Blood cell counting based on U-Net++ and YOLOv5

Clinical information about a variety of disorders is available through blood cell counting, which is usually done by manual methods. However, manual methods are complex, time-consuming and susceptible to the subjective experience of inspectors. Although many efforts have been made to develop automated blood cell counting algorithms, the complexity of blood cell distribution and the highly overlapping nature of some red blood cells (RBCs) remain significant challenges that limit the improvement of analytical accuracy. Here, we proposed an end-to-end method for blood cell counting based on deep learning. Firstly, U-Net++ was used to segment the whole blood cell image into several regions of interest (ROI), and each ROI contains only one single cell or multiple overlapping cells. Subsequently, YOLOv5 was used to detect blood cells in each ROI. Specifically, we proposed several strategies, including fine classification of RBCs, adaptive adjustment for non-maximal suppression (NMS) threshold and blood cell morphology constraints to improve the accuracy of detection. Finally, the detection outcomes for each ROI were combined and superimposed. The results show that our method can effectively address the issue of high overlap and precisely segment and detect blood cells, with a 98.18% accuracy rate for blood cell counting.     

Weak signal detection and adaptive synchronous stability of a novel fifth-order memristive circuit system

This paper is devoted to introduce a novel complex fifth-order memristive circuit system and its applications in synchronous stability and weak signal detection. Firstly, the typical dynamical behaviors of the memristive system are discussed by chaotic phase portrait, complexity analysis, one-parameter bifurcation and Lyapunov exponent spectrum. Secondly, the adaptive control method is applied to realize the synchronization between the drive memristive system (DMS) and the response memristive system (RMS). The results indicate that the synchronization method has strong robustness and anti-interference ability. Thirdly, the weak signal detection of the novel five-dimensional memristive system is realized by using the extreme sensitivity of chaotic system to initial values. Finally, the fifth-order memristive circuit is designed by using basic electronic elements and simulated by Multisim software. And the anti-interference ability and sensitivity of the fifth-order memristive circuit are further verified by adding different weak disturbance signals at different positions of the circuit.     

An improved U-Net for cell confluence estimation

Cell confluence is an important metric to determine the growth and the best harvest time of adherent cells. At present, the evaluation of cell confluence mainly relies on experienced labor, and thus it is not conducive to the automated cell culture. In this paper, we proposed an improved U-Net algorithm (called DU-Net) for the segmentation of adherent cells. First, the general convolution was replaced by the dilated convolution to expand the receptive fields for feature extraction. Then, the convolutional layers were combined with the batch normalization layers to reduce the dependence of the network on initialization. As a result, the segmentation accuracy and F1-score of the proposed DU-Net for adherent cells with low confluence (<50%) reached 96.94% and 93.87%, respectively, and for those with high confluence (≥50%), they reached 98.63% and 98.98%, respectively. Further, the paired t-test results showed that the proposed DU-Net was statistically superior to the traditional U-Net algorithm.     

基于子空间投影的复杂水下环境运动小目标检测前跟踪方法

针对复杂水下环境运动小目标检测中存在的目标信号强度弱、信杂比低等问题,该文提出基于子空间投影的检测前跟踪(TBD)算法:对原始图像数据截取序列片段,将3维时空片段中的短时运动航迹投影到2维子空间平面;利用2维投影图中平面航迹的形态特征进行初步筛选,提取目标的有效运动区域;将2维平面中的目标短时航迹在局部区域重建3维时序,在3维航迹回溯过程中利用目标运动特征再次筛选目标短时航迹.通过上述分级检测机制,可实现快速高精度的目标短时航迹检测.结合前景检测以及基于层次凝聚聚类(HAC)的长时航迹检测算法,构建了针对运动小目标的完整检测前跟踪方法.最后使用实测声呐图像数据验证了算法的检测精度和检测速度.     

基于CFD技术的单人小型节能赛车的造型设计研究

目的尝试运用其他学科的研究手段对产品的造型设计进行分析,从而找到一种对造型设计的定量评价方法。方法通过运用CFD技术对造型设计进行分析,找出影响车辆风阻的因素,并对造型设计进行反复调整,直至达到合格的风阻设计要求。结果通过调整造型细节,达到有限条件下最优化的造型设计方案。结论在车辆造型设计的过程中,CFD分析方法能够提供一种科学有效的评价手段,可以对车辆的风阻进行模拟测试,进而影响到车身造型,造型设计也应是基于各种限制因素的理性表达过程。     

温度对燃烧包覆LiMn2O4/ZnO及其电性能的影响

通过葡萄糖辅助低温燃烧制备ZnO包覆型LiMn2O4,利用X射线衍射仪、扫描电子显微镜、循环伏安、交流阻抗以及恒流充放电测试等手段,研究了温度对产物晶体结构、微观形貌及电化学性能的影响。XRD结果表明所有产物均为单相尖晶石型LiMn2O4结构。SEM结果表明产物的颗粒尺寸随温度的升高而增大。电化学性能测试表明400℃和500℃制备的LiMn2O4/ZnO具有相对优异的电化学性能,室温1C条件下首次放电比容量分别为119.3mAh/g、116.3mAh/g,循环100次后容量保持率分别85.6%、87.8%。尖晶石LiMn2O4电极的阻抗谱特征与温度有关,电池的电化学性能主要受电荷转移电阻(Rct)影响。     

暗藏外遮阳卷帘盒的窗户结构研究

本文结合传统的外遮阳做法,对外遮阳的构造做法进行了创新,力求实现既不影响建筑外立面效果又能切实起到遮阳实现节能建筑的要求构造方式.     

Mn对22%Cr双相不锈钢700℃时效σ相及韧性的影响

利用光学显微镜(OM)、X射线衍射仪(XRD)、扫描电镜(SEM)、透射电镜(TEM)结合析出动力学和冲击实验,研究了不同Mn含量(4.3%,6.9%,9.7%,质量分数,下同)对22%Cr节镍型双相不锈钢700℃时效析出相形成和韧性的影响。结果表明:随Mn含量由4.3%增加至9.7%,时效76h,析出形貌分别为铁素体/奥氏体(δ/γ)界面细小σ相颗粒析出和铁素体晶内σ相/二次奥氏体(γ_2)共析组织。Mn含量增加使Avrami指数n减小,反应常数B增大,Mn元素参与并促进σ相析出,σ相开始析出和完全析出时间均提前,开始析出与完全析出的时间间隔增大,析出速率降低。时效过程中δ相分解量低于1%(体积分数,下同)对冲击韧度影响不大,δ相分解量由1%增至5%会显著降低冲击韧度。Mn含量增加在时效前期对冲击韧度有利,时效中期则会促使δ相分解量更早超过1%,导致冲击韧度快速下降。     

银/氯化银电极用于监测混凝土中氯离子含量的研究

采用干湿循环渗透法,通过实验室制备的银/氯化银电极来监测混凝土中的氯离子含量,测试了电极的响应性能和长期稳定性,研究了总氯离子含量与自由氯离子含量之间、总氯离子含量与电位之间的关系。结果表明:银/氯化银电极电位能比较好地监测到混凝土中氯离子含量变化的过程,具有良好的长期稳定性能。总氯离子含量随自由氯离子含量的增加而增加,两者之间呈现幂函数的规律。总氯离子含量随电位上升而下降,两者之间呈指数函数的规律。