期刊文献+
共找到5篇文章
< 1 >
每页显示 20 50 100
Application of the back-error propagation artificial neural network(BPANN) on genetic variants in the PPAR-γ and RXR-α gene and risk of metabolic syndrome in a Chinese Han population 被引量:3
1
作者 Xu Zhao Kang Xu +11 位作者 Hui Shi Jinluo Cheng Jianhua Ma Yanqin Gao Qian Li Xinhua Ye Ying Lu Xiaofang Yu Juan Du Wencong Du Qing Ye Ling Zhou 《The Journal of Biomedical Research》 CAS 2014年第2期114-122,共9页
This study was aimed to explore the associations between the combined effects of several polymorphisms in the PPAR-γ and RXR-α gene and environmental factors with the risk of metabolic syndrome by back-error propaga... This study was aimed to explore the associations between the combined effects of several polymorphisms in the PPAR-γ and RXR-α gene and environmental factors with the risk of metabolic syndrome by back-error propaga- tion artificial neural network (BPANN). We established the model based on data gathered from metabolic syndrome patients (n = 1012) and normal controls (n = 1069) by BPANN. Mean impact value (MIV) for each input variable was calculated and the sequence of factors was sorted according to their absolute MIVs. Generalized multifactor dimensionality reduction (GMDR) confirmed a joint effect of PPAR-9" and RXR-a based on the results from BPANN. By BPANN analysis, the sequences according to the importance of metabolic syndrome risk fac- tors were in the order of body mass index (BMI), serum adiponectin, rs4240711, gender, rs4842194, family history of type 2 diabetes, rs2920502, physical activity, alcohol drinking, rs3856806, family history of hypertension, rs1045570, rs6537944, age, rs17817276, family history of hyperlipidemia, smoking, rs1801282 and rs3132291. However, no polymorphism was statistically significant in multiple logistic regression analysis. After controlling for environmental factors, A1, A2, B1 and B2 (rs4240711, rs4842194, rs2920502 and rs3856806) models were the best models (cross-validation consistency 10/10, P = 0.0107) with the GMDR method. In conclusion, the interaction of the PPAR-γ and RXR-α gene could play a role in susceptibility to metabolic syndrome. A more realistic model is obtained by using BPANN to screen out determinants of diseases of multiple etiologies like metabolic syndrome. 展开更多
关键词 back-error propagation artificial neural network (BPANN) metabolic syndrome peroxisome prolif-erators activated receptor-γ (PPAR) gene retinoid X receptor-α (RXR-α) gene ADIPONECTIN
下载PDF
Anti-apoptotic effect of Shudipingchan granule in the substantia nigra of rat models of Parkinson's disease 被引量:7
2
作者 Qing Ye Xiao-lei Yuan +3 位作者 Jing He Jie Zhou Can-xingYuan Xu-ming Yang 《Neural Regeneration Research》 SCIE CAS CSCD 2016年第10期1625-1632,共8页
Levodopa is the gold-standard treatment for Parkinson's disease. However, although it alleviates the clinical symptoms, it cannot delay the progressive apoptosis of dopaminergic neurons or prevent motor complications... Levodopa is the gold-standard treatment for Parkinson's disease. However, although it alleviates the clinical symptoms, it cannot delay the progressive apoptosis of dopaminergic neurons or prevent motor complications in the long term. In the present study, we investigated the effect of Shudipingchan granule on neuronal apoptosis in a rat model of Parkinson's disease, established by injecting 6-hydroxydopamine into the substantia nigra pars compacta and ventral tegmental area. We then administered levodopa (20 mg/kg intraperitoneally, twice daily) with or without Shudipingchan granule (7.5 mL/kg intragastrically, twice daily), for 4 weeks. The long-term use of levodopa accel- erated apoptosis of nigral cells and worsened behavioral symptoms by activating the extracellular signal-regulated kinase pathway and downstream apoptotic factors. However, administration of Shudipingchan granule with levodopa reduced expression of phosphorylated extracellular signal-regulated kinase 1/2 and Bax, increased tyrosine hydroxylase and Bcl-2, reduced apoptosis in the substantia nigra, and markedly improved dyskinesia. These findings suggest that Shudipingchan granule suppresses neuronal apoptosis by inhibiting the hyper- phosphorylation of extracellular signal-regulated kinase and downregulating expression of anti-apoptotic genes. Shudipingchan granule, used in combination with levodopa, can effectively reduce the symptoms of Parkinson's disease. 展开更多
关键词 nerve regeneration Parkinson's disease LEVODOPA substantia nigra APOPTOSIS Shudipingchan granule extracellular signal-regulatedkinase pathway behavior neural rege eration
下载PDF
双臂空间机器人姿态、关节协调运动基于RBF神经网络的自适应控制算法 被引量:10
3
作者 郭益深 陈力 《应用数学和力学》 CSCD 北大核心 2008年第9期1028-1036,共9页
讨论了载体位置无控、姿态受控情况下,双臂空间机器人姿态、关节协调运动的控制问题.由Lagrange第二类方法及系统动量守恒关系,建立了漂浮基双臂空间机器人的系统动力学方程.以此为基础,借助于RBF神经网络技术、GL矩阵及其乘积算子定义... 讨论了载体位置无控、姿态受控情况下,双臂空间机器人姿态、关节协调运动的控制问题.由Lagrange第二类方法及系统动量守恒关系,建立了漂浮基双臂空间机器人的系统动力学方程.以此为基础,借助于RBF神经网络技术、GL矩阵及其乘积算子定义,对双臂空间机器人系统进行了神经网络系统建模;之后针对双臂空间机器人所有惯性参数均未知的情况,设计了双臂空间机器人载体姿态与机械臂各关节协调运动基于RBF神经网络的自适应控制算法.提出的控制算法不要求系统动力学方程具有惯常的关于惯性参数的线性性质,且无需预知系统惯性参数的任何信息,也无需对神经网络进行离线训练、学习,因此更适于实时应用.一个平面漂浮基双臂空间机器人系统的数值仿真,证实了该控制算法的有效性. 展开更多
关键词 漂浮基双臂空间机器人 RBF神经网络 GL矩阵及其乘积算子 协调运动 自适应控制算法
下载PDF
基于GPU深度学习的家用智能垃圾桶设计 被引量:2
4
作者 李美锟 杨明夏 凌滨 《电子测试》 2021年第1期8-11,共4页
垃圾分类成为日常所需,为解决垃圾分类的问题,使投放垃圾变得更加环保高效,本文设计了基于GPU深度学习的智能垃圾桶。应用Tensorflow深度学习框架,使用GPU加速训练,并结合硬件树莓派处理垃圾的图像信息,通过单片机控制步进电机实现垃圾... 垃圾分类成为日常所需,为解决垃圾分类的问题,使投放垃圾变得更加环保高效,本文设计了基于GPU深度学习的智能垃圾桶。应用Tensorflow深度学习框架,使用GPU加速训练,并结合硬件树莓派处理垃圾的图像信息,通过单片机控制步进电机实现垃圾分类。本设计具有分类准确度高,使用简单便捷,可实现垃圾分类的清洁化、高效化、智能化。 展开更多
关键词 智能分类垃圾桶 神经网络 GPU加速 单片机控制
下载PDF
计及可再生能源接入配电网的负荷预测和优化
5
作者 翟哲 余杰文 +1 位作者 杜洋 曹泽江 《电子技术应用》 2024年第11期35-41,共7页
目前,可再生能源大量接入配电网,但是太阳能、风能、光伏及风电等可再生能源的间歇性和随机性不可避免地会造成配电网的波动。考虑电网内可再生能源发电功率与用电负荷随时间变化的特点,提出一种基于小波变换和神经网络的可再生能源接... 目前,可再生能源大量接入配电网,但是太阳能、风能、光伏及风电等可再生能源的间歇性和随机性不可避免地会造成配电网的波动。考虑电网内可再生能源发电功率与用电负荷随时间变化的特点,提出一种基于小波变换和神经网络的可再生能源接入配电网的负荷预测和优化方法。首先采集配电网的发电与负荷数据,利用小波变换处理收集到的数据,得到局部尺度和频率分解的特征参数,建立神经网络预测模型;然后,对经过小波变换后得到的特征参数进行训练,根据预测负荷对可再生能源的发电量进行调节,保持配电网供需侧的动态平衡。结果表明,所提方法能够对负荷进行有效预测,通过提前预测负荷量,保证配电网用电稳定性的同时,最大化利用可再生能源。 展开更多
关键词 云技术 神经网络 小波变换 风光发电 负荷预测 发电优化
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部