This paper presents an unsupervised range image segmentation based on Kohonen neural network. At first, the derivative and partial derivative of each point are calculated and the normal in each points is gotten. With ...This paper presents an unsupervised range image segmentation based on Kohonen neural network. At first, the derivative and partial derivative of each point are calculated and the normal in each points is gotten. With the character vectors including normal and range value, self-organization map is introduced to cluster. The normal analysis is used to eliminate over-segmentation and the last result is gotten. This method avoid selecting original seeds and uses fewer samples, moreover computes rapidly. The experiment shows the better performance.展开更多
The faults in switched reluctance motors(SRMs) were detected and diagnosed in real time with the Kohonen neural network. When a fault happens, both financial losses and undesired situations may occur. For these reason...The faults in switched reluctance motors(SRMs) were detected and diagnosed in real time with the Kohonen neural network. When a fault happens, both financial losses and undesired situations may occur. For these reasons, it is important to detect the incipient faults of SRMs and to diagnose which faults have occurred. In this study, a test rig was realized to determine the healthy and faulty conditions of SRMs. A data set for the Kohonen neural network was created with implemented measurements. A graphical user interface(GUI) was created in Matlab to test the performance of the Kohonen artificial neural network in real time. The data of the SRM was transferred to this software with a data acquisition card. The condition of the motor was monitored by marking the data measured in real time on the weight position graph of the Kohonen neural network. This test rig is capable of real-time monitoring of the condition of SRMs, which are used with intermittent or continuous operation, and is capable of detecting and diagnosing the faults that may occur in the motor. The Kohonen neural network used for detection and diagnosis of faults of the SRM in real time with Matlab GUI was embedded in an STM32 processor. A prototype with the STM32 processor was developed to detect and diagnose the faults of SRMs independent of computers.展开更多
The key methods of detection and classification of the electroencephalogram(EEG) used in recent years are introduced . Taking EEG for example, the design plan of Kohonen neural network system based on detection and cl...The key methods of detection and classification of the electroencephalogram(EEG) used in recent years are introduced . Taking EEG for example, the design plan of Kohonen neural network system based on detection and classification of complex signals is proposed, and both the network design and signal processing are analyzed, including pre-processing of signals, extraction of signal features, classification of signal and network topology, etc.展开更多
The local visual motion detection mechanism used in the visual systems of primatescan only sense the motion component oriented perpendicularly to the contrast gradient of thebrightness pattern.But the visual system of...The local visual motion detection mechanism used in the visual systems of primatescan only sense the motion component oriented perpendicularly to the contrast gradient of thebrightness pattern.But the visual system of higher animals can adaptively determine the actualdirection of motion through a learning process.In this paper a multilayered feedforward neuralnetwork model for perception of visual motion is presented.This model employs W.Reichardt’selementary motion detectors array and T.Kohonen’s self-organizing feature map.We explored theself-organizing principles for perception of visual motion.The computer simulations show thatthis neural network is able to recognize the true direction of motion through an unsupervisedlearning process.In addition,the neurons with the same or similar motion direction selectivitytend to appear in“functional columns”which seem to be qualitatively similar to the corticalmotion columns observed by electrophysiological and cytohistochemical studies in certain higherareas such as MT.It proves that motion-detection by spatio-temporal coherences,mapping,co-operation,competition,and Hebb rule may be the basic principles for the self-organization ofvisual motion perception networks.展开更多
拒绝服务(Denial of Service,DoS)是企图使其预期用户的一台主机或其他网络资源不可用,如临时或无限期地中断或暂停连接到因特网主机的服务.为了有效地阻止DoS攻击,首先需要提高DoS攻击检测的准确性,提出一种基于改进Kohonen网络的DoS...拒绝服务(Denial of Service,DoS)是企图使其预期用户的一台主机或其他网络资源不可用,如临时或无限期地中断或暂停连接到因特网主机的服务.为了有效地阻止DoS攻击,首先需要提高DoS攻击检测的准确性,提出一种基于改进Kohonen网络的DoS攻击检测算法.该方法通过对DoS攻击原始数据的预处理,为后续数据处理的方便和保证程序运行时加快收敛奠定必要的基础,采用检测结果的正确率作为该算法的评价指标,采用SOM学习算法是把高维空间的输入数据映射到低维神经网络上,并且保持原来的拓扑次序,然后建立S-Kohonen(Supervised-Kohonen)神经网络检测模型.实验结果表明,与传统的Kohonen方法相比,S-Kohonen网络具有更好的检测性能.展开更多
文摘This paper presents an unsupervised range image segmentation based on Kohonen neural network. At first, the derivative and partial derivative of each point are calculated and the normal in each points is gotten. With the character vectors including normal and range value, self-organization map is introduced to cluster. The normal analysis is used to eliminate over-segmentation and the last result is gotten. This method avoid selecting original seeds and uses fewer samples, moreover computes rapidly. The experiment shows the better performance.
基金Project(No.KBü-BAP-C-11-D-003)supported by the Karabük University BAP Unit,Turkey
文摘The faults in switched reluctance motors(SRMs) were detected and diagnosed in real time with the Kohonen neural network. When a fault happens, both financial losses and undesired situations may occur. For these reasons, it is important to detect the incipient faults of SRMs and to diagnose which faults have occurred. In this study, a test rig was realized to determine the healthy and faulty conditions of SRMs. A data set for the Kohonen neural network was created with implemented measurements. A graphical user interface(GUI) was created in Matlab to test the performance of the Kohonen artificial neural network in real time. The data of the SRM was transferred to this software with a data acquisition card. The condition of the motor was monitored by marking the data measured in real time on the weight position graph of the Kohonen neural network. This test rig is capable of real-time monitoring of the condition of SRMs, which are used with intermittent or continuous operation, and is capable of detecting and diagnosing the faults that may occur in the motor. The Kohonen neural network used for detection and diagnosis of faults of the SRM in real time with Matlab GUI was embedded in an STM32 processor. A prototype with the STM32 processor was developed to detect and diagnose the faults of SRMs independent of computers.
文摘The key methods of detection and classification of the electroencephalogram(EEG) used in recent years are introduced . Taking EEG for example, the design plan of Kohonen neural network system based on detection and classification of complex signals is proposed, and both the network design and signal processing are analyzed, including pre-processing of signals, extraction of signal features, classification of signal and network topology, etc.
基金Supported in part by the National Natural Science Foundation of China National Laboratory of Pattern Recognition,Institute of Automation,Academia Sinica.
文摘The local visual motion detection mechanism used in the visual systems of primatescan only sense the motion component oriented perpendicularly to the contrast gradient of thebrightness pattern.But the visual system of higher animals can adaptively determine the actualdirection of motion through a learning process.In this paper a multilayered feedforward neuralnetwork model for perception of visual motion is presented.This model employs W.Reichardt’selementary motion detectors array and T.Kohonen’s self-organizing feature map.We explored theself-organizing principles for perception of visual motion.The computer simulations show thatthis neural network is able to recognize the true direction of motion through an unsupervisedlearning process.In addition,the neurons with the same or similar motion direction selectivitytend to appear in“functional columns”which seem to be qualitatively similar to the corticalmotion columns observed by electrophysiological and cytohistochemical studies in certain higherareas such as MT.It proves that motion-detection by spatio-temporal coherences,mapping,co-operation,competition,and Hebb rule may be the basic principles for the self-organization ofvisual motion perception networks.
文摘拒绝服务(Denial of Service,DoS)是企图使其预期用户的一台主机或其他网络资源不可用,如临时或无限期地中断或暂停连接到因特网主机的服务.为了有效地阻止DoS攻击,首先需要提高DoS攻击检测的准确性,提出一种基于改进Kohonen网络的DoS攻击检测算法.该方法通过对DoS攻击原始数据的预处理,为后续数据处理的方便和保证程序运行时加快收敛奠定必要的基础,采用检测结果的正确率作为该算法的评价指标,采用SOM学习算法是把高维空间的输入数据映射到低维神经网络上,并且保持原来的拓扑次序,然后建立S-Kohonen(Supervised-Kohonen)神经网络检测模型.实验结果表明,与传统的Kohonen方法相比,S-Kohonen网络具有更好的检测性能.
