Search Results (7,219)

The accurate segmentation of skin lesions plays an important role in the diagnosis and treatment of skin cancers. However, skin lesion areas are rich in details and local features, including the appearance, size, shape, texture, etc., which pose challenges for the accurate localization and segmentation of the target area. Unfortunately, the consecutive pooling and stride convolutional operations in existing convolutional neural network (CNN)-based solutions lead to the loss of some spatial information and thus constrain the accuracy of lesion region segmentation. In addition, using only the traditional loss function in CNN cannot ensure that the model is adequately trained. In this study, a generative adversarial network is proposed, with global and local semantic feature awareness (GLSFA-GAN) for skin lesion segmentation based on adversarial training. Specifically, in the generator, a multi-scale localized feature fusion module and an effective channel-attention module are designed to acquire the multi-scale local detailed information of the skin lesion area. In addition, a global context extraction module in the bottleneck between the encoder and decoder of the generator is used to capture more global semantic features and spatial information about the lesion. After that, we use an adversarial training strategy to make the discriminator discern the generated labels and the segmentation prediction maps, which assists the generator in yielding more accurate segmentation maps. Our proposed model was trained and validated on three public skin lesion challenge datasets involving the ISIC2017, ISIC2018, and HAM10000, and the experimental results confirm that our proposed method provides a superior segmentation performance and outperforms several comparative methods. Full article

Abstract: Rice kernel smut caused by the biotrophic basidiomycete fungus Tilletia horrida causes significant yield losses in hybrid rice-growing areas around the world. Cytochrome P450 (CYP) enzyme is a membrane-bound heme-containing monooxygenase. In fungi, CYPs play a role in cellular metabolism, adaptation, pathogenicity, decomposition, and biotransformation of hazardous chemicals. In this study, we identified 20 CYP genes based on complete sequence analysis and functional annotation from the T. horrida JY-521 genome. The subcellular localization, conserved motifs, and structures of these 20 CYP genes were further predicted. The ThCYP genes exhibit differences in gene structures and protein motifs. Subcellular localization showed that they were located in the plasma membrane, cytoplasm, nucleus, mitochondria, and extracellular space, indicating that they had multiple functions. Some cis-regulatory elements related to stress response and plant hormones were found in the promoter regions of these genes. Protein–protein interaction (PPI) analysis showed that several ThCYP proteins interact with multiple proteins involved in the ergosterol pathway. Moreover, the expression of 20 CYP genes had different responses to different infection time points and underwent dynamic changes during T. horrida JY-521 infection, indicating that these genes were involved in the interaction with rice and their potential role in the pathogenic mechanism. These results provided valuable resources for elucidating the structure of T. horrida CYP family proteins and laid an important foundation for further research of their roles in the pathogenesis. Full article

This study focused on the isolation of actinobacteria capable of producing extracellular keratinase from keratin-rich residues, which led to the selection of an actinobacterial strain referenced as Streptomyces strain DZ 06 (ES41). The Plackett–Burman screening plan was used for the statistical optimization of the enzymatic production medium, leading to the identification of five key parameters that achieved a maximum activity of 180.1 U/mL. Further refinement using response surface methodology (RSM) with a Box–Behnken design enhanced enzyme production to approximately 458 U/mL. Model validation, based on the statistical predictions, demonstrated that optimal keratinase activity of 489.24 U/mL could be attained with 6.13 g/L of chicken feather meal, a pH of 6.25, incubation at 40.65 °C for 4.11 days, and an inoculum size of 3.98 × 10⁷ spores/mL. The optimized culture conditions yielded a 21.67-fold increase in keratinase compared with the initial non-optimized standard conditions. The results show that this bacterium is an excellent candidate for industrial applications when optimal conditions are used to minimize the overall costs of the enzyme production process. Full article

Background/Objectives: Obstructive hydrocephalus associated with vestibular schwannoma (VS) is the most common in giant VS. Despite tumor removal, some patients may require ongoing ventriculo-peritoneal (VP) surgery. This investigation explores the factors contributing to the requirement for VP surgery following VS surgery in instances of persistent hydrocephalus (HCP). Methods: Volumetric MRI analyses of pre- and postoperative tumor volumes, cerebellum, cerebrum, ventricle system, fourth ventricle, brainstem, and peritumoral edema were conducted using Brainlab Smartbrush and 3D Slicer. The total brain volume was defined as the sum of the cerebrum, cerebellum, and brainstem. ROC analyses were performed to identify the optimum cut-off values of the volumetric data. Results: Permanent cerebrospinal fluid (CSF) diversion after surgery was indicated in 12 patients (12/71; 16.9%). The ratio of baseline volume fraction of brain ventricles to total brain ventricle volume (VTB ratio) was found to predict postoperative VP shunt dependency. The AUC was 0.71 (95% CI: 0.51–0.91), and the optimum threshold value (</≥0.449) yielded a sensitivity and specificity of 67% and 81%, respectively. Multivariable logistic regression analyses of imaging data (pre- and postoperative VS volume, VTB ratio, and extent of resection (%) (EoR)) and patient-specific factors revealed that an increased VTB ratio (≥0.049, OR: 6.2, 95% CI: 1.0–38.0, p = 0.047) and an EoR < 96.4% (OR: 9.1, 95% CI: 1.2–69.3, p = 0.032) were independently associated with postoperative VP shunt dependency. Conclusions: Primary tumor removal remains the best treatment to reduce the risk of postoperative persistent hydrocephalus. However, patients with an increased preoperative VTB ratio are prone to needing postoperative VP shunt surgery and may benefit from perioperative EVD placement. Full article

The main objective of this study is to assess and contrast the efficacy of distinct spatial prediction methods in a simulation aimed at optimizing the embodied energy during the construction of prestressed slab bridge decks. A literature review and cross-sectional analysis have identified crucial design parameters that directly affect the design and construction of bridge decks. This analysis determines the critical design variables to improve the deck’s energy efficiency, providing practical guidance for engineers and professionals in the field. The methods analyzed in this study are ordinary Kriging and a multilayer perceptron neural network. The methodology involves analyzing the predictive performance of both models through error analysis and assessing their ability to identify local optima on the response surface. The results show that both models generally overestimate the observed values. The Kriging model with second-order polynomials yields a 4% relative error at the local optimum, while the neural network achieves lower root mean square errors (RMSEs). Neither the Kriging model nor the neural network provides precise predictions but point to promising solution regions. Optimizing the response surface to find a local minimum is crucial. High slenderness ratios (around 1/28) and 40 MPa concrete grade are recommended to improve energy efficiency. Full article

Accurately predicting winter wheat yield before harvest could greatly benefit decision-makers when making management decisions. In this study, we utilized weather forecast (WF) data combined with Sentinel-2 data to establish the deep-learning network and achieved an in-season county-scale wheat yield prediction in China’s main wheat-producing areas. We tested a combination of short-term WF data from the China Meteorological Administration to predict in-season yield at different forecast lengths. The results showed that explicitly incorporating WF data can improve the accuracy in crop yield predictions [Root Mean Square Error (RMSE) = 0.517 t/ha] compared to using only remote sensing data (RMSE = 0.624 t/ha). After comparing a series of WF data with different time series lengths, we found that adding 25 days of WF data can achieve the highest yield prediction accuracy. Specifically, the highest accuracy (RMSE = 0.496 t/ha) is achieved when predictions are made on Day of The Year (DOY) 215 (40 days before harvest). Our study established a deep-learning model which can be used for early yield prediction at the county level, and we have proved that weather forecast data can also be applied in data-driven deep-learning yield prediction tasks. Full article

Displacement prediction models based on measured data have been widely applied in structural health monitoring. However, most models neglect the particularity of displacement monitoring for arch dams with cracks, nor do they thoroughly analyze the non-stationarity and uncertainty of displacement. To address this issue, the influencing factors of displacement were first considered, with crack opening displacement being incorporated into them, leading to the construction of the HSCT model that accounts for the effects of cracks. Feature selection was performed on the factors of the HSCT model utilizing the max-relevance and min-redundancy (mRMR) algorithm, resulting in the screened subset of displacement influence factors. Next, displacement was decomposed into trend, seasonal, and remainder components applying the seasonal-trend decomposition using loess (STL) algorithm. The multifractal characteristics of these displacement components were then analyzed by multifractal detrended fluctuation analysis (MF-DFA). Subsequently, displacement components were predicted employing the convolutional neural network-long short-term memory (CNN-LSTM) model. Finally, the impact of uncertainty factors was quantified using prediction intervals based on the bootstrap method. The results indicate that the proposed methods and models are effective, yielding satisfactory prediction accuracy and providing scientific basis and technical support for the health diagnosis of hydraulic structures. Full article

The quality of wine depends upon the quality of the grapes, which, in turn, are affected by different viticulture aspects and the climate during the grape-growing season. Obtaining wine professionals’ judgments of the intrinsic qualities of selected wine products is a time-consuming task. It is also expensive. Instead of waiting for the wine to be produced, it is better to have an idea of the quality before harvesting, so that wine growers and wine manufacturers can use high-quality grapes. The main aim of the present study was to investigate the use of machine learning aspects in predicting Pinot Noir wine quality and to develop a pipeline which represents the major steps from vineyards to wine quality indices. This study is specifically related to Pinot Noir wines based on experiments conducted in vineyards and grapes produced from those vineyards. Climate factors and other wine production factors affect the wine quality, but our emphasis was to relate viticulture parameters to grape composition and then relate the chemical composition to quality as measured by the experts. This pipeline outputs the predicted yield, values for basic parameters of grape juice composition, values for basic parameters of the wine composition, and quality. We also found that the yield could be predicted because of input data related to the characteristics of the vineyards. Finally, through the creation of a web-based application, we investigated the balance of berry yield and wine quality. Using these tools further developed, vineyard owners should be able to predict the quality of the wine they intend to produce from their vineyards before the grapes are even harvested. Full article

In this work, the pyrolysis process and the characteristics of biochar produced using a bench-scale fixed-bed reactor and a prototype-scale auger reactor were studied. Residual forest biomass (RFB) from acacia, broom, gorse, and giant reed was used as feedstock. Besides information on pyrolysis characteristics of these specific biomass species from the Iberian Peninsula, new knowledge on the understanding of how results from small-scale reactors can be used to predict the behavior of higher-scale and continuous-operation reactors is offered. Batch pyrolysis was carried out using 40 g of biomass sample in a fixed-bed reactor with a heating rate of 20 °C∙min⁻¹, pyrolysis temperature of 450 and 550 °C, and a residence time of 30 min, while for the continuous process it was used a prototype of an auger reactor with continuous operation with a biomass flow rate up to 1 kg/h, with temperatures of 450 and 550 °C, and a solids residence time of 5 min. The biochar yield was in the range of 0.26 to 0.36 kg/kg biomass dry basis, being similar for both types of reactors and slightly lower when using the auger reactor. The proximate analysis of the biochar shows volatile matter in the range 0.10 to 0.27 kg/kg biochar dry basis, fixed carbon in the range 0.65 to 0.84 kg/kg biochar dry basis, and ash in the range 0.04 to 0.08 kg/kg biochar dry basis. The carbon, oxygen, and hydrogen content of the biochar was in the range of 0.71 to 0.81, 0.09 to 0.22, and 0.02 to 0.03 kg/kg biochar dry basis, respectively. The results show that the up-scaling of the reactor and regime of operation does not have an important influence on the yield and characteristics of the biochar produced. The biochar obtained in the two types of reactors has characteristics appropriate for environmental applications, such as an additive to improve soil properties. It is possible to see that the characteristics of the biochar are influenced by the type of biomass and the conditions and parameters of the process; therefore, it is of major importance to control and know of these conditions, especially when considering upscaling scenarios. Full article

Collaboration among road agents, such as connected autonomous vehicles and roadside units, enhances driving performance by enabling the exchange of valuable information. However, existing collaboration methods predominantly focus on perception tasks and rely on single-frame static information sharing, which limits the effective exchange of temporal data and hinders broader applications of collaboration. To address this challenge, we propose CoPnP, a novel collaborative joint perception and prediction system, whose core innovation is to realize multi-frame spatial–temporal information sharing. To achieve effective and communication-efficient information sharing, two novel designs are proposed: (1) a task-oriented spatial–temporal information-refinement model, which filters redundant and noisy multi-frame features into concise representations; (2) a spatial–temporal importance-aware feature-fusion model, which comprehensively fuses features from various agents. The proposed CoPnP expands the benefits of collaboration among road agents to the joint perception and prediction task. The experimental results demonstrate that CoPnP outperforms existing state-of-the-art collaboration methods, achieving a significant performance-communication trade-off and yielding up to 11.51%/10.34% Intersection over union and 12.31%/10.96% video panoptic quality gains over single-agent PnP on the OPV2V/V2XSet datasets. Full article

Bio-oil produced via fast pyrolysis, irrespective of the biomass source, faces several limitations, such as high water content, significant oxygenated compound concentration (35–40 wt.%), a low heating value (13–20 MJ/kg), and poor miscibility with fossil fuels. These inherent drawbacks hinder the bio-oil’s desirable properties and usability, highlighting the necessity for advanced processing techniques to overcome these challenges and improve the bio-oil’s overall quality and applicability in energy and industrial sectors. To address the limitations of bio-oil, a magnetic bimetallic oxide catalyst supported on activated rice straw biochar (ZrO₂-Fe₃O₄/AcB), which has not been previously employed for this purpose, was developed and characterized for upgrading rice straw bio-oil in supercritical butanol via esterification. Furthermore, the silica in the biochar, combined with the Lewis acid sites provided by ZrO₂ and Fe₃O₄, offers Brønsted acid sites. This synergistic combination enhances the bio-oil’s quality by facilitating esterification, deoxygenation, and mild hydrogenation, thereby reducing oxygen content and increasing carbon and hydrogen levels. The effects of variables, including time, temperature, and catalyst load, were optimized using response surface methodology (RSM). The optimal reaction conditions were determined using a three-factor, one-response, and three-level Box-Behnken design (BBD). The ANOVA results at a 95% confidence level indicate that the results are statistically significant due to a high Fisher’s test (F-value = 37.07) and a low probability (p-value = 0.001). The minimal difference between the predicted R² and adjusted R² for the ester yield (0.0092) suggests a better fit. The results confirm that the optimal reaction conditions are a catalyst concentration of 1.8 g, a reaction time of 2 h, and a reaction temperature of 300 °C. Additionally, the catalyst can be easily recycled for four reaction cycles. Moreover, the catalyst demonstrated remarkable reusability, maintaining its activity through four consecutive reaction cycles. Its magnetic properties allow for easy separation from the reaction mixture using an external magnet. Full article

Wind speed affects aviation performance, clean energy production, and other applications. By accurately predicting wind speed, operational delays and accidents can be avoided, while the efficiency of wind energy production can also be increased. This paper initially overviews the definition, characteristics, sensors capable of measuring the feature, and the relationship between this feature and wind speed for all Quality Indicators (QIs). Subsequently, the feature importance of each QI relevant to wind-speed prediction is assessed, and all QIs are employed to predict horizontal wind speed. In addition, we conduct a comparison between the performance of traditional point-wise machine learning models and temporally correlated deep learning ones. The results demonstrate that the Bidirectional Long Short-Term Memory (BiLSTM) neural network yielded the highest level of accuracy across three metrics. Additionally, the newly proposed set of QIs outperformed the previously utilised QIs to a significant degree. Full article

Background/Objectives: Routine postoperative ICU admission following brain tumor surgery may not benefit selected patients. The objective of this study was to develop a risk prediction instrument for early (within 24 h) postoperative adverse events using machine learning techniques. Methods: Retrospective cohort of 1000 consecutive adult patients undergoing elective brain tumor resection. Nine events/interventions (CPR, reintubation, return to OR, mechanical ventilation, vasopressors, impaired consciousness, intracranial hypertension, swallowing disorders, and death) were chosen as target variables. Potential prognostic features (n = 27) from five categories were chosen and a gradient boosting algorithm (XGBoost) was trained and cross-validated in a 5 × 5 fashion. Prognostic performance, potential clinical impact, and relative feature importance were analyzed. Results: Adverse events requiring ICU intervention occurred in 9.2% of cases. Other events not requiring ICU treatment were more frequent (35% of cases). The boosted decision trees yielded a cross-validated ROC-AUC of 0.81 ± 0.02 (mean ± CI95) when using pre- and post-op data. Using only pre-op data (scheduling decisions), ROC-AUC was 0.76 ± 0.02. PR-AUC was 0.38 ± 0.04 and 0.27 ± 0.03 for pre- and post-op data, respectively, compared to a baseline value (random classifier) of 0.092. Targeting a NPV of at least 95% would require ICU admission in just 15% (pre- and post-op data) or 30% (only pre-op data) of cases when using the prediction algorithm. Conclusions: Adoption of a risk prediction instrument based on boosted trees can support decision-makers to optimize ICU resource utilization while maintaining adequate patient safety. This may lead to a relevant reduction in ICU admissions for surveillance purposes. Full article

Quantifying the vertical distribution of leaf chlorophyll content (LCC) is integral for a comprehensive understanding of the physiological status and function of winter wheat crops, having significant implications for crop management and yield optimization. In this study, we investigated the vertical LCC trait of winter wheat during two consecutive field growth seasons using proximal multispectral imaging measurements to evaluate vertical variations of LCC within winter wheat canopies. The results revealed the non-uniform vertical LCC distribution varied across the entire growth season. The effects of nitrogen fertilization rate on LCC among vertical layers increased gradually from upper to lower layers of canopy. To enhance LCC prediction accuracy, this study proposes a deep transfer learning network model for leaf trait estimation (LeafTNet). It integrates the advantages of physical radiative transfer simulations with deep neural network through transfer learning. The results demonstrate that the LeafTNet achieved remarkable predictive performance and strong robustness. Furthermore, the proposed method exhibits superior estimation accuracy compared to empirical statistical method and traditional machine learning method. This study highlights the performance of LeafTNet in accurately and efficiently quantifying LCC from proximal multispectral data, which provide technical support for the estimation of the vertical distribution of leaf traits and improve crop management. Full article

Previous study revealed that isocitrate dehydrogenase (NADP (+)) 2, mitochondrial (IDH2), lactate dehydrogenase A (LDHA), and lactate dehydrogenase B (LDHB) genes were significantly differentially expressed in liver tissues of Holstein cows among different lactation periods and associated with lipid and protein metabolism; hence, they were considered as candidates for milk production traits. Herein, the genetic effects of the three genes on milk yield, fat, and protein traits were studied by association analysis using 926 Chinese Holstein cows from 45 sire families. As a result, five single nucleotide polymorphisms (SNPs) in IDH2, one in LDHA, and three in LDHB were identified by re-sequencing, and subsequently, they were genotyped in 926 Chinese Holstein cows by genotyping by target sequencing (GBTS). With the animal model, single-locus association analysis revealed that four SNPs in IDH2 and one SNP in LDHA were significantly associated with milk, fat, and protein yields (p ≤ 0.0491), and three SNPs in LDHB were associated with milk yield, milk fat yield, and fat percentage (p ≤ 0.0285). Further, four IDH2 SNPs were found to form a haplotype block significantly associated with milk yield, fat yield, protein yield, and protein percentage (p ≤ 0.0249). In addition, functional predictions indicated that one SNP in LDHA, g.26304153G>A, may affect transcription factor binding and two SNPs, g.88544541A>G and g.88556310T>C could alter LDHB mRNA secondary structure. In summary, this study profiled the significant genetic effects of IDH2, LDHA, and LDHB on milk yield and composition traits and provided referable genetic markers for genomic selection programs in dairy cattle. Full article