Search Results (171)

Systemic sclerosis (SSc) is an autoimmune connective tissue disorder characterized by vascular abnormalities, immune dysfunction, and progressive fibrosis. One of the most common manifestations of SSc is interstitial lung disease (ILD), known by a progressive course leading to significant morbidity and mortality. Aim: to investigate autoantibodies, cytokines, and genetic markers in SSc-ILD through a systematic review and analysis of a Kazakh cohort of SSc-ILD patients. Methods: A PubMed search over the past 10 years was performed with “SSc-ILD”, “autoantibodies”, “cytokines”, and “genes”. Thirty patients with SSc were assessed for lung involvement, EScSG score, and modified Rodnan skin score. IL-6 was measured by ELISA, antinuclear factor on HEp-2 cells by indirect immunofluorescence, and specific autoantibodies by immunoblotting. Genetic analysis was performed using a 120-gene AmpliSeq panel on the Ion Proton platform. Results: The literature review identified 361 articles, 26 addressed autoantibodies, 20 genetic variants, and 12 cytokine profiles. Elevated levels of IL-6, TGF-β, IL-33, and TNF-α were linked to SSc. Based on the results of the systemic review, we created a preliminary immunogenic panel for SSc-ILD with following analysis in Kazakh patients with SSc (n = 30). Fourteen of them (46.7%) demonstrated signs of ILD and/or lung hypertension, with frequent detection of antibodies such as Scl-70, U1-snRNP, SS-A, and genetic variants in SAMD9L, REL, IRAK1, LY96, IL6R, ITGA2B, AIRE, TREX1, and CD40 genes. Conclusions: Current research confirmed the presence of the broad range of autoantibodies and variations in IRAK1, TNFAIP3, SAMD9L, REL, IRAK1, LY96, IL6R, ITGA2B, AIRE, TREX1, CD40 genes in of Kazakhstani cohort of SSc-ILD patients. Full article

In order to meet the needs for the rapid detection of crop growth and support variable management in farmland, an intelligent chlorophyll content in cotton leaves (CCC) detection system based on hyperspectral imaging (HSI) technology was designed and developed. The system includes a near-infrared (NIR) hyperspectral image acquisition module, a spectral extraction module, a main control processor module, a model acceleration module, a display module, and a power module, which are used to achieve rapid and non-destructive detection of chlorophyll content. Firstly, spectral images of cotton canopy leaves during the seedling, budding, and flowering-boll stages were collected, and the dataset was optimized using the first-order differential algorithm (1D) and Savitzky–Golay five-term quadratic smoothing (SG) algorithm. The results showed that SG had better processing performance. Secondly, the sparrow search algorithm optimized backpropagation neural network (SSA-BPNN) and one-dimensional convolutional neural network (1DCNN) algorithms were selected to establish a chlorophyll content detection model. The results showed that the determination coefficients $R_p^2$ of the chlorophyll SG-1DCNN detection model during the seedling, budding, and flowering-boll stages were 0.92, 0.97, and 0.95, respectively, and the model performance was superior to SG-SSA-BPNN. Therefore, the SG-1DCNN model was embedded into the detection system. Finally, a CCC intelligent detection system was developed using Python 3.12.3, MATLAB 2020b, and ENVI, and the system was subjected to application testing. The results showed that the average detection accuracy of the CCC intelligent detection system in the three stages was 98.522%, 99.132%, and 97.449%, respectively. Meanwhile, the average detection time for the samples is only 20.12 s. The research results can effectively solve the problem of detecting the nutritional status of cotton in the field environment, meet the real-time detection needs of the field environment, and provide solutions and technical support for the intelligent perception of crop production. Full article

As a classical statistical method, multiple regression is widely used for forecasting tasks in power, medicine, finance, and other fields. The rise of machine learning has led to the adoption of neural networks, particularly Long Short-Term Memory (LSTM) models, for handling complex forecasting problems, owing to their strong ability to capture temporal dependencies in sequential data. Nevertheless, the performance of LSTM models is highly sensitive to hyperparameter configuration. Traditional manual tuning methods suffer from inefficiency, excessive reliance on expert experience, and poor generalization. Aiming to address the challenges of complex hyperparameter spaces and the limitations of manual adjustment, an enhanced sparrow search algorithm (ISSA) with adaptive parameter configuration was developed for LSTM-based multivariate regression frameworks, where systematic optimization of hidden layer dimensionality, learning rate scheduling, and iterative training thresholds enhances its model generalization capability. In terms of SSA improvement, first, the population is initialized by the reverse learning strategy to increase the diversity of the population. Second, the mechanism for updating the positions of producer sparrows is improved, and different update formulas are selected based on the sizes of random numbers to avoid convergence to the origin and improve search flexibility. Then, the step factor is dynamically adjusted to improve the accuracy of the solution. To improve the algorithm’s global search capability and escape local optima, the sparrow search algorithm’s position update mechanism integrates Lévy flight for detection and early warning. Experimental evaluations using benchmark functions from the CEC2005 test set demonstrated that the ISSA outperforms PSO, the SSA, and other algorithms in optimization performance. Further validation with power load and real estate datasets revealed that the ISSA-LSTM model achieves superior prediction accuracy compared to existing approaches, achieving an RMSE of 83.102 and an $R^2$ of 0.550 during electric load forecasting and an RMSE of 18.822 and an $R^2$ of 0.522 during real estate price prediction. Future research will explore the integration of the ISSA with alternative neural architectures such as GRUs and Transformers to assess its flexibility and effectiveness across different sequence modeling paradigms. Full article

The Upper Lianggaoshan (LGS) Formation in the northeastern Sichuan Basin, composed of shale with interbedded siltstone, is a promising target layer for shale oil. Accurate evaluation of pore structures is essential for effective exploration of shale oil. This study investigated pore structures of siltstone and shale samples from the Upper LGS Formation using low-pressure CO₂ adsorption (LTCA), low-temperature N₂ adsorption (LTNA), high-pressure mercury intrusion (HPMI), and nuclear magnetic resonance (NMR) methods. The single-exponent and multifractal dimensions of samples were determined, and the relationships between fractal dimensions and pore structures were explored. Results show that the pore size distribution (PSD) of siltstone and shale samples exhibits multi-peak characteristics, with mesopores (2–50 nm) being dominant in the total pore volumes. The multi-scaled pores in shale and siltstone samples exhibit fractal characteristics. The average values of single-fractal dimensions (D₁, D₂) obtained by LTNA data are 2.39 and 2.62 for shale samples, and 2.24 and 2.59 for siltstone samples, respectively. Compared to siltstones, the pore structures of shale samples exhibit greater complexity, indicated by larger fractal dimensions. The samples from subsections Liang 2 and Liang 3 exhibit greater heterogeneity compared to subsection Liang 1. The single-fractal dimensions of micropores and mesopores show positive correlations with specific surface area (SSA) and pore volume (PV), while the fractal dimension of macropores shows a negative correlation with average pore diameter and median radius. The average values of single-fractal dimension D₃ obtained from HPMI data are 2.9644 and 2.9471 for shale and siltstone samples, respectively, indicating more complex structures of macropores in shale samples compared to siltstone samples. The average value of $\Delta D^{NMR}$ and singularity strength range Δα obtained by a multifractal model for core samples from subsection Liang 1 are 1.868 and 2.155, respectively, which are the smallest among all of the three subsections, indicating that the heterogeneity of pore structures of subsection Liang 1 is the weakest. This research provides valuable guidance for shale oil development in the northeastern Sichuan Basin, China. Full article

The pressure fluctuations generated during high-speed train passage through tunnels can compromise both the train’s structural integrity and passenger comfort, highlighting the need for the accurate prediction of external pressure wave amplitudes. To address the high computational cost of multi-condition Computational Fluid Dynamics simulations, this study proposes a hybrid method combining numerical simulation and machine learning. A dataset was generated using simulations with five input features: tunnel length, train length, train speed, blockage ratio, and measurement point location. Four machine learning models—random forest, support vector regression, Extreme Gradient Boosting, and Multilayer Perceptron (MLP)—were evaluated, with the MLP model showing the highest baseline accuracy. To further improve performance, six metaheuristic algorithms were applied to optimize the MLP model, among which, the sparrow search algorithm (SSA) achieved the highest accuracy, with R² = 0.993, MAPE = 0.052, and RMSE = 0.112. A SHapley Additive exPlanations (SHAP) analysis indicated that the train speed and the blockage ratio were the most influential features. This study provides an effective and interpretable method for pressure wave prediction in tunnel environments and demonstrates the first integration of SSA optimization into aerodynamic pressure modeling. Full article

Oat is a highly nutritious cereal crop, and the moisture content of its seeds plays a vital role in cultivation management, storage preservation, and quality control. To enable efficient and non-destructive prediction of this key quality parameter, this study presents a modeling framework integrating hyperspectral imaging (HSI) technology with a dual-optimization machine learning strategy. Seven spectral preprocessing techniques—standard normal variate (SNV), multiplicative scatter correction (MSC), first derivative (FD), second derivative (SD), and combinations such as SNV + FD, SNV + SD, and SNV + MSC—were systematically evaluated. Among them, SNV combined with FD was identified as the optimal preprocessing scheme, effectively enhancing spectral feature expression. To further refine the predictive model, three feature selection methods—successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), and principal component analysis (PCA)—were assessed. PCA exhibited superior performance in information compression and modeling stability. Subsequently, a dual-optimized neural network model, termed Bayes-ASFSSA-BP, was developed by incorporating Bayesian optimization and the Adaptive Spiral Flight Sparrow Search Algorithm (ASFSSA). Bayesian optimization was used for global tuning of network structural parameters, while ASFSSA was applied to fine-tune the initial weights and thresholds, improving convergence efficiency and predictive accuracy. The proposed Bayes-ASFSSA-BP model achieved determination coefficients (R²) of 0.982 and 0.963, and root mean square errors (RMSEs) of 0.173 and 0.188 on the training and test sets, respectively. The corresponding mean absolute error (MAE) on the test set was 0.170, indicating excellent average prediction accuracy. These results significantly outperformed benchmark models such as SSA-BP, ASFSSA-BP, and Bayes-BP. Compared to the conventional BP model, the proposed approach increased the test R² by 0.046 and reduced the RMSE by 0.157. Moreover, the model produced the narrowest 95% confidence intervals for test set performance (Rp²: [0.961, 0.971]; RMSE: [0.185, 0.193]), demonstrating outstanding robustness and generalization capability. Although the model incurred a slightly higher computational cost (480.9 s), the accuracy gain was deemed worthwhile. In conclusion, the proposed Bayes-ASFSSA-BP framework shows strong potential for accurate and stable non-destructive prediction of oat seed moisture content. This work provides a practical and efficient solution for quality assessment in agricultural products and highlights the promise of integrating Bayesian optimization with ASFSSA in modeling high-dimensional spectral data. Full article

Reducing surface roughness can enhance the mechanical properties of processed materials. The variation law of the aluminum alloy surface roughness induced by continuous-nanosecond combined laser (CL) with different continuous laser power densities and laser delay is investigated experimentally. A back propagation neural network (BPNN) coupled with a sparrow search algorithm (SSA) is employed to predict surface roughness. The nanosecond laser energy density, continuous laser power density and laser delay are input parameters, while the surface roughness is output parameter. The lowest surface roughness is achieved with completely paint film removed by the CL while the nanosecond laser energy density is 1.99 J/cm², the continuous laser power density is 2118 W/cm² and the laser delay is 1 ms. Compared to the original target and the target irradiated by nanosecond pulse laser (ns laser), the reductions in the surface roughness are 20.62% and 12.00%, respectively. The SSA-BPNN model demonstrates high prediction accuracy, with a correlation coefficient (R²) of 0.98628, root mean square error (RMSE) of 0.024, mean absolute error (MAE) of 0.020 and mean absolute percentage error (MAPE) of 1.30% on the test set. These results indicate that the SSA-BPNN demonstrates higher-precision surface roughness prediction with limited experimental data than BPNN. Furthermore, the findings confirm that the CL can effectively reduce surface roughness. Full article

The recovery of green waste and biomass presents a significant challenge in the 21st century. In this context, this study aims to valorize waste generated by the fruit juice processing industry at the N’Gaous unit (composed of the orange peel, fibers, pulp, and seeds) as an adsorbent to eliminate an anionic dye and to enhance its adsorption capacity through thermal activation at 200 °C and 400 °C. The aim is also to determine the parameters for the adsorption process including contact time (0–120 min), solution pH (2–10), initial dye concentration (50–700 mg/L), and adsorbent dosage (0.5–10 g/L). The adsorption tests showed that waste activated at 400 °C (AR400) demonstrated a higher efficiency for removing indigo carmine (IC) from an aqueous solution than waste activated at 200 °C (AR200) and unactivated waste (R). The experimental maximum adsorption capacities for IC were 70 mg/g for unactivated waste, 500 mg/g for waste activated at 200 °C, and 680 mg/g for waste activated at 400 °C. These tests were conducted under conditions of pH 2, an equilibrium time of 50 min, and an adsorbent concentration of 1 g/L. The analysis of the kinetic data revealed that the pseudo-second-order model provides the best fit for the experimental results, indicating that this mechanism predominates in the sorption of the pollutant onto the three adsorbents. In terms of adsorption isotherms, the Freundlich model was found to be the most appropriate for describing the adsorption of dye molecules on the R, AR200, and AR400 supports, owing to its high correlation coefficient. Before adsorption tests, the powder R, AR200 and AR400 were characterized by various analyses, including Fourier transform infrared (FTIR), pH zero charge points and laser granularity for structural evaluation. According to the results of these analyses, the specific surface area (SSA) of the prepared material increases with the increase in the activation temperature, which expresses the increase in the adsorption of material activated at 400 °C, compared with materials activated at 200 °C and the raw material. Full article

Precise monitoring of the leaf area index (LAI) and soil–plant analysis development (SPAD, which represents chlorophyll content) at the field level is crucial for enhancing crop yield and formulating agricultural management strategies. Currently, most studies use multispectral sensors mounted on unmanned aerial vehicles (UAVs) to obtain images, whereby the spectral information is utilized to estimate rice growth parameters. Considering the cost of multispectral sensors and factors influencing rice growth parameters, this study integrated satellite remote sensing images with UAV visible-light images to obtain high-resolution multispectral images during key rice growth stages, thereby determining the rice LAI and SPAD on the same day. The vegetation indices and textural features most correlated with rice LAI and SPAD were selected using Pearson correlation analysis, and based on vegetation indices, textural features, and their combinations, regression models were established. The results indicate the following: (1) The fusion of satellite and UAV images, combined with spectral information and textural features, can significantly improve the estimation accuracy of LAI and SPAD compared to using only spectral information or textural features. (2) Sparrow search algorithm-optimized extreme gradient boosting (SSA-XGBoost) regression achieved the highest accuracy, with R² and RMSE of 0.904 and 0.183 in LAI estimation and 0.857 and 0.882 in SPAD estimation, respectively. This demonstrates that integrating satellite and UAV images, combined with vegetation indices and texture features, can effectively establish rice LAI and SPAD estimation models, using the SSA-optimized XGBoost method, as an effective and feasible solution for precise monitoring of rice growth parameters. Full article

(1) Background: GEP-NETs are frequently diagnosed at advanced stage. For well-differentiated somatostatin receptor-positive (SSTR+) NETs, SSA are the preferred first-line therapy. However, in newly diagnosed patients with G2/G3 and a high tumor burden, SSA alone might not be enough; (2) Methods: We conducted a retrospective analysis to assess the effectiveness of combining oxaliplatin–fluoropyrimidine chemotherapy with SSA as an upfront strategy in newly diagnosed metastatic G2/G3 GEP-NET patients treated with oxaliplatin–fluoropyrimidine-based chemotherapy; (3) Results: Between March 2017 and October 2023, 32 pts (19 males, 13 females; M:F = 1.5:1; median age 54 years, range 31–82) were deemed eligible to receive oxaliplatin–fluoropyrimidine chemotherapy in addition to SSA; 14 received XELOX and 18 FOLFOX. After a median follow-up of 26 mo., each patient had completed at least two cycles of chemotherapy. The ORR was 25%, with a median DoR of 21.3 mo. The DCR was 87.5%. Notably, 28.1% of patients experienced tumor shrinkage sufficient for radical surgery on residual tumor lesions, encompassing both primary tumors and metastases; (4) Conclusions: Upfront treatment with the combination of oxaliplatin–fluoropyrimidine and SSA demonstrated effectiveness and safety. This approach may be considered to facilitate conversion surgery in eligible patients. Full article

With the challenge of increasing global carbon emissions and climate change, the importance of solar energy as a clean energy source is becoming more pronounced. Accurate solar radiation prediction is crucial for planning and operating solar energy systems. However, the accurate measurement of solar radiation faces challenges due to the high cost of instruments, strict maintenance, and technical complexity. Therefore, this paper proposes a deep learning approach that integrates the Sparrow Search Algorithm (SSA), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks for solar radiation forecasting. The study utilizes solar radiation data from Songjiang District, Shanghai, China, from 2019 to 2020 for empirical analysis. Initially, a correlation analysis was conducted to identify the main factors affecting the intensity of solar radiation, including temperature, clear-sky GHI, solar zenith angle, and relative humidity. Subsequently, the forecasting effectiveness of the model was compared on datasets of 10 min, 30 min, and 60 min, revealing that the model performed best on the 60 min dataset, with a determination coefficient (R²) of 0.96221, root mean square error (RMSE) of 65.9691, and mean absolute error (MAE) of 37.9306. Moreover, comparative experimental results show that the SSA-CNN-LSTM model outperforms traditional LSTM, BiLSTM, and CNN-LSTM models in forecasting accuracy, confirming the effectiveness of SSA in parameter optimization. Thus, the SSA-CNN-LSTM model provides a new and efficient tool for solar radiation forecasting, which is of significant importance for the design and management of solar energy systems. Full article

Predicting the river discharge is essential for preparing effective measures against flood hazards or managing hydrological droughts. Despite mathematical modeling advancements, most algorithms have failed to capture the extreme values (especially the highest ones). In this article, we proposed a quantum neural networks (QNNs) approach for forecasting the river discharge in three scenarios. The algorithm was applied to the raw data series and the series without aberrant values. Comparisons with the results obtained on the same series by other neural networks (LSTM, BPNN, ELM, CNN-LSTM, SSA-BP, and PSO-ELM) emphasized the best performance of the present approach. The lower error between the recorded values and the predicted ones in the evaluation of maxima compared to the case of the competitors mentioned shows that the algorithm best fits the extremes. The most significant mean standard errors (MSEs) and mean absolute errors (MAEs) were 26.9424 and 4.8914, respectively, and the lowest R² was 84.36%, indicating the good performances of the algorithm. Full article

Background: Globally, approximately 65% of adolescents undergoing antiretroviral therapy (ART) adhered to their treatment, whereas only 55% achieved viral suppression in 2023. The low rate of viral suppression is concerning, as elevated viral loads are associated with a heightened risk of opportunistic infections, progression to advanced HIV disease, increased mortality, and greater HIV transmission rates. We conducted this scoping review to identify the facilitators and barriers to ART adherence among adolescents and young adults (AYAs) in sub-Saharan Africa (SSA). Methods: We conducted this scoping review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews (PRISMA-ScR) checklist. We searched for peer-reviewed articles published in English from 2014 to 2024 across the SCOPUS, ScienceDirect, PubMed, Africa Journals Online, and Google Scholar databases. Two reviewers independently selected the articles and extracted the data. We used NVivo to develop codes and categories of facilitators and barriers. Results: We used 30 articles reporting on studies conducted in 13 countries in this review. The total number of participants in the studies was 12,250. Sixteen articles reported on qualitative studies, nine on quantitative studies, and five on mixed-methods studies. This scoping review identified various personal (14 articles), interpersonal and social (15 articles), healthcare system-related (9 articles), medication-related (7 articles), and economic (2 articles) factors that facilitate ART adherence among AYAs. Additionally, the scoping review also identified various personal (28 articles), interpersonal and social (13 articles), healthcare system-related (14 articles), medication-related (20 articles), school- or work-related (6 articles), and economic (14 articles) factors that hinder ART adherence among AYAs. Conclusions: Enhancing ART adherence in AYAs requires multiple strategies, including the reduction of internalized stigma, implementation of community awareness campaigns, harm reduction approaches for AYAs who misuse substances, comprehensive education on HIV, and the provision of support from school staff and leadership, alongside the adoption of differentiated service delivery (DSD), which encompasses home-based ART delivery, refills at private pharmacies, community ART distribution centers, and patient-led community ART refill groups, as well as multi-month dispensing practices. Full article

The fermentation of oolong tea is a critical process that determines its quality and flavor. Current fermentation control relies on tea makers’ sensory experience, which is labor-intensive and time-consuming. In this study, using Tieguanyin oolong tea as the research object, features including the tea water loss rate, aroma, image color, and texture were obtained using weight sensors, a tin oxide-type gas sensor, and a visual acquisition system. Support vector regression (SVR), random forest (RF) machine learning, and long short-term memory (LSTM) deep learning algorithms were employed to establish models for assessing the fermentation degree based on both single features and fused multi-source features, respectively. The results showed that in the test set of the fermentation degree models based on single features, the mean absolute error (MAE) ranged from 4.537 to 6.732, the root mean square error (RMSE) ranged from 5.980 to 9.416, and the coefficient of determination (R²) values varied between 0.898 and 0.959. In contrast, the data fusion models demonstrated superior performance, with the MAE reduced to 2.232–2.783, the RMSE reduced to 2.693–3.969, and R² increased to 0.982–0.991, confirming that feature fusion enhanced characterization accuracy. Finally, the Sparrow Search Algorithm (SSA) was applied to optimize the data fusion models. After optimization, the models exhibited a MAE ranging from 1.703 to 2.078, a RMSE from 2.258 to 3.230, and R² values between 0.988 and 0.994 on the test set. The application of the SSA further enhanced model accuracy, with the Fusion-SSA-LSTM model demonstrating the best performance. The research results enable online real-time monitoring of the fermentation degree of Tieguanyin oolong tea, which contributes to the automated production of Tieguanyin oolong tea. Full article

To address the challenge of the real-time monitoring of alumina concentrations during the production process, this paper employs a Deep Belief Network (DBN) within the framework of deep learning to predict alumina concentration. Additionally, the improved Grey Wolf Optimizer (IGWO) is utilized to optimize key parameters of the DBN model, including the number of hidden layer nodes, reverse iteration count, and learning rate. An IGWO-DBN hybrid model is then constructed and compared against DBN models optimized by other techniques, such as the Sparrow Search Algorithm (SSA) and Particle Swarm Optimization (PSO), to evaluate the predictive performance. The comparative analysis reveals that, in terms of predictive accuracy, the IGWO-DBN model outperforms both the SSA-DBN and PSO-DBN models. Specifically, it achieves lower root mean square errors (RMSE) and mean absolute errors (MAE), alongside a higher coefficient of determination (R²). Furthermore, the IGWO-DBN model exhibits a faster convergence rate and a lower final convergence value, indicating superior generalization ability and robustness. Furthermore, the IGWO-DBN model not only demonstrates significant advantages in prediction accuracy for alumina concentration but also substantially reduces model training time through its efficient parameter optimization mechanism. The successful implementation of this model provides robust support for the intelligent and refined management of the aluminum electrolysis industry, aiding enterprises in reducing costs, improving production efficiency, and advancing the green and sustainable development of the industry. Full article