共查询到16条相似文献,搜索用时 62 毫秒
1.
2.
血清自体荧光光谱联合肿瘤标志物群在肺癌诊断中的价值 总被引:3,自引:0,他引:3
血清自体荧光光谱可以反映血清中癌细胞在代谢过程中发生的异常改变而导致的血清中荧光物质的成分、含量及微环境的变化,可作为癌症辅助诊断的一种新方法。利用荧光光谱分析技术,探讨了肺癌、肺良性疾病以及正常人血清的荧光光谱的异同,建立了血清荧光光谱检测的方法。同时联合肿瘤标志物群CEA, NSE, SCC-Ag, CYFRA21-1和p16甲基化,并运用人工神经网络技术和Fisher线性判别分析法分别建立了肺癌的诊断预测模型,并用ROC判别法对其预测结果进行比较。结果表明,荧光光谱联合肿瘤标志物建立的人工神经网络模型的预测效果优于单纯的荧光光谱神经网络模型,判别效果优于Fisher线性判别分析。 相似文献
3.
4.
沉积岩中放射性元素铀、钍、钾的含量主要取决于岩石中泥质的含量,而泥质含量的高低是判别沉积岩类别的主要依据,因此,可以将铀、钍、钾的比活度或含量值作为判别沉积岩岩类的量化指标。利用低本底伽马能谱法测量岩石样品中铀、钍、钾的比活度或含量,可以快速、准确地进行岩类判别。由于放射性测量受样品几何形状、样品质量及其所含水分含量变化的影响,因此岩类判别的准确性会受到影响。通过理论探讨和实验验证,发现各待测核素特征峰计数率值与样品质量成线性关系, 且不同的能量区域、不同的岩性,线性关系系数与趋势拟合程度都是不同的;当样品的水分含量不超过10%(取样时,岩屑水分不超过10%)时,对测量结果的影响很小(变化值均在一倍均方差以内),因此,水分含量对低本底伽马能谱法判别沉积岩岩类的准确性不产生显著的影响,一般可以不予考虑。对陕西定边某油气勘查区钻孔岩屑样品进行判别试验,对实测数据进行质量校正后,利用铀、钍、钾道的“归一化”计数率值(即单位质量的计数率)只能粗略地划分不同沉积岩的大类,再以铀、钍、钾特征峰的合峰计数率建立综合判别模式,能够对岩类进行进一步细分,且判别准确度达到75%以上。 相似文献
5.
一种新的自组织聚类网络及其在数据融合目标分类中的应用 总被引:2,自引:0,他引:2
介绍了一种新的自组织聚类人工神经网络(DIGNET)模型和网络的非监督学习算法。针对数据融合和目标识别的特点,提出了基于DIGNET的决策层数据融合目标分类方法。利用仿真数据研究了DIGNET和自组织特征映射网络(SOFM)的聚类性能以及基于DIGNET的决策层数据融合结构,实验结果表明DIGNET较SOFM正确分类率高、抗噪能力好;基于DIGNET的决策层数据融合能够有效地实现融合识别。将该数据融合方法应用于前视红外(FLIR)和可见光摄像机目标跟踪系统,结果表明该方法是可行的。 相似文献
6.
7.
8.
We present the concept of integrated processing to combine intuitive processing of neural networks with logical processing of the conventional digital computer. We investigate a way to embody the concept in the neural network system by introducing external constraints in terms of external input. The effect of the external input is analyzed using the generalized projection method. The concept of integrated processing is applied to an image associative memory system, and the system is optically implemented for high-speed parallel processing incorporating it with the computer. The experimental result is presented to illustrate the effectiveness of the external input to control the output of the image associative memory. 相似文献
9.
In this paper effects of a new evolutionary rule added to the dynamics of the steepest descending asynchronous network model were studied. By numerical simulations, we found that the neural network operates very efficiently to improve the fault-tolerance when ,its capacity a ≤ 1 under the new rule. The simulations were conducted on both the low- and the highdimensional networks. A modified training scheme is also introduced. 相似文献
10.
应用形态击中周不中变换,提出了一种提高光学全息关联存储寻址准确性的方法,并给出了实验演示。 相似文献
11.
为了模拟人与动物感知信息的真实环境,以脉动神经元节点组成神经元网络,研究在随机刺激和混沌刺激等极端条件下的记忆模式存储与时间分割问题.研究表明:网络对于若干种模式的叠加输入,能够以一部分神经元同步发放的形式在时间域上分割出每一模式. 如果输入模式是缺损的,系统能够把它们恢复到原型,即具有联想记忆功能.通过调节耦合强度和噪声强度等参数使得网络在中等强度噪声达到最优的时间分割,与广泛讨论的随机共振现象一致.
关键词:
神经网络
空时模式
联想记忆
随机共振 相似文献
12.
13.
建立了冷冻干燥微波消解ICP-MS法测定肺癌患者肺组织中33种元素的方法。样品经真空冷冻干燥,采用纯化硝酸-过氧化氢体系微波消解,稀释定容后用ICP-MS对溶液进行元素的测定,在优化仪器工作参数后,以铑(Rh)和铼(Re)双内标进行校正。测定结果表明,元素检出限为0.01~0.45 ng·mL-1,测定了国家标准物质GBW(E)080193牛肝中的元素,测定值与标准值或参考值一致,元素精密度(RSD)为2.1%~14.3%,回收率为90.1%~117.5%。用该法测定了6例肺癌患者的肺癌、癌旁和正常组织中33种元素的含量。所建立的方法快速、简便、准确,适于肺组织等生物样品中多种元素的测定。 相似文献
14.
人工神经网络及其在光谱分析中的应用 总被引:11,自引:2,他引:11
介绍了人工神经网络的原理及研究进展,对典型神经网络系统作了详细的介绍,对人工神经网络在光谱分析中的应用做了较全面的评述。人工神经网络已成为光谱分析中重要的研究方法之一。 相似文献
15.
16.
Objective: Preoperative performance status is an important factor in thoracic surgery, but little is known about the effect of preoperative physical activity (PA) on the postoperative course. This study investigated the associations between preoperative PA and postoperative complications and clinical outcomes of lung cancer surgery. Methods: This prospective observational study included patients who underwent surgery for lung cancer at a single institution. PA was measured before hospitalization for 5 consecutive days and then after surgery until hospital discharge. The daily step count and time spent performing moderate intensity activity (> 3 metabolic equivalents) were measured with an accelerometer. We examined the correlations between PA and preoperative pulmonary function and physical fitness, and examined the relationship between postoperative complication and PA. Finally, a multivariate analysis was performed with pre-hospital PA as the dependent variable. Results: Forty-two patients were analyzed. Univariate analysis found no correlation between pre-hospital PA and preoperative pulmonary function, but found significant positive correlations between pre-hospital PA and time spent performing moderate intensity activity, in-hospital PA, preoperative 6-minute walk distance, and maximum gait speed (r > 0.5, p < 0.01). The nine patients who developed postoperative complications had significantly lower pre-hospital and postoperative step count than the patients with no complication (p = 0.04). Multiple regression analysis showed that pre-hospital PA was significantly associated with time spent performing moderate intensity activity, maximum gait speed, and postoperative complication. Conclusions: Evaluation of pre-hospital PA is useful in predicting the postoperative course after lung cancer surgery. 相似文献