Background:Excessive heat exposure can lead to hyperthermia in humans,which impairs physical performance and disrupts cognitive function.While heat is a known physiological stressor,it is unclear how severe heat stres...Background:Excessive heat exposure can lead to hyperthermia in humans,which impairs physical performance and disrupts cognitive function.While heat is a known physiological stressor,it is unclear how severe heat stress affects brain physiology and function.Methods:Eleven healthy participants were subjected to heat stress from prolonged exercise or warm water immersion until their rectal temperatures(T_(re))attained 39.5℃,inducing exertional or passive hyperthermia,respectively.In a separate trial,blended ice was ingested before and during exercise as a cooling strategy.Data were compared to a control condition with seated rest(normothermic).Brain temperature(T_(br)),cerebral perfusion,and task-based brain activity were assessed using magnetic resonance imaging techniques.Results:T_(br)in motor cortex was found to be tightly regulated at rest(37.3℃±0.4℃(mean±SD))despite fluctuations in T_(re).With the development of hyperthermia,T_(br)increases and dovetails with the rising T_(re).Bilateral motor cortical activity was suppressed during high-intensity plantarflexion tasks,implying a reduced central motor drive in hyperthermic participants(T_(re)=38.5℃±0.1℃).Global gray matter perfusion and regional perfusion in sensorimotor cortex were reduced with passive hyperthermia.Executive function was poorer under a passive hyperthermic state,and this could relate to compromised visual processing as indicated by the reduced activation of left lateral-occipital cortex.Conversely,ingestion of blended ice before and during exercise alleviated the rise in both T_(re)and T_(bc)and mitigated heat-related neural perturbations.Conclusion:Severe heat exposure elevates T_(br),disrupts motor cortical activity and executive function,and this can lead to impairment of physical and cognitive performance.展开更多
Deep learning(DL),derived from the domain of Artificial Neural Networks(ANN),forms one of the most essential components of modern deep learning algorithms.DL segmentation models rely on layer-by-layer convolution-base...Deep learning(DL),derived from the domain of Artificial Neural Networks(ANN),forms one of the most essential components of modern deep learning algorithms.DL segmentation models rely on layer-by-layer convolution-based feature representation,guided by forward and backward propagation.Acritical aspect of this process is the selection of an appropriate activation function(AF)to ensure robustmodel learning.However,existing activation functions often fail to effectively address the vanishing gradient problem or are complicated by the need for manual parameter tuning.Most current research on activation function design focuses on classification tasks using natural image datasets such asMNIST,CIFAR-10,and CIFAR-100.To address this gap,this study proposesMed-ReLU,a novel activation function specifically designed for medical image segmentation.Med-ReLU prevents deep learning models fromsuffering dead neurons or vanishing gradient issues.It is a hybrid activation function that combines the properties of ReLU and Softsign.For positive inputs,Med-ReLU adopts the linear behavior of ReLU to avoid vanishing gradients,while for negative inputs,it exhibits the Softsign’s polynomial convergence,ensuring robust training and avoiding inactive neurons across the training set.The training performance and segmentation accuracy ofMed-ReLU have been thoroughly evaluated,demonstrating stable learning behavior and resistance to overfitting.It consistently outperforms state-of-the-art activation functions inmedical image segmentation tasks.Designed as a parameter-free function,Med-ReLU is simple to implement in complex deep learning architectures,and its effectiveness spans various neural network models and anomaly detection scenarios.展开更多
Background and objective:Activated carbon is commonly used as an immobilisation matrix due to its large surface area,making it a highly desirable matrix for use in immobilising enzymes as preparation for use on the in...Background and objective:Activated carbon is commonly used as an immobilisation matrix due to its large surface area,making it a highly desirable matrix for use in immobilising enzymes as preparation for use on the industrial scale.The objective of this research is to determine the effectiveness of different acids for functionalisation on immobilisation capacity and also to characterize the functionalized activated carbon for the functional groups present.Materials and methods:Activated carbon was functionalised with three acids(hydrochloric acid,nitric acid and sulphuric acid)along with a control sample washed with distilled water.Immobilisation capacity was calculated with hydrochloric acid functionalized activated carbon(HCl-FAC)giving the highest immobilization capacity(6.022 U/g).Characterisation of the functionalised activated carbon was conducted using FT-IR(Fourier Transform Infra-Red)spectroscopy analysis of the samples with the aim of analyzing the various functional groups present to determine the sample with distinct characteristics thus telling the degree of adsorption of lipase onto the activated carbon powder.Results:HNO3-FAC(functionalized activated carbon)showed a very distinct pattern as a larger number of surface functional groups emerged.The immobilisation on a matrix ensures thermal stability and increased reusability of the enzyme.Therefore,in this research,lipase sourced from Candida antarctica was immobilised on acid functionalised activated carbon.The best acid for functionalisation was found to be hydrochloric acid.Conclusion:Due to the very distinct patterns shown by the FT-IR spectrum of the HNO3-FAC after a fair comparison with others,it allows for a larger number of surface functional groups which will definitely enhance the stability of the enzyme lipase.展开更多
BACKGROUND： At present, central cholinergic neuron system is regarded the most major structural basis of cognitive function. Changes in structure of cholinergic neuron system of brain and receptor expression after br...BACKGROUND： At present, central cholinergic neuron system is regarded the most major structural basis of cognitive function. Changes in structure of cholinergic neuron system of brain and receptor expression after brain injury can cause cognitive impairment. OBJECTIVE＂ To comparatively observe the intelligence quotient （IQ）, latent period and wave amplitude of P300 event-related potential and the difference of activity of acetylcholinesterase （ACHE） in blood and cerebrospinal fluid between patients with type 2 diabetes mellitus and with non-diabetes mellitus, and analyze the correlation of IQ of cognitive impairment patients with diabetes mellitus with AChE activity, latent period and wave amplitude of P300 event-related potential in cerebrospinal fluid. DESIGN： Correlation analysis of contrast observation SETTING： Department of Endocrinology, Affiliated Hospital of Binzhou Medical College PARTICIPANTS： Totally 32 patients with type 2 diabetes mellitus who received the treatment in the Department of Endocrinology, Affiliated Hospital of Binzhou Medical College between April 2004 and April 2005 were recruited, serving as diabetes mellitus group. They, including 19 male and 13 female, aged 49 to 73 years, with disease course of 4 to 11 years, all met the diagnostic criteria of diabetes mellitus revised by World Health Organization in 1999. Another 30 patients with non-diabetes mellitus who homeochronously underwent lumbar anesthesia in the Department of Surgery and Department of Gynecology were recruited, serving as non-diabetes mellitus group. The 30 patients included 18 male and 12 female, and their age ranged from 46 to 71 years. Informed consents of detected items were obtained from the involved patients. METHODS： ① Evaluation,on IQ： The IQ of involved subjects was evaluated with Chinese Version of the Wechsler Adult Intelligence Scale revised by Gong Yao-xian （WAIS-RC）. WAIS-RC included 6 verbal subscales and 5 performance subscales. The test scores of the 11 subscales integrated into the scores of the whole scale, and the scores on the WAIS-RC included verbal IQ （VlQ）, performance IQ （PIQ） and full scale IQ （FIQ）. FIQ ≤79 scores indicated low IQ and FIQ≤69 indicated intelligence impairment. ② Detection of P300 wave： P300 wave was detected with evoked potential instrument （MYTOPRO, Italian）, and data of latent period and amplitude of P300 event-related potential were automatically shown by computer. ③ Detection of AChE activity in blood and cerebrospinal fluid： Activity of AChE of blood and cerebrospinal fluid was measured with biochemical methods by using CORNING-560 autoanalyzer.④Correlation analysis： Correlation of FIQ with AChE of cerebrospinal fluid and P300 wave of patients with type 2 diabetes mellitus was analyzed, t test was used in intergroup comparison and linear correlation analysis for relevant treatment. MAIN OUTCOME MEASURES： ① Comparison of IQ, latent period and wave amplitude of P300 wave as well as the activity of AChE between two groups. ② Analysis on the correlation of FIQ of patients with type 2 diabetes mellitus with AChE of cerebrospinal fluid and P300 wave. RESULTS： Thirty-two patients with diabetes mellitus and 30 non-diabetes mellitus participated in the result analysis. ①Comparison of IQ, latent period and wave amplitude of P300 wave as well as the activity of AChE between two groups： The scores of VIP, PIQ and FIQ of patients with type 2 diabetes mellitus were （97.4±10.4）. （92.6±8.4） and （95.2±9.7） scores, respectively; and those of patients with non-diabetes mellitus were （104.7±9.6）, （102.5±8.5）and（102.7±8.9） scores, respectively, and P 〈 0.05-0.01 was set in intergroup comparison. The latent period of P300 wave at points Fz , Cz and Pz of patients with type 2 diabetes mellitus was （370.8±41.8）.（371.5±39.1）and （375.1±43.1） ms, respectively, and that of patients with non-diabetes mellitus was （ 332.1 ±28.3 ）, （335.7 ±29.4）and （339.7 ±27.3） ms, respectively, and P 〈 0.01 was set in intergroup comparison; Wave amplitude of P300 of patients with type 2 diabetes mellitus was （8.6±4.1）,（8.6±4.0） and （7.7±4.0） μV, respectively and that of patients with non-diabetes mellitus was （11.9±4.1）,（11.5±4.4） and （10.9±5.0） μV, respectively , and P 〈 0.05-0.01 was set in intergroup comparison; The level of AChE in blood and cerebrospinal fluid of patients with type 2 diabetes mellitus was （235.61 ±50.34）and （17.89±4.46） μkat/L, respectively, which was significantly higher than that of patients with non-diabetes mellitus [（205.03±44.15）and （14.63±0.48） μkat /L, respectively], and P 〈 0.05-0.01 was set in the intergroup comparison. ② Correlation of FIQ value of patients with type 2 diabetes mellitus with AChE of cerebrospinal fluid and P300 wave： The value of FIQ was significantly negatively correlated with the AChE activity of cerebrospinal fluid （r=-0.588 1, P 〈 0.01 ）, significantly negatively correlated with the latent period at points Fz. C and Pz of P300 wave （r= -0.700 5, -0.689 4, -0.688 5, P 〈 0.01 ）, and significantly positively correlated with the amplitude at points Fz . Cz and Pz of P300 wave（r= 0.607 4,0.616 1,0.592 0,P 〈 0.01 ）. CONCLUSION： ① Cognitive impairment of patients with type 2 diabetes mellitus might be related to the increase of activity of AChE in cerebrospinal fluid. ②Combined application of examination of P300 wave and evaluation of IQ is more useful in deciding the state of cognitive function of patients with type 2 diabetes mellitus.展开更多
A vehicle engine cooling system is of utmost importance to ensure that the engine operates in a safe temperature range.In most radiators that are used to cool an engine,water serves as a cooling fluid.The performance ...A vehicle engine cooling system is of utmost importance to ensure that the engine operates in a safe temperature range.In most radiators that are used to cool an engine,water serves as a cooling fluid.The performance of a radiator in terms of heat transmission is significantly influenced by the incorporation of nanoparticles into the cooling water.Concentration and uniformity of nanoparticle distribution are the two major factors for the practical use of nanofluids.The shape and size of nanoparticles also have a great impact on the performance of heat transfer.Many researchers are investigating the impact of nanoparticles on heat transfer.This study aims to develop an artificial neural network(ANN)model for predicting the thermal conductivity of an ethylene glycol(EG)/waterbased crystalline nanocellulose(CNC)nanofluid for cooling internal combustion engine.The implementation of an artificial neural network considering different activation functions in the hidden layer is made to find the bestmodel for the cooling of an engine using the nanofluid.Accuracies of the model with different activation functions in artificial neural networks are analyzed for different nanofluid concentrations and temperatures.In artificial neural networks,Levenberg–Marquardt is an optimization approach used with activation functions,including Tansig and Logsig functions in the training phase.The findings of each training,testing,and validation phase are presented to demonstrate the network that provides the highest level of accuracy.The best result was obtained with Tansig,which has a correlation of 0.99903 and an error of 3.7959×10^(–8).It has also been noticed that the Logsig function can also be a good model due to its correlation of 0.99890 and an error of 4.9218×10^(–8).Thus ourANNwith Tansig and Logsig functions demonstrates a high correlation between the actual output and the predicted output.展开更多
The effect of lymphotoxin (LT)-containing supernatant produced by lectin-stimulated human lymphocytes on tumor cells and the relation between interleukin-2 (IL-2) and LT were studied in this article. Results showed th...The effect of lymphotoxin (LT)-containing supernatant produced by lectin-stimulated human lymphocytes on tumor cells and the relation between interleukin-2 (IL-2) and LT were studied in this article. Results showed that LT-containing superna-tants had cytotoxicities on many different kinds of tumor cells from human and mice, that actinomycin D increased the LT activities on target cells and that IL-2 had the ability to increase the cytotoxicity of human PBMC on tumor cells, after being treated with LT, the target cells were more easy to kill by PBMC as well.展开更多
The purpose of this study was to address the challenges in predicting and classifying accuracy in modeling Container Dwell Time (CDT) using Artificial Neural Networks (ANN). This objective was driven by the suboptimal...The purpose of this study was to address the challenges in predicting and classifying accuracy in modeling Container Dwell Time (CDT) using Artificial Neural Networks (ANN). This objective was driven by the suboptimal outcomes reported in previous studies and sought to apply an innovative approach to improve these results. To achieve this, the study applied the Fusion of Activation Functions (FAFs) to a substantial dataset. This dataset included 307,594 container records from the Port of Tema from 2014 to 2022, encompassing both import and transit containers. The RandomizedSearchCV algorithm from Python’s Scikit-learn library was utilized in the methodological approach to yield the optimal activation function for prediction accuracy. The results indicated that “ajaLT”, a fusion of the Logistic and Hyperbolic Tangent Activation Functions, provided the best prediction accuracy, reaching a high of 82%. Despite these encouraging findings, it’s crucial to recognize the study’s limitations. While Fusion of Activation Functions is a promising method, further evaluation is necessary across different container types and port operations to ascertain the broader applicability and generalizability of these findings. The original value of this study lies in its innovative application of FAFs to CDT. Unlike previous studies, this research evaluates the method based on prediction accuracy rather than training time. It opens new avenues for machine learning engineers and researchers in applying FAFs to enhance prediction accuracy in CDT modeling, contributing to a previously underexplored area.展开更多
In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantl...In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantly degrades image quality.Traditional denoising methods,typically based on filter techniques,often face challenges related to inefficiency and limited adaptability.To address these limitations,this study proposes a novel SAR image denoising algorithm based on an enhanced residual network architecture,with the objective of enhancing the utility of SAR imagery in complex electromagnetic environments.The proposed algorithm integrates residual network modules,which directly process the noisy input images to generate denoised outputs.This approach not only reduces computational complexity but also mitigates the difficulties associated with model training.By combining the Transformer module with the residual block,the algorithm enhances the network's ability to extract global features,offering superior feature extraction capabilities compared to CNN-based residual modules.Additionally,the algorithm employs the adaptive activation function Meta-ACON,which dynamically adjusts the activation patterns of neurons,thereby improving the network's feature extraction efficiency.The effectiveness of the proposed denoising method is empirically validated using real SAR images from the RSOD dataset.The proposed algorithm exhibits remarkable performance in terms of EPI,SSIM,and ENL,while achieving a substantial enhancement in PSNR when compared to traditional and deep learning-based algorithms.The PSNR performance is enhanced by over twofold.Moreover,the evaluation of the MSTAR SAR dataset substantiates the algorithm's robustness and applicability in SAR denoising tasks,with a PSNR of 25.2021 being attained.These findings underscore the efficacy of the proposed algorithm in mitigating speckle noise while preserving critical features in SAR imagery,thereby enhancing its quality and usability in practical scenarios.展开更多
Objective:To conduct a scoping review on the application status of the Functional Activity Score(FAS)in postoperative active pain management in China,providing a reference for its standardized and normative promotion....Objective:To conduct a scoping review on the application status of the Functional Activity Score(FAS)in postoperative active pain management in China,providing a reference for its standardized and normative promotion.Methods:Computerized searches of Chinese and English databases were performed to collect studies published by Chinese scholars from 2005 to July 2025 on the application of FAS in postoperative active pain management.After strict screening,the basic characteristics,application fields,assessment models,evaluation timing,types of functional activities,and clinical outcomes of the included literature were systematically analyzed.Results:A total of 18 studies were included,involving surgical types such as thoracic surgery,general surgery,and orthopedics.All studies adopted FAS combined with the Numeric Rating Scale(NRS)for assessment,with evaluation timing mostly concentrated within 72 hours postoperatively.The selected functional activities primarily included respiration-related and limb movements.Evaluation indicators covered pain control,functional recovery,complications,adverse events,patient experience,and tool assessment,with most studies reporting positive outcomes.Conclusion:FAS can effectively enhance pain control and promote functional recovery in postoperative active pain management in China,demonstrating high clinical value.However,existing studies exhibit inconsistencies in assessment criteria,selection of activity types,and research quality.展开更多
An electrochemically reduced graphene oxide sample, ERGO_0.8v, was prepared by electrochemical reduction of graphene oxide （GO） at -0.8 V, which shows unique electrocatalytic activity toward tetracycline （TTC） det...An electrochemically reduced graphene oxide sample, ERGO_0.8v, was prepared by electrochemical reduction of graphene oxide （GO） at -0.8 V, which shows unique electrocatalytic activity toward tetracycline （TTC） detection compared to the ERGO-12v （GO applied to a negative potential of-1.2 V）, GO, chemically reduced GO （CRGO）-modified glassy carbon electrode （GC） and bare GC electrodes. The redox peaks of TTC on an ERGO-0.8v-modifled glass carbon electrode （GC/ERGO-0.8v） were within 0-0.5 V in a pH 3.0 buffer solution with the oxidation peak current correlating well with TTC concentration over a wide range from 0.1 to 160 mg/L Physical characterizations with Fourier transform infrared （FT-IR）, Raman, and X-ray photoelectron spectroscopies （XPS） demonstrated that the oxygen-containing functional groups on GO diminished after the electrochemical reduction at -0.8 V, yet still existed in large amounts, and the defect density changed as new sp2 domains were formed. These changes demonstrated that this adjustment in the number of oxygen-containing groups might be the main factor affecting the electrocatalytic behavior of ERGO. Additionally, the defect density and sp2 domains also exert a profound influence on this behavior. A possible mechanism for the TTC redox reaction at the GC/ERGO-0.8v electrode is also presented. This work suggests that the electrochemical reduction is an effective method to establish new catalytic activities of GO by setting appropriate parameters.展开更多
Objective: to investigate the effect of rehabilitation nursing on activity function in knee meniscus injury. Methods: 60 patients with knee meniscus injury from 12-2020-December 2021. The control group was given routi...Objective: to investigate the effect of rehabilitation nursing on activity function in knee meniscus injury. Methods: 60 patients with knee meniscus injury from 12-2020-December 2021. The control group was given routine care, and the rehabilitation nursing group implements routine nursing combined rehabilitation nursing. The pain level, depression, anxiety, activity function, and satisfaction degree were compared between the two groups. Results: pain level, depression, activity function and satisfaction were lower than the control group, P <0.05. Conclusion: in case of knee meniscus injury, it can relieve depression and anxiety, improve activity function and reduce pain and improve satisfaction.展开更多
To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with ad...To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with adaptive centers and widths,which is composed of more than one hidden layer.In the hidden layer of the RBF-activated MLP network(MLPRBF),the outputs of the preceding layer are first linearly transformed and then fed into the univariate Gaussian RBF,which exploits the highly nonlinear property of RBF.Adaptive RBFs might address the issues of saturated outputs,low sensitivity,and vanishing gradients in MLPs activated by other prevailing nonlinear functions.Finally,we apply four MLP networks with the rectified linear unit(ReLU),sigmoid function(sigmoid),hyperbolic tangent function(tanh),and Gaussian RBF as the activation functions to approximate the one-dimensional(1D)sinusoidal function,the analytical solution of viscous Burgers’equation,and the two-dimensional(2D)steady lid-driven cavity flows.Using the same network structure,MLP-RBF generally predicts more accurately and converges faster than the other threeMLPs.MLP-RBF using less hidden layers and/or neurons per layer can yield comparable or even higher approximation accuracy than other MLPs equipped with more layers or neurons.展开更多
The humid agroclimatic conditions of Kerala,India permit the cultivation of an array of bamboo species of which Dendrocalamus strictus Roxb.(Nees.) is an important one on account of its high growth rate and multiple u...The humid agroclimatic conditions of Kerala,India permit the cultivation of an array of bamboo species of which Dendrocalamus strictus Roxb.(Nees.) is an important one on account of its high growth rate and multiple uses. Stand density, a potential tool in controlling the productivity of woody ecosystems, its effect on growth and root distribution patterns may provide a better understanding of productivity optimization especially when bamboo-based intercropping options are considered.Growth attributes of 7-year-old bamboo(D. strictus) stands managed at variable spacing(4×4 m, 6×6 m, 8×8 m,10×10 m, 12×12 m) were studied. Functional root activity among bamboo clumps were also studied using a radio tracer soil injection method in which the radio isotopeP was applied to soil at varying depths and lateral distances from the clump. Results indicate that spacing exerts a profound influence on growth of bamboo. Widely spaced bamboo exhibited higher clump diameters and crown widths while clump heights were better under closer spacing. Clump height was 30% lower and DBH 52%higher at the widest spacing(12×12 m) compared to the closest spacing(4×4 m). With increasing soil depth and lateral distance, root activity decreased significantly. Root activity near the clump base was highest(809 counts per minute, cpm; 50 cm depth and 50 cm lateral distance) at 4×4 m. Tracer study further showed wider distribution of root activity with increase in clump spacing. It may be concluded that the intensive foraging zone of bamboo is within a 50-cm radius around the clump irrespective of spacing. N, P and K content in the upper 20 cm was 2197,21, and 203 kg/ha respectively for the closely spaced bamboo(4×4 m) which were significantly higher than corresponding nutrient content at wider spacings. About 50% of N, P and K were present within the 0–20 cm soil layer, which decreased drastically beyond the 20 cm depth.The results suggest that stand management practices through planting density regulation can modify the resource acquisition patterns of D. strictus which in turn can change growth and productivity considerably. Such information on root activities, spatial and temporal strategies of resource sharing will be helpful in deciding the effective nutrition zone for D. strictus. Further, the study throws light on the spatial distribution of non-competitive zones for productivity optimization yields, especially when intercropping practices are considered.展开更多
Exploration of soil environmental characteristics governing soil microbial community structure and activity may improve our understanding of biogeochemical processes and soil quality. The impact of soil environmental ...Exploration of soil environmental characteristics governing soil microbial community structure and activity may improve our understanding of biogeochemical processes and soil quality. The impact of soil environmental characteristics especially organic carbon availability after 15-yr different organic and inorganic fertilizer inputs on soil bacterial community structure and functional metabolic diversity of soil microbial communities were evaluated in a 15-yr fertilizer experiment in Changping County, Beijing, China. The experiment was a wheat-maize rotation system which was established in 1991 including four different fertilizer treatments. These treatments included： a non-amended control（CK）, a commonly used application rate of inorganic fertilizer treatment（NPK）; a commonly used application rate of inorganic fertilizer with swine manure incorporated treatment（NPKM）, and a commonly used application rate of inorganic fertilizer with maize straw incorporated treatment（NPKS）. Denaturing gradient gel electrophoresis（DGGE） of the 16 S r RNA gene was used to determine the bacterial community structure and single carbon source utilization profiles were determined to characterize the microbial community functional metabolic diversity of different fertilizer treatments using Biolog Eco plates. The results indicated that long-term fertilized treatments significantly increased soil bacterial community structure compared to CK. The use of inorganic fertilizer with organic amendments incorporated for long term（NPKM, NPKS） significantly promoted soil bacterial structure than the application of inorganic fertilizer only（NPK）, and NPKM treatment was the most important driver for increases in the soil microbial community richness（S） and structural diversity（H）. Overall utilization of carbon sources by soil microbial communities（average well color development, AWCD） and microbial substrate utilization diversity and evenness indices（H＇ and E） indicated that long-term inorganic fertilizer with organic amendments incorporated（NPKM, NPKS） could significantly stimulate soil microbial metabolic activity and functional diversity relative to CK, while no differences of them were found between NPKS and NPK treatments. Principal component analysis（PCA） based on carbon source utilization profiles also showed significant separation of soil microbial community under long-term fertilization regimes and NPKM treatment was significantly separated from the other three treatments primarily according to the higher microbial utilization of carbohydrates, carboxylic acids, polymers, phenolic compounds, and amino acid, while higher utilization of amines/amides differed soil microbial community in NPKS treatment from those in the other three treatments. Redundancy analysis（RDA） indicated that soil organic carbon（SOC） availability, especially soil microbial biomass carbon（Cmic） and Cmic/SOC ratio are the key factors of soil environmental characteristics contributing to the increase of both soil microbial community structure and functional metabolic diversity in the long-term fertilization trial. Our results showed that long-term inorganic fertilizer and swine manure application could significantly improve soil bacterial community structure and soil microbial metabolic activity through the increases in SOC availability, which could provide insights into the sustainable management of China＇s soil resource.展开更多
AIM： To evaluate the differences in the functional connectivity（FC） of the primary visual cortex（V1） between the youth comitant exotropia（CE） patients and health subjects using resting functional magnetic reson...AIM： To evaluate the differences in the functional connectivity（FC） of the primary visual cortex（V1） between the youth comitant exotropia（CE） patients and health subjects using resting functional magnetic resonance imaging（f MRI） data.METHODS： Totally, 32 CEs（25 males and 7 females） and 32 healthy control subjects（HCs）（25 males and 7 females） were enrolled in the study and underwent the MRI scanning. Two-sample t-test was used to examine differences in FC maps between the CE patients and HCs. RESULTS： The CE patients showed significantly less FC between the left brodmann area（BA17） and left lingual gyrus/cerebellum posterior lobe, right middle occipital gyrus, left precentral gyrus/postcentral gyrus and right inferior parietal lobule/postcentral gyrus. Meanwhile, CE patients showed significantly less FC between right BA17 and right middle occipital gyrus（BA19, 37）.CONCLUSION： Our findings show that CE involves abnormal FC in primary visual cortex in many regions, which may underlie the pathologic mechanism of impaired fusion and stereoscopic vision in CEs.展开更多
Recently,deep learning has achieved remarkable results in fields that require human cognitive ability,learning ability,and reasoning ability.Activation functions are very important because they provide the ability of ...Recently,deep learning has achieved remarkable results in fields that require human cognitive ability,learning ability,and reasoning ability.Activation functions are very important because they provide the ability of artificial neural networks to learn complex patterns through nonlinearity.Various activation functions are being studied to solve problems such as vanishing gradients and dying nodes that may occur in the deep learning process.However,it takes a lot of time and effort for researchers to use the existing activation function in their research.Therefore,in this paper,we propose a universal activation function(UA)so that researchers can easily create and apply various activation functions and improve the performance of neural networks.UA can generate new types of activation functions as well as functions like traditional activation functions by properly adjusting three hyperparameters.The famous Convolutional Neural Network(CNN)and benchmark datasetwere used to evaluate the experimental performance of the UA proposed in this study.We compared the performance of the artificial neural network to which the traditional activation function is applied and the artificial neural network to which theUA is applied.In addition,we evaluated the performance of the new activation function generated by adjusting the hyperparameters of theUA.The experimental performance evaluation results showed that the classification performance of CNNs improved by up to 5%through the UA,although most of them showed similar performance to the traditional activation function.展开更多
In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition,...In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.展开更多
The stability of a periodic oscillation and the global exponential class of recurrent neural networks with non-monotone activation functions and time-varying delays are analyzed. For two sets of activation functions, ...The stability of a periodic oscillation and the global exponential class of recurrent neural networks with non-monotone activation functions and time-varying delays are analyzed. For two sets of activation functions, some algebraic criteria for ascertaining global exponential periodicity and global exponential stability of the class of recurrent neural networks are derived by using the comparison principle and the theory of monotone operator. These conditions are easy to check in terms of system parameters. In addition, we provide a new and efficacious method for the qualitative analysis of various neural networks.展开更多
Activation functions play an essential role in converting the output of the artificial neural network into nonlinear results,since without this nonlinearity,the results of the network will be less accurate.Nonlinearity...Activation functions play an essential role in converting the output of the artificial neural network into nonlinear results,since without this nonlinearity,the results of the network will be less accurate.Nonlinearity is the mission of all nonlinear functions,except for polynomials.The activation function must be dif-ferentiable for backpropagation learning.This study’s objective is to determine the best activation functions for the approximation of each fractal image.Different results have been attained using Matlab and Visual Basic programs,which indi-cate that the bounded function is more helpful than other functions.The non-lin-earity of the activation function is important when using neural networks for coding fractal images because the coefficients of the Iterated Function System are different according to the different types of fractals.The most commonly cho-sen activation function is the sigmoidal function,which produces a positive value.Other functions,such as tansh or arctan,whose values can be positive or negative depending on the network input,tend to train neural networks faster.The coding speed of the fractal image is different depending on the appropriate activation function chosen for each fractal shape.In this paper,we have provided the appro-priate activation functions for each type of system of iterated functions that help the network to identify the transactions of the system.展开更多
This paper describes our implementation of several neural networks built on a field programmable gate array (FPGA) and used to recognize a handwritten digit dataset—the Modified National Institute of Standards and Te...This paper describes our implementation of several neural networks built on a field programmable gate array (FPGA) and used to recognize a handwritten digit dataset—the Modified National Institute of Standards and Technology (MNIST) database. We also propose a novel hardware-friendly activation function called the dynamic Rectifid Linear Unit (ReLU)—D-ReLU function that achieves higher performance than traditional activation functions at no cost to accuracy. We built a 2-layer online training multilayer perceptron (MLP) neural network on an FPGA with varying data width. Reducing the data width from 8 to 4 bits only reduces prediction accuracy by 11%, but the FPGA area decreases by 41%. Compared to networks that use the sigmoid functions, our proposed D-ReLU function uses 24% - 41% less area with no loss to prediction accuracy. Further reducing the data width of the 3-layer networks from 8 to 4 bits, the prediction accuracies only decrease by 3% - 5%, with area being reduced by 9% - 28%. Moreover, FPGA solutions have 29 times faster execution time, even despite running at a 60× lower clock rate. Thus, FPGA implementations of neural networks offer a high-performance, low power alternative to traditional software methods, and our novel D-ReLU activation function offers additional improvements to performance and power saving.展开更多
基金supported by Defence Innovative Research Program(DIRP)Grant(PA No.9015102335)from Defence Research&Technology Office,Ministry of Defence,Singapore。
文摘Background:Excessive heat exposure can lead to hyperthermia in humans,which impairs physical performance and disrupts cognitive function.While heat is a known physiological stressor,it is unclear how severe heat stress affects brain physiology and function.Methods:Eleven healthy participants were subjected to heat stress from prolonged exercise or warm water immersion until their rectal temperatures(T_(re))attained 39.5℃,inducing exertional or passive hyperthermia,respectively.In a separate trial,blended ice was ingested before and during exercise as a cooling strategy.Data were compared to a control condition with seated rest(normothermic).Brain temperature(T_(br)),cerebral perfusion,and task-based brain activity were assessed using magnetic resonance imaging techniques.Results:T_(br)in motor cortex was found to be tightly regulated at rest(37.3℃±0.4℃(mean±SD))despite fluctuations in T_(re).With the development of hyperthermia,T_(br)increases and dovetails with the rising T_(re).Bilateral motor cortical activity was suppressed during high-intensity plantarflexion tasks,implying a reduced central motor drive in hyperthermic participants(T_(re)=38.5℃±0.1℃).Global gray matter perfusion and regional perfusion in sensorimotor cortex were reduced with passive hyperthermia.Executive function was poorer under a passive hyperthermic state,and this could relate to compromised visual processing as indicated by the reduced activation of left lateral-occipital cortex.Conversely,ingestion of blended ice before and during exercise alleviated the rise in both T_(re)and T_(bc)and mitigated heat-related neural perturbations.Conclusion:Severe heat exposure elevates T_(br),disrupts motor cortical activity and executive function,and this can lead to impairment of physical and cognitive performance.
基金The researchers would like to thank the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2025).
文摘Deep learning(DL),derived from the domain of Artificial Neural Networks(ANN),forms one of the most essential components of modern deep learning algorithms.DL segmentation models rely on layer-by-layer convolution-based feature representation,guided by forward and backward propagation.Acritical aspect of this process is the selection of an appropriate activation function(AF)to ensure robustmodel learning.However,existing activation functions often fail to effectively address the vanishing gradient problem or are complicated by the need for manual parameter tuning.Most current research on activation function design focuses on classification tasks using natural image datasets such asMNIST,CIFAR-10,and CIFAR-100.To address this gap,this study proposesMed-ReLU,a novel activation function specifically designed for medical image segmentation.Med-ReLU prevents deep learning models fromsuffering dead neurons or vanishing gradient issues.It is a hybrid activation function that combines the properties of ReLU and Softsign.For positive inputs,Med-ReLU adopts the linear behavior of ReLU to avoid vanishing gradients,while for negative inputs,it exhibits the Softsign’s polynomial convergence,ensuring robust training and avoiding inactive neurons across the training set.The training performance and segmentation accuracy ofMed-ReLU have been thoroughly evaluated,demonstrating stable learning behavior and resistance to overfitting.It consistently outperforms state-of-the-art activation functions inmedical image segmentation tasks.Designed as a parameter-free function,Med-ReLU is simple to implement in complex deep learning architectures,and its effectiveness spans various neural network models and anomaly detection scenarios.
文摘Background and objective:Activated carbon is commonly used as an immobilisation matrix due to its large surface area,making it a highly desirable matrix for use in immobilising enzymes as preparation for use on the industrial scale.The objective of this research is to determine the effectiveness of different acids for functionalisation on immobilisation capacity and also to characterize the functionalized activated carbon for the functional groups present.Materials and methods:Activated carbon was functionalised with three acids(hydrochloric acid,nitric acid and sulphuric acid)along with a control sample washed with distilled water.Immobilisation capacity was calculated with hydrochloric acid functionalized activated carbon(HCl-FAC)giving the highest immobilization capacity(6.022 U/g).Characterisation of the functionalised activated carbon was conducted using FT-IR(Fourier Transform Infra-Red)spectroscopy analysis of the samples with the aim of analyzing the various functional groups present to determine the sample with distinct characteristics thus telling the degree of adsorption of lipase onto the activated carbon powder.Results:HNO3-FAC(functionalized activated carbon)showed a very distinct pattern as a larger number of surface functional groups emerged.The immobilisation on a matrix ensures thermal stability and increased reusability of the enzyme.Therefore,in this research,lipase sourced from Candida antarctica was immobilised on acid functionalised activated carbon.The best acid for functionalisation was found to be hydrochloric acid.Conclusion:Due to the very distinct patterns shown by the FT-IR spectrum of the HNO3-FAC after a fair comparison with others,it allows for a larger number of surface functional groups which will definitely enhance the stability of the enzyme lipase.
基金the Grants from Department of Education of Shandong Province, No.J02K11
文摘BACKGROUND： At present, central cholinergic neuron system is regarded the most major structural basis of cognitive function. Changes in structure of cholinergic neuron system of brain and receptor expression after brain injury can cause cognitive impairment. OBJECTIVE＂ To comparatively observe the intelligence quotient （IQ）, latent period and wave amplitude of P300 event-related potential and the difference of activity of acetylcholinesterase （ACHE） in blood and cerebrospinal fluid between patients with type 2 diabetes mellitus and with non-diabetes mellitus, and analyze the correlation of IQ of cognitive impairment patients with diabetes mellitus with AChE activity, latent period and wave amplitude of P300 event-related potential in cerebrospinal fluid. DESIGN： Correlation analysis of contrast observation SETTING： Department of Endocrinology, Affiliated Hospital of Binzhou Medical College PARTICIPANTS： Totally 32 patients with type 2 diabetes mellitus who received the treatment in the Department of Endocrinology, Affiliated Hospital of Binzhou Medical College between April 2004 and April 2005 were recruited, serving as diabetes mellitus group. They, including 19 male and 13 female, aged 49 to 73 years, with disease course of 4 to 11 years, all met the diagnostic criteria of diabetes mellitus revised by World Health Organization in 1999. Another 30 patients with non-diabetes mellitus who homeochronously underwent lumbar anesthesia in the Department of Surgery and Department of Gynecology were recruited, serving as non-diabetes mellitus group. The 30 patients included 18 male and 12 female, and their age ranged from 46 to 71 years. Informed consents of detected items were obtained from the involved patients. METHODS： ① Evaluation,on IQ： The IQ of involved subjects was evaluated with Chinese Version of the Wechsler Adult Intelligence Scale revised by Gong Yao-xian （WAIS-RC）. WAIS-RC included 6 verbal subscales and 5 performance subscales. The test scores of the 11 subscales integrated into the scores of the whole scale, and the scores on the WAIS-RC included verbal IQ （VlQ）, performance IQ （PIQ） and full scale IQ （FIQ）. FIQ ≤79 scores indicated low IQ and FIQ≤69 indicated intelligence impairment. ② Detection of P300 wave： P300 wave was detected with evoked potential instrument （MYTOPRO, Italian）, and data of latent period and amplitude of P300 event-related potential were automatically shown by computer. ③ Detection of AChE activity in blood and cerebrospinal fluid： Activity of AChE of blood and cerebrospinal fluid was measured with biochemical methods by using CORNING-560 autoanalyzer.④Correlation analysis： Correlation of FIQ with AChE of cerebrospinal fluid and P300 wave of patients with type 2 diabetes mellitus was analyzed, t test was used in intergroup comparison and linear correlation analysis for relevant treatment. MAIN OUTCOME MEASURES： ① Comparison of IQ, latent period and wave amplitude of P300 wave as well as the activity of AChE between two groups. ② Analysis on the correlation of FIQ of patients with type 2 diabetes mellitus with AChE of cerebrospinal fluid and P300 wave. RESULTS： Thirty-two patients with diabetes mellitus and 30 non-diabetes mellitus participated in the result analysis. ①Comparison of IQ, latent period and wave amplitude of P300 wave as well as the activity of AChE between two groups： The scores of VIP, PIQ and FIQ of patients with type 2 diabetes mellitus were （97.4±10.4）. （92.6±8.4） and （95.2±9.7） scores, respectively; and those of patients with non-diabetes mellitus were （104.7±9.6）, （102.5±8.5）and（102.7±8.9） scores, respectively, and P 〈 0.05-0.01 was set in intergroup comparison. The latent period of P300 wave at points Fz , Cz and Pz of patients with type 2 diabetes mellitus was （370.8±41.8）.（371.5±39.1）and （375.1±43.1） ms, respectively, and that of patients with non-diabetes mellitus was （ 332.1 ±28.3 ）, （335.7 ±29.4）and （339.7 ±27.3） ms, respectively, and P 〈 0.01 was set in intergroup comparison; Wave amplitude of P300 of patients with type 2 diabetes mellitus was （8.6±4.1）,（8.6±4.0） and （7.7±4.0） μV, respectively and that of patients with non-diabetes mellitus was （11.9±4.1）,（11.5±4.4） and （10.9±5.0） μV, respectively , and P 〈 0.05-0.01 was set in intergroup comparison; The level of AChE in blood and cerebrospinal fluid of patients with type 2 diabetes mellitus was （235.61 ±50.34）and （17.89±4.46） μkat/L, respectively, which was significantly higher than that of patients with non-diabetes mellitus [（205.03±44.15）and （14.63±0.48） μkat /L, respectively], and P 〈 0.05-0.01 was set in the intergroup comparison. ② Correlation of FIQ value of patients with type 2 diabetes mellitus with AChE of cerebrospinal fluid and P300 wave： The value of FIQ was significantly negatively correlated with the AChE activity of cerebrospinal fluid （r=-0.588 1, P 〈 0.01 ）, significantly negatively correlated with the latent period at points Fz. C and Pz of P300 wave （r= -0.700 5, -0.689 4, -0.688 5, P 〈 0.01 ）, and significantly positively correlated with the amplitude at points Fz . Cz and Pz of P300 wave（r= 0.607 4,0.616 1,0.592 0,P 〈 0.01 ）. CONCLUSION： ① Cognitive impairment of patients with type 2 diabetes mellitus might be related to the increase of activity of AChE in cerebrospinal fluid. ②Combined application of examination of P300 wave and evaluation of IQ is more useful in deciding the state of cognitive function of patients with type 2 diabetes mellitus.
基金supported by the International Publication Research Grant No.RDU223301.
文摘A vehicle engine cooling system is of utmost importance to ensure that the engine operates in a safe temperature range.In most radiators that are used to cool an engine,water serves as a cooling fluid.The performance of a radiator in terms of heat transmission is significantly influenced by the incorporation of nanoparticles into the cooling water.Concentration and uniformity of nanoparticle distribution are the two major factors for the practical use of nanofluids.The shape and size of nanoparticles also have a great impact on the performance of heat transfer.Many researchers are investigating the impact of nanoparticles on heat transfer.This study aims to develop an artificial neural network(ANN)model for predicting the thermal conductivity of an ethylene glycol(EG)/waterbased crystalline nanocellulose(CNC)nanofluid for cooling internal combustion engine.The implementation of an artificial neural network considering different activation functions in the hidden layer is made to find the bestmodel for the cooling of an engine using the nanofluid.Accuracies of the model with different activation functions in artificial neural networks are analyzed for different nanofluid concentrations and temperatures.In artificial neural networks,Levenberg–Marquardt is an optimization approach used with activation functions,including Tansig and Logsig functions in the training phase.The findings of each training,testing,and validation phase are presented to demonstrate the network that provides the highest level of accuracy.The best result was obtained with Tansig,which has a correlation of 0.99903 and an error of 3.7959×10^(–8).It has also been noticed that the Logsig function can also be a good model due to its correlation of 0.99890 and an error of 4.9218×10^(–8).Thus ourANNwith Tansig and Logsig functions demonstrates a high correlation between the actual output and the predicted output.
文摘The effect of lymphotoxin (LT)-containing supernatant produced by lectin-stimulated human lymphocytes on tumor cells and the relation between interleukin-2 (IL-2) and LT were studied in this article. Results showed that LT-containing superna-tants had cytotoxicities on many different kinds of tumor cells from human and mice, that actinomycin D increased the LT activities on target cells and that IL-2 had the ability to increase the cytotoxicity of human PBMC on tumor cells, after being treated with LT, the target cells were more easy to kill by PBMC as well.
文摘The purpose of this study was to address the challenges in predicting and classifying accuracy in modeling Container Dwell Time (CDT) using Artificial Neural Networks (ANN). This objective was driven by the suboptimal outcomes reported in previous studies and sought to apply an innovative approach to improve these results. To achieve this, the study applied the Fusion of Activation Functions (FAFs) to a substantial dataset. This dataset included 307,594 container records from the Port of Tema from 2014 to 2022, encompassing both import and transit containers. The RandomizedSearchCV algorithm from Python’s Scikit-learn library was utilized in the methodological approach to yield the optimal activation function for prediction accuracy. The results indicated that “ajaLT”, a fusion of the Logistic and Hyperbolic Tangent Activation Functions, provided the best prediction accuracy, reaching a high of 82%. Despite these encouraging findings, it’s crucial to recognize the study’s limitations. While Fusion of Activation Functions is a promising method, further evaluation is necessary across different container types and port operations to ascertain the broader applicability and generalizability of these findings. The original value of this study lies in its innovative application of FAFs to CDT. Unlike previous studies, this research evaluates the method based on prediction accuracy rather than training time. It opens new avenues for machine learning engineers and researchers in applying FAFs to enhance prediction accuracy in CDT modeling, contributing to a previously underexplored area.
文摘In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantly degrades image quality.Traditional denoising methods,typically based on filter techniques,often face challenges related to inefficiency and limited adaptability.To address these limitations,this study proposes a novel SAR image denoising algorithm based on an enhanced residual network architecture,with the objective of enhancing the utility of SAR imagery in complex electromagnetic environments.The proposed algorithm integrates residual network modules,which directly process the noisy input images to generate denoised outputs.This approach not only reduces computational complexity but also mitigates the difficulties associated with model training.By combining the Transformer module with the residual block,the algorithm enhances the network's ability to extract global features,offering superior feature extraction capabilities compared to CNN-based residual modules.Additionally,the algorithm employs the adaptive activation function Meta-ACON,which dynamically adjusts the activation patterns of neurons,thereby improving the network's feature extraction efficiency.The effectiveness of the proposed denoising method is empirically validated using real SAR images from the RSOD dataset.The proposed algorithm exhibits remarkable performance in terms of EPI,SSIM,and ENL,while achieving a substantial enhancement in PSNR when compared to traditional and deep learning-based algorithms.The PSNR performance is enhanced by over twofold.Moreover,the evaluation of the MSTAR SAR dataset substantiates the algorithm's robustness and applicability in SAR denoising tasks,with a PSNR of 25.2021 being attained.These findings underscore the efficacy of the proposed algorithm in mitigating speckle noise while preserving critical features in SAR imagery,thereby enhancing its quality and usability in practical scenarios.
基金School-level Educational Reform Project of Hangzhou Normal University(Project No.:HLXYJG202304)。
文摘Objective:To conduct a scoping review on the application status of the Functional Activity Score(FAS)in postoperative active pain management in China,providing a reference for its standardized and normative promotion.Methods:Computerized searches of Chinese and English databases were performed to collect studies published by Chinese scholars from 2005 to July 2025 on the application of FAS in postoperative active pain management.After strict screening,the basic characteristics,application fields,assessment models,evaluation timing,types of functional activities,and clinical outcomes of the included literature were systematically analyzed.Results:A total of 18 studies were included,involving surgical types such as thoracic surgery,general surgery,and orthopedics.All studies adopted FAS combined with the Numeric Rating Scale(NRS)for assessment,with evaluation timing mostly concentrated within 72 hours postoperatively.The selected functional activities primarily included respiration-related and limb movements.Evaluation indicators covered pain control,functional recovery,complications,adverse events,patient experience,and tool assessment,with most studies reporting positive outcomes.Conclusion:FAS can effectively enhance pain control and promote functional recovery in postoperative active pain management in China,demonstrating high clinical value.However,existing studies exhibit inconsistencies in assessment criteria,selection of activity types,and research quality.
基金supported by the National Natural Science Foundation of China(21007033)the Fundamental Research Funds of Shandong University(2015JC017)~~
文摘An electrochemically reduced graphene oxide sample, ERGO_0.8v, was prepared by electrochemical reduction of graphene oxide （GO） at -0.8 V, which shows unique electrocatalytic activity toward tetracycline （TTC） detection compared to the ERGO-12v （GO applied to a negative potential of-1.2 V）, GO, chemically reduced GO （CRGO）-modified glassy carbon electrode （GC） and bare GC electrodes. The redox peaks of TTC on an ERGO-0.8v-modifled glass carbon electrode （GC/ERGO-0.8v） were within 0-0.5 V in a pH 3.0 buffer solution with the oxidation peak current correlating well with TTC concentration over a wide range from 0.1 to 160 mg/L Physical characterizations with Fourier transform infrared （FT-IR）, Raman, and X-ray photoelectron spectroscopies （XPS） demonstrated that the oxygen-containing functional groups on GO diminished after the electrochemical reduction at -0.8 V, yet still existed in large amounts, and the defect density changed as new sp2 domains were formed. These changes demonstrated that this adjustment in the number of oxygen-containing groups might be the main factor affecting the electrocatalytic behavior of ERGO. Additionally, the defect density and sp2 domains also exert a profound influence on this behavior. A possible mechanism for the TTC redox reaction at the GC/ERGO-0.8v electrode is also presented. This work suggests that the electrochemical reduction is an effective method to establish new catalytic activities of GO by setting appropriate parameters.
文摘Objective: to investigate the effect of rehabilitation nursing on activity function in knee meniscus injury. Methods: 60 patients with knee meniscus injury from 12-2020-December 2021. The control group was given routine care, and the rehabilitation nursing group implements routine nursing combined rehabilitation nursing. The pain level, depression, anxiety, activity function, and satisfaction degree were compared between the two groups. Results: pain level, depression, activity function and satisfaction were lower than the control group, P <0.05. Conclusion: in case of knee meniscus injury, it can relieve depression and anxiety, improve activity function and reduce pain and improve satisfaction.
基金This work was partially supported by the research grant of the National University of Singapore(NUS),Ministry of Education(MOE Tier 1).
文摘To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with adaptive centers and widths,which is composed of more than one hidden layer.In the hidden layer of the RBF-activated MLP network(MLPRBF),the outputs of the preceding layer are first linearly transformed and then fed into the univariate Gaussian RBF,which exploits the highly nonlinear property of RBF.Adaptive RBFs might address the issues of saturated outputs,low sensitivity,and vanishing gradients in MLPs activated by other prevailing nonlinear functions.Finally,we apply four MLP networks with the rectified linear unit(ReLU),sigmoid function(sigmoid),hyperbolic tangent function(tanh),and Gaussian RBF as the activation functions to approximate the one-dimensional(1D)sinusoidal function,the analytical solution of viscous Burgers’equation,and the two-dimensional(2D)steady lid-driven cavity flows.Using the same network structure,MLP-RBF generally predicts more accurately and converges faster than the other threeMLPs.MLP-RBF using less hidden layers and/or neurons per layer can yield comparable or even higher approximation accuracy than other MLPs equipped with more layers or neurons.
基金financially supported by the Kerala Agricultural University
文摘The humid agroclimatic conditions of Kerala,India permit the cultivation of an array of bamboo species of which Dendrocalamus strictus Roxb.(Nees.) is an important one on account of its high growth rate and multiple uses. Stand density, a potential tool in controlling the productivity of woody ecosystems, its effect on growth and root distribution patterns may provide a better understanding of productivity optimization especially when bamboo-based intercropping options are considered.Growth attributes of 7-year-old bamboo(D. strictus) stands managed at variable spacing(4×4 m, 6×6 m, 8×8 m,10×10 m, 12×12 m) were studied. Functional root activity among bamboo clumps were also studied using a radio tracer soil injection method in which the radio isotopeP was applied to soil at varying depths and lateral distances from the clump. Results indicate that spacing exerts a profound influence on growth of bamboo. Widely spaced bamboo exhibited higher clump diameters and crown widths while clump heights were better under closer spacing. Clump height was 30% lower and DBH 52%higher at the widest spacing(12×12 m) compared to the closest spacing(4×4 m). With increasing soil depth and lateral distance, root activity decreased significantly. Root activity near the clump base was highest(809 counts per minute, cpm; 50 cm depth and 50 cm lateral distance) at 4×4 m. Tracer study further showed wider distribution of root activity with increase in clump spacing. It may be concluded that the intensive foraging zone of bamboo is within a 50-cm radius around the clump irrespective of spacing. N, P and K content in the upper 20 cm was 2197,21, and 203 kg/ha respectively for the closely spaced bamboo(4×4 m) which were significantly higher than corresponding nutrient content at wider spacings. About 50% of N, P and K were present within the 0–20 cm soil layer, which decreased drastically beyond the 20 cm depth.The results suggest that stand management practices through planting density regulation can modify the resource acquisition patterns of D. strictus which in turn can change growth and productivity considerably. Such information on root activities, spatial and temporal strategies of resource sharing will be helpful in deciding the effective nutrition zone for D. strictus. Further, the study throws light on the spatial distribution of non-competitive zones for productivity optimization yields, especially when intercropping practices are considered.
基金funded by the National Natural Science Foundation of China(NSFC31301843)the National Nonprofit Institute Research Grant of Chinese Academy of Agricultural Sciences(IARRP-202-5)
文摘Exploration of soil environmental characteristics governing soil microbial community structure and activity may improve our understanding of biogeochemical processes and soil quality. The impact of soil environmental characteristics especially organic carbon availability after 15-yr different organic and inorganic fertilizer inputs on soil bacterial community structure and functional metabolic diversity of soil microbial communities were evaluated in a 15-yr fertilizer experiment in Changping County, Beijing, China. The experiment was a wheat-maize rotation system which was established in 1991 including four different fertilizer treatments. These treatments included： a non-amended control（CK）, a commonly used application rate of inorganic fertilizer treatment（NPK）; a commonly used application rate of inorganic fertilizer with swine manure incorporated treatment（NPKM）, and a commonly used application rate of inorganic fertilizer with maize straw incorporated treatment（NPKS）. Denaturing gradient gel electrophoresis（DGGE） of the 16 S r RNA gene was used to determine the bacterial community structure and single carbon source utilization profiles were determined to characterize the microbial community functional metabolic diversity of different fertilizer treatments using Biolog Eco plates. The results indicated that long-term fertilized treatments significantly increased soil bacterial community structure compared to CK. The use of inorganic fertilizer with organic amendments incorporated for long term（NPKM, NPKS） significantly promoted soil bacterial structure than the application of inorganic fertilizer only（NPK）, and NPKM treatment was the most important driver for increases in the soil microbial community richness（S） and structural diversity（H）. Overall utilization of carbon sources by soil microbial communities（average well color development, AWCD） and microbial substrate utilization diversity and evenness indices（H＇ and E） indicated that long-term inorganic fertilizer with organic amendments incorporated（NPKM, NPKS） could significantly stimulate soil microbial metabolic activity and functional diversity relative to CK, while no differences of them were found between NPKS and NPK treatments. Principal component analysis（PCA） based on carbon source utilization profiles also showed significant separation of soil microbial community under long-term fertilization regimes and NPKM treatment was significantly separated from the other three treatments primarily according to the higher microbial utilization of carbohydrates, carboxylic acids, polymers, phenolic compounds, and amino acid, while higher utilization of amines/amides differed soil microbial community in NPKS treatment from those in the other three treatments. Redundancy analysis（RDA） indicated that soil organic carbon（SOC） availability, especially soil microbial biomass carbon（Cmic） and Cmic/SOC ratio are the key factors of soil environmental characteristics contributing to the increase of both soil microbial community structure and functional metabolic diversity in the long-term fertilization trial. Our results showed that long-term inorganic fertilizer and swine manure application could significantly improve soil bacterial community structure and soil microbial metabolic activity through the increases in SOC availability, which could provide insights into the sustainable management of China＇s soil resource.
基金Supported by the National Natural Science Foundation of China(No.81660158No.81160118No.81400372)
文摘AIM： To evaluate the differences in the functional connectivity（FC） of the primary visual cortex（V1） between the youth comitant exotropia（CE） patients and health subjects using resting functional magnetic resonance imaging（f MRI） data.METHODS： Totally, 32 CEs（25 males and 7 females） and 32 healthy control subjects（HCs）（25 males and 7 females） were enrolled in the study and underwent the MRI scanning. Two-sample t-test was used to examine differences in FC maps between the CE patients and HCs. RESULTS： The CE patients showed significantly less FC between the left brodmann area（BA17） and left lingual gyrus/cerebellum posterior lobe, right middle occipital gyrus, left precentral gyrus/postcentral gyrus and right inferior parietal lobule/postcentral gyrus. Meanwhile, CE patients showed significantly less FC between right BA17 and right middle occipital gyrus（BA19, 37）.CONCLUSION： Our findings show that CE involves abnormal FC in primary visual cortex in many regions, which may underlie the pathologic mechanism of impaired fusion and stereoscopic vision in CEs.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2022R1F1A1062953).
文摘Recently,deep learning has achieved remarkable results in fields that require human cognitive ability,learning ability,and reasoning ability.Activation functions are very important because they provide the ability of artificial neural networks to learn complex patterns through nonlinearity.Various activation functions are being studied to solve problems such as vanishing gradients and dying nodes that may occur in the deep learning process.However,it takes a lot of time and effort for researchers to use the existing activation function in their research.Therefore,in this paper,we propose a universal activation function(UA)so that researchers can easily create and apply various activation functions and improve the performance of neural networks.UA can generate new types of activation functions as well as functions like traditional activation functions by properly adjusting three hyperparameters.The famous Convolutional Neural Network(CNN)and benchmark datasetwere used to evaluate the experimental performance of the UA proposed in this study.We compared the performance of the artificial neural network to which the traditional activation function is applied and the artificial neural network to which theUA is applied.In addition,we evaluated the performance of the new activation function generated by adjusting the hyperparameters of theUA.The experimental performance evaluation results showed that the classification performance of CNNs improved by up to 5%through the UA,although most of them showed similar performance to the traditional activation function.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61374094 and 61503338)the Natural Science Foundation of Zhejiang Province,China(Grant No.LQ15F030005)
文摘In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.
基金Supported by the Natural Science Foundation of Hubei Province (2007ABA124)the Youth Project Foundation of Hubei Province Education Department (Q200722001)the Major Foundation of Hubei Province Education Department (D200722002)
文摘The stability of a periodic oscillation and the global exponential class of recurrent neural networks with non-monotone activation functions and time-varying delays are analyzed. For two sets of activation functions, some algebraic criteria for ascertaining global exponential periodicity and global exponential stability of the class of recurrent neural networks are derived by using the comparison principle and the theory of monotone operator. These conditions are easy to check in terms of system parameters. In addition, we provide a new and efficacious method for the qualitative analysis of various neural networks.
文摘Activation functions play an essential role in converting the output of the artificial neural network into nonlinear results,since without this nonlinearity,the results of the network will be less accurate.Nonlinearity is the mission of all nonlinear functions,except for polynomials.The activation function must be dif-ferentiable for backpropagation learning.This study’s objective is to determine the best activation functions for the approximation of each fractal image.Different results have been attained using Matlab and Visual Basic programs,which indi-cate that the bounded function is more helpful than other functions.The non-lin-earity of the activation function is important when using neural networks for coding fractal images because the coefficients of the Iterated Function System are different according to the different types of fractals.The most commonly cho-sen activation function is the sigmoidal function,which produces a positive value.Other functions,such as tansh or arctan,whose values can be positive or negative depending on the network input,tend to train neural networks faster.The coding speed of the fractal image is different depending on the appropriate activation function chosen for each fractal shape.In this paper,we have provided the appro-priate activation functions for each type of system of iterated functions that help the network to identify the transactions of the system.
文摘This paper describes our implementation of several neural networks built on a field programmable gate array (FPGA) and used to recognize a handwritten digit dataset—the Modified National Institute of Standards and Technology (MNIST) database. We also propose a novel hardware-friendly activation function called the dynamic Rectifid Linear Unit (ReLU)—D-ReLU function that achieves higher performance than traditional activation functions at no cost to accuracy. We built a 2-layer online training multilayer perceptron (MLP) neural network on an FPGA with varying data width. Reducing the data width from 8 to 4 bits only reduces prediction accuracy by 11%, but the FPGA area decreases by 41%. Compared to networks that use the sigmoid functions, our proposed D-ReLU function uses 24% - 41% less area with no loss to prediction accuracy. Further reducing the data width of the 3-layer networks from 8 to 4 bits, the prediction accuracies only decrease by 3% - 5%, with area being reduced by 9% - 28%. Moreover, FPGA solutions have 29 times faster execution time, even despite running at a 60× lower clock rate. Thus, FPGA implementations of neural networks offer a high-performance, low power alternative to traditional software methods, and our novel D-ReLU activation function offers additional improvements to performance and power saving.
