An improved pulse coupled neural networks model for semantic IoT

In recent years,the Internet of Things(IoT)has gradually developed applications such as collecting sensory data and building intelligent services,which has led to an explosion in mobile data traffic.Meanwhile,with the rapid development of artificial intelligence,semantic communication has attracted great attention as a new communication paradigm.However,for IoT devices,however,processing image information efficiently in real time is an essential task for the rapid transmission of semantic information.With the increase of model parameters in deep learning methods,the model inference time in sensor devices continues to increase.In contrast,the Pulse Coupled Neural Network(PCNN)has fewer parameters,making it more suitable for processing real-time scene tasks such as image segmentation,which lays the foundation for real-time,effective,and accurate image transmission.However,the parameters of PCNN are determined by trial and error,which limits its application.To overcome this limitation,an Improved Pulse Coupled Neural Networks(IPCNN)model is proposed in this work.The IPCNN constructs the connection between the static properties of the input image and the dynamic properties of the neurons,and all its parameters are set adaptively,which avoids the inconvenience of manual setting in traditional methods and improves the adaptability of parameters to different types of images.Experimental segmentation results demonstrate the validity and efficiency of the proposed self-adaptive parameter setting method of IPCNN on the gray images and natural images from the Matlab and Berkeley Segmentation Datasets.The IPCNN method achieves a better segmentation result without training,providing a new solution for the real-time transmission of image semantic information.

A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets

An artificial neural network(ANN)method is introduced to predict drop size in two kinds of pulsed columns with small-scale data sets.After training,the deviation between calculate and experimental results are 3.8%and 9.3%,respectively.Through ANN model,the influence of interfacial tension and pulsation intensity on the droplet diameter has been developed.Droplet size gradually increases with the increase of interfacial tension,and decreases with the increase of pulse intensity.It can be seen that the accuracy of ANN model in predicting droplet size outside the training set range is reach the same level as the accuracy of correlation obtained based on experiments within this range.For two kinds of columns,the drop size prediction deviations of ANN model are 9.6%and 18.5%and the deviations in correlations are 11%and 15%.

Artificial neural network algorithm for pulse shape discrimination in 2πα and 2πβ particle surface emission rate measurements

To enhance the accuracy of 2πα and 2πβ particle surface emission rate measurements and address the identification issues of nuclides in conventional methods, this study introduces two artificial neural network(ANN) algorithms: back-propagation(BP) and genetic algorithm-based back-propagation(GA-BP). These algorithms classify pulse signals from distinct α and β particles. Their discrimination efficacy is assessed by simulating standard pulse signals and those produced by contaminated sources, mixing α and β particles within the detector. This study initially showcases energy spectrum measurement outcomes, subsequently tests the ANNs on the measurement and validation datasets, and contrasts the pulse shape discrimination efficacy of both algorithms. Experimental findings reveal that the proportional counter's energy resolution is not ideal, thus rendering energy analysis insufficient for distinguishing between 2πα and 2πβ particles. The BP neural network realizes approximately 99% accuracy for 2πα particles and approximately 95% for 2πβ particles, thus surpassing the GA-BP's performance. Additionally, the results suggest enhancing β particle discrimination accuracy by increasing the digital acquisition card's threshold lower limit. This study offers an advanced solution for the 2πα and 2πβ surface emission rate measurement method, presenting superior adaptability and scalability over conventional techniques.

Neural Network Modeling and System Simulating for the Dynamic Process of Varied Gap Pulsed GTAW with Wire Filler

As the base of the research work on the weld shape control during pulsed gas tungsten arc welding （GTAW） with wire filler, this paper addressed the modeling of the dynamic welding process. Topside length Lt, maximum width Wt and half-length ratio Rh1 were selected to depict topside weld pool shape, and were measured on-line by vision sensing. A dynamic neural network model was constructed to predict the usually unmeasured backside width and topside height of the weld through topside shape parameters and welding parameters. The inputs of the model were the welding parameters （peak current, pulse duty ratio, welding speed, filler rate）, the joint gap, the topside pool shape parameters （Lt, Wt, and Rh1）, and their history values at two former pulse, a total of 24 numbers. The validating experiment results proved that the artificial neural network （ANN） model had high precision and could be used in process control. At last, with the developed dynamic model, steady and dynamic behavior was analyzed by simulation experiments, which discovered the variation rules of weld pool shape parameters under different welding parameters, and further knew well the characteristic of the welding process.

Self-learning fuzzy neural network control for backside width of weld pool in pulsed GTAW with wire filler

The weld pool shape control by intelligent strategy was studied. In order to improve the ability of self-learning and self-adaptation of the ordinary fuzzy control, a self-learning fuzzy neural network controller (FNNC) for backside width of weld pool in pulsed gas tungsten arc welding (GTAW) with wire filler was designed. In FNNC, the fuzzy system was expressed by an equivalence neural network, the membership functions and inference rulers were decided through the learning of the neural network. Then, the FNNC control arithmetic was analyzed, simulating experiment was done, and the validating experiments on varied heat sink workpiece and varied gap workpiece were implemented. The maximum error between the real value and the given one was 0.39mm, the mean error was 0.014mm, and the root-mean-square was 0.14mm. The real backside width was maintained around the given value. The results show that the self-learning fuzzy neural network control strategy can achieve a perfect control effect under different set values and conditions, and is suitable for the welding process with the varied structure and coefficients of control model.

Study on the Classification of Pulse Signal Based on the BP Neural Network

The objectification of the pulse signal analysis is a practical problem. The classification of the pulse signal is studied based on the BP neural network. It is first analyzed how to select the characteristic factors of the pulse signal. Then the method of nondimensionalization/normalization on the pulse signal is presented to preprocess the characteristic factors. The classification of the pulse signal and the effects of the selection of characteristic factors are studied by using the normalized data and BP neural network. It is shown that nondimensionalization/normalization of the data is in favor of the training and forecasting of the network. The selection of characteristic factors affects the accuracy of forecasting obviously. The results of forecasting by selection of 8, 6 and 4 factors respectively show that the less the factors are, the worse the effects are.

Anti-noise performance of the pulse coupled neural network applied in discrimination of neutron and gamma-ray

In this study,the anti-noise performance of a pulse-coupled neural network(PCNN)was investigated in the neutron and gamma-ray(n-γ)discrimination field.The experiments were conducted in two groups.In the first group,radiation pulse signals were pre-processed using a Fourier filter to reduce the original noise in the signals,whereas in the second group,the original noise was left untouched to simulate an extremely high-noise scenario.For each part,artificial Gaussian noise with different intensity levels was added to the signals prior to the discrimination process.In the aforementioned conditions,the performance of the PCNN was evaluated and compared with five other commonly used methods of n-γdiscrimination:(1)zero crossing,(2)charge comparison,(3)vector projection,(4)falling edge percentage slope,and(5)frequency gradient analysis.The experimental results showed that the PCNN method significantly outperforms other methods with outstanding FoM-value at all noise levels.Furthermore,the fluctuations in FoM-value of PCNN were significantly better than those obtained via other methods at most noise levels and only slightly worse than those obtained via the charge comparison and zerocrossing methods under extreme noise conditions.Additionally,the changing patterns and fluctuations of the FoMvalue were evaluated under different noise conditions.Hence,based on the results,the parameter selection strategy of the PCNN was presented.In conclusion,the PCNN method is suitable for use in high-noise application scenarios for n-γdiscrimination because of its stability and remarkable discrimination performance.It does not rely on strict parameter settings and can realize satisfactory performance over a wide parameter range.

FPGA implementation of neural network accelerator for pulse information extraction in high energy physics

Extracting the amplitude and time information from the shaped pulse is an important step in nuclear physics experiments.For this purpose,a neural network can be an alternative in off-line data processing.For processing the data in real time and reducing the off-line data storage required in a trigger event,we designed a customized neural network accelerator on a field programmable gate array platform to implement specific layers in a convolutional neural network.The latter is then used in the front-end electronics of the detector.With fully reconfigurable hardware,a tested neural network structure was used for accurate timing of shaped pulses common in front-end electronics.This design can handle up to four channels of pulse signals at once.The peak performance of each channel is 1.665 Giga operations per second at a working frequency of 25 MHz.

Image Fusion Algorithm Based on Spatial Frequency-Motivated Pulse Coupled Neural Networks in Nonsubsampled Contourlet Transform Domain

Nonsubsampled contourlet 变换(NSCT ) 为图象提供灵活 multiresolution， anisotropy，和方向性的扩大。与原来的 contourlet 变换相比，它是移动不变的并且能在奇特附近克服 pseudo-Gibbs 现象。脉搏联合了神经网络(PCNN ) 是一个视觉启发外皮的神经网络并且由全球联合和神经原的脉搏同步描绘。它为图象处理被证明合适并且成功地在图象熔化采用。在这份报纸， NSCT 与 PCNN 被联系并且在图象熔化使用了充分利用他们的特征。在 NSCT 领域的空间频率是输入与大开火的时间在 NSCT 领域激发 PCNN 和系数作为熔化图象的系数被选择。试验性的结果证明建议算法超过典型基于小浪，基于 contourlet，基于 PCNN，并且 contourlet-PCNN-based 熔化算法以客观标准和视觉外观。

Feature-Based Fusion of Dual Band Infrared Image Using Multiple Pulse Coupled Neural Network

To improve the quality of the infrared image and enhance the information of the object,a dual band infrared image fusion method based on feature extraction and a novel multiple pulse coupled neural network(multi-PCNN)is proposed.In this multi-PCNN fusion scheme,the auxiliary PCNN which captures the characteristics of feature image extracting from the infrared image is used to modulate the main PCNN,whose input could be original infrared image.Meanwhile,to make the PCNN fusion effect consistent with the human vision system,Laplacian energy is adopted to obtain the value of adaptive linking strength in PCNN.After that,the original dual band infrared images are reconstructed by using a weight fusion rule with the fire mapping images generated by the main PCNNs to obtain the fused image.Compared to wavelet transforms,Laplacian pyramids and traditional multi-PCNNs,fusion images based on our method have more information,rich details and clear edges.

基于LSTM-PNN神经网络的电潜泵故障诊断方法

针对电潜螺杆泵故障预测中发生故障难以及时发现、发现难以准确判别故障类型等问题,提出一种基于深度学习长短期记忆网络(LSTM)结合概率神经网络(PNN)的电潜螺杆泵故障预测方法。以LSTM网络为回归模型,使用时间序列法预测故障信号的未来趋势,利用小波包分解螺杆泵的故障信号,提取其中的故障特征,再结合油压、产量等多个工作参数,构建电潜螺杆泵的故障特征向量,并凭借PNN网络判别预测信号故障类型。收集新疆油田120组故障数据作为数据集对预测模型进行训练,从中取出90组数据作为故障数据库对模型进行训练,取出30组数据作为测试组测试模型准确率,使用LSTM-PNN神经网络预测模型分别对两组数据进行电潜螺杆泵故障预测。结果表明:预测前提取故障信号特征可有效提高电潜螺杆泵的故障预测精度,较常规电潜螺杆泵故障预测方法,LSTM-PNN网络预测具有更高的准确率且准确率提升了3%~16%。

基于PNN神经网络的凿岩台车电液控制系统故障诊断研究

针对凿岩台车电液控制系统故障诊断效率低的问题,该文提出一种结合故障树分析法和概率神经网络(probabilistic neural network,PNN)的故障诊断方法。首先,基于电液控制系统的结构和工作原理构建其故障树模型;然后通过对故障树模型进行定性分析,确定其最小割集和典型故障种类,以选取的典型故障种类的关键参数构建故障征兆矩阵,通过PNN神经网络对该矩阵进行训练和计算,实现对系统典型故障状态的自动识别。实验结果表明,该文方法的平均诊断时间为1.2 s,平均诊断准确率为80%,能够快速准确地定位系统故障,可满足凿岩台车电液控制系统故障诊断的工程实际需求。

Information Fusing Recognition of Traditional Chinese Medicine (TCM) Pulse State Based on Stochastic Fuzzy Neural Network

Based on the fuzzy characteristic of the pulse state and syndromes differentiation thinking mode of TCM, an information fusing recognition method of pulse states based on SFNN (Stochastic Fuzzy Neural Network) is presented in this paper. With the learning ability in parameters and structure, SFNN fuses the measurement information of three pulse-state sensors distributed in Cun, Guan, and Chi location of body for the pulse state recognition. The experimental results show that the percentage of correct recognition with new method is higher than that by single-data recognition one, with fewer off-line train numbers.

Prediction of Pulsation Frequency of Pulsing Flow in Trickle Beds Based on Artificial Neural Network

An extensive database (946 measurements) for the frequency of pulsing flow in trickle beds was established by collecting the experimental results published over past 30 years. A new correlation based on artificial neural network (ANN) to predict the pulsation frequency was developed. Seven dimensionless numbers (groups) employed in the proposed correlation were liquid and gas Reynolds, liquid Weber, liquid Eotvos, gas Froude, and gas Stokes numbers and a bed correction factor. The comparisons of performance reported in the of literature and present correlations show that ANN correlation is a significant improvement in predicting pulsation frequency with an average absolute relative error (AARE) of 10% and a standard deviation less than 18%.

Irregular Segmented Region Compression Coding Based on Pulse Coupled Neural Network

An irregular segmented region coding algorithm based on pulse coupled neural network(PCNN) is presented. PCNN has the property of pulse-coupled and changeable threshold, through which these adjacent pixels with approximate gray values can be activated simultaneously. One can draw a conclusion that PCNN has the advantage of realizing the regional segmentation, and the details of original image can be achieved by the parameter adjustment of segmented images, and at the same time, the trivial segmented regions can be avoided. For the better approximation of irregular segmented regions, the Gram-Schmidt method, by which a group of orthonormal basis functions is constructed from a group of linear independent initial base functions, is adopted. Because of the orthonormal reconstructing method, the quality of reconstructed image can be greatly improved and the progressive image transmission will also be possible.

Classification of Ultrasonic Signs Pre-processed by Fourier Transform through Artificial Neural Network Using the Echo Pulse Technique for the Identification of Defects in Welded Joints of Structural Steel

It is due to the need to ensure the security and integrity of equipment, that the non-destructive tests have been increasingly used in the industrial sector. Among these, the ultrasonic pulse echo technique is the most used in industry, mainly for its simplicity and efficiency. With one transducer only, it is possible to emit the ultrasonic and receive the echo pulse. The ANNs （artificial neural networks） are artificial intelligence techniques that, when properly trained, align themselves to inspection tests becoming a powerful tool in the detection and fault identification. In this work, the echo pulse technique was used to detect discontinuities in welds, where ANNs were fed from the information obtained by digital signal processing techniques （Fourier transform）, to identify and classify three distinct classes of defects. Results showed that with the combination of feature extraction by Fourier transformation and classification with neural networks, it is possible to obtain an automatic defect detection system in welded joints with average efficiency.

基于IWOA-PNN模型的管道焊缝腐蚀剩余强度预测

针对管道焊缝腐蚀问题构建基于改进鲸鱼优化算法(Improved Whale Optimization Algorithm, IWOA)的概率神经网络(Probabilistic Neural Network, PNN)剩余强度预测模型。首先,通过种群初始化、非线性收敛因子和惯性权重因子提高鲸鱼优化算法的寻优速度和精度;然后,利用IWOA算法优化PNN的光滑因子,构建IWOA-PNN预测模型;最后,以水压爆破试验数据为基础,使用MATLAB软件进行仿真试验,并与另外2个模型进行对比分析。结果表明:IWOA-PNN模型的ERMS为0.633 1,EAR为2.19%,R^(2)为0.954 6,均优于PNN和鲸鱼优化算法(Whale Optimization Algorithm, WOA)-PNN模型;IWOA-PNN模型与传统模型相比误差更小,能够更为准确地预测焊缝腐蚀后剩余强度,为管道的维修和更换提供参考。

Remote Sensing Image Segmentation with Probabilistic Neural Networks

This paper focuses on the image segmentation with probabilistic neural networks (PNNs). Back propagation neural networks (BpNNs) and multi perceptron neural networks (MLPs) are also considered in this study. Especially, this paper investigates the implementation of PNNs in image segmentation and optimal processing of image segmentation with a PNN. The comparison between image segmentations with PNNs and with other neural networks is given. The experimental results show that PNNs can be successfully applied to image segmentation for good results.

Neural network analysis of overturning response under near-fault type excitation

Under strong seismic excitation, a rigid block will uplift from its support and undergo rocking oscillations which may lead to （complete） overturning. Numerical and analytical solutions to this highly nonlinear vibration problem are first highlighted in the paper and then utilized to demonstrate how sensitive the overturning behavior is not only to the intensity and frequency content of the base motion, but also to thc presence of strong pulses, to their detailed sequence, and even to their asymnletry. Five idealised pulses capable of representing ＂rupture-directivity＂ and ＂fling＂ affected ground motions near the fault, are utilized to this end ： the one-cycle sinus, the one-cycle cosinus, the Ricker wavelet, the truncated （T）-Ricker wavelet, and the rectangular pulse ＂Overturning-Acceleration Amplification＂ and ＂Rotation＂ spectra are introduced and presented. Artificial neural network modeling is then developed as an alternative numerical solution. The neural network analysis leads to closed-form expressions for predicting the overturning failure or survival of a rigid block, as a function of its geometric properties and the characteristics of the excitation time history. The capability of the developed neural network modeling is validated through comparisons with the numerical solution. The derived analytical expressions could also serve as a tool for assessing the destructiveness of near-fault ground motions, for structures sensitive to rocking with foundation uplift.