This paper proposes an improved steel surface defect detection algorithm YOLOv5-TBC based on YOLOv5s to address the issues of insufficient defect feature extraction capability and inadequate feature fusion in steel surface defect detection tasks.Firstly,a triplet attention mechanism is introduced into the core feature extraction module of the Backbone to enhance its adaptability and representational ability.Secondly,a weighted Bi-directional Feature Pyramid Network(BiFPN)is introduced to improve feature fusion,and a CBAM attention mechanism is introduced to optimize the model's detection capability for small-scale targets.Finally,a lightweight upsampling operator CARAFE is added to enlarge the model's receptive field,further improving the detection performance for targets of different sizes.Experimental results demonstrate that the improved YOLOv5s model achieves a precision(P)of 74.0%and a mean Average Precision(mAP)of 76.6%on the NEU-DET dataset,which is an increase of 5.8%in P and 3.0%in mAP compared to YOLOv5s,and an increase of 3.8%in P and 2.1%in mAP compared to YOLOv7,proving that the network model has better detection performance.
A new prediction framework is proposed to improve short-term power load forecasting accuracy. The framework is based on particle swarm optimization (PSO)-variational mode decomposition (VMD) combined with a time convolution network (TCN) embedded attention mechanism (Attention). The framework follows a two-step process. In the first step, PSO is applied to optimize the VMD decomposition method. The original electricity load sequence is decomposed, and the fitness function uses sample entropy to describe the complexity of the time series. The decomposed sub-sequences are combined with relevant features, such as meteorological data, to form the input sequence of the prediction model. In the second step, TCN is selected as the prediction model, and it is embedded with an attention mechanism to improve prediction accuracy. The above input sequence is fed to the model to obtain the PSO-VMD-TCN-Attention prediction framework. Load datasets and various prediction models validate the PSO-optimized VMD decomposition method and the TCN-Attention prediction model. Simulation results demonstrate that the PSO-optimized VMD decomposition method enhances the model’s prediction accuracy, and the TCN-Attention prediction model outperforms other prediction models in terms of prediction accuracy and ability.
In recent years, artificial intelligence has been applied to 3D COVID-19 medical image diagnosis, which reduces detection costs and missed diagnosis rates with higher predictive accuracy, and diagnostic efficiency. However, the limited size and low quality of clinical 3D medical image samples have hindered the segmentation performance of 3D models. Therefore, we propose a 3D medical image segmentation model based on semi-supervised learning using co-training. Multi-view and multi-modal images are generated using spatial flipping and windowing techniques to enhance the spatial diversity of 3D image samples. A pseudo label generation module based on confidence-weights is employed to generate reliable pseudo labels for non-annotated data, thereby increasing the sample size and reducing overfitting. The proposed approach utilizes a three-stage training process: firstly, training a single network based on annotated data; secondly, incorporating non-annotated data to train a dual-modal network and generate pseudo labels; finally, jointly training six models in three dimensions using both annotated and pseudo labels generated from multi-view and multi-modal images, aiming to enhance segmentation accuracy and generalization performance. Additionally, a consistency regularization loss is applied to reduce noises and accelerate convergence of the training. Moreover, a heatmap visualization method is employed to focus on the attention of features at each stage of training, providing effective reference for clinical diagnosis. Experiments were conducted on an open dataset of 3D COVID-19 CT samples and a non-annotated dataset from TCIA, including 771 NIFTI-format CT images from 661 COVID-19 patients. The results of 5-fold cross-validation show that the proposed model achieves a segmentation accuracy of Dice=73.30%, ASD=10.633, Sensitivity=63.00%, and Specificity=99.60%. Compared to various typical semi-supervised learning 3D segmentation models, it demonstrates better segmentation accuracy and generalization performance.
Timely and accurate air quality prediction data is very important for environmental management,especially,during the period of heavy air pollution.The prediction data can provide data support for the decision-making of the government's ecological environment management departments to cope with the pollution situation and accurately allocate social resources.The artificial intelligence based deep learning model AirNet6 proposed in this article can give consideration to both accuracy and real-time performance to achieve 7-day or longer air quality prediction for ozone,sulfur dioxide,carbon monoxide and other factors.Unlike traditional chemical model calculations,this model base on Spatio-Temporal Graph Convolutional Networks(STGCN),which captures the laws of historical monitoring data,weather prediction data,social activities and other data,and completes the prediction of more than one hundred points for the next 168 hours in two minutes.Experiments show that the AirNet6 model has made significant progress in speed,energy efficiency,and accuracy compared to traditional chemical models and time series AI models.
Multimodal image registration is the fundamental technique for scene analysis with series remote sensing images of different spectrum region. Due to the highly nonlinear radiometric relationship, it is quite challenging to find common features between images of different modal types. This paper resorts to the deep neural network, and tries to learn descriptors for multimodal image patch matching, which is the key issue of image registration. A Siamese fully convolutional network is set up and trained with a novel loss function, which adopts the strategy of maximizing the feature distance between positive and hard negative samples. The two branches of the Siamese network are connected by the convolutional operation, resulting in the similarity score between the two input image patches. The similarity score value is used, not only for correspondence point location, but also for outlier identification. A generalized workflow for deep feature based multimodal RS image registration is constructed, including the training data curation, candidate feature point generation, and outlier removal. The proposed network is tested on a variety of optical, near infrared, thermal infrared, SAR, and map images. Experiment results verify the superiority over other state-of-the-art approaches.
MIFS algorithm and its improved algorithms adhere to the idea of "maximum correlation and minimum redundancy" to select features in medical diagnostic data sets, which pay attention to the relevant information and the redundant information, but do not consider the interaction information. In order to emphasize the role of Interaction information, Feature Interaction Based MIFS Algorithm（MIFS-FI） is proposed. MIFS-FI algorithm achieve "maximum correlation", and the redundant features are almost removed and the interactive features are nearly retained. Secondly, it effectively solves the problems of parameter uncertainty and correlation-redundancy incomparable in MIFS algorithm. Finally, the MIFS-FI algorithm and seven other feature selection methods based on mutual information are compared to 14 medical diagnosis datasets, and the results show that the MIFS-FI algorithm outperforms the others in terms of classification accuracy, recall,F 1 score and classification accuracy.
印制电路板(Print Circuit Board,PCB)表现形式多样,缺陷特征表征困难.针对印制电路板缺陷类别识别难度较大等问题,提出了一种基于卷积神经网络融合多尺度特征的PCB裸板缺陷识别方法.该方法首先提取PCB裸板缺陷的多尺度灰度共生矩阵特征、多尺度方向投影特征以及多尺度梯度方向直方图特征,构建缺陷浅层图像特征,然后基于迁移学习,利用VGGl6-Net预训练神经网络模型的特征提取网络,提取PCB裸板缺陷图像深度语义特征,将得到的浅层图像特征与深度语义特征进行融合,最后将特征向量以特征序列方式输入给支持向量机进行分类识别.试验结果表明,融合深度特征和多尺度浅层特征的算法相较于传统卷积神经网络算法,对PCB裸板缺陷具有较高的识别率.
针对现有监督学习的单目深度估计存在编码器模型参数量大、计算复杂度高等问题,本文构建了一种基于轻量化融合损失网络的单目深度估计模型,该模型基于编码器-解码器设计.首先,编码器采用网络搜索技术的EfficientNet;其次,解码器设计一种结合双通道空间注意力机制的SU-Net结构模型;最后,在解码器的输出端基于该模型构建ResNet50 损失网络,对物体边缘、纹理和轮廓差异进行惩罚,来弥补编码-解码阶段特征信息表达能力不足的问题.在NYU-Depth V2 数据集上开展了试验,试验结果表明:该模型深度估计的均方根误差(RMSE)达到了 0.419,优于原始基准模型.
针对轴承故障特征提取能力不足、源域与目标域数据分布差异过大等问题,本文提出了一种基于小波包域对抗注意力迁移学习的故障诊断方法(WWRESE-IDALM).首先,通过小波包变换(Wavelet Packet Transform,WPT)获得不同重点节构的时频域信息;其次,将重构后的时频域信息数据经过一层大卷积核和通道注意力模块(Squeeze and Excitation,SE)提取轴承深度关键信息特征;利用改进的域对抗网络(Domain-Adversarial Training of Neural Networks,DANN)和局部最大平均差异(Local Maximum Mean Discrepancy,LMMD)对齐子域分布,减少相关子域和全局域之间的结构差异;最后,通过标签分类网络完成故障分类.在帕德博恩大学轴承数据集诊断结果证明了所提出的WWRESE-IDALM方法具有良好的变工况故障分类能力.
本文基于方法融合感知的思想,探究了集成学习算法在图像质量评估中的应用,对利用支持向量机及神经网络搭建集成学习框架进行图像质量评估的性能表现进行了分析.为保证集成学习后评估算法的通用性,使用保真度、结构相似性、颜色质量与数据驱动学习等多种估计器指标进行集成,使用LIVE、多重失真LIVE及TID 2013 3 种数据库进行验证.实验结果表明,集成学习方法通常可以提高图像质量评估能力,基于深度学习网络的评估能力增强优于基于支持向量机的增强,当存在两种以上附加方法进行融合感知时,二者较原有最佳性能方法均可取得较为有效地提升.
针对传统算法在地铁车辆轴箱盖螺栓检测任务中出现模型体积和模型参数较大的问题,本文提出了一种改进Yolov5s算法,采用GhostNet残差结构思想和挤压激励,构建一个GGS 模型结构作为主干,在多尺度融合时使用深度可分离卷积进行降维和降采样的轻量化的目标检测网络算法.实验结果表明,本文基于改进Yolov5 网络在螺栓定位平均精确度达到了72%,Yolov5 网络提升了2.8%,网络模型尺寸更是减少到5.6 m,相比于Yolov5s网络模型降低了62.2%,相对Yolov5s网络精度无损失的情况下,本文的网络的模型尺寸和模型参数大幅度下降.
以往高分辨率遥感图像分割方法由于没有对遥感图像中的数据模点进行检测,导致分割精度不高,本文设计了一种基于深度学习的高分辨率遥感图像分割方法.首先,通过对遥感图像进行预处理,保留重要的细节信息;其次,对预处理后的遥感图像进行特征提取,并对特征提取后的图像进行滤波处理,增加图像光谱的一致性;最后,利用深度学习方法对遥感图像中的数据模点进行检测,得到遥感图像的最终分割结果.通过实验并与以往的高分辨率遥感图像分割方法进行对比证明基于深度学习的高分辨率遥感图像分割方法具有更高的分割精度.
针对工业生产场景中常采用硬接线的方式来传输急停信号存在的安全隐患,本文提出采用基于Profisafe通讯协议的分布式自动化网络,将漏波电缆作为传输的介质,分析了该电缆的工作原理、衰减特性及各频段下的传输距离,在两端分别加入安全PLC,组成一个无线通讯系统,并在TIA PORTAL中进行设备组态,以此实现一些急停及复位信号的安全传输.通过实验验证了该系统的可行性,极大地提升了原有生产线的工作效率及工作的稳定性.
人类的情绪会极大地影响一个人的行为,情绪识别技术在医疗、网络学习、监控等多个领域都有广泛的应用.为了更有效地提取脑电信号特征,提升脑电信号情绪分类效果,本文提出了一种基于mRMR(最小冗余最大相关)的多频段脑电信号特征提取方法.针对脑电信号在不同通道电极间特征差异,利用最小冗余最大相关性算法,根据空间导联电极与特征频段分布不同,选择与情绪特性关联较大的空间电极并提出多频段融合算法,提取微分熵特征.利用脑电情绪数据库,在长短期记忆网络(Long Short-Term Memory,LSTM)网络中引入双向LSTM(Bi-directional LongShort-Term Memory,BiLSTM)层进行训练,根据唤醒和效价等级进行情绪划分,平均准确率分别达到 96.23%、93.16%.
为了提高在人体步伐识别中异常状态检测的识别率和精度,引入机器学习算法,研究人体步态异常状态检测与识别方法.根据采集到的人体步态图像序列结构,构建人体步态模型.利用所构建的模型检测人体步态,并对人体步态图像进行二值化处理,实现模型参数的优化,从中提取人体步态运动特征,实现对变化的人体步态的具体描述.结合机器学习算法中的决策树、NN分类器和KNN分类器,对人体步态中的异常状态进行识别.经过对比实验可知,本文所提识别方法具备更高的识别率和识别精度,能够有效检测出人在行走中出现的异常状态.
预测药物-疾病关联关系,有助于降低药物开发的成本和时间开销.先前的方法没有基于异构网络的拓扑信息对缺失属性的疾病节点进行节点属性补全,本文提出了一个新的预测方法来编码和整合多个元路径的语义,学习得到药物和疾病节点的拓扑嵌入.以节点间的拓扑关系为指导,对有属性的药物节点属性进行加权聚合,来补全没有属性的疾病节点.此外,本文还设计了一个元路径层面注意力机制和一个邻居层面注意力机制,分别融合来自多个元路径的语义信息和节点邻居的信息.采用了五倍交叉验证的方法进行评估,结果表明新的预测模型取得了比其它模型更高的预测性能.
随着第五次信息革命的兴盛,一种新型建筑体系—智能建筑应运而生.使用文献计量法,以Web of Science(WOS)数据库作为数据来源,搜集基于人工智能和大数据的智能建筑研究相关文献数据;利用 CiteSpace 软件绘制知识图谱;将数据可视化处理分析,以研究其涵盖的方向及热点.结果表明,前期研究热点主要有建筑能耗管理策略、简单传感网络和电气自动化在建筑领域的应用;当前的研究热点主要有物联网技术、基于数据驱动的建筑能耗预测和先进建筑能源管理技术.
传统的模糊C均值(FCM)算法容易受到噪声的影响,难以对具有褶皱、污渍和色彩差异大的苗族服饰图像进行有效的分割.本文提出可靠性模糊局部信息C均值聚类算法,在FCM的目标函数中增加一个模糊因子来度量局部的相似性,充分结合空间信息与灰度信息,提高对噪声的鲁棒性.此外,引入一个模糊不确定性聚类模型,对像素进行可靠性分析,进一步降低噪声点和边缘点的影响.利用含噪的苗族服饰图像进行实验,实验结果表明本文所提算法对含噪的苗族服饰图像分割效果好,对于褶皱、污渍及色彩差异大的苗族服饰图像,本文所提算法都获得最高的划分系数和最低的划分熵,分割质量均优于对比算法.
基数估计是数据库查询中关键的一步,数据库的查询优化器会根据基数估计的预期结果来从多个物理执行计划中选择最终要执行的计划.针对传统的基数估计方法没有考虑数据各个列之间可能存在的逻辑关系,在数据量过大时估计准确性较低的问题,本文提出了一种基于神经网络的多头注意力机制的基数估计模型,利用数据列之间的逻辑关系提高SQL特征关系的提取效率,通过针对语句的不同组成部分,采用多种细粒度的编码方式有效提取数据之间的逻辑特征;利用多头自注意力机制对特征数据进行加权计算,提高模型的预判准确性.在IMDb数据集上的实验结果表明,该模型可以有效提高基数估计的准确性.
依据电气前沿领域发展趋势及新工科建设要求,本文提出了以电气信息实时仿真器为核心的电力系统新工科实验平台建设方案,将需求分析、系统设计、镜像仿真和产品定义各个环节全程打通,训练培养学生项目开发能力,梳理贯通多课程的碎片知识;基于智能微电网实验项目教学案例,研究模型搭建、离线仿真、实时仿真、半实物仿真整个流程.教学实践证明,该平台可支撑新工科教学电气实验教学模式,对培养学生大工程观、工程思维和创新素质有重要意义,是对新型电力系统背景下电气新工科建设的有益探索.
