Background: Endometriosis-associated ovarian cancer (EAOC) is a well-known type of cancer that arises from ovarian endometrioma (OE). OE contains iron-rich fluid in its cysts due to repeated hemorrhages in the ovaries. However, distinguishing between benign and malignant tumors can be challenging. We conducted a retrospective study on magnetic resonance (MR) relaxometry of cyst fluid to distinguish EAOC from OE and reported that this method showed good accuracy. The purpose of this study is to evaluate the accuracy of a non-invasive method in re-evaluating pre-surgical diagnosis of malignancy by a prospective multicenter cohort study. Methods: After the standard diagnosis process, the R2 values were obtained using a 3T system. Data on the patients were then collected through the Case Report Form (CRF). Between December 2018 and March 2023, six hospitals enrolled 109 patients. Out of these, 81 patients met the criteria required for the study. Results: The R2 values calculated using MR relaxometry showed good discriminating ability with a cut-off of 15.74 (sensitivity 80.6%, specificity 75.0%, AUC = 0.750, p < 0.001) when considering atypical or borderline tumors as EAOC. When atypical and borderline cases were grouped as OE, EAOC could be distinguished with a cut-off of 16.87 (sensitivity 87.0%, specificity 61.1%). Conclusions: MR relaxometry has proven to be an effective tool for discriminating EAOC from OE. Regular use of this method is expected to provide significant insights for clinical practice. Full article

A microwave-assisted synthesis of dialkyl and cyclic H-phosphonates via bis(2,2,2 trifluoroethyl) phosphonate (BTFEP) is described. This method enables the synthesis of various cyclic H-phosphonates and hetero-substituted dialkyl H-phosphonates by simple alcoholysis under non-inert and additive-free conditions. Short reaction times and the requirement for only stoichiometric amounts of alcohol render this method attractive for synthetic applications. Full article

This study offers a detailed analysis of building information modeling (BIM) policy and implementation across Europe, significantly contributing to the sector’s digital transformation. By collating data from governmental, academic, and industry sources, it identifies key trends and evaluates the effectiveness of BIM policies in advancing technology within construction. A systematic literature review and text mining across major databases revealed an increasing focus on sustainability, particularly “life cycle assessment” and “energy efficiency”, aligning with the Industry 5.0 initiative. The research shows that 35% of European countries have or plan to introduce BIM mandates, highlighting BIM’s crucial role in enhancing construction practices and influencing policy frameworks. Insights from this study are valuable for researchers, practitioners, and policymakers, guiding the adoption and operationalization of BIM and emphasizing the need for thorough market preparation, including funding, training, and standardization. Additionally, the study suggests a correlation between a country’s economic development and its propensity to enforce BIM mandates. Future research could explore regional policy variations and delve into the theoretical aspects of policy adoption and innovation diffusion to further understand BIM uptake dynamics. Full article

A review of the last 399 years (1624–2023) on fin whales (Balaenoptera physalus) in the Mediterranean Sea was conducted, based on an extensive compilation of records published in the scientific literature, technical reports, public databases, journals, and social media. A total of 10,716 sightings and 575 mortality events have been computed, analysed by semesters and mapped in order to compare the summer–winter seasons especially and their implications on migration–residence. Visual and acoustic detections, feedings, migrations, primary production areas (chlorophyll), threats and causes of death and their relations have been addressed, and a mini-review on heavy metals and pollutants has been carried out on fin whales in the Mediterranean Sea. Mortality events were most frequent between November and April, coinciding with the decreased sighting period. Ship strikes posed the greatest threat, peaking between May and October, when marine traffic tends to increase in the Mediterranean Sea. Two populations coexist in the Mediterranean Sea, one resident and the other migratory, the latter using the Strait of Gibraltar for its biannual movements. Two areas with a presence of calves (up to 7 m in length) between October and February were detected: one scattered in the northern Mediterranean and the Strait of Gibraltar and its surroundings. A critical zone for collisions has been established according to the results for fin whales in the Mediterranean Sea. Full article

Sports-related muscle injuries account for 10–55% of all injuries, which is a growing concern, especially given the aging world population. To evaluate the process of skeletal muscle injury and compare it with muscle lesions observed in humans, we developed a novel in vivo model in sheep. In this model, muscle injury was induced by an ultrasound-guided transverse biopsy at the myotendinous junction of the medial gastrocnemius muscle. Twelve male sheep were examined at 3, 7, 14, and 28 days post-injury. Histological, immunofluorescence, and MRI analyses indicate that our sheep model could resemble key human clinicopathological features. Statistically significant differences (p < 0.05) were observed in collagen I, dMHC, α-SMA, and CD68 immunohistochemical detection when comparing injured and healthy muscles. The injured gastrocnemius muscle exhibited elevated levels of type I collagen, infiltration of CD68(+) macrophages, angiogenesis, and the emergence of newly regenerated dMHC(+) myofibers, which persisted for up to 4 weeks post-injury. Similarly, the progression of muscle injury in the sheep model was assessed using advanced clinical 3 T MRI and compared with MRI scans from human patients. The data indicate that the sheep muscle injury model presents features similar to those observed in human skeletal muscle injuries. This makes it a valuable large animal model for studying muscle injuries and developing novel therapeutic strategies. Full article

Coagulation is a process affected by multiple variables, nonlinear mapping and multiple perturbations. In order to realize the precise dosage of flocculants, polyaluminum chloride (PAC) was taken as the research object to explore the effects of temperature, water turbidity, pH and COD_Mn on the dosage of PAC and coagulation effect. A response surface methodology (RSM) experiment was carried out based on a single-factor experiment. The turbidity, pH and dosage of a single parameter, as well as the interaction term and secondary term, all have significant influence on coagulation effect. The optimal reaction conditions were calculated using Design-Expert software: pH, 7.48; turbidity, 14.59 NTU; dosage, 24.01 mg/L; and the error between the experimental value and the predicted value, 4.08%. Establishing a model with residual turbidity as a consideration index can help to calculate the optimal dosage of PAC, which is conducive to a reasonable and accurate control of the dosage of PAC in the coagulation process, so as to achieve the goal of low turbidity of effluent and low production cost. Full article

Lightweight and high-strength insulation materials have important application prospects in the aerospace, metallurgical, and nuclear industries. In this study, a highly porous silica fiber reinforced phenolic resin matrix composite was prepared by vacuum impregnation and atmospheric drying using quartz fiber needled felt as reinforcement and anhydrous ethanol as a pore-making agent. The effects of curing agent content on the structure, composition, density, and thermal conductivity of the composite were studied. The mechanical properties of the composite in the xy direction and z direction were analyzed. The results showed that this process can also produce porous phenolic resin (PR) with a density as low as 0.291 g/cm³, where spherical phenolic resin particles are interconnected to form a porous network structure with a particle size of about 5.43 μm. The fiber-reinforced porous PR had low density (0.372~0.397 g/cm³) and low thermal conductivity (0.085~0.095 W/m·K). The spherical phenolic resin particles inside the composite were well combined with the fiber at the interface and uniformly distributed in the fiber lap network. The composite possessed enhanced mechanical properties with compressive strength of 3.5–5.1 MPa in the xy direction and appeared as gradual compaction rather than destruction as the strain reached 30% in the z direction. This research provides a lightweight and high-strength insulation material with a simple preparation process and excellent performance. Full article

Mild steel corrosion is a significant challenge in oil and gas exploitation. Inhibitors are frequently employed to minimize the corrosive impact on mild steel. Mixing corrosion inhibitors is an effective method in reducing the dosage of toxic compounds and expanding the potential applications of inhibitors in NaCl solutions. Herein, a mixed corrosion inhibitor composed of imidazoline (IM), sodium molybdate, and sodium dodecylbenzenesulfonate (SDBS) for mild steel in a 3.5 wt% NaCl solution are investigated by orthogonal experimental design and electrochemical measurement. The imidazoline compound was synthesized and identified using Fourier transform infrared (FTIR) spectroscopy. The inhibitory effect is improved by higher concentrations of sodium molybdate and is further enhanced with the addition of 10 mg/L of SDBS. The electrochemical impedance spectroscopy indicates that the combination of IM (100 mg/L), sodium molybdate (50 mg/L), and SDBS (100 mg/L) results in excellent performance with electrochemical impedance (1.8 kohm·cm²). The mild steel surfaces after electrochemical measurement were analyzed using scanning electron microscopy (SEM). The information can contribute to the development of corrosion inhibitors with high performance or to understand the influence of mixing inhibitors on corrosion processes of mild steels. Full article

Fibre metal laminates (FMLs) are the most interesting composite materials of the past decade. They possess the properties of both polymer composites and metallic alloys. However, there is a problem with corrosion when the outer layers are made of aluminium or magnesium. The electrochemical changes that occur during the corrosion process and the mechanisms associated with the corrosion phenomenon are still being investigated. Recently, self-healing phenomena have emerged as a useful approach to prevent corrosion. However, there is limited research on the combination of FMLs and self-healing layers. Therefore, the main purpose of this article is to evaluate the self-healing ability of a magnesium/PEO layer based on microcapsules in a corrosion environment. It was observed that the corrosion mechanism in magnesium alloys is very complex. However, the use of a barrier layer with PEO treatment and microcapsules yielded positive anti-corrosion results. The FML samples were subjected to a 6-week corrosion test, and the addition of microcapsules to the layers showed positive results. In contrast, the samples without microcapsules exhibited intergranular corrosion. In the future, comprehensive tests using self-healing microcapsules in FMLs could greatly enhance their anti-corrosion properties and improve the integrity of the structure. Full article

This review, complemented by empirical investigations, delves into the intricate world of industrial powders, examining their elastic properties through diverse methodologies. The study critically assesses Young’s modulus (E) across eight different powder samples from various industries, including joint filler, wheat flour, wheat starch, gluten, glass beads, and sericite. Employing a multidisciplinary approach, integrating uniaxial compression methodologies—both single and cyclic—with vibration techniques, has revealed surprising insights. Particularly notable is the relationship between porosity and Young’s modulus, linking loose powders to the compacts generated under compression methods. Depending on the porosity of the powder bed, Young’s modulus can vary from a few MPa (loose powder) to several GPa (tablet), following an exponential trend. The discussion emphasizes the necessity of integrating various techniques, with a specific focus on the consolidation state of the powder bed, to achieve a comprehensive understanding of bulk elasticity. This underscores the need for low-consolidation methodologies that align more closely with powder technologies and unit operations such as conveying, transport, storage, and feeding. In conclusion, the study suggests avenues for further research, highlighting the importance of exploring bulk elastic properties in loose packing conditions, their relation with flowability, alongside the significance of powder conditioning. Full article

The utility of transcranial sonography (TCS) remains unclarified for the auxiliary diagnosis of Parkinson’s disease (PD). We investigated iodine-123 metaiodobenzylguanidine (MIBG) and TCS during the examination and diagnosis of high-signal-intensity substantia nigra lesion (HSI-SNL) incidence in PD patients previously diagnosed with dopamine transporter scintigraphy (DAT). The subjects were 67 patients with definitively diagnosed PD after DAT evaluation. Patients with midbrain substantia nigra visible during TCS who previously underwent MIBG were analyzed. The SN+ group comprised patients with extensive pathological HSI-SNL of Okawa class III/IV observed during TCS. The MIBG+ group comprised patients with a heart-to-mediastinum ratio of ≤2.2 during MIBG. TCS was performed to divide patients into the SN+ and SN− groups, and patient characteristics and MIBG findings were compared between the groups. PD was definitively diagnosed in 67 patients, among whom midbrain was visualized during TCS in 43 (64.1%) patients and pathological HSI-SNL was observed in 24 (35.8%). The MIBG findings were normal in six patients (27.3%) with HSI-SNL, and abnormal in seven (63.6%) without HSI-SNL. No significant differences were noted by Okawa classification in clinical characteristics based on the presence or absence of HSI-SNL. Multiple patients with normal findings during MIBG may have HSI-SNL. Thus, confirmatory imaging of HSI-SNL with TCS may be useful for diagnosis. Full article

The traditional receiver employs scalar tracking loops, resulting in degraded navigation performance in weak signal and high dynamic scenarios. An innovative design of a vector tracking receiver based on nonlinear Kalman filter (KF) tracking loops is proposed in this paper, which combines the strengths of both vector tracking and KF-based tracking loops. First, a comprehensive description of the vector tracking receiver model is presented, and unscented Kalman filter (UKF) is applied to nonlinear tracking loop. Second, to enhance the stability and robustness of the KF tracking loop, we introduce square root filtering and an adaptive mechanism. The tracking loop based on square root UKF (SRUKF) can dynamically adjust its filtering parameters based on signal noise and feedback Doppler error. Finally, the proposed method is implemented on a software-defined receiver (SDR), and the field vehicle experiment demonstrates the superiority of this method over other tracking methods in complex dynamic environments. Full article

Gestational diabetes mellitus (GDM) is a hyperglycemic state that is typically diagnosed by an oral glucose tolerance test (OGTT), which is unpleasant, time-consuming, has low reproducibility, and results are tardy. The machine learning (ML) predictive models that have been proposed to improve GDM diagnosis are usually based on instrumental methods that take hours to produce a result. Near-infrared (NIR) spectroscopy is a simple, fast, and low-cost analytical technique that has never been assessed for the prediction of GDM. This study aims to develop ML predictive models for GDM based on NIR spectroscopy, and to evaluate their potential as early detection or alternative screening tools according to their predictive power and duration of analysis. Serum samples from the first trimester (before GDM diagnosis) and the second trimester (at the time of GDM diagnosis) of pregnancy were analyzed by NIR spectroscopy. Four spectral ranges were considered, and 80 mathematical pretreatments were tested for each. NIR data-based models were built with single- and multi-block ML techniques. Every model was subjected to double cross-validation. The best models for first and second trimester achieved areas under the receiver operating characteristic curve of 0.5768 ± 0.0635 and 0.8836 ± 0.0259, respectively. This is the first study reporting NIR-spectroscopy-based methods for the prediction of GDM. The developed methods allow for prediction of GDM from 10 µL of serum in only 32 min. They are simple, fast, and have a great potential for application in clinical practice, especially as alternative screening tools to the OGTT for GDM diagnosis. Full article

Emerging research links the endocannabinoid system to gut microbiota, influencing nociception, mood, and immunity, yet the molecular interactions remain unclear. This study focused on the effects of probiotics on ECS markers—cannabinoid receptor type 2 (CB2) and fatty acid amide hydrolase (FAAH)—in dancers, a group selected due to their high exposure to physical and psychological stress. In a double-blind, placebo-controlled trial (ClinicalTrials.gov NCT05567653), 15 dancers were assigned to receive either a 12-week regimen of Lactobacillus helveticus Rosell-52 and Bifidobacterium longum Rosell-17 or a placebo (PLA: n = 10, PRO: n = 5). There were no significant changes in CB2 (probiotic: 0.55 to 0.29 ng/mL; placebo: 0.86 to 0.72 ng/mL) or FAAH levels (probiotic: 5.93 to 6.02 ng/mL; placebo: 6.46 to 6.94 ng/mL; p > 0.05). A trend toward improved sleep quality was observed in the probiotic group, while the placebo group showed a decline (PRO: from 1.4 to 1.0; PLA: from 0.8 to 1.2; p = 0.07841). No other differences were noted in assessed outcomes (pain and fatigue). Probiotic supplementation showed no significant impact on CB2 or FAAH levels, pain, or fatigue but suggested potential benefits for sleep quality, suggesting an area for further research. Full article

Background: Inflammatory bowel disease (IBD) consists of Crohn’s disease (CD) and Ulcerative colitis (UC). The main goal of treatment is to obtain mucosal healing via endoscopy. More recently, intestinal ultrasounds, along with biochemical markers, have been increasingly popular as point-of-care testing to monitor treatment response. This systemic review and meta-analysis aimed to assess the diagnostic test performance of ultrasonography and biochemical markers (C-reactive protein and fecal calprotectin) compared with endoscopy for detecting inflammation in IBD. Methods: A comprehensive literature search was conducted using PubMed Medline, EMBASE, ScienceDirect, and CINAHL from 1 January 2018 to 1 January 2024. The included studies were prospective and retrospective observational studies, clinical trials, and cross-sectional studies investigating the diagnostic sensitivity and specificity of ultrasonography, biochemical markers, and endoscopy. Studies were selected based on the Preferred Reporting Items for Systematic Review and Meta-analysis Statement (PRISMA). Results: Of the 1035 studies retrieved, 16 met the inclusion criteria, and most of the included studies were prospective observational studies. Diagnostic test accuracy was conducted, and the pooled sensitivity and specificity of all the studies revealed that ultrasonography has the highest pooled sensitivity, at 85% (95% CI, 78 to 91%), and specificity, at 92% (95% CI, 86 to 96%), as compared with biochemical markers and endoscopy. More specifically, biochemical markers had a pooled sensitivity and specificity of 85% (95% CI, 81 to 87%) and 61% (95% CI, 58 to 64%), respectively, and endoscopy had 60% (95% CI, 52 to 68%) and 82% (95% CI, 76 to 87%), respectively. However, the results also show substantial heterogeneity in the studies because of various populations, protocols, and outcomes in the studies included. This was especially noted in the assessment of biochemical markers, in which a metaregression was performed showing a nonsignificant p-value of 0.8856 for the coefficient. Conclusions: IUS was found to have the highest pooled sensitivity and specificity of all the included studies for diagnosing inflammation in patients with CD and UC, and this, coupled with biochemical markers, can improve diagnostic utility. Full article

Industrial solid waste is characterized by complex mineral phases and various components. Low-carbon cementitious materials can be prepared through precise regulation based on the material composition and properties of various industrial solid wastes. In this study, electrolytic manganese residue (EMR), carbide slag (CS), and granulated blast-furnace slag (GBFS) were used as alternatives to cement to prepare multicomponent solid waste cementitious materials. The effects of the proportions of EMR and CS on the cementitious activity of GBFS and the activation mechanism of alkali and sulfur were studied. The results showed that with increasing EMR content, the strength first increased and then decreased. At a GBFS content of 20%, CS content of 2%, and EMR content of 8%, the compressive strength was highest, reaching 45.5 MPa after 28 days of curing, mainly because the OH⁻ in CS and SO₄²⁻ in EMR synergistically stimulated the active components in GBFS. Hydrated products such as ettringite and hydrated calcium silicate (C–S–H gel) were generated and interlaced with each other to improve the densification of the mortar. Overall, the proposed system provides an avenue to reduce or replace the production of cement clinker and achieve the high-value-added utilization of industrial solid waste. Full article

Existing point cloud feature learning networks often learn high-semantic point features representing the global context by incorporating sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation. However, this process may result in a substantial loss of granular information due to the sampling operation and the widely-used max pooling feature aggregation, which neglects information from non-maximum point features. Consequently, the resulting high-semantic point features could be insufficient to represent the local context, hindering the network’s ability to distinguish fine shapes. To address this problem, we propose PointStack, a novel point cloud feature learning network that utilizes multi-resolution feature learning and learnable pooling (LP). PointStack aggregates point features of various resolutions across multiple layers to capture both high-semantic and high-resolution information. The LP function calculates the weighted sum of multi-resolution point features through an attention mechanism with learnable queries, enabling the extraction of all available information. As a result, PointStack can effectively represent both global and local contexts, allowing the network to comprehend both the global structure and local shape details. PointStack outperforms various existing feature learning networks for shape classification and part segmentation on the ScanObjectNN and ShapeNetPart datasets, achieving 87.2% overall accuracy and instance mIoU. Full article

An increased demand for natural products nowadays most specifically probiotics (PROs) is evident since it comes in conjunction with beneficial health effects for consumers. In this regard, it is well known that encapsulation could positively affect the PROs’ viability throughout food manufacturing and long-term storage. This paper aims to analyze and review various double/multilayer strategies for encapsulation of PROs. Double-layer encapsulation of PROs by electrohydrodynamic atomization or electrospraying technology has been reported along with layer-by-layer assembly and water-in-oil-in-water (W₁/O/W₂) double emulsions to produce multilayer PROs-loaded carriers. Finally, their applications in food products are presented. The resistance and viability of loaded PROs to mechanical damage, during gastrointestinal transit and shelf life of these trapping systems, are also described. The PROs encapsulation in double- and multiple-layer coatings combined with other technologies can be examined to increase the opportunities for new functional products with amended functionalities opening a novel horizon in food technology. Full article

Oscillatory baffled flows (OBFs) provide a combined active and passive means of achieving convective heat transfer enhancement, and previous studies at large scale have demonstrated the heat transfer benefits of OBFs. To date, however, this technology has not been scaled down for the purpose of heat sink performance enhancement. Presented in this study is a numerical investigation of a single baffled channel with a hydraulic diameter of 2.8 mm, containing gate baffles, with a 50% open area, which are spaced 7.5 mm apart. Three net-flow rates were investigated while varying the oscillation conditions by varying the oscillation amplitude (3 mm to 7 mm) and by varying the oscillation frequency (0 to 8 Hz). Increasing the oscillation intensity had a greater impact on the Nusselt number compared to simply increasing the net-flow rate, with Nu enhancements of up to 330% observed when imposing oscillatory flow on a purely steady flow. Ideal operating conditions were identified by grouping the data by velocity ratio (Ψ) and graphing the theoretical pumping power against the thermal resistance of the channel. The highest Nu enhancement of 330% was achieved for a net-flow Reynolds number (Re_n) of 165, oscillatory amplitude of 5 mm and a frequency of 8 Hz. Ideal operating conditions can be predicted by selecting conditions with Ψ > 1. A flow with a Re_n of 46, Ψ of 7 and Nu = 12 required the same pumping power as a flow with a of Re_n 165, Ψ of 0.65 and Nu = 6. Full article

The EuroQoL 5-Dimension 5-Level questionnaire (EQ-5D-5L) and the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core-30 (EORTC QLQ-C30) are commonly used Patient-Reported Outcome Measures (PROMs) for breast cancer. This study assesses and compares the internal responsiveness of the EQ-5D-5L and EORTC QLQ-C30 in Dutch breast cancer patients during the first year post-surgery. Women diagnosed with breast cancer who completed the EQ-5D-5L and EORTC QLQ-C30 pre-operatively (T0), 6 months (T6), and 12 months post-surgery (T12) were included. Mean differences of the EQ-5D-5L and EORTC QLQ-C30 between baseline and 6 months (delta 1) and between baseline and 12 months post-surgery (delta 2) were calculated and compared against the respective minimal clinically important differences (MCIDs) of 0.08 and 5. Internal responsiveness was assessed using effect sizes (ES) and standardized response means (SRM) for both deltas. In total, 333 breast cancer patients were included. Delta 1 and delta 2 for the EQ-5D-5L index and most scales of the EORTC QLQ-C30 were below the MCID. The internal responsiveness for both PROMs was small (ES and SRM < 0.5), with greater internal responsiveness for delta 1 compared to delta 2. The EQ-5D-5L index showed greater internal responsiveness than the EORTC QLQ-C30 Global Quality of Life scale and summary score. These findings are valuable for the interpretation of both PROMs in Dutch breast cancer research and clinical care. Full article

This study examines the environmental impacts of informal e-waste recycling processes in Agbogbloshie, Ghana, which is one of the most notorious e-waste recycling sites in sub-Saharan Africa. Despite being unsafe and unorganized, the informal sector is still actively involved in dismantling, extracting, and disposing of e-waste in unauthorized locations on a considerably large scale. However, the academic research on the environmental consequences of informal recycling practices is limited. Soil and groundwater samples for five important and representative informal e-waste recycling processes and one related oil process were collected and analyzed to determine heavy metal-, PBDEs, PCBs, CBs, and PAHs concentrations. Contamination indices were used to assess and compare the effects of informal recycling processes, thereby providing a geochemical evaluation of soil conditions. As a result, the manual dismantling of CRT and ICT devices is the major source of heavy metal pollution. Furthermore, the burning of e-waste plastic for waste reduction purposes and the oil collection process substantially contribute to the input of organic pollutants. Regulatory measures for CRT and ICT recycling would result in an 85% reduction of heavy metals and the enforcement of a compulsory collection system for plastic and oil would eliminate 86% of the organic pollutants. Full article

The effectiveness of a wind turbine elastic support in reducing vibrations significantly impacts the unit’s lifespan. During the structural design process, it is necessary to consider the influence of structural design parameters on multiple performance indicators. While neural networks can fit the relationships between design parameters on multiple performance indicators, traditional modeling methods often isolate multiple tasks, hindering the learning on correlations between tasks and reducing efficiency. Moreover, acquiring training data through physical experiments is expensive and yields limited data, insufficient for effective model training. To address these challenges, this research introduces a data generation method using a digital twin model, simulating physical conditions to generate data at a lower cost. Building on this, a Multi-gate Mixture-of-Experts multi-task prediction model with Long Short-Term Memory (MMoE-LSTM) module is developed. LSTM enhances the model’s ability to extract nonlinear features from data, improving learning. Additionally, a dynamic weighting strategy, based on coefficient of variation weighting and ridge regression, is employed to automate loss weight adjustments and address imbalances in multi-task learning. The proposed model, validated on datasets created using the digital twin model, achieved over 95% predictive accuracy for multiple tasks, demonstrating that this method is effective. Full article