基于ANFIS的太阳能-空气源热泵供暖系统温度控制研究

针对太阳能-空气源热泵供暖系统运行环境复杂多变,模糊控制器的设计高度依赖人工经验的问题,提出一种基于自适应神经模糊推理系统(ANFIS)改进的模糊控制方法。该方法利用ANFIS在复杂系统建模中的优势,结合供暖系统温度响应特性和实际运行数据,建立联合供暖系统变工况ANFIS模型,生成与系统性能适配的模糊规则库并传递给模糊控制器执行。Matlab/Simulink仿真对比试验表明,与单一的模糊控制相比,该方法的控制精度提高了17.65%,调节时间缩短了36.4%,具有更高的控制精度和响应速度。

基于ANFIS系统的无刷直流电机控制仿真研究

无刷直流电机运用环境多变复杂,众多不确定因素都会影响无刷直流电机运行的稳定性和响应速度。传统的模糊控制参数调整困难、性能不稳定、计算开销大。针对无刷直流电机速度控制的优化,本文提出了一种采用评论家学习方案下循环全局反馈的ANFIS系统,其中包括三层级联神经网络和模糊控制算法的结合。ANFIS系统通过采样无刷直流电机实际转速,对比参考转速,实现对PID参数的预测;同时ANFIS系统采用双曲正切作为传递函数来调整权值,缩放共轭梯度法作为优化器来减小训练误差,减法聚类方法来提高预测的适应性和准确性。

基于ANFIS-IPD的飞行模拟器座椅舒适度评价模型

为提升现有飞行模拟器座椅舒适度,减轻驾驶员长时间训练的疲劳感,基于自适应神经模糊推理系统(Adaptive Network-based Fuzzy Inference System,ANFIS)和理想压力分布(Ideal Pressure Distribution,IPD)构建一种飞行模拟器座椅舒适度评价模型。通过座椅压力分布采集系统获取压力分布数据,采用IPD将所得数据归一化作为模型输入数据,同时收集受试人员主观评分作为模型输出数据。采用非均匀有理B样条曲线(Non-Uniform Rational B-Splines,NURBS)对座椅进行改进设计,将处理后的试验数据通过ANFIS工具训练模型进行验证,并用评价模型评估设计方案及优越性。结果表明:该评价模型对飞行模拟器座椅舒适度有较好的预测能力,为提升飞行模拟器座椅舒适度提供指导和参考。

基于ANFIS-LSSVM的计算颜色恒常性算法研究

计算颜色恒常性是指消除场景光源的影响从而再现物体真实颜色的能力。目前,深度神经网络的应用使颜色恒常性精度显著提高,但大多数深度学习算法训练时间长、计算复杂度高,且需要大量的训练样本。针对此问题,提出了一种结合自适应神经模糊推理系统(ANFIS)和最小二乘支持向量机(LSSVM)的简单有效的方法。该方法分为训练和预测两个阶段:在训练阶段,首先提取图像特征分别训练ANFIS、LSSVM两种初始光源估计模型,接着利用核函数变换将两种模型融合,然后利用预留训练样本进一步训练得到多元线性回归光源估计模型;在预测阶段,提取测试图像特征后,直接由训练所得模型预测得到该测试图像最终的场景光源颜色值。实验结果表明,与深度学习方法相比,本文所提方法计算复杂度较低,即使在小训练样本中也能有很好的光源估计性能。

基于PSO-ANFIS模型的矩形薄板荷载情况反演

荷载情况反演在汽车工程和医学等领域有重要意义,目前常用的方法普遍存在需要的观测点较多、计算量大和计算效率低的问题。为了通过少量观测点的挠度高效准确地反演矩形薄板荷载情况,建立了基于粒子群算法(particle swarm optimization,PSO)改进自适应神经模糊网络(adaptive network-based fuzzy inference system,ANFIS)的反演模型。利用解析法求解矩形薄板在不同集中荷载作用下的挠度作为训练样本,输入4个观测点的挠度,再利用粒子群算法对自适应神经模糊网络的适应度寻优,反演集中荷载的位置和大小。结果显示,PSO算法可以有效提高ANFIS模型的精度,ANFIS迭代次数的增加能提高精度。PSO-ANFIS模型中荷载位置x_(F)、y_(F)和荷载大小F的最大残差分别为0.027 m、0.025 m和0.126 N,最大相对误差分别为5.00%、4.40%和4.50%。

基于递阶ANFIS树的室内定位算法研究

室内指纹定位算法易受到多种因素的影响,造成指纹数据集的模糊性。针对应用在室内定位中的自适应神经模糊推理系统(ANFIS),随着模糊系统输入参数的增加,造成ANFIS的维数灾难和计算的复杂性等问题,提出了一种基于递阶自适应神经模糊推理系统树(HANFIS-Tree)的室内定位算法。将整体ANFIS拆分为互联型的HANFIS-Tree结构,减少模糊规则数量,以此提高了系统的计算效率和模糊系统的可解释性,同时采用改进的特征权重算法选取与坐标位置相关性较高的信号强度(RSSI)之差作为输入参数,提高了系统的定位精度,并且引入减法聚类算法初始化输入参数,提高了系统的收敛速度。实验结果表明,与ANFIS相比,HANFIS-Tree在室内定位算法中,横坐标上定位精度提高了3.5cm,纵坐标上运算效率均提高了约1倍。

基于SSA-ANFIS模型的BDS-3卫星钟差短期预报

针对卫星钟差时间序列具有非线性和非平稳的特性,以及趋势分量与随机分量相互干扰可能会影响预报精度的问题,提出一种以奇异谱分析(singular spectrum analysis, SSA)为基础,融合自适应模糊神经网络(adaptive neuro-fuzzy inference system, ANFIS)的卫星钟差预报模型SSA-ANFIS。首先利用SSA对钟差一次差序列进行分解和重构,从而得到趋势项和残差项;然后,使用ANFIS对重构分量进行预报,并将预报结果叠加还原,得到最终预报钟差值;最后,通过实验对比SSA-ANFIS与GM、QP、LSTM和ANFIS模型的预报效果。结果表明,相较于LSTM和ANFIS模型,该模型预报精度分别提高25.7%~40.7%和39.4%~45.7%。

Peripheral blood RNA biomarkers can predict lesion severity in degenerative cervical myelopathy

Degenerative cervical myelopathy is a common cause of spinal cord injury,with longer symptom duration and higher myelopathy severity indicating a worse prognosis.While numerous studies have investigated serological biomarkers for acute spinal cord injury,few studies have explored such biomarkers for diagnosing degenerative cervical myelopathy.This study involved 30 patients with degenerative cervical myelopathy(51.3±7.3 years old,12 women and 18 men),seven healthy controls(25.7±1.7 years old,one woman and six men),and nine patients with cervical spondylotic radiculopathy(51.9±8.6 years old,three women and six men).Analysis of blood samples from the three groups showed clear differences in transcriptomic characteristics.Enrichment analysis identified 128 differentially expressed genes that were enriched in patients with neurological disabilities.Using least absolute shrinkage and selection operator analysis,we constructed a five-gene model(TBCD,TPM2,PNKD,EIF4G2,and AP5Z1)to diagnose degenerative cervical myelopathy with an accuracy of 93.5%.One-gene models(TCAP and SDHA)identified mild and severe degenerative cervical myelopathy with accuracies of 83.3%and 76.7%,respectively.Signatures of two immune cell types(memory B cells and memory-activated CD4^(+)T cells)predicted levels of lesions in degenerative cervical myelopathy with 80%accuracy.Our results suggest that peripheral blood RNA biomarkers could be used to predict lesion severity in degenerative cervical myelopathy.

基于ANFIS的锅炉故障诊断研究

随着现代社会对电力需求的不断增加和先进火力发电系统的日益复杂,提高系统的性能和可靠性变得越来越重要。故障诊断系统可在噪声测量条件下自动补偿不利影响。为提高直流锅炉的过程监控能力和故障诊断的准确性,基于各测量传感器间的强相关作用,提出基于6种ANFIS的数据驱动故障诊断方法,每个ANFIS分类器均可诊断一种特定锅炉系统故障。通过不同场景的测试仿真,验证了所提ANFIS在噪声测量条件下对锅炉6种主要故障诊断的有效性和性能。

The autophagy-lysosome pathway:a potential target in the chemical and gene therapeutic strategies for Parkinson’s disease

Parkinson’s disease is a common neurodegenerative disease with movement disorders associated with the intracytoplasmic deposition of aggregate proteins such asα-synuclein in neurons.As one of the major intracellular degradation pathways,the autophagy-lysosome pathway plays an important role in eliminating these proteins.Accumulating evidence has shown that upregulation of the autophagy-lysosome pathway may contribute to the clearance ofα-synuclein aggregates and protect against degeneration of dopaminergic neurons in Parkinson’s disease.Moreover,multiple genes associated with the pathogenesis of Parkinson’s disease are intimately linked to alterations in the autophagy-lysosome pathway.Thus,this pathway appears to be a promising therapeutic target for treatment of Parkinson’s disease.In this review,we briefly introduce the machinery of autophagy.Then,we provide a description of the effects of Parkinson’s disease–related genes on the autophagy-lysosome pathway.Finally,we highlight the potential chemical and genetic therapeutic strategies targeting the autophagy–lysosome pathway and their applications in Parkinson’s disease.

Dysregulation of genes involved in the long-chain fatty acid transport in pancreatic ductal adenocarcinoma

BACKGROUND Pancreatic ductal adenocarcinoma(PDAC)is an aggressive lethal malignancy with limited options for treatment and a 5-year survival rate of 11%in the United States.As for other types of tumors,such as colorectal cancer,aberrant de novo lipid synthesis and reprogrammed lipid metabolism have been suggested to be associated with PDAC development and progression.AIM To identify the possible involvement of lipid metabolism in PDAC by analyzing in tumoral and non-tumoral tissues the expression level of the most relevant genes involved in the long-chain fatty acid(FA)import into cell.METHODS A gene expression analysis of FASN,CD36,SLC27A1,SLC27A2,SLC27A3,SLC27A4,SLC27A5,ACSL1,and ACSL3 was performed by qRT-PCR in 24 tumoral PDAC tissues and 11 samples from non-tumoral pancreatic tissues obtained via fine needle aspiration or via surgical resection.The genes were considered significantly dysregulated between the groups when the p value was<0.05 and the fold change(FC)was≤0.5 and≥2.RESULTS We found that three FA transporters and two long-chain acyl-CoA synthetases genes were significantly upregulated in the PDAC tissue compared to the non-tumoral tissue:SLC27A2(FC=5.66;P=0.033),SLC27A3(FC=2.68;P=0.040),SLC27A4(FC=3.13;P=0.033),ACSL1(FC=4.10;P<0.001),and ACSL3(FC=2.67;P=0.012).We further investigated any possible association between the levels of the analyzed mRNAs and the specific characteristics of the tumors,including the anatomic location,the lymph node involvement,and the presence of metastasis.A significant difference in the expression of SLC27A3(FC=3.28;P=0.040)was found comparing patients with and without lymph nodes involvement with an overexpression of this transcript in 17 patients presenting tumoral cells in the lymph nodes.CONCLUSION Despite the low number of patients analyzed,these preliminary results seem to be promising.Addressing lipid metabolism through a broad strategy could be a beneficial way to treat this malignancy.Future in vitro and in vivo studies on these genes may offer important insights into the mechanisms linking PDAC with the long-chain FA import pathway.

Recovery of the injured neural system through gene delivery to surviving neurons in Parkinson’s disease

A critical unaddressed problem in Parkinson’s disease is the lack of therapy that slows or hampers neurodegeneration.While medications effectively manage symptoms,they offer no long-term benefit because they fail to address the underlying neuronal loss.This highlights that the elusive goals of halting progression and restoring damaged neurons limit the long-term impact of current approaches.Recent clinical trials using gene therapy have demonstrated the safety of various vector delivery systems,dosages,and transgenes expressed in the central nervous system,signifying tangible and substantial progress in applying gene therapy as a promising Parkinson’s disease treatment.Intriguingly,at diagnosis,many dopamine neurons remain in the substantia nigra,offering a potential window for recovery and survival.We propose that modulating these surviving dopamine neurons and axons in the substantia nigra and striatum using gene therapy offers a potentially more impactful therapeutic approach for future research.Moreover,innovative gene therapies that focus on preserving the remaining elements may have significant potential for enhancing long-term outcomes and the quality of life for patients with Parkinson’s disease.In this review,we provide a perspective on how gene therapy can protect vulnerable elements in the substantia nigra and striatum,offering a novel approach to addressing Parkinson’s disease at its core.

AAV2-PDE6B restores retinal structure and function in the retinal degeneration 10 mouse model of retinitis pigmentosa by promoting phototransduction and inhibiting apoptosis

Retinitis pigmentosa is a group of inherited diseases that lead to retinal degeneration and photoreceptor cell death.However,there is no effective treatment for retinitis pigmentosa caused by PDE6B mutation.Adeno-associated virus(AAV)-mediated gene therapy is a promising strategy for treating retinitis pigmentosa.The aim of this study was to explore the molecular mechanisms by which AAV2-PDE6B rescues retinal function.To do this,we injected retinal degeneration 10(rd10)mice subretinally with AAV2-PDE6B and assessed the therapeutic effects on retinal function and structure using dark-and light-adapted electroretinogram,optical coherence tomography,and immunofluorescence.Data-independent acquisition-mass spectrometry-based proteomic analysis was conducted to investigate protein expression levels and pathway enrichment,and the results from this analysis were verified by real-time polymerase chain reaction and western blotting.AAV2-PDE6B injection significantly upregulated PDE6βexpression,preserved electroretinogram responses,and preserved outer nuclear layer thickness in rd10 mice.Differentially expressed proteins between wild-type and rd10 mice were closely related to visual perception,and treating rd10 mice with AAV2-PDE6B restored differentially expressed protein expression to levels similar to those seen in wild-type mice.Kyoto Encyclopedia of Genes and Genome analysis showed that the differentially expressed proteins whose expression was most significantly altered by AAV2-PDE6B injection were enriched in phototransduction pathways.Furthermore,the phototransductionrelated proteins Pde6α,Rom1,Rho,Aldh1a1,and Rbp1 exhibited opposite expression patterns in rd10 mice with or without AAV2-PDE6B treatment.Finally,Bax/Bcl-2,p-ERK/ERK,and p-c-Fos/c-Fos expression levels decreased in rd10 mice following AAV2-PDE6B treatment.Our data suggest that AAV2-PDE6B-mediated gene therapy promotes phototransduction and inhibits apoptosis by inhibiting the ERK signaling pathway and upregulating Bcl-2/Bax expression in retinitis pigmentosa.

Heterogeneity of mature oligodendrocytes in the central nervous system

Mature oligodendrocytes form myelin sheaths that are crucial for the insulation of axons and efficient signal transmission in the central nervous system.Recent evidence has challenged the classical view of the functionally static mature oligodendrocyte and revealed a gamut of dynamic functions such as the ability to modulate neuronal circuitry and provide metabolic support to axons.Despite the recognition of potential heterogeneity in mature oligodendrocyte function,a comprehensive summary of mature oligodendrocyte diversity is lacking.We delve into early 20th-century studies by Robertson and Río-Hortega that laid the foundation for the modern identification of regional and morphological heterogeneity in mature oligodendrocytes.Indeed,recent morphologic and functional studies call into question the long-assumed homogeneity of mature oligodendrocyte function through the identification of distinct subtypes with varying myelination preferences.Furthermore,modern molecular investigations,employing techniques such as single cell/nucleus RNA sequencing,consistently unveil at least six mature oligodendrocyte subpopulations in the human central nervous system that are highly transcriptomically diverse and vary with central nervous system region.Age and disease related mature oligodendrocyte variation denotes the impact of pathological conditions such as multiple sclerosis,Alzheimer's disease,and psychiatric disorders.Nevertheless,caution is warranted when subclassifying mature oligodendrocytes because of the simplification needed to make conclusions about cell identity from temporally confined investigations.Future studies leveraging advanced techniques like spatial transcriptomics and single-cell proteomics promise a more nuanced understanding of mature oligodendrocyte heterogeneity.Such research avenues that precisely evaluate mature oligodendrocyte heterogeneity with care to understand the mitigating influence of species,sex,central nervous system region,age,and disease,hold promise for the development of therapeutic interventions targeting varied central nervous system pathology.

Pan-TRK positive uterine sarcoma in immunohistochemistry without neurotrophic tyrosine receptor kinase gene fusions:A case report

BACKGROUND The classification of uterine sarcomas is based on distinctive morphological and immunophenotypic characteristics,increasingly supported by molecular genetic diagnostics.Data on neurotrophic tyrosine receptor kinase(NTRK)gene fusionpositive uterine sarcoma,potentially aggressive and morphologically similar to fibrosarcoma,are limited due to its recent recognition.Pan-TRK immunohistochemistry(IHC)analysis serves as an effective screening tool with high sensitivity and specificity for NTRK-fusion malignancies.CASE SUMMARY We report a case of a malignant mesenchymal tumor originating from the uterine cervix,which was pan-TRK IHC-positive but lacked NTRK gene fusions,accompanied by a brief literature review.A 55-year-old woman presented to the emergency department with abdominal pain and distension,exhibiting significant ascites and multiple solid pelvic masses.Pelvic examination revealed a tumor encompassing the uterine cervix,extending to the vagina and uterine corpus.A punch biopsy of the cervix indicated NTRK sarcoma with positive immunochemical pan-TRK stain.However,subsequent next generation sequencing revealed no NTRK gene fusion,leading to a diagnosis of poorly differentiated,advanced-stage sarcoma.CONCLUSION The clinical significance of NTRK gene fusion lies in potential treatment with TRK inhibitors for positive sarcomas.Identifying such rare tumors is crucial due to the potential applicability of tropomyosin receptor kinase inhibitor treatment.

Genetic and epigenetic alterations associated with gestational diabetes mellitus and adverse neonatal outcomes

Gestational diabetes mellitus(GDM)is a metabolic disorder,recognised during 24-28 weeks of pregnancy.GDM is linked with adverse newborn outcomes such as macrosomia,premature delivery,metabolic disorder,cardiovascular,and neurological disorders.Recent investigations have focused on the correlation of genetic factors such asβ-cell function and insulin secretary genes(transcription factor 7 like 2,potassium voltage-gated channel subfamily q member 1,adipo-nectin etc.)on maternal metabolism during gestation leading to GDM.Epigenetic alterations like DNA methylation,histone modification,and miRNA expression can influence gene expression and play a dominant role in feto-maternal meta-bolic pathways.Interactions between genes and environment,resulting in differ-ential gene expression patterns may lead to GDM.Researchers suggested that GDM women are more susceptible to insulin resistance,which alters intrauterine surroundings,resulting hyperglycemia and hyperinsulinemia.Epigenetic modi-fications in genes affecting neuroendocrine activities,and metabolism,increase the risk of obesity and type 2 diabetes in offspring.There is currently no treatment or effective preventive method for GDM,since the molecular processes of insulin resistance are not well understood.The present review was undertaken to un-derstand the pathophysiology of GDM and its effects on adverse neonatal out-comes.In addition,the study of genetic and epigenetic alterations will provide lead to researchers in the search for predictive molecular biomarkers.

Autophagy-targeting modulation to promote peripheral nerve regeneration

Nerve regeneration following traumatic peripheral nerve injuries and neuropathies is a complex process modulated by diverse factors and intricate molecular mechanisms.Past studies have focused on factors that stimulate axonal outgrowth and myelin regeneration.However,recent studies have highlighted the pivotal role of autophagy in peripheral nerve regeneration,particularly in the context of traumatic injuries.Consequently,autophagy-targeting modulation has emerged as a promising therapeutic approach to enhancing peripheral nerve regeneration.Our current understanding suggests that activating autophagy facilitates the rapid clearance of damaged axons and myelin sheaths,thereby enhancing neuronal survival and mitigating injury-induced oxidative stress and inflammation.These actions collectively contribute to creating a favorable microenvironment for structural and functional nerve regeneration.A range of autophagyinducing drugs and interventions have demonstrated beneficial effects in alleviating peripheral neuropathy and promoting nerve regeneration in preclinical models of traumatic peripheral nerve injuries.This review delves into the regulation of autophagy in cell types involved in peripheral nerve regeneration,summarizing the potential drugs and interventions that can be harnessed to promote this process.We hope that our review will offer novel insights and perspectives on the exploitation of autophagy pathways in the treatment of peripheral nerve injuries and neuropathies.

AAV-mediated expression of p65shRNA and bone morphogenetic protein 4 synergistically enhances chondrocyte regeneration

BACKGROUND:Adeno-associated virus(AAV)gene therapy has been proven to be reliable and safe for the treatment of osteoarthritis in recent years.However,given the complexity of osteoarthritis pathogenesis,single gene manipulation for the treatment of osteoarthritis may not produce satisfactory results.Previous studies have shown that nuclear factorκB could promote the inflammatory pathway in osteoarthritic chondrocytes,and bone morphogenetic protein 4(BMP4)could promote cartilage regeneration.OBJECTIVE:To test whether combined application of AAV-p65shRNA and AAV-BMP4 will yield the synergistic effect on chondrocytes regeneration and osteoarthritis treatment.METHODS:Viral particles containing AAV-p65-shRNA and AAV-BMP4 were prepared.Their efficacy in inhibiting inflammation in chondrocytes and promoting chondrogenesis was assessed in vitro and in vivo by transfecting AAV-p65-shRNA or AAV-BMP4 into cells.The experiments were divided into five groups:PBS group;osteoarthritis group;AAV-BMP4 group;AAV-p65shRNA group;and BMP4-p65shRNA 1:1 group.Samples were collected at 4,12,and 24 weeks postoperatively.Tissue staining,including safranin O and Alcian blue,was applied after collecting articular tissue.Then,the optimal ratio between the two types of transfected viral particles was further investigated to improve the chondrogenic potential of mixed cells in vivo.RESULTS AND CONCLUSION:The combined application of AAV-p65shRNA and AAV-BMP4 together showed a synergistic effect on cartilage regeneration and osteoarthritis treatment.Mixed cells transfected with AAV-p65shRNA and AAV-BMP4 at a 1:1 ratio produced the most extracellular matrix synthesis(P<0.05).In vivo results also revealed that the combination of the two viruses had the highest regenerative potential for osteoarthritic cartilage(P<0.05).In the present study,we also discovered that the combined therapy had the maximum effect when the two viruses were administered in equal proportions.Decreasing either p65shRNA or BMP4 transfected cells resulted in less collagen II synthesis.This implies that inhibiting inflammation by p65shRNA and promoting regeneration by BMP4 are equally important for osteoarthritis treatment.These findings provide a new strategy for the treatment of early osteoarthritis by simultaneously inhibiting cartilage inflammation and promoting cartilage repair.

ANFIS在植被叶绿素含量高光谱反演中的应用

利用ASD便携式野外光谱仪和SPAD-502叶绿素计实测了落叶阔叶树法国梧桐、毛白杨叶片的高光谱反射率与叶片绿度,建立了10个常见植被指数叶绿素含量估算模型,并采用相关系数较大波段作为BP人工神经网络模型(ANN-BP)的输入变量进行了叶绿素含量的估算,将自适应神经模糊推理系统(ANFIS)应用到植被叶绿素含量高光谱反演中。结果表明:10个常见植被指数中归一化植被指数可以较为精确反演叶绿素含量,法国梧桐、毛白杨归一化植被指数回归模型确定性系数R2分别为0.795 7和0.754 6,法国梧桐、毛白杨ANN-BP预测值与实测值之间的线性回归的确定性系数R2分别为0.935 2和0.917 1,ANFIS可以大大提高反演精度,法国梧桐、毛白杨预测值与实测值之间的线性回归的确定性系数R2分别为0.9998和0.995 6,是一种良好的植被叶绿素含量高光谱反演模式。

应用自适应神经模糊推理系统(ANFIS)的ET_0预测

参照作物腾发量是计算作物需水量和进行灌溉预报的基础要素。该文利用自适应神经模糊推理系统(ANFIS)所具有的直接通过模糊推理实现输入层与输出层之间非线性映射能力,和神经网络的信息存储和学习能力,将其应用于参照作物腾发量预测中。根据相关分析,输入变量选择日照时数和日最高气温;用5年共1827个数据组对系统进行训练,建立了参照作物腾发量预测系统。利用该系统对近年213个数据组进行了实际预测,与Penman-Monteith方法计算结果进行比较,结果相关性良好。