基于改进3D UNet的前列腺MR图像分割

针对前列腺磁共振 (magnetic resonance, MR)图像边缘模糊、对比度较低,灰度值分布不均衡而导致分割精度较差的问题,提出了一种结合双路径注意力(dual path attention,DPA) 和多尺度特征聚合(multi-scale feature aggregation,MFA) 模块的改进3D UNet网络模型。首先,对数据集进行重采样和裁剪处理以适应模型输入。然后,在3D UNet网络的编码器各层引入DPA 并添加残差连接,加强特征的 编码能力。同时,在网络解码器中加入MFA模块,以充分利用空间上下文信息,增强语义信息。最后,在公开数据集PROMISE12上进行验证,所提出的模型的Dice系数为89.90%,Hausdorff 距离为9.37 mm。相比较于其他模型,所提出模型的分割结果更优,且参数量和运算量更少。     

基于提取双选紧密特征的RGB-D显著性检测网络

针对现有算法对不同来源特征之间的交互选择关注度欠缺以及对跨模态特征提取不充分的问题,提出了一种基于提取双选紧密特征的RGB-D显著性检测网络。首先,为了筛选出能够同时增强RGB图像显著区域和深度图像显著区域的特征,引入双向选择模块(bi-directional selection module, BSM);为了解决跨模态特征提取不充分,导致算法计算冗余且精度低的问题,引入紧密提取模块(dense extraction module, DEM);最后,通过特征聚合模块(feature aggregation module, FAM)对密集特征进行级联融合,并将循环残差优化模块(recurrent residual refinement aggregation module, RAM)配合深度监督实现粗显著图的持续优化,最终得到精确的显著图。在4个广泛使用的数据集上进行的综合实验表明,本文提出的算法在4个关键指标方面优于7种现有方法。     

基于样本扩充和特征优选的IGWO优化SVM的变压器故障诊断技术

为了增强变压器故障诊断模型对不平衡样本的学习能力从而提高少数类故障样本的识别精度,提出了一种基于样本扩充和特征优选的融合多策略改进灰狼算法(improved grey wolf optimizer with multi-strategy, IGWO)优化支持向量机(support vector machine, SVM)的变压器故障诊断技术。首先,使用基于K最近邻过采样方法及核密度估计自适应样本合成算法的混合过采样技术对少数类样本进行扩充得到均衡数据集,并在此基础上采用方差分析对变压器候选比值征兆进行特征优选。然后,通过改进灰狼优化算法(grey wolf optimizer, GWO)初始化策略、参数及位置更新公式,并引入差分进化策略调整种群,提出了融合多策略的改进灰狼算法。最后,构建了一种基于混合过采样技术的IGWO优化SVM的变压器故障诊断模型,并通过多组对比实验验证了所提方法能够有效增强模型对少数类故障样本的识别能力,并提升模型的整体分类性能。     

基于同步相量数据幅频特征的次超同步振荡模式辨识

随着可再生能源和高压直流输电的快速发展,次超同步振荡事故频发,对现有电力系统振荡的在线监测提出了更高要求。为此,提出了一种基于同步相量数据幅频特征的次超同步振荡模式辨识方法。首先分析了次同步振荡和超同步振荡对同步相量测量装置(phasor measurement unit, PMU)数据的影响机制,结果表明,PMU数据的正负频谱与次超同步振荡的模态线性相关。其次利用多点PMU数据相干谱判别振荡与噪声,有效减少了噪声引起的误判断。然后对次超同步振荡下的PMU数据开展频谱分析,建立了4个幅频特征量,并将振荡数据的特征集合作为输入训练并优化极限梯度提升树(extreme gradient boosting, XGBoost)模型,建立幅频特征与振荡模式的映射关系。所提方法利用振荡环境下PMU数据的固有幅频特征以及XGBoost算法强大的泛化性与计算效率,实现了噪声环境下次超同步振荡模式的快速、准确辨识。最后,利用仿真数据和实测数据验证了所提方法的有效性和实用性。     

基于高频重构信号与Bayes-XGBoost的低压电弧故障辨识方法研究

针对低压配电系统中单个用电负载支路串联电弧故障辨识困难的问题,提出一种基于高频重构信号和Bayes-XGBoost的低压电弧辨识方法。首先,搭建多支路、多负载类型的低压电弧故障真型实验平台,并采集相关数据。其次,基于故障前后主线路电流高频信号变化规律,提出信号微弱变化叠加法重构故障有效信号。最后,建立适用于单个负载支路电弧故障辨识的XGBoost模型,并采用Bayes算法对模型多个超参数进行优化。实验结果表明,所提方法在多种工况下对单个负载支路电弧故障具有较高的辨识准确率。与6种主流故障分析方法对比,所提方法在精度、训练速度和泛化能力等方面展现出了显著的优越性,有利于实现低压配电系统单个负载支路电弧故障的可靠辨识。     

基于状态熵权和双轨制TOPSIS的电能质量实时综合评估方法

为实现电能质量连续、实时综合评估,提出了一种全域电能质量评估体系,设计了综合评估方法。首先,使用熵权法构造各指标间数据信息量的对比通道,实现对电能质量指标影响权重的常权赋予,保证赋权的客观性。通过构造状态变元,对计算单元内各点权重进行动态调整,保证指标时序赋权的动态特性,增强时域下的权重分辨率。然后,提出了双轨制TOPSIS评估方法,分别开辟数据与等级的TOPSIS计算路径,避免数据与等级杂糅对两者内部相对关系的破坏,减小评估标准对于数据的依赖,保证各时段评估标准的一致性。最后,实时判断两者贴合度,完成数据向等级的并轨,得到以综合评估等级为判据的电能质量整体状态评价和以状态权重为参考的等级变化成因分析。通过算例分析验证了该评估方法能够实现实时评估,具备准确快速地反映电能质量随时间变化的能力,且评估流程具有普适性。     

Multi-scale-based joint super-resolution and inverse tone-mapping with data synthesis for UHD HDR video

The performance of current joint super-resolution (SR) and inverse tone-mapping (ITM) frameworks is limited since they only account for information in small local receptive fields. Moreover, the SDR images in the existing dataset for joint SR-ITM are oversaturated compared to the HDR ground truths. The models trained on this dataset produce HDR images with color shift. This paper proposes a multi-scale-based joint SR-ITM model to reconstruct HR HDR videos. Image features are downsampled to different resolutions to increase the local receptive fields. Thus the proposed model can react to more complex patterns of input images. And we design a novel multi-path residual dense block (MRDB) as the model’s fundamental component to extract features. The proposed MRDBs can improve performance by combining dense feature learning and novel multi-path residual learning. Experiments show that the proposed model outperforms the state-of-the-art methods in terms of quantitative and qualitative results. Furthermore, we propose a data synthesis pipeline to generate perceptually identical SDR images from their HDR counterparts. These SDR-HDR pairs are used to create a new dataset. Experiments demonstrate that models trained with our new dataset prevent color shift and preserve creative intent.     

Ship detection based on multi-scale weighted fusion

Ship surveillance plays an important role in ensuring the safety of maritime transportation and navigation. Due to the influence of factors such as waves and special weather, the existing detection methods still cannot balance the accuracy, speed and the parameters of the model in the changeable and complex marine environment. To solve this problem, this paper proposes an improved real-time method based on YOLOv5, which has few parameters and achieves high detection accuracy with little memory and computation cost. Collaborative Attention (CA) mechanism is added to the network structure, which enables the model to more accurately locate and identify target regions. We also design a Spatial Pyramid Pooling module (SPP) and a weighted pyramid network called Bidirectional Feature Pyramid Network (BiFPN) based on the characteristics of the ships to better fuse feature information. Transformer encoder is introduced to capture long-distance dependencies and preserve global and local features to the greatest extent. Furthermore, the ability of our proposed structure to localize objects at each stage is improved through integrating the output of multiple modules. The experimental results show that, the comprehensive performance of this method is better than the existing technology in ship detection on different evaluation criteria.     

Relational-Convergent Transformer for image captioning

Image captioning describes the visual content of a given image by using natural language sentences, and plays a key role in the fusion and utilization of the image features. However, in the existing image captioning models, the decoder sometimes fails to efficiently capture the relationships between image features because of their lack of sequential dependencies. In this paper, we propose a Relational-Convergent Transformer (RCT) network to obtain complex intramodality representations in image captioning. In RCT, a Relational Fusion Module (RFM) is designed for capturing the local and global information of an image by a recursive fusion. Then, a Relational-Convergent Attention (RCA) is proposed, which is composed of a self-attention and a hierarchical fusion module for aggregating global relational information to extract a more comprehensive intramodal contextual representation. To validate the effectiveness of the proposed model, extensive experiments are conducted on the MSCOCO dataset. The experimental results show that the proposed method outperforms some of the state-of-the-art methods.     

Ensemble feature selection and classification methods for machine learning-based coronary artery disease diagnosis

Coronary artery disease (CAD) is a condition in which the heart is not fed sufficiently as a result of the accumulation of fatty matter. As reported by the World Health Organization, around 32% of the total deaths in the world are caused by CAD, and it is estimated that approximately 23.6 million people will die from this disease in 2030. CAD develops over time, and the diagnosis of this disease is difficult until a blockage or a heart attack occurs. In order to bypass the side effects and high costs of the current methods, researchers have proposed to diagnose CADs with computer-aided systems, which analyze some physical and biochemical values at a lower cost. In this study, for the CAD diagnosis, (i) seven different computational feature selection (FS) methods, one domain knowledge-based FS method, and different classification algorithms have been evaluated; (ii) an exhaustive ensemble FS method and a probabilistic ensemble FS method have been proposed. The proposed approach is tested on three publicly available CAD data sets using six different classification algorithms and four different variants of voting algorithms. The performance metrics have been comparatively evaluated with numerous combinations of classifiers and FS methods. The multi-layer perceptron classifier obtained satisfactory results on three data sets. Performance evaluations show that the proposed approach resulted in 91.78%, 85.55%, and 85.47% accuracy for the Z-Alizadeh Sani, Statlog, and Cleveland data sets, respectively.