Molecular mechanisms underlying microglial sensing and phagocytosis in synaptic pruning

Microglia are the main non-neuronal cells in the central nervous system that have important roles in brain development and functional connectivity of neural circuits.In brain physiology,highly dynamic microglial processes are facilitated to sense the surrounding environment and stimuli.Once the brain switches its functional states,microglia are recruited to specific sites to exert their immune functions,including the release of cytokines and phagocytosis of cellular debris.The crosstalk of microglia between neurons,neural stem cells,endothelial cells,oligodendrocytes,and astrocytes contributes to their functions in synapse pruning,neurogenesis,vascularization,myelination,and blood-brain barrier permeability.In this review,we highlight the neuron-derived“find-me,”“eat-me,”and“don't eat-me”molecular signals that drive microglia in response to changes in neuronal activity for synapse refinement during brain development.This review reveals the molecular mechanism of neuron-microglia interaction in synaptic pruning and presents novel ideas for the synaptic pruning of microglia in disease,thereby providing important clues for discovery of target drugs and development of nervous system disease treatment methods targeting synaptic dysfunction.

Quantitatively characterizing sandy soil structure altered by MICP using multi-level thresholding segmentation algorithm

The influences of biological,chemical,and flow processes on soil structure through microbially induced carbonate precipitation(MICP)are not yet fully understood.In this study,we use a multi-level thresholding segmentation algorithm,genetic algorithm(GA)enhanced Kapur entropy(KE)(GAE-KE),to accomplish quantitative characterization of sandy soil structure altered by MICP cementation.A sandy soil sample was treated using MICP method and scanned by the synchrotron radiation(SR)micro-CT with a resolution of 6.5 mm.After validation,tri-level thresholding segmentation using GAE-KE successfully separated the precipitated calcium carbonate crystals from sand particles and pores.The spatial distributions of porosity,pore structure parameters,and flow characteristics were calculated for quantitative characterization.The results offer pore-scale insights into the MICP treatment effect,and the quantitative understanding confirms the feasibility of the GAE-KE multi-level thresholding segmentation algorithm.

Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

基于PN-YOLO v8s-Pruned的轻量化三七收获目标检测方法

为实现三七联合收获作业过程中的自适应分级输送和收获状态实时监测,本文针对三七根土复合体特征和复杂田间收获工况,提出一种基于YOLO v8s并适用于Jetson Nano端部署的三七目标检测方法。在YOLO v8s对三七准确识别的基础上,针对其新的模型结构特性,利用通道剪枝算法,制定相应剪枝策略,保证模型精度的同时提升实时检测性能。采用TensorRT推理加速框架将改进模型部署至Jetson Nano,实现了三七目标检测模型的灵活部署。试验结果表明,改进后的PN-YOLO v8s-Pruned模型在主机端的平均精度均值为93.71%,参数量、计算量、模型内存占用量分别为原始模型的39.75%、57.69%、40.25%,检测速度提升44.26%,与其他目标检测模型相比,本文改进模型在计算复杂度、检测精度和实时性方面具有更好的综合检测性能。在Jetson Nano端部署后,改进模型检测速度达18.9 f/s,较加速前提升2.7倍,较原始模型提升5.8 f/s。台架试验结果表明,4种输送分离收获作业工况下三七目标检测的平均精度均值达87%以上,不同输送分离收获作业工况和不同流量等级下的目标三七计数平均正确率分别达92.61%、91.76%。田间试验结果表明,三七目标检测平均精度均值达84%,计数平均正确率达88.11%,图像推理速度达31.0 f/s。模型检测性能和计数效果能够满足复杂田间收获工况下目标三七的检测需求,可为基于边缘计算设备的三七联合收获作业自适应分级输送系统和收获作业质量监测系统提供技术支撑。

An Investigation of Frequency-Domain Pruning Algorithms for Accelerating Human Activity Recognition Tasks Based on Sensor Data

The rapidly advancing Convolutional Neural Networks(CNNs)have brought about a paradigm shift in various computer vision tasks,while also garnering increasing interest and application in sensor-based Human Activity Recognition(HAR)efforts.However,the significant computational demands and memory requirements hinder the practical deployment of deep networks in resource-constrained systems.This paper introduces a novel network pruning method based on the energy spectral density of data in the frequency domain,which reduces the model’s depth and accelerates activity inference.Unlike traditional pruning methods that focus on the spatial domain and the importance of filters,this method converts sensor data,such as HAR data,to the frequency domain for analysis.It emphasizes the low-frequency components by calculating their energy spectral density values.Subsequently,filters that meet the predefined thresholds are retained,and redundant filters are removed,leading to a significant reduction in model size without compromising performance or incurring additional computational costs.Notably,the proposed algorithm’s effectiveness is empirically validated on a standard five-layer CNNs backbone architecture.The computational feasibility and data sensitivity of the proposed scheme are thoroughly examined.Impressively,the classification accuracy on three benchmark HAR datasets UCI-HAR,WISDM,and PAMAP2 reaches 96.20%,98.40%,and 92.38%,respectively.Concurrently,our strategy achieves a reduction in Floating Point Operations(FLOPs)by 90.73%,93.70%,and 90.74%,respectively,along with a corresponding decrease in memory consumption by 90.53%,93.43%,and 90.05%.

Pruning Techniques for Prunus mume

Prunusmumehas high ornamental value,and its maintenance and management should be more meticulous,with pruning being an important task.Pruning can make P.mume more robust,reduce the occurrence of diseases and pests,maintain a good shape,and promote more flowering,further improving its ornamental value.The difficulty of pruning lies in flexibly adopting suitable pruning methods according to the time of the tree,which requires understanding the impact of pruning operations on the growth and flowering of P.mume,as well as some techniques in pruning operations.This paper introduces the botanical characteristics of P.mume,common pruning methods and achievable effects of P.mume,and suitable time for using various methods,and analyzes the possible consequences and reasons of some incorrect operations.Moreover,corresponding correct practices are provided,which can provide reference for standardized pruning of P.mume,thereby reducing or avoiding losses caused by improper operation.

Deep neural network based on multi-level wavelet and attention for structured illumination microscopy

Structured illumination microscopy(SIM)is a popular and powerful super-resolution(SR)technique in biomedical research.However,the conventional reconstruction algorithm for SIM heavily relies on the accurate prior knowledge of illumination patterns and signal-to-noise ratio(SNR)of raw images.To obtain high-quality SR images,several raw images need to be captured under high fluorescence level,which further restricts SIM’s temporal resolution and its applications.Deep learning(DL)is a data-driven technology that has been used to expand the limits of optical microscopy.In this study,we propose a deep neural network based on multi-level wavelet and attention mechanism(MWAM)for SIM.Our results show that the MWAM network can extract high-frequency information contained in SIM raw images and accurately integrate it into the output image,resulting in superior SR images compared to those generated using wide-field images as input data.We also demonstrate that the number of SIM raw images can be reduced to three,with one image in each illumination orientation,to achieve the optimal tradeoff between temporal and spatial resolution.Furthermore,our MWAM network exhibits superior reconstruction ability on low-SNR images compared to conventional SIM algorithms.We have also analyzed the adaptability of this network on other biological samples and successfully applied the pretrained model to other SIM systems.

An Expert System to Detect Political Arabic Articles Orientation Using CatBoost Classifier Boosted by Multi-Level Features

The number of blogs and other forms of opinionated online content has increased dramatically in recent years.Many fields,including academia and national security,place an emphasis on automated political article orientation detection.Political articles(especially in the Arab world)are different from other articles due to their subjectivity,in which the author’s beliefs and political affiliation might have a significant influence on a political article.With categories representing the main political ideologies,this problem may be thought of as a subset of the text categorization(classification).In general,the performance of machine learning models for text classification is sensitive to hyperparameter settings.Furthermore,the feature vector used to represent a document must capture,to some extent,the complex semantics of natural language.To this end,this paper presents an intelligent system to detect political Arabic article orientation that adapts the categorical boosting(CatBoost)method combined with a multi-level feature concept.Extracting features at multiple levels can enhance the model’s ability to discriminate between different classes or patterns.Each level may capture different aspects of the input data,contributing to a more comprehensive representation.CatBoost,a robust and efficient gradient-boosting algorithm,is utilized to effectively learn and predict the complex relationships between these features and the political orientation labels associated with the articles.A dataset of political Arabic texts collected from diverse sources,including postings and articles,is used to assess the suggested technique.Conservative,reform,and revolutionary are the three subcategories of these opinions.The results of this study demonstrate that compared to other frequently used machine learning models for text classification,the CatBoost method using multi-level features performs better with an accuracy of 98.14%.

Construction of a Multi-Level Strategic System for Cultivating Cultural Industry Management Talents in Colleges and Universities

Through SWOT(strengths,weaknesses,opportunities,and threats)and PEST(political,economic,social,and technological)analysis,this study discusses the construction of a multi-level strategic system for the cultivation of cultural industry management talents in colleges and universities.First of all,based on SWOT analysis,it is found that colleges and universities have rich educational resources and policy support,but they face challenges such as insufficient practical teaching and intensified international competition.External opportunities come from the rapid development of the cultivation of cultural industry management talents and policy promotion,while threats come from global market competition and talent flow.Secondly,PEST analysis reveals the key factors in the macro-environment:at the political level,the state vigorously supports the cultivation of cultural industry management talents;at the economic level,the market demand for cultural industries is strong;at the social level,the public cultural consumption is upgraded;at the technological level,digital transformation promotes industry innovation.On this basis,this paper puts forward a multi-level strategic system covering theoretical education,practical skill improvement,interdisciplinary integration,and international vision training.The system aims to solve the problems existing in talent training in colleges and universities and cultivate high-quality cultural industry management talents with theoretical knowledge,practical skills,and global vision,so as to adapt to the increasingly complex and diversified cultural industry management talents market demand and promote the long-term development of the industry.

结合通道剪枝和通道注意力的轻量型车辆点云补全网络

针对现有的点云补全网络多关注于补全的精度而忽视补全效率问题,提出了一种轻量型点云补全网络来准确、高效地修复自动驾驶中的不完整车辆点云。为了提高网络推理效率,采用一种高效的一次性通道剪枝技术提高网络的补全效率;在特征提取阶段,网络加入通道注意力模块,将加权特征与全局特征拼接,通过两层多维特征信息提取,得到最终的特征向量;将特征向量传入双解码器结构中,分别通过全连接层和多层感知机生成稠密的粗糙点云和输入点云偏差值;将粗糙点云与输入点云偏差值相加得到最终的精细化完整点云。在PCN数据集和KITTI数据集上进行实验,实验结果表明在补全缺失车辆信息的实时性上有着显著的提升,并且在补全精度上也有不错的表现。

腋皱襞小切口皮下修剪术治疗腋臭患者的临床效果及对术后并发症发生情况的影响

目的探究腋皱襞小切口皮下修剪术治疗腋臭患者的临床效果及对术后并发症发生情况的影响。方法选取2021年5月至2022年10月我院收治的142例腋臭患者作为研究对象,根据治疗方式不同将其分为对照组(n=68)和观察组(n=74)。对照组采用搔刮抽吸术治疗,观察组采用腋皱襞小切口皮下修剪术治疗。比较两组的临床疗效、围术期指标、疼痛情况及并发症发生情况。结果观察组的治疗总有效率高于对照组,差异具有统计学意义(P<0.05)。观察组的手术时间、拆线时间及住院时间长于对照组,差异具有统计学意义(P<0.05)。术后1、3、7 d,两组的视觉模拟量表(VAS)评分比较,差异无统计学意义(P>0.05)。观察组的并发症总发生率为6.76%,明显低于对照组的22.06%,差异具有统计学意义(P<0.05)。结论腋皱襞小切口皮下修剪术治疗腋臭患者有助于提高临床疗效,降低并发症发生率,在术后疼痛控制方面与搔刮抽吸术相当,但在手术时间、拆线时间及住院时间方面劣于搔刮抽吸术。

Analysis on Fuji Apple Tree Structures and Related Factors under Different Pruning Modes

To determine the correlations between the tree structuresof Fuji apple with different pruning modes and each factor, the data about 3 tree structures which were free spindle short shoot, free spindle long shoot and slenderspindle short shoot in Xingtang County of Hebai Province were investigated, then by SPSS anal- ysis, the correlations between the taperingness and each growth factor of inserted small branch were compared. The results showed that the taperingness of central trunk of free spindle dwarf-shoot Fuji apple treeshad negative correlations with each factor of inserted small branch, while the taperingness of central trunk of free spin- dle long-shoot Fuji apple treeshad positive correlations with each factor of inserted small branch, the taperingness of central trunk of slenderspindle short-shootFuji ap- ple treeshad negative correlation with total thickness of inserted small branch, but had positive correlations with other factors. This study can provide a scientifictheo- retical basis for the pruning technology of high-density planting trees grafting by dwarfing self-rooted rootstock.

面向无人机协同定位的机载深度计算编译优化

随着无人机技术快速发展,在定位信号缺失的情况下进行无人机定位成为一个研究难题。而近几年图神经网络的出现与发展,为解决这一难题提供了一种新的解决思路。然而在资源受限的无人机端侧部署图神经网络面临着无人机算储资源受限及实时性难以满足等挑战。提出面向无人机协同定位的机载深度计算编译优化方法。采用了一种轻量化的时间图卷积神经网络模型,该时间图卷积网络由图卷积网络和门控递归单元组成,将无人机群的空间依赖性和无人机位置变化的时间依赖性同时加以考虑,对无人机群位置进行精确的预测;针对该模型在时间图卷积网络上的冗余特性,提出了基于逆向Cuthill-McKee图重排和基于双深度确定性策略梯度的全局自适应剪枝算法。在保证无人机群坐标精确预测的同时,不仅能提高数据在主存的空间局部性,加速模型的运算速度,而且能够对模型进行自适应的非结构化剪枝,降低模型的存储复杂度。实验结果表明,相对于已有的时间图卷积神经网络模型,编译优化后的轻量化时间图卷积神经网络模型在保留78.8%准确率的同时,模型计算时间降低37.9%,模型的平均剪枝率达到90.3%。

基于改进YOLOv7-Tiny的轻量化激光器芯片缺陷检测算法

【目的】高功率半导体激光器的光学灾变损伤是限制其可靠性和寿命的主要因素,因此,有效的缺陷检测对于优化激光器芯片的制造工艺和结构设计至关重要。提出了一种基于改进YOLOv7-Tiny的轻量化激光器芯片缺陷检测算法,旨在解决深度学习应用于缺陷检测时面临的高计算量和参数量问题。【方法】利用轻量化卷积神经网络替换特征提取主干有效减少对计算资源消耗,有效提取电致发光图像中缺陷特征。为从上下文特征获取更丰富的信息,引入多分支重参数化卷积块重构聚合模块,通过多路径分支丰富特征表示,训练与推理的解耦保证检测效率。此外,结合坐标注意力,提升定位精度。进行了剪枝实验和模型部署,验证算法的初步应用。【结果】在电致发光缺陷数据集上的实验结果显示,本文方法能在较低的参数和计算量下准确地检测出芯片缺陷,展现出良好的性能。

Multi-level access control model for tree-like hierarchical organizations

An access control model is proposed based on the famous Bell-LaPadula （BLP） model.In the proposed model,hierarchical relationships among departments are built,a new concept named post is proposed,and assigning security tags to subjects and objects is greatly simplified.The interoperation among different departments is implemented through assigning multiple security tags to one post, and the more departments are closed on the organization tree,the more secret objects can be exchanged by the staff of the departments.The access control matrices of the department,post and staff are defined.By using the three access control matrices,a multi granularity and flexible discretionary access control policy is implemented.The outstanding merit of the BLP model is inherited,and the new model can guarantee that all the information flow is under control.Finally,our study shows that compared to the BLP model,the proposed model is more flexible.

Analysis on Apple Tree Structures by Free Spindle Pruning Mode

To determine the correlation between the stem taperingness and central shaft by free spindle pruning mode on different apple cultivars, the central shaft growth data of three cultivars of free spindle short shoot ＂Fuji＂, free spindle long shoot ＂Fuji＂, free spindle ＂Huaguan＂ were investigated in Xingtang County of Hebei Province by SPSS analysis. The results showed that the stem taperingness on free spindle short shoot ＂Fuji＂ was in negative correlation with central shaft, but the correlation was not significant. While the stem taperingness on free spindle long shoot ＂Fuji＂ was in positive correlation with central shaft, but the correlation was not significant either. The stern taperingness on free spindle ＂Huaguan＂ was in negative correlation with central shaft, and the correlation between the stem taperingness and the central shaft total length was significant at the level of 0.01. The results.provided scientific theoretical basis for guiding the dwarfing rootstocks close planting apple tree pruning technology.

北方典型果树剪枝原料能源特性与热解规律

对果树修剪树枝的能源特性及热解规律开展研究,可以为林果废弃物的能源化高效利用提供基础参考信息。以华北地区几种典型的果树修剪树枝为试样,系统研究了原料的元素组成、化学组成、工业分析和热值等能源特性,采用热重分析、热重红外分析和热解气质联用分析等方法研究了其分析性热解规律。实验结果表明,从元素组成来看,果树修剪树枝中的碳元素质量分数为50%左右,碳元素是组成固定碳组分的主要元素,碳元素含量越高,热值越高;从化学组成来看,果树修剪树枝中纤维素质量分数为36.9%~43.7%,半纤维素质量分数为28.6%~36.1%,木质素质量分数为21.0%~24.4%,综纤维素主要影响热解时脱挥发分和液相产物的产率,而木质素则主要影响炭产率;对干态原料的工业分析得出果树修剪树枝的挥发分质量分数最高,其次是固定碳质量分数,灰分质量分数最少;果树修剪树枝的热值为17.1~19.9 MJ/kg,大约相当于标准煤热值的60%~70%。热解规律分析结果表明,265~410℃为脱挥发分的主要失重区,产生的气相产物具有丰富的化学官能团红外吸收峰,主要是醛酮类、酸类、醇类和酚类等物质。果树修剪树枝是一种固定碳含量和热值高、灰分低的典型木质纤维素生物质,适宜通过热解等方法实现能源化处理和资源化利用。

Impact of training methods and biostimulant applications on sweet pepper(Capsicum annuum) yield and nutritional values:Under greenhouse condition

Pepper (Capsicum annuum L.) is an important agricultural crop because of the nutritional value of the fruit and its economic importance.Various techniques have been practiced to enhance pepper's productivity and nutritional value.Therefore,this study was conducted to determine the impact of different training methods and biostimulant applications on sweet pepper plants'growth,yield,and chemical composition under greenhouse conditions.For the training method,unpruned plants were compared with one stem and two stem plants.Unpruned plants had the fruit number of 33.98,fruit weight of 2.18 kg·plant^(-1),and total marketable yield of 1 090.0 kg·hm^(-2).One stem plant gave the best average fruit weight of 86.63 g,vitamin C content of 13.66 mg·kg^(-1)FW,and TSS content of 7.21%.However,two stem plants had the highest fruit setting of 62.41%,carotenoid content of 0.14 mg·kg^(-1)FW,and fruit chlorophyll content of 3.57 mg·kg^(-1)FW.For biostimulant applications,control plants were compared with the Disper Root (DR) and Disper Vital (DV).DR application significantly increased total sugar,carotenoid,fruit chlorophyll,and TSS contents compared to the control and DV applications.While,applying DV increased fruit setting,plant fruit number,weight,and total marketable yield.In addition,integrating one stem plant with the DR application improved fiber,vitamin C,and TSS contents significantly.Two stem plants,and the DV application improved fruit setting and carotenoid content.Thus,one and two stem training methods integrated with the DR and DV biostimulant applications could be considered for developing agricultural practices to obtain commercial yield and improve the nutrition values of sweet peppers,as unpruned plants without biostimulant applications have a negative impact.

基于结构化剪枝的矿区地质灾害检测算法

本文提出基于YOLOv5s模型的结构化剪枝目标检测算法,解决矿区无人机巡检中常规算法过大、参数多、难以部署的问题。通过遍历网络中的BN层,对γ进行排序,并设定全局阈值评估通道重要性,剔除低于阈值的通道。实验结果显示,相较于YOLOv5s,该算法模型减小52.9%,检测时间降低18.1%,平均精度仅下降1.5%。

改进的基于FFT pruning的窄带高分辨率频谱算法

提出一种改进的基于FFT pruning的窄带高分辨率频谱计算方法。该方法是对Sreenivas's FFT pruning算法和Nagai的利用频移变换的FFT pruning算法的推广。同时提出输出点分级思想,可实现任意窄带上非2的整数幂次频点输出。该算法比Sreenivas's FFT pruning算法具有更小的计算量和更简单的信号流图。