基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。     

黄沙坪铅锌多金属矿的成矿规律及深部找矿远景

众所周知,矿物质的成分是多种多样的,社会的发展和科学的进步需要运用到多重金属矿物质,在专业人员的勘探与挖掘中,发现了黄沙坪铅锌多金属矿,这个矿区中有丰富的有色金属,这个矿的发掘为研究成矿规律提供了物质基础,同时也为深部找矿提供了可靠的依据。本文主要分析黄沙坪铅锌多金属矿的成矿规律及深部找矿远景。     

高校实验室计算机网络故障诊断技术研究

为了提升高校实验数据处理水平,高校实验室的相关建设工作已经步入正轨,但层出不穷的信息安全问题也向高校实验室计算机网络维护工作提出了新的挑战。文章从现阶段高校实验室计算机网络的相关建设工作出发,简要论述引发网络故障的具体原因,并对其诊断技术进行探讨。     

Intelligent scheduling of discrete automated production line via deep reinforcement learning

The reinforcement learning (RL) is being used for scheduling to improve the adaptability and flexibility of an automated production line. However, the existing methods only consider processing time certain and known and ignore production line layouts and transfer unit, such as robots. This paper introduces deep RL to schedule an automated production line, avoiding manually extracted features and overcoming the lack of structured data sets. Firstly, we present a state modelling method in discrete automated production lines, which is suitable for linear, parallel and re-entrant production lines of multiple processing units. Secondly, we propose an intelligent scheduling algorithm based on deep RL for scheduling automated production lines. The algorithm establishes a discrete-event simulation environment for deep RL, solving the confliction of advancing transferring time and the most recent event time. Finally, we apply the intelligent scheduling algorithm into scheduling linear, parallel and re-entrant automated production lines. The experiment shows that our scheduling strategy can achieve competitive performance to the heuristic scheduling methods and maintains stable convergence and robustness under processing time randomness.     

基于序列模型的无线传感网入侵检测系统

随着物联网(IoT)的快速发展，越来越多的IoT节点设备被部署，但伴随而来的安全问题也不可忽视。IoT的网络层节点设备主要通过无线传感网进行通信，其相较于互联网更开放也更容易受到拒绝服务等网络攻击。针对无线传感网面临的网络层安全问题，提出了一种基于序列模型的网络入侵检测系统，对网络层入侵进行检测和报警，具有较高的识别率以及较低的误报率。另外，针对无线传感网节点设备面临的节点主机设备的安全问题，在考虑节点开销的基础上，提出了一种基于简单序列模型的主机入侵检测系统。实验结果表明，针对无线传感网的网络层以及主机层的两个入侵检测系统的准确率都达到了99%以上，误报率在1%左右，达到了工业需求，这两个系统可以全面有效地保护无线传感网安全。     

Effects of deep etching methods on the microstructure of the etched vias of the silicon-based SIWF

The microstructure and the array accuracy of the etched vias of the silicon-basedsubstrate integrated waveguide filter (SIWF) are crucial to the electromagnetic performance and the reliability of the silicon-based SIWF. In this paper, three different etching methods, including potassiumhydroxide etching, picosecond UV laser etching, and inductively coupled plasma (ICP) etching are utilized to etch via arrays onhigh resistivity ［100］-siliconsubstrates. The profiles and the array accuracy of the vias are measured by optical critical dimension and the micromorphology of the vias is characterized byscanning electron microscopy (SEM), on the basis of which the effects of different deep etching methods on the microstructure of the viasidewall of the silicon-based SIWF are studied. The results indicate that the microstructure of the vias etched by the inductively coupled plasma etching method is the best. Meanwhile, this kind of vias has the highest array accuracy and the lowest roughness. So, under the current condition of process equipment and technical level, ICP etching is the optimal method for manufacturing deep via arrays of the silicon-based SIWF.     

某校化工院一级学生实验室急救知识调查干预

了解化学与化工院大学生实验室安全和急救知识掌握现状,探讨提高大学生实验室安全和急救知识水平的有效途径。整群随机抽样法抽取湖南某校263名化工学院一年级学生,随机分为实验组和对照组,向实验组大学生发放实验室安全和急救知识速查手册并进行讲解,对照组则不进行任何干预,每组均于干预前和干预后发放实验室安全和急救知识问卷进行测试。结果表明:第一次调查发现2个组大约有12个题目(占总题目的 48%)的回答正确率低于60%;干预后,实验组有21个题目的回答正确率高于干预前。第一次调查时2个组有4个问题的回答正确率在80%以上,且实验组的干预无法提高其正确率。大学生实验室安全和急救知识水平亟待提高,进行有效的干预可以提高他们这方面的知识水平。     

Genetic algorithm to simultaneously optimise stope sequencing and equipment dispatching in underground short-term mine planning under time uncertainty

ABSTRACT

The main issue in short-term planning optimisation for underground mining is organising the mining process with limited resources in the form of equipment and materials to satisfy production targets and stable feed grade requirements. In this paper, an integrated optimisation model is proposed based on an individual generation algorithm and an improved Genetic Algorithm to simultaneously optimise stope extraction sequencing and timing, extracted ore grade and equipment dispatching. The model objectives are to shorten the time gap between the stope mining processes and the overall working time. When the uncertainty of equipment working time is taken into account in a short-term scheduling model, the Monte Carlo simulation is applied to evaluate the risk of not meeting the production target. A modification strategy is defined to evaluate equipment failure. Consequently, any available equipment is automatically reassigned to the mining site to replace the broken-down equipment. A case study is used to validate the model in the Sanshandao gold mine of China to formulate an optimal monthly schedule. Compared with the conventional approach, the new model could reduce the variance of ore tonnage and feed grade and improve the equipment allocation efficiency. Discussions are presented to address the uncertainty.