公开(公告)号：US06571228B1

公开(公告)日：2003-05-27

申请号：US09635071

申请日：2000-08-09

Applicant: Po-Tong Wang ,  Ching-Han Chen

Inventor： Po-Tong Wang ,  Ching-Han Chen

IPC: G06F1518

CPC classification number: G06K9/4652 ,  G06N3/0454

Abstract: A method uses a hybrid neural network including a self organizing mapping neural network (SOM NN) and a, back-propagation neural network (BP NN) for color identification. In the method the red, green and blue (RGB) of color samples are input as features of training samples and are automatically classified by way of SOM NN. Afterwards, the outcomes of SOM NN are respectively delivered to various BP NN for further learning; and the map relationship of the input and the output defines the X,Y, Z corresponding the x, y and z values of a coordinate system of the standard color samples of RGB and IT8. By way of the above learning structure, a non-linear model of color identification can be set up. After color samples are self organized and classified by SOM NN network, data can be categorized in clusters as a result of characteristic difference thereof. Then the data are respectively sent to BP NN for learning whereby-the learning system not only can be quickly converged but also lower error discrepancy in operation effectively.

Abstract translation: 一种方法使用包括自组织映射神经网络（SOM NN）和反向传播神经网络（BP NN）的混合神经网络进行颜色识别。 在该方法中，将彩色样本的红色，绿色和蓝色（RGB）作为训练样本的特征输入，并通过SOM NN自动分类。 之后，SOM NN的结果分别交给各种BP NN进行进一步学习; 并且输入和输出的映射关系定义对应于RGB和IT8的标准颜色样本的坐标系的x，y和z值的X，Y，Z。 通过上述学习结构，可以建立一个非线性的颜色识别模型。 在通过SOM NN网络对彩色样本进行自组织和分类后，由于其特征差异，可以将数据分类为簇。 然后将数据分别发送到BP NN学习，学习系统不仅可以快速收敛，而且有效降低运行误差。

公开(公告)号：US20130169407A1

公开(公告)日：2013-07-04

申请号：US13531796

申请日：2012-06-25

Applicant: Ching-Han Chen ,  Jia-Hong Dai ,  Hsin Pei Hsieh ,  Jia-Wei Liou

Inventor： Ching-Han Chen ,  Jia-Hong Dai ,  Hsin Pei Hsieh ,  Jia-Wei Liou

IPC: G05B11/01

CPC classification number: H04L12/28 ,  H04L12/2818

Abstract: A wireless sensor actuator network (WSAN) is provided, which includes: at least one sensor, for sensing situations of surrounding environments to generate a transferring condition, the transferring condition corresponding to a transferring condition serial number; at least one actuator, driven by a driving signal; and a gateway, for receiving the transferring condition of the sensor corresponding to the transferring condition serial number, transferring an active state serial number to a transferring state serial number which meets the transferring condition according to an encoding table of the gateway, and executing functions called by the transferring state serial number to generate the driving signal for driving the actuator.

Abstract translation: 提供无线传感器执行器网络（WSAN），其包括：至少一个传感器，用于感测周围环境的情况以产生传送条件，与传送条件序列号对应的传送条件; 由驱动信号驱动的至少一个致动器; 以及网关，用于接收对应于传送条件序列号的传感器的传送条件，根据网关的编码表将活动状态序列号传送到满足传送条件的传送状态序列号，并执行称为 通过传送状态序列号来产生用于驱动致动器的驱动信号。