基于自监督学习的病理图像层次分割

在苏木精-伊红(HE)染色病理图像中，细胞染色分布的不均匀和各类组织形态的多样性给病理图像的自动分割带来极大挑战。为解决该问题，提出了一种基于自监督学习的病理图像三步层次分割方法，对病理图像中各类组织进行由粗略到精细的全自动逐层分割。首先，根据互信息的计算结果在RGB色彩空间中进行特征选择；其次，采用K-means聚类将图像初步分割为各类组织结构的色彩稳定区域与模糊区域；然后，以色彩稳定区域为训练集采用朴素贝叶斯分类对模糊区域进行进一步分割，得到完整的细胞核、细胞质和胞外间隙这三类组织结构；最后，对细胞核部分进行结合形状和色彩强度的混合分水岭分割得到细胞核间的精确边界，进而量化计算细胞核个数、核占比、核质比等指标。对脑膜瘤HE染色病理图像的分割实验结果表明，所提方法对于染色和细胞形态差异保持较高的鲁棒性，各类组织区域分割误差在5%以内，在细胞核分割精度的对比实验中平均正确率在96%以上，满足临床自动图像分析的要求，其量化结果可以为定量病理分析提供依据。     

涡流空气分级机熵产与分级性能分析

利用热力学第二定律中的熵产理论对涡流空气分级机各不可逆因素引起的熵产进行分析，通过粉料分级试验对其分级性能进行验证，获得了黏性熵产、湍流熵产和壁面熵产分布特点及操作参数对熵产和分级精度的影响规律。熵产分析结果表明，涡流空气分级机内湍流熵产和壁面熵产占总熵产的比例高达56.41%和43.11%，湍流熵产主要产生于转笼叶片间和转笼内部，进风口和细粉出口壁面剪切引起较大壁面熵产；此外，转笼转速和进口风速变化分别仅对转笼区域和切向进风口区域内气流运动熵产影响较大，进口风速-转笼转速处于8.6m/s、 800r/min和18m/s、1200r/min操作工况附近时，涡流空气分级机内总熵产/总能变化率较小，分级流场稳定性较高，对粗、细颗粒分离有利，该工况下分级机的粉料分级试验效果较好，说明熵产理论可用于涡流分级机内流动分析及其操作参数的优化匹配。     

DS-M型超细分选机的开发与应用

文章介绍了高效超细粉煤灰专用分级机的研究,在此基础上,重点介绍了DS-M型超细分级机的工作原理及性能特点,分析了DS-M型超细分级机组成的圈流粉磨分选系统的应用效果。实践证明,针对超细粉煤灰分选的选粉机的设计是成功的,在45μm的超细粒径下的分级效率达到80%～90%     

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.     

基于数据驱动理念的电力日负荷曲线预测方法研究

针对短期日负荷预测的精度问题,本文提出一种基于数据驱动理念的电力负荷预测方法。在建立预测模型前对所给数据采取一定的预处理:首先提取所收集的海量数据的负荷特征,对负荷特征进行分析,然后进行负荷数据与影响负荷值的因素之间的相关性分析,以此确定对负荷影响较密切的因素,随后建立分类器得到各主要影响因素与各负荷类别之间的关系为后续预测模型奠定基础。对预处理后得到的不同类型的负荷数据采用最小二乘支持向量机方法建立不同的负荷预测模型。以南方某发达城市2008年的负荷数据作为算例验证数据,将本文所提负荷预测方法所得结果与未经数据预处理的负荷预测方法所得结果进行比较,结果表明本文提出的方法得到的预测结果精度较传统方法提高约6%。     

基于光谱分类模型的保险杠物证无损研究

采用中红外光谱结合化学计量学的方法对车用保险杠碎片进行鉴别，分别对52个车用保险杠碎片样本的全波段光谱数据、指纹区光谱数据和主成分分析降维后的光谱数据建立Fisher判别分析和K近邻算法2种分类模型，并对分类结果进行比较。结果表明，主成分分析提取特征变量后构建的分类模型，分类的准确率更高，对聚丙烯（PP）、PP/滑石粉、PP/滑石粉/碳酸钙（CaCO₃）3种类型的样本分类准确率达到92.3 %，对PP/滑石粉类型中的10种品牌样本分类准确率达到88.9 %，分类结果理想；在构建的2种分类模型中，Fisher判别分析模型的分类率远高于K近邻算法模型，分析认为K近邻算法模型受到样本不均衡的影响；中红外光谱结合化学计量学可以实现对车用保险杠碎片的准确区分，且满足快速、无损的检验要求。     

Effect of excess hydrogen on hydrogen fueled internal combustion engine under full load

Detailed hydrogen-air chemical reaction mechanisms were coupled with three dimension grids of an experimental hydrogen fueled internal combustion engine (HICE) to establish a combustion model based on CONVERGE software. The influence of excess hydrogen coefficient on the combustion and emission characteristics of HICE under full load was studied based on the CFD model. Simulation results showed that excess hydrogen leaded to higher concentration of OH species in flame front, and quicker hydrogen-oxygen reaction and flame propagation speed, which in turn leaded to higher pressure and temperature in cylinder. The rise of pressure and temperature in turn contributed to the increase of indicate power but un-burned hydrogen leaded to decrease of efficiency. NOx, especially NO emissions decreased significantly with excess hydrogen under full load not only because increased of H concentration, and decreased of O and OH concentration, which leaded to reverse reaction of NO formation through thermal NO routes. Low excess hydrogen coefficient can achieve a good trade-off between power and emissions under full load.     

Application of Vis–NIR hyperspectral imaging in classification between fresh and frozen-thawed pork Longissimus Dorsi muscles

Fresh and frozen-thawed (F-T) pork meats were classified by Vis–NIR hyperspectral imaging. Eight optimal wavelengths (624, 673, 460, 588, 583, 448, 552 and 609 nm) were selected by successive projections algorithm (SPA). The first three principal components (PCs) obtained by principal component analysis (PCA) accounted for over 99.98% of variance. Gray-level-gradient co-occurrence matrix (GLGCM) was applied to extract 45 textural features from the PC images. The correct classification rate (CCR) was employed to evaluate the performance of the partial least squares-discriminate analysis (PLS-DA) models, by using (A) the reflected spectra at full wavelengths and (B) those at the optimal wavelengths, (C) the extracted textures based on the PC images, and (D) the fused variables combining spectra at the optimal wavelengths and textures. The results showed that the best CCR of 97.73% was achieved by applying (D), confirming the high potential of textures for fresh and F-T meat discrimination.     

Duplex real-time PCR assay for the simultaneous determination of the roe deer (Capreolus capreolus) and deer (sum of fallow deer,red deer and sika deer) content in game meat products

Due to the high price of game meat, food producers may be tempted to adulterate their products with cheaper meat. This paper presents a duplex real-time PCR assay which allows the simultaneous determination of the content of roe deer (Capreolus capreolus) and deer* (the sum of fallow deer (Dama dama), red deer (Cervus elaphus) and sika deer (Cervus nippon)) in food products to detect food adulteration. Relative quantification is carried out by using a reference (“all meat”) PCR assay based on the myostatin gene. The quantification approach was validated by analyzing binary meat mixtures with pork, “all game” meat mixtures containing each of the four game species in pork and a model game sausage. Compared to singleplex assays the duplex assay is time and cost saving. Thus, it is highly applicable to routine analysis in order to verify the authenticity of game meat products.     

Mining citizen emotions to estimate the urgency of urban issues

Crowdsourcing technology offers exciting possibilities for local governments. Specifically, citizens are increasingly taking part in reporting and discussing issues related to their neighborhood and problems they encounter on a daily basis, such as overflowing trash-bins, broken footpaths and lifts, illegal graffiti, and potholes. Pervasive citizen participation enables local governments to respond more efficiently to these urban issues. This interaction between citizens and municipalities is largely promoted by civic engagement platforms, such as See-Click-Fix, FixMyStreet, CitySourced, and OpenIDEO, which allow citizens to report urban issues by entering free text describing what needs to be done, fixed or changed. In order to develop appropriate action plans and priorities, government officials need to figure out how urgent are the reported issues. In this paper we propose to estimate the urgency of urban issues by mining different emotions that are implicit in the text describing the issue. More specifically, a reported issue is first categorized according to the emotions expressed in it, and then the corresponding emotion scores are combined in order to produce a final urgency level for the reported issue. Our experiments use the SeeClickFix hackathon data and diverse emotion classification algorithms. They indicate that (i) emotions can be categorized efficiently with supervised learning algorithms, and (ii) the use of citizen emotions leads to accurate urgency estimates. Further, using additional features such as the type of issue or its author leads to no further accuracy gains.