing of both large amounts of data and more limited sets of specific information. To test the approach’s operability and obtain the values of quality indicators, experiments were conducted to train and test the model on various sets of satellite image data. The results of the experiment suggest that the accuracy of categorization achieved on the basis of the created model meets the requirements of the Federal Service for State Registration, Cadastre and Cartography for studying remote Territories for the suitability of land for their rational use, and the proposed method can be used to solve practical problems.

Modification of bone architecture following sleeve gastrectomy: a five-year follow-up.

Bariatric surgery induces a decrease in areal BMD (aBMD), but the long-term effect on trabecular and cortical volumetric BMD (vBMD) has not been well assessed. The main aim of this 5-yr longitudinal study was to investigate the changes following sleeve gastrectomy (SG) in aBMD, bone turnover markers, and trabecular and cortical vBMD. Forty-five patients with obesity were assessed before and 1, 2, and 5yr after SG. Trabecular and cortical vBMD, cortical thickness, and structural parameters were assessed by 3D-Shaper software at the hip. Values of bone turnover markers peaked after 1yr and decreased after 2 and 5yr, but without returning to baseline values. aBMD decreased mostly at the femoral neck (-9.7%) and total hip (-10.7%) over the 5yr, with the greatest loss occurring at 1yr (-5.9% and -6.3%, respectively). A similar profile of decrease was observed for integral hip vBMD with significant decreases of 6.6%, 7.7%, and 10.7% after 1, 2, and 5yr, mainly due to a reduction in the trabecular (10.5%, 12.0%, and 17.2%, respectively) rather than cortical (1.4%, 1.9%, and 2.9%, respectively) component. A modest decrease in mean cortical thickness (2.5%, 2.8%, and 3.9%, respectively) and an alteration in the structural parameters were concomitantly observed. Older age and greater body weight loss were the factors most associated with an increased loss of aBMD and vBMD. In conclusion, the study demonstrates that SG induces not only an alteration in bone turnover and aBMD, but also a reduction in vBMD at the hip, predominantly due to trabecular component deterioration as determined by 3D-Shaper software. The maintenance of bone deterioration for at least 5yr-ie, after 4yr of relative body weight stabilization or minimal weight regain-suggests the need for a therapeutic approach to preserve bone health in patients who undergo SG.

Segmentation for mammography classification utilizing deep convolutional neural network

BackgroundMammography for the diagnosis of early breast cancer (BC) relies heavily on the identification of breast masses. However, in the early stages, it might be challenging to ascertain whether a breast mass is benign or malignant. Consequently, many deep learning (DL)-based computer-aided diagnosis (CAD) approaches for BC classification have been developed.MethodsRecently, the transformer model has emerged as a method for overcoming the constraints of convolutional neural networks (CNN). Thus, our primary goal was to determine how well an improved transformer model could distinguish between benign and malignant breast tissues. In this instance, we drew on the Mendeley data repository’s INbreast dataset, which includes benign and malignant breast types. Additionally, the segmentation anything model (SAM) method was used to generate the optimized cutoff for region of interest (ROI) extraction from all mammograms. We implemented a successful architecture modification at the bottom layer of a pyramid transformer (PTr) to identify BC from mammography images.ResultsThe proposed PTr model using a transfer learning (TL) approach with a segmentation technique achieved the best accuracy of 99.96% for binary classifications with an area under the curve (AUC) score of 99.98%, respectively. We also compared the performance of the proposed model with other transformer model vision transformers (ViT) and DL models, MobileNetV3 and EfficientNetB7, respectively.ConclusionsIn this study, a modified transformer model is proposed for BC prediction and mammography image classification using segmentation approaches. Data segmentation techniques accurately identify the regions affected by BC. Finally, the proposed transformer model accurately classified benign and malignant breast tissues, which is vital for radiologists to guide future treatment.

First use of cord blood platelet-rich plasma in the treatment of vulvar lichen sclerosus: a preliminary study towards a randomized controlled trial.

Although topical corticosteroids (TCS) represent first-line treatment for vulvar lichen sclerosus (VLS) and as such should be prescribed to all women at time of diagnosis, approximately 30% of patients do not experience complete symptom resolution following such treatment. TCS may not effectively improve vulvar trophism and elasticity, both of which are crucial for sexual function. Owing to its regenerative and healing properties, cord blood platelet-rich plasma (CB-PRP) may represent an efficacious supplementary therapy, to be administered following first line treatment with TCS. The primary aim of this study was to assess safety and tolerability of CB-PRP in women with VLS. This is a pilot study which precedes a randomized controlled trial of CB-PRP vs placebo in women with VLS. Ten consecutive patients with VLS, who had previously undergone standard TCS-treatment, received three vulvar CB-PRP injections monthly. Follow-up was conducted three months after the last injection using vulvoscopy and validated questionnaires to evaluate safety and tolerability, as well as patient satisfaction, symptom improvement, sexual function, psychological well-being, quality of life, frequency of TCS application as a maintenance treatment, vulvar trophism and architectural modifications. No adverse clinical effects were observed. Five patients (50%) were either satisfied or very satisfied with the procedure, four (40%) were uncertain about their satisfaction with the treatment. One patient (10%) dropped out for personal reasons and was classified as unsatisfied according to an intention-to-treat analysis. At follow-up median numeric rating scale scores were significantly reduced for vulvar burning compared to baseline (p<0.05) there was a trend toward improvement in itching, dyspareunia, and dysuria. A significant improvement in sexual arousal and satisfaction was observed in all treated women (p<0.05). CB-PRP may be a promising treatment for VLS. It appears to be safe and improve symptoms and sexual function.

Causal Inference for Modality Debiasing in Multimodal Emotion Recognition

Multimodal emotion recognition (MER) aims to enhance the understanding of human emotions by integrating visual, auditory, and textual modalities. However, previous MER approaches often depend on a dominant modality rather than considering all modalities, leading to poor generalization. To address this, we propose Causal Inference in Multimodal Emotion Recognition (CausalMER), which leverages counterfactual reasoning and causal graphs to capture relationships between modalities and reduce direct modality effects contributing to bias. This allows CausalMER to make unbiased predictions while being easily applied to existing MER methods in a model-agnostic manner, without requiring any architectural modifications. We evaluate CausalMER on the IEMOCAP and CMU-MOSEI datasets, widely used benchmarks in MER, and compare it with existing methods. On the IEMOCAP dataset with the MulT backbone, CausalMER achieves an average accuracy of 83.4%. On the CMU-MOSEI dataset, the average accuracies with MulT, PMR, and DMD backbones are 50.1%, 48.8%, and 48.8%, respectively. Experimental results demonstrate that CausalMER is robust in missing modality scenarios, as shown by its low standard deviation in performance drop gaps. Additionally, we evaluate modality contributions and show that CausalMER achieves balanced contributions from each modality, effectively mitigating direct biases from individual modalities.