The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence...The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence problem. Firstly, we utilize a network model architecture combining Gelu activation function and deep neural network;Secondly, the cross-entropy loss function is improved to a weighted cross entropy loss function, and at last it is applied to intrusion detection to improve the accuracy of intrusion detection. In order to compare the effect of the experiment, the KDDcup99 data set, which is commonly used in intrusion detection, is selected as the experimental data and use accuracy, precision, recall and F1-score as evaluation parameters. The experimental results show that the model using the weighted cross-entropy loss function combined with the Gelu activation function under the deep neural network architecture improves the evaluation parameters by about 2% compared with the ordinary cross-entropy loss function model. Experiments prove that the weighted cross-entropy loss function can enhance the model’s ability to discriminate samples.展开更多
Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instabili...Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics.展开更多
Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning sc...Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning scenarios.In this work,we propose an Adaptive Meta-Loss Network(Adaptive-MLN)that learns to generate taskagnostic loss functions tailored to evolving classification problems.Unlike traditional methods that rely on static objectives,Adaptive-MLN treats the loss function itself as a trainable component,parameterized by a shallow neural network.To enable flexible,gradient-free optimization,we introduce a hybrid evolutionary approach that combines GeneticAlgorithms(GA)for global exploration and Evolution Strategies(ES)for local refinement.This co-evolutionary process dynamically adjusts the loss landscape,improvingmodel generalization without relying on analytic gradients or handcrafted heuristics.Experimental evaluations on synthetic tasks and the CIFAR-10 andMNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy,convergence,and adaptability.展开更多
Thermal energy systems(TES)are an essential part of industries that have evolved over time through the engagement of managers and researchers.The development of digital twin(DT)technology has enabled accurate predicti...Thermal energy systems(TES)are an essential part of industries that have evolved over time through the engagement of managers and researchers.The development of digital twin(DT)technology has enabled accurate prediction of their performance.The inherent limitations of complex thermal systems,such as noisy input data and occasional lack of measurement data or boundary conditions,have recently created opportunities to apply physics-based problem-solving alongside DT technology.This paper aims to systematically review the novel physics-informed neural network-digital twin(PINN-DT)methodology as a potential solution to these challenges,and to present a taxonomy for problem-solving.The outcome of this study provides valuable guidance in selecting PINN-DT technology in thermal energy system(TES)modeling.A review of the proposed loss functions demonstrates that their design is critical for achieving precise outcomes in this technology,effectively serving as the foundational core of PINN-DT.As a result,it is recommended that the construction of the loss function be fundamentally guided by two principal considerations:forecasting accuracy and compliance with physical principles,which serve as foundational pillars in the surrogate model design framework.A significant gap exists in applying this technology to industries that use discrete sampling for quality control.Implementing the PINN-DT framework could address this issue by determining optimal sampling intervals,thereby offering vital decision-making support.Moreover,the absence of exergy analysis in formulating the physical loss component of the loss function represents a significant research gap.Future studies should therefore incorporate the exergy concept into the design of the loss function.展开更多
Chromosomal abnormalities are categorized into chromosomal-level(ROH,polyploidy,aneuploidy),local copy number,and gene-level(insertion/deletion)types.Unlike invasive prenatal diagnostics with miscarriage risks,NIPT is...Chromosomal abnormalities are categorized into chromosomal-level(ROH,polyploidy,aneuploidy),local copy number,and gene-level(insertion/deletion)types.Unlike invasive prenatal diagnostics with miscarriage risks,NIPT is noninvasive,reducing medical risks and maternal anxiety.This study addresses clinical NIPT bottlenecks(inaccurate timing,inconsistent abnormality determination)using high BMI pregnant women’s data via three core approaches:Spearman correlation and mixed-effects models confirm gestational age’s weak positive(rs=0.084,p<0.01)and BMI’s weak negative(rs=-0.155,p<0.001)correlation with fetal Y chromosome concentration;BMI grouping+Logistic regression+comprehensive loss function identifies robust optimal detection timing for each group;K-means clustering(4 groups)+three-layer weighted risk model(accuracy 0.4,timeliness 0.4,stability 0.2)optimizes multi-factor timing.Rational timing and multivariate models improve detection accuracy,supporting early clinical decisions.展开更多
Natural gas hydrate(NGH)has attracted increasing attention as a promising unconventional energy resource owing to its high volumetric storage capacity,yet its development is accompanied by significant greenhouse gas r...Natural gas hydrate(NGH)has attracted increasing attention as a promising unconventional energy resource owing to its high volumetric storage capacity,yet its development is accompanied by significant greenhouse gas risks.Therefore,accurate reservoir characterization is vital for marine resource exploration and sustainable development.Full waveform inversion(FWI)offers high-resolution imaging,yet suffers from heavy computation,sensitivity to initial models and non-uniqueness.Recent deep learning(DL)methods improve efficiency and accuracy,nevertheless,still struggle with clear boundary extraction and multi-level semantic representation.The authors propose a novel deep architecture(SC-UNeXt)designed to learn a mapping from seismic records to velocity models,which integrates a U-Net backbone,ConvNeXt residual blocks,spatial-channel squeeze-and-excitation attention and pixel shuffle up-sampling.Furthermore,a hybrid loss integrating mean squared error,multi-scale structural similarity,and perceptual discrepancy simultaneously optimizes pixel-wise accuracy,structural fidelity,and semantic consistency.Comprehensive tests on both synthetic NGH data and the 3D SEG/EAGE marine overthrust model with NGH demonstrate that SC-UNeXt outperforms FWI and advanced DL methods in boundary delineation,structural preservation,noise robustness,and computational efficiency.These results highlight SC-UNeXt as a reliable tool for high-resolution seismic characterization of NGH reservoirs,thereby supporting sustainable exploration and risk assessment of marine hydrate resources.展开更多
Wildtype fruit of cultivated strawberry(Fragaria×ananassa)are typically soft and highly perishable when fully ripe.The development of firm-fruited cultivars by phenotypic selection has greatly increased shelf-lif...Wildtype fruit of cultivated strawberry(Fragaria×ananassa)are typically soft and highly perishable when fully ripe.The development of firm-fruited cultivars by phenotypic selection has greatly increased shelf-life,decreased postharvest perishability,and driven the expansion of strawberry production worldwide.Hypotheses for the firm-fruited phenotype include mutations affecting the expression of genes encoding polygalacturonases(PGs)that soften fruit by degrading cell wall pectins.Here we show that loss-of-function mutations in the fruit softening gene POLYGALACTURONASE1(FaPG1;PG1-6A1)double fruit firmness in strawberry.PG1-6A1 was one of three tandem duplicated PG genes found to be in linkage disequilibrium(LD)with a quantitative trait locus(QTL)affecting fruit firmness on chromosome 6A.PG1-6A1 was strongly expressed in soft-fruited(wildtype)homozygotes and weakly expressed in firm-fruited(mutant)homozygotes.Genome-wide association,quantitative trait transcript,DNA sequence,and expression-QTL analyses identified genetic variants in LD with PG1-6A1 that were positively correlated with fruit firmness and negatively correlated with PG1-6A1 expression.An Enhancer/Suppressor-mutator(En/Spm)transposable element insertion was discovered upstream of PG1-6A1 in mutant homozygotes that we hypothesize transcriptionally downregulates the expression of PG1-6A1.The PG1-6A1 locus was incompletely dominant and explained 26–76%of the genetic variance for fruit firmness among phenotypically diverse individuals.Additional loci are hypothesized to underlie the missing heritability.Highly accurate codominant genotyping assays were developed for modifying fruit firmness by marker-assisted selection of the En/Spm insertion and single nucleotide polymorphisms associated with the PG1-6A1 locus.展开更多
Improving the utilization of agricultural biological waste resources is a critical issue.This study initially assessed the effects of adding attapulgite to vegetable compost.Additionally,the study investigated the eff...Improving the utilization of agricultural biological waste resources is a critical issue.This study initially assessed the effects of adding attapulgite to vegetable compost.Additionally,the study investigated the effects of attapulgite-modified compost on soil nutrient release and microbial community changes through nutrient loss experiments.Results indicated that adding attapulgite increased compost humification,significantly promoted humic acid synthesis,and improved the aromaticity and structural stability of humus.Attapulgite-modified organic fertilizer effectively retains soil nutrients,improves soil urease and alkaline phosphatase activities,and promotes microbial activity,synergy,and carbohydrate metabolism,with a 30%increase in tricarboxylic acid(TCA)cycle activity.ASV78 and ASV292 were highly sensitive to soil nutrient changes and may play a crucial role in regulating soil element cycling.This study provides valuable insights into the enhancement and application of clay minerals in composting,thereby improving the resource utilization of biological waste.展开更多
Objective To analyze the clinical efficacy of combined orthodontic and prosthodontic therapy versus simple prosthodontic therapy in patients with congenital tooth loss aged 18–20 years. Methods A total of 60 patients...Objective To analyze the clinical efficacy of combined orthodontic and prosthodontic therapy versus simple prosthodontic therapy in patients with congenital tooth loss aged 18–20 years. Methods A total of 60 patients with congenital tooth loss aged 18–20 years admitted to our hospital from January to December 2024 were enrolled and randomly divided into a combined group and a prosthodontic group (n=30 each) using a random number table. The prosthodontic group received only simple prosthodontic treatment, while the combined group received orthodontic combined with prosthodontic therapy. The dental function scores, aesthetic scores, complication rates, and overall treatment efficacy were compared between the two groups. Results The combined group demonstrated higher dental function scores and aesthetic scores than the prosthodontic group, lower complication rates, and higher overall treatment efficacy, with all differences being statistically significant (P<0.05). Conclusion For patients with congenital tooth loss aged 18–20 years, combined orthodontic and prosthodontic therapy can more effectively improve dental function and aesthetics, reduce post-treatment complication risks, and enhance therapeutic outcomes, demonstrating significant clinical value.展开更多
AIM: To explore the effects and mechanism of action of antidepressant mirtazapine in functional dyspepsia(FD) patients with weight loss.METHODS: Sixty depressive FD patients with weight loss were randomly divided into...AIM: To explore the effects and mechanism of action of antidepressant mirtazapine in functional dyspepsia(FD) patients with weight loss.METHODS: Sixty depressive FD patients with weight loss were randomly divided into a mirtazapine group(MG), a paroxetine group(PG) or a conventional therapy group(CG) for an 8-wk clinical trial. Adverse effects and treatment response were recorded. The Nepean Dyspepsia Index-symptom(NDSI) checklist and the 17-item Hamilton Rating Scale of Depression(HAMD-17) were used to evaluate dyspepsia and depressive symptoms, respectively. The body composition analyzer was used to measure body weight and fat. Serum hormone levels were measured by ELISA.RESULTS:(1) After 2 wk of treatment, NDSI scores were significantly lower for the MG than for the PG and CG;(2) After 4 or 8 wk of treatment, HAMD-17 scores were significantly lower for the MG and PG than for the CG;(3) After 8 wk of treatment, patients in the MG experienced a weight gain of 3.58 ± 1.57 kg, which was significantly higher than that observed for patients in the PG and CG. Body fat increased by 2.77 ± 0.14kg, the body fat ratio rose by 4%, and the visceral fat area increased by 7.56 ± 2.25 cm2; and(4) For the MG, serum hormone levels of ghrelin, neuropeptide Y(NPY), motilin(MTL) and gastrin(GAS) were significantly upregulated; in contrast, those of leptin, 5-hydroxytryptamine(5-HT) and cholecystokinin(CCK) were significantly downregulated. CONCLUSION: Mirtazapine not only alleviates symptoms associated with dyspepsia and depression linked to FD in patients with weight loss but also significantly increases body weight(mainly the visceral fat in body fat). The likely mechanism of mirtazapine action is regulation of brain-gut or gastrointestinal hormone levels.展开更多
CRISPR/Cas systems have been widely used for genome engineering in many plant species.However,their potentials have remained largely untapped in fruit crops,particularly in pear,due to the high levels of genomic heter...CRISPR/Cas systems have been widely used for genome engineering in many plant species.However,their potentials have remained largely untapped in fruit crops,particularly in pear,due to the high levels of genomic heterozygosity and difficulties in tissue culture and stable transformation.To date,only a few reports on the application of the CRISPR/Cas9 system in pear have been documented,and have shown very low editing efficiency.Here we report a highly efficient CRISPR toolbox for loss-of-function and gain-of-function research in pear.We compared four different CRISPR/Cas9 expression systems for loss-of-function analysis and identified a potent system that showed nearly 100% editing efficiency for multi-site mutagenesis.To expand the targeting scope,we further tested different CRISPR/Cas12a and Cas12b systems in pear for the first time,albeit with low editing efficiency.In addition,we established a CRISPR activation(CRISPRa)system for multiplexed gene activation in pear calli for gain-of-function analysis.Furthermore,we successfully engineered the anthocyanin and lignin biosynthesis pathways using both CRISPR/Cas9 and CRISPRa systems in pear calli.Taking these results together,we have built a highly efficient CRISPR toolbox for genome editing and gene regulation,paving the way for functional genomics studies as well as molecular breeding in pear.展开更多
Centromeres are the sites where kinetochores assemble and spindle microtubules anchor to the chromosomes during cell division.Centromeres are epigenetically specified by the centromeric histone H3(CENH3).The imbalance...Centromeres are the sites where kinetochores assemble and spindle microtubules anchor to the chromosomes during cell division.Centromeres are epigenetically specified by the centromeric histone H3(CENH3).The imbalance of CENH3 loading rate or dosage on parental centromeres often leads to uniparental chromosome elimination in the offspring.A body of studies of CENH3 in genome stability have been reported in Arabidopsis,cotton,and many other monocots,but not in soybean(Glycine max),an important dicot crop.In our study,we identified a singlecopy functional CENH3 in soybean and found its role in genome stability and parent-of-origin effect caused by the mutation of a conserved glycine site and parental genetic background.This study provides evidence that knockout of CENH3 in soybean has the potential to induce chromosome elimination and would shed light on the future development of CENH3-based haploid induction(HI)system and centromere biology in soybean.展开更多
The application of organic fertilizers has become an increasingly popular practice in maize production to reduce thegaseous nitrogen(N) loss and soil degradation caused by inorganic fertilizers. Organic fertilizer pla...The application of organic fertilizers has become an increasingly popular practice in maize production to reduce thegaseous nitrogen(N) loss and soil degradation caused by inorganic fertilizers. Organic fertilizer plays a key rolein improving soil quality and stabilizing maize yields, but few studies have compared different substitution rates. Afield study was carried out in 2021 and 2022, based on a long-term trial initiated in 2016, which included five organicfertilizer N substitution rates with equal inputs of 200 kg N ha–1: 0% organic fertilizer(T1, 100% inorganic fertilizer),50.0% organic+50.0% inorganic fertilizer(T2), 37.5% organic+62.5% inorganic fertilizer(T3), 25.0% organic+75.0%inorganic fertilizer(T4), and 12.5% organic+87.5% inorganic fertilizer(T5), as well as a no fertilizer control(T6). Theresults of the two years showed that T3 and T1 had the highest grain yield and biomass, respectively, and there wasno significant difference between T1 and T3. Compared with T1, the 12.5, 25.0, 37.5, and 50.0% substitution rates in T5, T4, T3, and T2 significantly reduced total nitrogen losses(NH3, N2O) by 8.3, 16.1, 18.7, and 27.0%, respectively.Nitrogen use efficiency(NUE) was higher in T5, T3, and T1, and there were no significant differences among them.Organic fertilizer substitution directly reduced NH3volatilization and N2O emission from farmland by lowering theammonium nitrogen and alkali-dissolved N contents and by increasing soil moisture. These substitution treatmentsreduced N2O emissions indirectly by regulating the abundances of AOB and nirK-harboring genes by promotingsoil moisture. Specifically, the 37.5% organic fertilizer substitution reduces NH3volatilization and N2O emission from farmland by reducing the ammonium nitrogen and alkali-dissolved N contents and increasing moisture, which negatively regulate the abundance of AOB and nir K-harboring genes to reduce N2O emissions indirectly in rainfed maize fields on the Loess Plateau of China.展开更多
The cochlea is one of the most complex organs in the human body,exhibiting a complex interplay of characteristics in acoustic,mechanical,electrical,and biological functions.Functional cochlea models are an essential p...The cochlea is one of the most complex organs in the human body,exhibiting a complex interplay of characteristics in acoustic,mechanical,electrical,and biological functions.Functional cochlea models are an essential platform for studying hearing mechanics and are crucial for developing next-generation auditory prostheses and artificial hearing systems for sensorineural hearing restoration.Recent advances in additive manufacturing,organ-on-a-chip models,drug delivery platforms,and artificial intelligence have provided valuable insights into how to manufacture artificial cochlea models that more accurately replicate the complex anatomy and physiology of the inner ear.This paper reviews recent advancements in the applications of advanced manufacturing techniques in reproducing the physical,biological,and intelligent functions of the cochlea.It also outlines the current challenges to developing mechanically,electrically,and anatomically accurate functional models of the inner ear.Finally,this review identifies the major requirements and outlook for impactful research in this field going forward.Through interdisciplinary collaboration and innovation,these functional cochlea models are poised to drive significant advancements in hearing treatments,and ultimately enhance the quality of life for individuals with hearing loss.展开更多
The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology pro...The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.展开更多
Much research effort has been devoted to economic design of X & S control charts,however,there are some problems in usual methods.On the one hand,it is difficult to estimate the relationship between costs and other...Much research effort has been devoted to economic design of X & S control charts,however,there are some problems in usual methods.On the one hand,it is difficult to estimate the relationship between costs and other model parameters,so the economic design method is often not effective in producing charts that can quickly detect small shifts before substantial losses occur;on the other hand,in many cases,only one type of process shift or only one pair of process shifts are taken into consideration,which may not correctly reflect the actual process conditions.To improve the behavior of economic design of control chart,a cost & loss model with Taguchi's loss function for the economic design of X & S control charts is embellished,which is regarded as an optimization problem with multiple statistical constraints.The optimization design is also carried out based on a number of combinations of process shifts collected from the field operation of the conventional control charts,thus more hidden information about the shift combinations is mined and employed to the optimization design of control charts.At the same time,an improved particle swarm optimization(IPSO) is developed to solve such an optimization problem in design of X & S control charts,IPSO is first tested for several benchmark problems from the literature and evaluated with standard performance metrics.Experimental results show that the proposed algorithm has significant advantages on obtaining the optimal design parameters of the charts.The proposed method can substantially reduce the total cost(or loss) of the control charts,and it will be a promising tool for economic design of control charts.展开更多
Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be di...Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be difficult. This paper investigates Neyman- Pearson classification with convex loss function in the arbitrary class of real measurable functions. A general condition is given under which Neyman-Pearson classification with convex loss function has the same classifier as that with indicator loss function. We give analysis to NP-ERM with convex loss function and prove it's performance guarantees. An example of complexity penalty pair about convex loss function risk in terms of Rademacher averages is studied, which produces a tight PAC bound of the NP-ERM with convex loss function.展开更多
Among cases of spinal cord injury are injuries involving the dorsal column in the cervical spinal cord that interrupt the major cutaneous afferents from the hand to the cuneate nucleus(Cu)in the brainstem.Deprivatio...Among cases of spinal cord injury are injuries involving the dorsal column in the cervical spinal cord that interrupt the major cutaneous afferents from the hand to the cuneate nucleus(Cu)in the brainstem.Deprivation of touch and proprioceptive inputs consequently impair skilled hand use.展开更多
Dear Editor,Sleep deprivation and loss can have detrimental effects on brain function.Among common patterns of sleep loss are delayed sleep onset(early night sleep loss,EL)and premature awakening(late night sleep loss...Dear Editor,Sleep deprivation and loss can have detrimental effects on brain function.Among common patterns of sleep loss are delayed sleep onset(early night sleep loss,EL)and premature awakening(late night sleep loss,LL).Here,we investigated the distinct impacts of EL and LL on resting-state brain activity.A total of 100 healthy students from several universities in Beijing were recruited and randomly assigned to one of three groups:EL,LL,or full sleep(FS).Restingstate functional magnetic resonance imaging(rs-fMRI)scans were conducted following the sleep manipulations.Compared to the FS group,the LL group showed abnormal low-frequency fluctuation(fALFF)in the prefrontal cortex and insula.展开更多
摘要The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence problem. Firstly, we utilize a network model architecture combining Gelu activation function and deep neural network;Secondly, the cross-entropy loss function is improved to a weighted cross entropy loss function, and at last it is applied to intrusion detection to improve the accuracy of intrusion detection. In order to compare the effect of the experiment, the KDDcup99 data set, which is commonly used in intrusion detection, is selected as the experimental data and use accuracy, precision, recall and F1-score as evaluation parameters. The experimental results show that the model using the weighted cross-entropy loss function combined with the Gelu activation function under the deep neural network architecture improves the evaluation parameters by about 2% compared with the ordinary cross-entropy loss function model. Experiments prove that the weighted cross-entropy loss function can enhance the model’s ability to discriminate samples.
基金Supported by the National Defense Basic Scientific Research Program of China.
摘要Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics.
基金supported by the National Natural Science Foundation of China(NSFC)under Grant number:82171965.
摘要Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning scenarios.In this work,we propose an Adaptive Meta-Loss Network(Adaptive-MLN)that learns to generate taskagnostic loss functions tailored to evolving classification problems.Unlike traditional methods that rely on static objectives,Adaptive-MLN treats the loss function itself as a trainable component,parameterized by a shallow neural network.To enable flexible,gradient-free optimization,we introduce a hybrid evolutionary approach that combines GeneticAlgorithms(GA)for global exploration and Evolution Strategies(ES)for local refinement.This co-evolutionary process dynamically adjusts the loss landscape,improvingmodel generalization without relying on analytic gradients or handcrafted heuristics.Experimental evaluations on synthetic tasks and the CIFAR-10 andMNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy,convergence,and adaptability.
摘要Thermal energy systems(TES)are an essential part of industries that have evolved over time through the engagement of managers and researchers.The development of digital twin(DT)technology has enabled accurate prediction of their performance.The inherent limitations of complex thermal systems,such as noisy input data and occasional lack of measurement data or boundary conditions,have recently created opportunities to apply physics-based problem-solving alongside DT technology.This paper aims to systematically review the novel physics-informed neural network-digital twin(PINN-DT)methodology as a potential solution to these challenges,and to present a taxonomy for problem-solving.The outcome of this study provides valuable guidance in selecting PINN-DT technology in thermal energy system(TES)modeling.A review of the proposed loss functions demonstrates that their design is critical for achieving precise outcomes in this technology,effectively serving as the foundational core of PINN-DT.As a result,it is recommended that the construction of the loss function be fundamentally guided by two principal considerations:forecasting accuracy and compliance with physical principles,which serve as foundational pillars in the surrogate model design framework.A significant gap exists in applying this technology to industries that use discrete sampling for quality control.Implementing the PINN-DT framework could address this issue by determining optimal sampling intervals,thereby offering vital decision-making support.Moreover,the absence of exergy analysis in formulating the physical loss component of the loss function represents a significant research gap.Future studies should therefore incorporate the exergy concept into the design of the loss function.
摘要Chromosomal abnormalities are categorized into chromosomal-level(ROH,polyploidy,aneuploidy),local copy number,and gene-level(insertion/deletion)types.Unlike invasive prenatal diagnostics with miscarriage risks,NIPT is noninvasive,reducing medical risks and maternal anxiety.This study addresses clinical NIPT bottlenecks(inaccurate timing,inconsistent abnormality determination)using high BMI pregnant women’s data via three core approaches:Spearman correlation and mixed-effects models confirm gestational age’s weak positive(rs=0.084,p<0.01)and BMI’s weak negative(rs=-0.155,p<0.001)correlation with fetal Y chromosome concentration;BMI grouping+Logistic regression+comprehensive loss function identifies robust optimal detection timing for each group;K-means clustering(4 groups)+three-layer weighted risk model(accuracy 0.4,timeliness 0.4,stability 0.2)optimizes multi-factor timing.Rational timing and multivariate models improve detection accuracy,supporting early clinical decisions.
基金jointly supported by the Natural Science Foundation of China(42574195)。
摘要Natural gas hydrate(NGH)has attracted increasing attention as a promising unconventional energy resource owing to its high volumetric storage capacity,yet its development is accompanied by significant greenhouse gas risks.Therefore,accurate reservoir characterization is vital for marine resource exploration and sustainable development.Full waveform inversion(FWI)offers high-resolution imaging,yet suffers from heavy computation,sensitivity to initial models and non-uniqueness.Recent deep learning(DL)methods improve efficiency and accuracy,nevertheless,still struggle with clear boundary extraction and multi-level semantic representation.The authors propose a novel deep architecture(SC-UNeXt)designed to learn a mapping from seismic records to velocity models,which integrates a U-Net backbone,ConvNeXt residual blocks,spatial-channel squeeze-and-excitation attention and pixel shuffle up-sampling.Furthermore,a hybrid loss integrating mean squared error,multi-scale structural similarity,and perceptual discrepancy simultaneously optimizes pixel-wise accuracy,structural fidelity,and semantic consistency.Comprehensive tests on both synthetic NGH data and the 3D SEG/EAGE marine overthrust model with NGH demonstrate that SC-UNeXt outperforms FWI and advanced DL methods in boundary delineation,structural preservation,noise robustness,and computational efficiency.These results highlight SC-UNeXt as a reliable tool for high-resolution seismic characterization of NGH reservoirs,thereby supporting sustainable exploration and risk assessment of marine hydrate resources.
基金supported by grants to S.J.K.from the United Stated Department of Agriculture(USDA)(http://gffzz4205af39ffde493ehu095xq6nccnx6q0b.ffgz.tsg.suse.edu.cn/10.13039/1000000199)National Institute of Food and Agriculture(NIFA)Specialty Crops Research Initiative(SCRI)(#2017-51181B6833)+1 种基金the USDA NIFA SCRI(#2022-51181-38328-0)the California Strawberry Commission(http://gffzz4205af39ffde493ehu095xq6nccnx6q0b.ffgz.tsg.suse.edu.cn/10.13039/100006760).
摘要Wildtype fruit of cultivated strawberry(Fragaria×ananassa)are typically soft and highly perishable when fully ripe.The development of firm-fruited cultivars by phenotypic selection has greatly increased shelf-life,decreased postharvest perishability,and driven the expansion of strawberry production worldwide.Hypotheses for the firm-fruited phenotype include mutations affecting the expression of genes encoding polygalacturonases(PGs)that soften fruit by degrading cell wall pectins.Here we show that loss-of-function mutations in the fruit softening gene POLYGALACTURONASE1(FaPG1;PG1-6A1)double fruit firmness in strawberry.PG1-6A1 was one of three tandem duplicated PG genes found to be in linkage disequilibrium(LD)with a quantitative trait locus(QTL)affecting fruit firmness on chromosome 6A.PG1-6A1 was strongly expressed in soft-fruited(wildtype)homozygotes and weakly expressed in firm-fruited(mutant)homozygotes.Genome-wide association,quantitative trait transcript,DNA sequence,and expression-QTL analyses identified genetic variants in LD with PG1-6A1 that were positively correlated with fruit firmness and negatively correlated with PG1-6A1 expression.An Enhancer/Suppressor-mutator(En/Spm)transposable element insertion was discovered upstream of PG1-6A1 in mutant homozygotes that we hypothesize transcriptionally downregulates the expression of PG1-6A1.The PG1-6A1 locus was incompletely dominant and explained 26–76%of the genetic variance for fruit firmness among phenotypically diverse individuals.Additional loci are hypothesized to underlie the missing heritability.Highly accurate codominant genotyping assays were developed for modifying fruit firmness by marker-assisted selection of the En/Spm insertion and single nucleotide polymorphisms associated with the PG1-6A1 locus.
基金supported by the Natural Science Foundation of Chongqing(No.CSTB2022NSCQ-MSX0538)Chongqing Solid Waste Management Center Project(No.CQGGZX2024003)+1 种基金Chongqing Research Institution Performance Incentive and Guidance Project(No.Cqhky2021jxjl00001)the Key Project of Technology Innovation and Application Development of Chongqing(No.CSTB2022TIADKPX0120).
摘要Improving the utilization of agricultural biological waste resources is a critical issue.This study initially assessed the effects of adding attapulgite to vegetable compost.Additionally,the study investigated the effects of attapulgite-modified compost on soil nutrient release and microbial community changes through nutrient loss experiments.Results indicated that adding attapulgite increased compost humification,significantly promoted humic acid synthesis,and improved the aromaticity and structural stability of humus.Attapulgite-modified organic fertilizer effectively retains soil nutrients,improves soil urease and alkaline phosphatase activities,and promotes microbial activity,synergy,and carbohydrate metabolism,with a 30%increase in tricarboxylic acid(TCA)cycle activity.ASV78 and ASV292 were highly sensitive to soil nutrient changes and may play a crucial role in regulating soil element cycling.This study provides valuable insights into the enhancement and application of clay minerals in composting,thereby improving the resource utilization of biological waste.
摘要Objective To analyze the clinical efficacy of combined orthodontic and prosthodontic therapy versus simple prosthodontic therapy in patients with congenital tooth loss aged 18–20 years. Methods A total of 60 patients with congenital tooth loss aged 18–20 years admitted to our hospital from January to December 2024 were enrolled and randomly divided into a combined group and a prosthodontic group (n=30 each) using a random number table. The prosthodontic group received only simple prosthodontic treatment, while the combined group received orthodontic combined with prosthodontic therapy. The dental function scores, aesthetic scores, complication rates, and overall treatment efficacy were compared between the two groups. Results The combined group demonstrated higher dental function scores and aesthetic scores than the prosthodontic group, lower complication rates, and higher overall treatment efficacy, with all differences being statistically significant (P<0.05). Conclusion For patients with congenital tooth loss aged 18–20 years, combined orthodontic and prosthodontic therapy can more effectively improve dental function and aesthetics, reduce post-treatment complication risks, and enhance therapeutic outcomes, demonstrating significant clinical value.
摘要AIM: To explore the effects and mechanism of action of antidepressant mirtazapine in functional dyspepsia(FD) patients with weight loss.METHODS: Sixty depressive FD patients with weight loss were randomly divided into a mirtazapine group(MG), a paroxetine group(PG) or a conventional therapy group(CG) for an 8-wk clinical trial. Adverse effects and treatment response were recorded. The Nepean Dyspepsia Index-symptom(NDSI) checklist and the 17-item Hamilton Rating Scale of Depression(HAMD-17) were used to evaluate dyspepsia and depressive symptoms, respectively. The body composition analyzer was used to measure body weight and fat. Serum hormone levels were measured by ELISA.RESULTS:(1) After 2 wk of treatment, NDSI scores were significantly lower for the MG than for the PG and CG;(2) After 4 or 8 wk of treatment, HAMD-17 scores were significantly lower for the MG and PG than for the CG;(3) After 8 wk of treatment, patients in the MG experienced a weight gain of 3.58 ± 1.57 kg, which was significantly higher than that observed for patients in the PG and CG. Body fat increased by 2.77 ± 0.14kg, the body fat ratio rose by 4%, and the visceral fat area increased by 7.56 ± 2.25 cm2; and(4) For the MG, serum hormone levels of ghrelin, neuropeptide Y(NPY), motilin(MTL) and gastrin(GAS) were significantly upregulated; in contrast, those of leptin, 5-hydroxytryptamine(5-HT) and cholecystokinin(CCK) were significantly downregulated. CONCLUSION: Mirtazapine not only alleviates symptoms associated with dyspepsia and depression linked to FD in patients with weight loss but also significantly increases body weight(mainly the visceral fat in body fat). The likely mechanism of mirtazapine action is regulation of brain-gut or gastrointestinal hormone levels.
基金supported by grants from the National Science Foundation of China(31820103012,31725024)the National Key Research and Development Program(2018YFD1000200)+3 种基金the Earmarked Fund for China Agriculture Research System(CARS-28)the Earmarked Fund for Jiangsu Agricultural Industry Technology System JATS[2021]453supported by the National Science Foundation Plant Genome Research Programgrant(IOS-1758745)to Y.Q.H.L,J.C.supported by a scholarship from the National Training Program of Innovation and Entrepreneurship for Undergraduates(202110307017).
摘要CRISPR/Cas systems have been widely used for genome engineering in many plant species.However,their potentials have remained largely untapped in fruit crops,particularly in pear,due to the high levels of genomic heterozygosity and difficulties in tissue culture and stable transformation.To date,only a few reports on the application of the CRISPR/Cas9 system in pear have been documented,and have shown very low editing efficiency.Here we report a highly efficient CRISPR toolbox for loss-of-function and gain-of-function research in pear.We compared four different CRISPR/Cas9 expression systems for loss-of-function analysis and identified a potent system that showed nearly 100% editing efficiency for multi-site mutagenesis.To expand the targeting scope,we further tested different CRISPR/Cas12a and Cas12b systems in pear for the first time,albeit with low editing efficiency.In addition,we established a CRISPR activation(CRISPRa)system for multiplexed gene activation in pear calli for gain-of-function analysis.Furthermore,we successfully engineered the anthocyanin and lignin biosynthesis pathways using both CRISPR/Cas9 and CRISPRa systems in pear calli.Taking these results together,we have built a highly efficient CRISPR toolbox for genome editing and gene regulation,paving the way for functional genomics studies as well as molecular breeding in pear.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Science(XDA24020306)National Natural Science Foundation of China(31991203)+2 种基金the National Key Research and Development Program of China(2022YFF1003500)CAS Project for Young Scientists in Basic Research(No.YSBR-078)Hainan Yazhou Bay Seed Laboratory and China National Seed Group(project of B23YQ1505).
摘要Centromeres are the sites where kinetochores assemble and spindle microtubules anchor to the chromosomes during cell division.Centromeres are epigenetically specified by the centromeric histone H3(CENH3).The imbalance of CENH3 loading rate or dosage on parental centromeres often leads to uniparental chromosome elimination in the offspring.A body of studies of CENH3 in genome stability have been reported in Arabidopsis,cotton,and many other monocots,but not in soybean(Glycine max),an important dicot crop.In our study,we identified a singlecopy functional CENH3 in soybean and found its role in genome stability and parent-of-origin effect caused by the mutation of a conserved glycine site and parental genetic background.This study provides evidence that knockout of CENH3 in soybean has the potential to induce chromosome elimination and would shed light on the future development of CENH3-based haploid induction(HI)system and centromere biology in soybean.
基金supported by the State Key Laboratory of Arid Land Crop Science, Gansu Agricultural University,China (GSCS-2022-Z02)the National Key R&D Program of China (2022YFD1900300)+2 种基金the National Natural Science Foundation of China (32260549)the Innovation Group of Basic Research in Gansu Province, China (25JRRA807)the Major Special Research Projects in Gansu Province, China (22ZD6NA009)。
摘要The application of organic fertilizers has become an increasingly popular practice in maize production to reduce thegaseous nitrogen(N) loss and soil degradation caused by inorganic fertilizers. Organic fertilizer plays a key rolein improving soil quality and stabilizing maize yields, but few studies have compared different substitution rates. Afield study was carried out in 2021 and 2022, based on a long-term trial initiated in 2016, which included five organicfertilizer N substitution rates with equal inputs of 200 kg N ha–1: 0% organic fertilizer(T1, 100% inorganic fertilizer),50.0% organic+50.0% inorganic fertilizer(T2), 37.5% organic+62.5% inorganic fertilizer(T3), 25.0% organic+75.0%inorganic fertilizer(T4), and 12.5% organic+87.5% inorganic fertilizer(T5), as well as a no fertilizer control(T6). Theresults of the two years showed that T3 and T1 had the highest grain yield and biomass, respectively, and there wasno significant difference between T1 and T3. Compared with T1, the 12.5, 25.0, 37.5, and 50.0% substitution rates in T5, T4, T3, and T2 significantly reduced total nitrogen losses(NH3, N2O) by 8.3, 16.1, 18.7, and 27.0%, respectively.Nitrogen use efficiency(NUE) was higher in T5, T3, and T1, and there were no significant differences among them.Organic fertilizer substitution directly reduced NH3volatilization and N2O emission from farmland by lowering theammonium nitrogen and alkali-dissolved N contents and by increasing soil moisture. These substitution treatmentsreduced N2O emissions indirectly by regulating the abundances of AOB and nirK-harboring genes by promotingsoil moisture. Specifically, the 37.5% organic fertilizer substitution reduces NH3volatilization and N2O emission from farmland by reducing the ammonium nitrogen and alkali-dissolved N contents and increasing moisture, which negatively regulate the abundance of AOB and nir K-harboring genes to reduce N2O emissions indirectly in rainfed maize fields on the Loess Plateau of China.
基金support from the UCL GRS/ORS scholarshipUCL Fellowship Incubator Award+9 种基金supported by the NIHR Cambridge Biomedical Research Centre(NIHR203312)funded by the Royal National Institute for Deaf People(RNID,G100138)funded by the Rosetrees Trust Enterprise Fellowship(EF2020100099)RNID Flexigrant(F112)Wellcome Trust Developing Concept Fund(RG93172/BANCE/40181)by the Evelyn Trustfunded by the Woolf Fisher Trust,New Zealandthe Cambridge Commonwealth,European,&International Trustby Trinity CollegeUniversity of Cambridge。
摘要The cochlea is one of the most complex organs in the human body,exhibiting a complex interplay of characteristics in acoustic,mechanical,electrical,and biological functions.Functional cochlea models are an essential platform for studying hearing mechanics and are crucial for developing next-generation auditory prostheses and artificial hearing systems for sensorineural hearing restoration.Recent advances in additive manufacturing,organ-on-a-chip models,drug delivery platforms,and artificial intelligence have provided valuable insights into how to manufacture artificial cochlea models that more accurately replicate the complex anatomy and physiology of the inner ear.This paper reviews recent advancements in the applications of advanced manufacturing techniques in reproducing the physical,biological,and intelligent functions of the cochlea.It also outlines the current challenges to developing mechanically,electrically,and anatomically accurate functional models of the inner ear.Finally,this review identifies the major requirements and outlook for impactful research in this field going forward.Through interdisciplinary collaboration and innovation,these functional cochlea models are poised to drive significant advancements in hearing treatments,and ultimately enhance the quality of life for individuals with hearing loss.
基金Jilin Science and Technology Development Plan Project(No.20200403075SF)Doctoral Research Start-Up Fund of Northeast Electric Power University(No.BSJXM-2018202).
摘要The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.
基金supported by Defense Industrial Technology Development Program of China (Grant No. A2520110003)
摘要Much research effort has been devoted to economic design of X & S control charts,however,there are some problems in usual methods.On the one hand,it is difficult to estimate the relationship between costs and other model parameters,so the economic design method is often not effective in producing charts that can quickly detect small shifts before substantial losses occur;on the other hand,in many cases,only one type of process shift or only one pair of process shifts are taken into consideration,which may not correctly reflect the actual process conditions.To improve the behavior of economic design of control chart,a cost & loss model with Taguchi's loss function for the economic design of X & S control charts is embellished,which is regarded as an optimization problem with multiple statistical constraints.The optimization design is also carried out based on a number of combinations of process shifts collected from the field operation of the conventional control charts,thus more hidden information about the shift combinations is mined and employed to the optimization design of control charts.At the same time,an improved particle swarm optimization(IPSO) is developed to solve such an optimization problem in design of X & S control charts,IPSO is first tested for several benchmark problems from the literature and evaluated with standard performance metrics.Experimental results show that the proposed algorithm has significant advantages on obtaining the optimal design parameters of the charts.The proposed method can substantially reduce the total cost(or loss) of the control charts,and it will be a promising tool for economic design of control charts.
基金This is a Plenary Report on the International Symposium on Approximation Theory and Remote SensingApplications held in Kunming, China in April 2006Supported in part by NSF of China under grants 10571010 , 10171007 and Startup Grant for Doctoral Researchof Beijing University of Technology
摘要Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be difficult. This paper investigates Neyman- Pearson classification with convex loss function in the arbitrary class of real measurable functions. A general condition is given under which Neyman-Pearson classification with convex loss function has the same classifier as that with indicator loss function. We give analysis to NP-ERM with convex loss function and prove it's performance guarantees. An example of complexity penalty pair about convex loss function risk in terms of Rademacher averages is studied, which produces a tight PAC bound of the NP-ERM with convex loss function.
基金supported by NIH grants NS067017 to HXQNS16446 to JHK
摘要Among cases of spinal cord injury are injuries involving the dorsal column in the cervical spinal cord that interrupt the major cutaneous afferents from the hand to the cuneate nucleus(Cu)in the brainstem.Deprivation of touch and proprioceptive inputs consequently impair skilled hand use.
基金supported by the STI2030-Major Projects(2021ZD0202100,2021ZD0200801,and 2021ZD0201900)the National Natural Science Foundation of China(82130040,82288101).
摘要Dear Editor,Sleep deprivation and loss can have detrimental effects on brain function.Among common patterns of sleep loss are delayed sleep onset(early night sleep loss,EL)and premature awakening(late night sleep loss,LL).Here,we investigated the distinct impacts of EL and LL on resting-state brain activity.A total of 100 healthy students from several universities in Beijing were recruited and randomly assigned to one of three groups:EL,LL,or full sleep(FS).Restingstate functional magnetic resonance imaging(rs-fMRI)scans were conducted following the sleep manipulations.Compared to the FS group,the LL group showed abnormal low-frequency fluctuation(fALFF)in the prefrontal cortex and insula.