Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on li...Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on linear processes,leading to poor performance in dynamic nonlinear processes.In this paper,a novel quality-related fault detection method,named DiCAE-PLS,is developed by combining dynamic-inner convolutional autoencoder with PLS.In the proposed DiCAE-PLS method,latent features are first extracted through dynamic-inner convolutional autoencoder (DiCAE) to capture process dynamics and nonlinearity from process variables.Then,a PLS model is established to build the relationship between the extracted latent features and the final product quality.To detect quality-related faults,Hotelling's T^(2) statistic is employed.The developed quality-related fault detection is applied to the widely used industrial benchmark of the Tennessee.展开更多
Due to highly underdetermined nature of Single Image Super-Resolution(SISR)problem,deep learning neural networks are required to be more deeper to solve the problem effectively.One of deep neural networks successful i...Due to highly underdetermined nature of Single Image Super-Resolution(SISR)problem,deep learning neural networks are required to be more deeper to solve the problem effectively.One of deep neural networks successful in the Super-Resolution(SR)problem is ResNet which can render the capability of deeper networks with the help of skip connections.However,zero padding(ZP)scheme in the network restricts benefits of skip connections in SRResNet and its performance as the ratio of the number of pure input data to that of zero padded data increases.In this paper.we consider the ResNet with Partial Convolution based Padding(PCP)instead of ZP to solve SR problem.Since training of deep neural networks using patch images is advantageous in many aspects such as the number of training image data and network complexities,patch image based SR performance is compared with single full image based one.The experimental results show that patch based SRResNet SR results are better than single full image based ones and the performance of deep SRResNet with PCP is better than the one with ZP.展开更多
The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditio...The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.展开更多
In this paper, we proposed new results in quadruple Laplace transform and proved some properties concerned with quadruple Laplace transform. We also developed some applications based on these results and solved homoge...In this paper, we proposed new results in quadruple Laplace transform and proved some properties concerned with quadruple Laplace transform. We also developed some applications based on these results and solved homogeneous as well as non-homogeneous partial differential equations involving four variables. The performance of quadruple Laplace transform is shown to be very encouraging by concrete examples. An elementary table of quadruple Laplace transform is also provided.展开更多
针对交通目标检测时物体尺度变化大,检测目标较为密集的问题,基于YOLO(you only look once)v8s提出一种高效多尺度YOLO(fast multiscale powerful-YOLO,FMP-YOLO)模型。在主干网络中,引入基于部分卷积(partial convolution,PConv)与快...针对交通目标检测时物体尺度变化大,检测目标较为密集的问题,基于YOLO(you only look once)v8s提出一种高效多尺度YOLO(fast multiscale powerful-YOLO,FMP-YOLO)模型。在主干网络中,引入基于部分卷积(partial convolution,PConv)与快速傅里叶卷积(fast Fourier convolution,FFC)设计的Faster Block模块,减少了冗余计算和内存访问,提高了推理速度,改善了感受野受限的问题;在聚合网络中,使用改进后的组混洗卷积(group shuffle convolution,GSConv)替换普通卷积,更好地捕获不同尺度的特征,进一步降低了模型的参数量和计算量;将Powerful-IoU与软非极大值抑制(soft non maximum suppression,SoftNMS)结合替换原有的非极大值抑制算法(non maximum suppression,NMS),改善了由参数量降低导致特征学习能力下降的问题,并且提高了模型的精度。在SODA10M和MS COCO数据集上进行实验,实验结果表明,改进后的模型性能超越原始模型,参数量和计算量下降40%左右,mAP分别提高了1.7%和1.4%,FMP-YOLO在体积与精度上优于其他经典模型,具有较强的实用性。展开更多
基金supported in part by the National Natural Science Foundation of China(62573387)the Natural Science Foundation of Zhejiang province,China(LY24F030004)the Fundamental Research Funds of Zhejiang Sci-Tech University(25222139-Y).
文摘Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on linear processes,leading to poor performance in dynamic nonlinear processes.In this paper,a novel quality-related fault detection method,named DiCAE-PLS,is developed by combining dynamic-inner convolutional autoencoder with PLS.In the proposed DiCAE-PLS method,latent features are first extracted through dynamic-inner convolutional autoencoder (DiCAE) to capture process dynamics and nonlinearity from process variables.Then,a PLS model is established to build the relationship between the extracted latent features and the final product quality.To detect quality-related faults,Hotelling's T^(2) statistic is employed.The developed quality-related fault detection is applied to the widely used industrial benchmark of the Tennessee.
文摘Due to highly underdetermined nature of Single Image Super-Resolution(SISR)problem,deep learning neural networks are required to be more deeper to solve the problem effectively.One of deep neural networks successful in the Super-Resolution(SR)problem is ResNet which can render the capability of deeper networks with the help of skip connections.However,zero padding(ZP)scheme in the network restricts benefits of skip connections in SRResNet and its performance as the ratio of the number of pure input data to that of zero padded data increases.In this paper.we consider the ResNet with Partial Convolution based Padding(PCP)instead of ZP to solve SR problem.Since training of deep neural networks using patch images is advantageous in many aspects such as the number of training image data and network complexities,patch image based SR performance is compared with single full image based one.The experimental results show that patch based SRResNet SR results are better than single full image based ones and the performance of deep SRResNet with PCP is better than the one with ZP.
基金funded by the National Natural Science Foundation of China under Grant No.62371187the Open Program of Hunan Intelligent Rehabilitation Robot and Auxiliary Equipment Engineering Technology Research Center under Grant No.2024JS101.
文摘The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.
文摘In this paper, we proposed new results in quadruple Laplace transform and proved some properties concerned with quadruple Laplace transform. We also developed some applications based on these results and solved homogeneous as well as non-homogeneous partial differential equations involving four variables. The performance of quadruple Laplace transform is shown to be very encouraging by concrete examples. An elementary table of quadruple Laplace transform is also provided.
文摘针对交通目标检测时物体尺度变化大,检测目标较为密集的问题,基于YOLO(you only look once)v8s提出一种高效多尺度YOLO(fast multiscale powerful-YOLO,FMP-YOLO)模型。在主干网络中,引入基于部分卷积(partial convolution,PConv)与快速傅里叶卷积(fast Fourier convolution,FFC)设计的Faster Block模块,减少了冗余计算和内存访问,提高了推理速度,改善了感受野受限的问题;在聚合网络中,使用改进后的组混洗卷积(group shuffle convolution,GSConv)替换普通卷积,更好地捕获不同尺度的特征,进一步降低了模型的参数量和计算量;将Powerful-IoU与软非极大值抑制(soft non maximum suppression,SoftNMS)结合替换原有的非极大值抑制算法(non maximum suppression,NMS),改善了由参数量降低导致特征学习能力下降的问题,并且提高了模型的精度。在SODA10M和MS COCO数据集上进行实验,实验结果表明,改进后的模型性能超越原始模型,参数量和计算量下降40%左右,mAP分别提高了1.7%和1.4%,FMP-YOLO在体积与精度上优于其他经典模型,具有较强的实用性。
