Wisdom of management in ＂The quintessence of wisdom in books of all sorts＂

This paper briefly introduces the wisdom of management contained in the quintessence of the wisdom of Chinese ancient sages ＂The quintessence of wisdom in books of all sorts＂, and explores the application of the traditional Chinese wisdom in resolving vari- ous dilemmas or crisis in today＇s human society, to help the society, the nation, and the enterprises solve the management problems.

基于视频和BCE-YOLO模型的奶牛采食行为检测

【目的】动物采食行为是一个重要的动物福利评价指标,本研究旨在解决复杂饲养环境下奶牛采食行为识别精度差、特征提取不充分的问题,实现对奶牛采食行为的自动监控。【方法】本文提出了一种基于改进BCEYOLO模型的识别方法,该方法通过添加BiFormer、CoT、EMA 3个增强模块,提高YOLOv8模型特征提取的能力,进一步与优于Staple、SiameseRPN算法的Deep SORT算法结合,实现对奶牛采食时头部轨迹的跟踪。在奶牛采食过程的俯视和正视视频中提取11288张图像,按照6∶1比例分为训练集和测试集,构建采食数据集。【结果】改进的BCE-YOLO模型在前方和上方拍摄的数据集上精确度分别为77.73%、76.32%,召回率分别为82.57%、86.33%,平均精确度均值分别为83.70%、76.81%;相较于YOLOv8模型,整体性能提升6~8个百分点。Deep SORT算法相比于Staple、SiameseRPN算法,综合性能提高1~4个百分点;并且改进的BCE-YOLO模型与Deep SORT目标跟踪算法结合良好,能对奶牛采食行为进行准确跟踪且有效地抑制了奶牛ID(Identity document)的变更。【结论】本文提出的方法能有效解决复杂饲养环境下奶牛采食行为识别精度差、特征提取不充分的问题,为智能畜牧与精确养殖提供重要参考。

基于SORT映射的IRCMFDE在旋转机械故障诊断中的应用

针对旋转机械振动信号的强非线性和非平稳性,导致故障特征提取困难的问题,提出了一种基于SORT映射的改进精细复合多尺度波动散布熵(IRCMFDE)和蝙蝠算法优化的相关向量机(BA-RVM)的旋转机械故障诊断方法。首先,利用SORT映射函数替换了精细复合多尺度波动散布熵(RCMFDE)方法的正态累积分布函数,同时对RCMFDE方法的粗粒化方式进行了改进,提出了基于SORT映射的IRCMFDE方法;随后,利用IRCMFDE方法提取了旋转机械振动信号的故障特征,构造了故障特征集;最后,采用BA-RVM分类器对旋转机械的故障类型进行了智能化的识别和分类;将基于IRCMFDE和BA-RVM的故障诊断方法应用于滚动轴承、离心泵和齿轮箱的实验数据分析,并将其与现有故障诊断方法进行了对比分析。研究结果表明:基于IRCMFDE和BA-RVM的故障诊断方法能够有效地识别旋转机械的故障状态,识别准确率分别达到了100%、98%和99%,相比基于RCMFDE、精细复合多尺度熵、精细复合多尺度模糊熵、精细复合多尺度排列熵和精细复合多尺度散布熵的故障特征提取方法,该故障诊断方法的效率和平均识别准确率均优于对比方法,其更适合应用于旋转机械的在线实时故障监测。

适用于无人机的自动跟踪算法的研究

入侵农田问题给试验田的安全保护带来了严重挑战,传统的保护手段存在诸多限制。为解决这一问题,将无人机技术和目标检测与跟踪算法相结合,提出一种创新的解决方案。该方法通过无人机高空航拍视角获取农田图像数据,并利用YOLO(You Only Look Once)算法实现实时目标检测。同时,采用SORT(Simple Online and Realtime Tracking)算法对入侵目标进行持续跟踪。通过在海南试验田中的应用实验验证该方法的可行性和有效性。实验结果表明,基于YOLO和SORT算法的无人机目标检测与跟踪系统能够在0.4 s内快速检测和跟踪入侵农田目标,为试验田的安全保护工作提供了重要支持。

Digital Twin Technology of Human-Machine Integration in Cross-Belt Sorting System

The Chinese express delivery industry processes nearly 110 billion items in 2022,averaging an annual growth rate of 200%.Among the various types of sorting systems used for handling express items,cross-belt sorting systems stand out as the most crucial.However,despite their high degree of automation,the workload for operators has intensified owing to the surging volume of express items.In the era of Industry 5.0,it is imperative to adopt new technologies that not only enhance worker welfare but also improve the efficiency of cross-belt systems.Striking a balance between efficiency in handling express items and operator well-being is challenging.Digital twin technology offers a promising solution in this respect.A realization method of a human-machine integrated digital twin is proposed in this study,enabling the interaction of biological human bodies,virtual human bodies,virtual equipment,and logistics equipment in a closed loop,thus setting an operating framework.Key technologies in the proposed framework include a collection of heterogeneous data from multiple sources,construction of the relationship between operator fatigue and operation efficiency based on physiological measurements,virtual model construction,and an online optimization module based on real-time simulation.The feasibility of the proposed method was verified in an express distribution center.

A novel integrated microfluidic chip for on-demand electrostatic droplet charging and sorting

On-demand droplet sorting is extensively applied for the efficient manipulation and genome-wide analysis of individual cells.However,state-of-the-art microfluidic chips for droplet sorting still suffer from low sorting speeds,sample loss,and labor-intensive preparation procedures.Here,we demonstrate the development of a novel microfluidic chip that integrates droplet generation,on-demand electrostatic droplet charging,and high-throughput sorting.The charging electrode is a copper wire buried above the nozzle of the microchannel,and the deflecting electrode is the phosphate buffered saline in the microchannel,which greatly simplifies the structure and fabrication process of the chip.Moreover,this chip is capable of high-frequency droplet generation and sorting,with a frequency of 11.757 kHz in the drop state.The chip completes the selective charging process via electrostatic induction during droplet generation.On-demand charged microdroplets can arbitrarilymove to specific exit channels in a three-dimensional(3D)-deflected electric field,which can be controlled according to user requirements,and the flux of droplet deflection is thereby significantly enhanced.Furthermore,a lossless modification strategy is presented to improve the accuracy of droplet deflection or harvest rate from 97.49% to 99.38% by monitoring the frequency of droplet generation in real time and feeding it back to the charging signal.This chip has great potential for quantitative processing and analysis of single cells for elucidating cell-to-cell variations.

Microfluidic thermotaxic selection of highlymotile sperm and in vitro fertilization

The selection of the most motile and functionally competent sperm is an essential basis for in vitro fertilization(IVF)and normal embryonic development.Widely adopted clinical approaches for sperm sample processing intensely rely on centrifugation and wash steps that may induce mechanical damage and oxidative stress to sperm.Although a few microfluidic sperm sorting devices may avoid these adverse effects by exploiting intrinsic guidance mechanisms of sperm swimming,none of these approaches have been fully validated by clinical-grade assessment criteria.In this study,a microfluidic sperm sorting device that enables the selection of highly motile and functional sperm via their intrinsic thermotaxis is presented.Bioinspired by the temperature microenvironment in the fallopian tube during natural sperm selection,a microfluidic device with controllable temperature gradients along the sperm separation channel was designed and fabricated.This study investigated the optimal temperature conditions for human sperm selection and fully characterized thermotaxis-selected sperm with 45 human sperm samples.Results indicated that a temperature range of 35–36.5℃along the separation channel significantly improves human sperm motility rate((85.25±6.28)%vs.(60.72±1.37)%;P=0.0484),increases normal sperm morphology rate((16.42±1.43)%vs.(12.55±0.88)%;P<0.0001),and reduces DNA fragmentation((7.44±0.79)%vs.(10.36±0.72)%;P=0.0485)compared to the nonthermotaxis group.Sperm thermotaxis is species-specific,and selected mouse sperm displayed the highest motility in response to a temperature range of 36–37.5℃ along the separation channel.Furthermore,IVF experiments indicated that the selected sperm permitted an increased fertilization rate and improved embryonic development from zygote to blastocyst.This microfluidic thermotaxic selection approach will be translated into clinical practice to improve the IVF success rate for patients with oligozoospermia and asthenozoospermia.

Comparative analysis shows high level of lineage sorting in genomic regions with low recombination in the extended Picea likiangensis species complex

Genome-scale data,while promising for illuminating phylogenetic relationships,frequently pose a conundrum by yielding conflicting topologies and highly variable gene tree distributions(Pease et al.,2016).This complexity likely arises from the reticulate evolution observed in many taxa,where genetic information exchange occurs through diverse biological processes.

Phylotranscriptomic discordance is best explained by incomplete lineage sorting within Allium subgenus Cyathophora and thus hemiplasy accounts for interspecific trait transition

The transition of traits between genetically related lineages is a fascinating topic that provides clues to understanding the drivers of speciation and diversification.Much can be learned about this process from phylogeny-based trait evolution.However,such inference is often plagued by genome-wide gene-tree discordance(GTD),mostly due to incomplete lineage sorting(ILS)and/or introgressive hybridization,especially when the genes underlying the traits appear discordant.Here,by collecting transcriptomes,whole chloroplast genomes(cpDNA),and population genetic datasets,we used the coalescent model to turn GTD into a source of information for ILS and employed hemiplasy to explain specific cases of apparent“phylogenetic discordance”between different morphological traits and probable species phylogeny in the Allium subg.Cyathophora.Both concatenation and coalescence methods consistently showed the same phylogenetic topology for species tree inference based on single-copy genes(SCGs),as supported by the KS distribution.However,GTD was high across the genomes of subg.Cyathophora:~27%e38.9%of the SCG trees were in conflict with the species tree.Plasmid and nuclear incongruence was also present.Our coalescent simulations indicated that such GTD was mainly a product of ILS.Our hemiplasy risk factor calculations supported that random fixation of ancient polymorphisms in different populations during successive speciation events along the subg.Cyathophora phylogeny may have caused the character transition,as well as the anomalous cpDNA tree.Our study exemplifies how phylogenetic noise can be transformed into evolutionary information for understanding character state transitions along species phylogenies.

Biogenesis of Rab14-positive Endosome Buds at Golgi-endosome Contacts by the RhoBTB3-SHIP164-Vps26B Complex

As one of the basic processes of cellular activity,endocytosis sorting determines the fate of many proteins on the endosomal membranes,thus affecting a variety of important cellular processes,such as nutrient uptake,cell signal transduction,intracellular ion homeostasis,etc.

A Multi-Objective Optimization for Locating Maintenance Stations and Operator Dispatching of Corrective Maintenance

In this study,we introduce a novel multi-objective optimization model tailored for modern manufacturing,aiming to mitigate the cost impacts of operational disruptions through optimized corrective maintenance.Central to our approach is the strategic placement of maintenance stations and the efficient allocation of personnel,addressing a crucial gap in the integration of maintenance personnel dispatching and station selection.Our model uniquely combines the spatial distribution of machinery with the expertise of operators to achieve a harmonious balance between maintenance efficiency and cost-effectiveness.The core of our methodology is the NSGA Ⅲ+Dispatch,an advanced adaptation of the Non-Dominated Sorting Genetic Algorithm Ⅲ(NSGA-Ⅲ),meticulously designed for the selection of maintenance stations and effective operator dispatching.This method integrates a comprehensive coding process,crossover operator,and mutation operator to efficiently manage multiple objectives.Rigorous empirical testing,including a detailed analysis from a taiwan region electronic equipment manufacturer,validated the effectiveness of our approach across various scenarios of machine failure frequencies and operator configurations.The findings reveal that the proposed model significantly outperforms current practices by reducing response times by up to 23%in low-frequency and 28.23%in high-frequency machine failure scenarios,leading to notable improvements in efficiency and cost reduction.Additionally,it demonstrates significant improvements in oper-ational efficiency,particularly in selective high-frequency failure contexts,while ensuring substantial manpower cost savings without compromising on operational effectiveness.This research significantly advances maintenance strategies in production environments,providing the manufacturing industry with practical,optimized solutions for diverse machine malfunction situations.Furthermore,the methodologies and principles developed in this study have potential applications in various other sectors,including healthcare,transportation,and energy,where maintenance efficiency and resource optimization are equally critical.

基于改进Faster RCNN的茶叶叶部病害识别

针对茶园复杂背景下茶叶叶部病害识别较为困难的问题,提出一种基于改进Faster RCNN算法的茶叶叶部病害识别方法。通过对优化区域建议框的特征提取网络VGG-16、MobileNetV2和ResNet50进行比较,选择识别效果较好的ResNet50作为骨干网络,增加模型在茶园复杂背景下对茶叶叶部病害特征的提取能力;融入特征金字塔网络(feature pyramid network,FPN)改善小目标漏检问题和病斑的多尺度问题;采用Rank&Sort(RS)Loss函数代替原Faster RCNN中的损失函数,缓解样本分布不均给模型带来的性能影响,进一步提高检测精度。结果显示:改进模型平均精度均值PmA为88.06%,检测速度为19.1帧/s,对藻斑病、白星病、炭疽病、煤烟病识别平均精度分别为75.54%、86.84%、90.42%、99.45%,比Faster RCNN算法分别提高40.98、44.16、13.9和2.43百分点。以上结果表明,基于改进Faster RCNN算法的茶叶叶部病害识别方法能够弱化茶园复杂背景的干扰,准确识别茶园复杂背景下茶叶叶部病害目标。

Enhancing XRF sensor-based sorting of porphyritic copper ore using particle swarm optimization-support vector machine(PSO-SVM)algorithm

X-ray fluorescence(XRF)sensor-based ore sorting enables efficient beneficiation of heterogeneous ores,while intraparticle heterogeneity can cause significant grade detection errors,leading to misclassifications and hindering widespread technology adoption.Accurate classification models are crucial to determine if actual grade exceeds the sorting threshold using localized XRF signals.Previous studies mainly used linear regression(LR)algorithms including simple linear regression(SLR),multivariable linear regression(MLR),and multivariable linear regression with interaction(MLRI)but often fell short attaining satisfactory results.This study employed the particle swarm optimization support vector machine(PSO-SVM)algorithm for sorting porphyritic copper ore pebble.Lab-scale results showed PSO-SVM out-performed LR and raw data(RD)models and the significant interaction effects among input features was observed.Despite poor input data quality,PSO-SVM demonstrated exceptional capabilities.Lab-scale sorting achieved 93.0%accuracy,0.24%grade increase,84.94%recovery rate,57.02%discard rate,and a remarkable 39.62 yuan/t net smelter return(NSR)increase compared to no sorting.These improvements were achieved by the PSO-SVM model with optimized input combinations and highest data quality(T=10,T is XRF testing times).The unsuitability of LR methods for XRF sensor-based sorting of investigated sample is illustrated.Input element selection and mineral association analysis elucidate element importance and influence mechanisms.

Strengthened Dominance Relation NSGA-Ⅲ Algorithm Based on Differential Evolution to Solve Job Shop Scheduling Problem

The job shop scheduling problem is a classical combinatorial optimization challenge frequently encountered in manufacturing systems.It involves determining the optimal execution sequences for a set of jobs on various machines to maximize production efficiency and meet multiple objectives.The Non-dominated Sorting Genetic Algorithm Ⅲ(NSGA-Ⅲ)is an effective approach for solving the multi-objective job shop scheduling problem.Nevertheless,it has some limitations in solving scheduling problems,including inadequate global search capability,susceptibility to premature convergence,and challenges in balancing convergence and diversity.To enhance its performance,this paper introduces a strengthened dominance relation NSGA-Ⅲ algorithm based on differential evolution(NSGA-Ⅲ-SD).By incorporating constrained differential evolution and simulated binary crossover genetic operators,this algorithm effectively improves NSGA-Ⅲ’s global search capability while mitigating pre-mature convergence issues.Furthermore,it introduces a reinforced dominance relation to address the trade-off between convergence and diversity in NSGA-Ⅲ.Additionally,effective encoding and decoding methods for discrete job shop scheduling are proposed,which can improve the overall performance of the algorithm without complex computation.To validate the algorithm’s effectiveness,NSGA-Ⅲ-SD is extensively compared with other advanced multi-objective optimization algorithms using 20 job shop scheduling test instances.The experimental results demonstrate that NSGA-Ⅲ-SD achieves better solution quality and diversity,proving its effectiveness in solving the multi-objective job shop scheduling problem.

Improving path planning efficiency for underwater gravity-aided navigation based on a new depth sorting fast search algorithm

This study focuses on the improvement of path planning efficiency for underwater gravity-aided navigation.Firstly,a Depth Sorting Fast Search(DSFS)algorithm was proposed to improve the planning speed of the Quick Rapidly-exploring Random Trees*(Q-RRT*)algorithm.A cost inequality relationship between an ancestor and its descendants was derived,and the ancestors were filtered accordingly.Secondly,the underwater gravity-aided navigation path planning system was designed based on the DSFS algorithm,taking into account the fitness,safety,and asymptotic optimality of the routes,according to the gravity suitability distribution of the navigation space.Finally,experimental comparisons of the computing performance of the ChooseParent procedure,the Rewire procedure,and the combination of the two procedures for Q-RRT*and DSFS were conducted under the same planning environment and parameter conditions,respectively.The results showed that the computational efficiency of the DSFS algorithm was improved by about 1.2 times compared with the Q-RRT*algorithm while ensuring correct computational results.

基于SORT算法的图像轨迹跟踪混合控制方法

当目标物体被其他物体部分或完全遮挡时,目标的有效特征点数量会逐渐减少,跟踪器无法继续准确地锁定目标,导致目标轨迹中断。为此,文中研究基于SORT算法的图像轨迹跟踪混合控制方法。选取FCOS算法,利用特征金字塔结构,依据检测头层输出的目标分类得分、位置回归结果以及中心度检测图像目标。将目标检测结果作为卡尔曼滤波器的输入,利用离散控制过程系统描述视频图像中的目标运动状态,预测目标轨迹。利用SORT算法控制图像目标检测结果与目标轨迹预测结果进行级联匹配与IoU匹配,输出匹配成功的目标,即图像目标轨迹跟踪结果。实验结果表明,该方法可有效地跟踪视频图像目标轨迹,未出现ID变更情况,轨迹中断占比低于0.2%。

THE OBSERVATION ON NUCLEIC ACID RELEASED FROM SOME SORTS OF INSECT VIRUS PARTICLES UNDER ELECTRON MICROSCOPE

In order to obtain the intact nucleic acid of virus particles, on the basis of one-stepreleased method, two-step-released method and phages we have observed nucleic acid released from some sorts of insect virus particles under electron microscope. It has been found that under the condition of reacting on the urea of low concentration for a long time, the nucleic acid from four sorts of viruses could not only be released directly, but also be observed clearly.

基于深度学习的智能交通车流监测与预测研究

为了方便交通部门改善交通拥堵问题,使用旭日X3嵌入式开发板作为硬件平台,通过YOLOv8深度学习网络识别道路上通行的车辆及其车辆类型。使用开放神经网络交换(Open Neural Network Exchange, ONNX)格式可视化编辑工具去掉了模型的输出头,将网络中的激活函数由SiLU函数更换为ReLU函数,将模型输出由80个检测类别更改为4个检测类别,在Small版本中,使用非极大值抑制算法(Non-Maximum Suppression, NMS)将最合适的检测框筛选出来,然后用SORT(Simple Online and Realtime Tracking)多目标追踪算法和匹配算法将独立帧检测到的车辆关联起来,实现车辆自动计数。在服务器上配置好YOLOv8的训练环境,训练3个周期,测试模型的mAP指标为0.635,推理速度提升至20 fps左右,目标检测系统的计数精度达到98%,可以准确获取到路口的交通流数据,帮助改善交通拥堵问题。

Accelerating Large-Scale Sorting through Parallel Algorithms

This study explores the application of parallel algorithms to enhance large-scale sorting, focusing on the QuickSort method. Implemented in both sequential and parallel forms, the paper provides a detailed comparison of their performance. This study investigates the efficacy of both techniques through the lens of array generation and pivot selection to manage datasets of varying sizes. This study meticulously documents the performance metrics, recording 16,499.2 milliseconds for the serial implementation and 16,339 milliseconds for the parallel implementation when sorting an array by using C++ chrono library. These results suggest that while the performance gains of the parallel approach over its serial counterpart are not immediately pronounced for smaller datasets, the benefits are expected to be more substantial as the dataset size increases.

基于YOLO v5s和改进SORT算法的黑水虻幼虫计数方法

目前农业环境下的无序目标的精确计数有很高的应用需求,这种计数对其生物量、生物密度管理起到了重要的指导作用。如黑水虻幼虫目标追踪过程中,追踪对象具有高速和非线性的特征,常规算法存在追踪目标速度不足和丢失目标后的再识别困难等问题。针对以上问题,本文提出了一种改进SORT算法,通过改进卡尔曼滤波模型的方式提升目标追踪算法的快速性和准确性,提升了计数的精度。另外,针对黑水虻幼虫目标识别过程中幼虫性状的多样性和混料导致的复杂背景问题,本文通过实验对比多种深度学习网络性能选定YOLO v5s算法提取图像多维度特征,提升了目标识别精度。实验结果表明:在划线计数方面,本文提出的改进SORT算法与原模型相比,平均精度从91.36%提升到95.55%,提升4.19个百分点,通过仿真和实际应用,证明了本文模型的有效性;在目标识别方面,使用YOLO v5s模型在训练集上帧率为156 f/s,mAP@0.5为99.10%,精度为90.11%,召回率为99.22%,综合性能优于其他网络。