Microscopic melanoma detection and classification: A framework of pixel‐based fusion and multilevel features reduction

The numbers of diagnosed patients by melanoma are drastic and contribute more deaths annually among young peoples. An approximately 192,310 new cases of skin cancer are diagnosed in 2019, which shows the importance of automated systems for the diagnosis process. Accordingly, this article presents an automated method for skin lesions detection and recognition using pixel‐based seed segmented images fusion and multilevel features reduction. The proposed method involves four key steps: (a) mean‐based function is implemented and fed input to top‐hat and bottom‐hat filters which later fused for contrast stretching, (b) seed region growing and graph‐cut method‐based lesion segmentation and fused both segmented lesions through pixel‐based fusion, (c) multilevel features such as histogram oriented gradient (HOG), speeded up robust features (SURF), and color are extracted and simple concatenation is performed, and (d) finally variance precise entropy‐based features reduction and classification through SVM via cubic kernel function. Two different experiments are performed for the evaluation of this method. The segmentation performance is evaluated on PH2, ISBI2016, and ISIC2017 with an accuracy of 95.86, 94.79, and 94.92%, respectively. The classification performance is evaluated on PH2 and ISBI2016 dataset with an accuracy of 98.20 and 95.42%, respectively. The results of the proposed automated systems are outstanding as compared to the current techniques reported in state of art, which demonstrate the validity of the proposed method.     

一种计算空间异面高压线间最短距离的方法

在电力工程建设、运行、管理中,需要遵循许多行业规范,尤其是高压线间的间距,关系到电网运行的安全与否。对于一些容易判断两线间最短距离的高压线,如平行的高压线等,可以方便的求出其最短距离,但是,在遇到一些不易判断出两线间最短距离位置的高压线时,需要通过一定的方法求出两高压线间的最短距离,以判断是否符合规范要求,确保电网的安全运行。本文提出一种利用Mathematica软件计算空间异面高压线间最短距离的方法。     

关于信息化测绘时代工程测量发展的思考

如今我国信息化技术全面发展，尤其对于工程测量工作领域来讲，不管是在工程建设和管理方面都产生不小的支撑引导效用。由此，笔者具体结合如今工程建设信息化测绘核心任何以及设备布置细节，进行结构整体安全管理周期和周边地理空间信息技术发展能效整理解析，试图将工程测量最新发展机遇和技术挑战问题处理完全。希望能够借此为日后一定时期范围内相关工程测量规划主体提供合理指导性建议内容，最终为我国各类工程事业可持续发展前景绽放奠定深刻适应基础。     

受限空间内天然气爆炸反应过程模拟分析

为定量研究受限空间内天然气爆炸反应动力学特征，开展了3个方面的研究工作，①建立了基于激波管的天然气爆炸过程数值分析模型；②将天然气气相燃烧动力学反应分解为53种反应组分、325种基元反应，给出了朗金―雨贡尼关系式和正激波的压强比、密度比和温度比计算方法；③利用化学反应模拟软件CHEMKIN构建天然气燃烧过程机理文件，对激波诱导受限空间内天然气混气爆炸过程进行数值模拟，讨论了反应过程、初始压力和空间尺寸对天然气爆炸过程的影响，并绘制了天然气爆炸温度、压力变化特征曲线。结果表明：采用入射激波模拟混气引爆过程中体系温度会出现跳跃式上升随之向下扰动；混气被引爆后温度逐步提高，在温度达到峰值时压力随之提高；提高初始压力将缩短混气引爆时间，高的初始压力可以得到更为迅速的反应速度和更高的爆炸压力；空间尺寸对散热作用的影响高于其对活性基团消毁作用的影响，小尺寸空间条件下可以获得更迅速的爆炸升压速度。     

Electrical Breakdown Properties and Space Charge Formation in High Temperature Region in Ultraviolet Ray Irradiated PVC

Polyvinyl chloride (PVC) is the most popular insulating material for electric wiring instruments. However, an exothermic reaction above 150 °C may cause deterioration of the insulating properties of PVC. Therefore, it is important to clarify the heat degradation in PVC, not only to investigate the ignition of electrical wiring products but also to use electrical products safely. It is known that ultraviolet (UV) irradiation causes chemical deterioration of PVC and an increase in its conductivity. Generally, it has been thought that the electrical breakdown properties, electrical conduction, and insulating performance are affected by space charge accumulation in an insulating material. A high temperature pulsed electroacoustic (PEA) system usable up to 250 °C has been developed, and the PEA system can measure the space charge distribution and conduction current in the high temperature range simultaneously. In this investigation, the space charge distribution and conduction current were measured up to electrical breakdown in a non‐UV irradiated sample (normal PVC) and in 353 nm and 253 nm UV‐irradiated PVC samples in the range from room temperature to 200 °C in a DC electric field. In the short wavelength UV irradiated PVC sample (253 nm, 300 h), a deterioration of breakdown strength at 90 °C to 150 °C and negative packet‐like charges were observed at 60 °C and 100 °C, a positive charge accumulated in front of both the anode and cathode above 90 °C, and a higher electric field near the cathode side because the positive charge of the cathode side was greater.     

Model-Based Design Space Exploration for FPGA-based Image Processing Applications Employing Parameterizable Approximations

The increasing demand for low power consumption and high computational performance is outpacing available technological improvements in embedded systems. Approximate computing is a novel design paradigm trying to bridge this gap by leveraging the inherent error resilience of certain applications and trading in quality to achieve reductions in resource usage. Numerous approximation methods have emerged in this research field. While these methods are commonly demonstrated in isolation, their combination can increase the achieved benefits in complex systems. However, the propagation of errors throughout the system necessitates a global optimization of parameters, leading to an exponentially growing design space. Additionally, the parameterization of approximated components must consider potential cross-dependencies between them. This work proposes a systematic approach to integrate and optimally configure parameterizable approximate components in FPGA-based applications, focusing on low-level but high-bandwidth image processing pipelines. The design space is explored by a multi-objective genetic algorithm which takes parameter dependencies between different components into account. During the exploration, appropriate models are used to estimate the quality-resource trade-off for probed solutions without the need for time-consuming synthesis. We demonstrate and evaluate the effectiveness of our approach on two image processing applications that employ multiple approximations. The experimental results show that the proposed methods are able to produce a wide range of Pareto-optimal solutions, offering various choices regarding the desired quality-resource trade-off.     

基于聚类的数据加权优化在犯罪预测中的应用

近年来，我国传统暴力犯罪与成年人犯罪呈下降态势，但是，犯罪案由层出不穷。为有效提升公安实践工作中犯罪预测能力，打击各类违法犯罪事件,本文针对犯罪数据，提出一种新型犯罪预测模型。利用密度聚类分析方法将犯罪数据分类，然后进行数据降维提取关键属性生成特征数据，继而对特征数据进行加权优化并采用机器学习的方式对特征数据进行学习，从而预测犯罪案由。实验结果表明，与传统方法相比，本文方法具有更好的预测效果，为公安实践工作中类似案件的侦破和预防，提供新的路径支撑。     

基于密集神经网络的灰度图像着色算法

针对在灰度图像着色领域中，传统算法信息提取率不高、着色效果不理想的问题，提出了基于密集神经网络的灰度图像着色算法，以实现改善着色效果，让人眼更好地观察图片信息的目的。利用密集神经网络的信息提取高效性，构建并训练了一个端到端的深度学习模型，对图像中的各类信息及特征进行提取。训练网络时与原图像进行对比，以逐渐减小网络输出结果的信息、分类等各类型的损失。训练完成后，只需向网络输入一张灰度图片，即可生成一张颜色饱满、鲜明逼真的彩色图片。实验结果表明，引入密集网络后，可有效改善着色过程中的漏色、细节信息损失、对比度低等问题，所提算法着色效果较基于VGG网络及U-Net、双流网络结构、残差网络（ResNet）等性能优异的先进着色算法而言取得了显著的改进。     

基于特征融合的中文简历解析方法研究

针对基于规则和统计的传统中文简历解析方法效率低、成本高、泛化能力差的缺点，提出一种基于特征融合的中文简历解析方法，即级联Word2Vec生成的词向量和用BLSTM（Bidirectional Long Short-Term Memory）建模字序列生成的词向量，然后再结合BLSTM和CRF（Conditional Random Fields）对中文简历进行解析（BLSTM-CRF）。为了提高中文简历解析的效率，级联包含字序列信息的词向量和用Word2Vec生成的词向量，融合成一个新的词向量表示；再由BLSTM强大的学习能力融合词的上下文信息，输出所有可能标签序列的分值给CRF层；再由CRF引入标签之间约束关系求解最优序列。利用梯度下降算法训练神经网络，使用预先训练的词向量和Dropout优化神经网络，最终完成对中文简历的解析工作。实验结果表明，所提的特征融合方法优于传统的简历解析方法。     

结合细粒度特征与深度卷积网络的手绘图检索

目的 传统的手绘图像检索方法主要集中在检索相同类别的图像，忽略了手绘图像的细粒度特征。对此，提出了一种新的结合细粒度特征与深度卷积网络的手绘图像检索方法，既注重通过深度跨域实现整体匹配，也实现细粒度细节匹配。方法 首先构建多通道混合卷积神经网络，对手绘图像和自然图像分别进行不同的处理；其次通过在网络中加入注意力模型来获取细粒度特征；最后将粗细特征融合，进行相似性度量，得到检索结果。结果 在不同的数据库上进行实验，与传统的尺度不变特征（SIFT）、方向梯度直方图（HOG）和深度手绘模型Deep SaN（sketch-a-net）、Deep 3DS（sketch）、Deep TSN（triplet sketch net）等5种基准方法进行比较，选取了Top-1和Top-10，在鞋子数据集上，本文方法Top-1正确率提升了12%，在椅子数据集上，本文方法Top-1正确率提升了11%，Top-10提升了3%，与传统的手绘检索方法相比，本文方法得到了更高的准确率。在实验中，本文方法通过手绘图像能在第1幅检索出绝大多数的目标图像，达到了实例级别手绘检索的目的。结论 提出了一种新的手绘图像检索方法，为手绘图像和自然图像的跨域检索提供了一种新思路，进行实例级别的手绘检索，与原有的方法相比，检索精度得到明显提升，证明了本文方法的可行性。