基于深度学习的牛肉大理石花纹等级手机评价系统

大理石花纹是影响牛肉品质等级的重要指标,目前中国牛肉加工企业对大理石花纹的评价是由专业分级人员参照标准图谱完成,具有主观性强、耗费人工的缺点。针对上述问题,该研究提出了基于深度学习的智能分级方法,设计一种具有4层卷积的神经网络结构,实现了大理石花纹特征的自动提取,并基于智能手机开发了牛肉大理石花纹检测软件。该研究共采集样本图像1 800张,按3:1:1分为校正集、验证集和测试集。为进一步验证模型,将该方法与传统机器视觉方法进行了比较,提取了牛肉大理石花纹的大、中、小脂肪颗粒个数,脂肪总面积和脂肪分布均匀度5个参数,并建立了多元线性回归模型。试验结果表明,该研究所用方法大理石花纹检测准确率更高,验证集检测正确率为97.67%。最后编写了手机软件,将模型移植入Android手机,在手机平台上调用模型进行大理石花纹检测。试验表明,该软件对测试集样本的检测准确率为95.56%,单张检测时间低于0.5 s。该研究结合卷积神经网络分类能力强和智能手机运行速度快等优点,开发了牛肉大理石花纹的手机评价系统,具有较好的实用性和便携性,可提高牛肉大理石花纹检测效率,有助于提高农畜产品检测的智能化水平。     

基于SDAE-BP的联合收割机作业故障监测

为了解决联合收割机作业故障的非线性特征信号难以提取的问题,该研究提出了一种基于堆叠去噪自动编码器(Stack Denoising Auto Encoder, SDAE)和BP神经网络(Back Propagation,BP)融合的联合收割机作业故障监测及诊断的方法(SDAE-BP)。以转速传感器采集联合收割机脱粒滚筒转速、籽粒搅龙转速、喂入搅龙转速、杂余搅龙转速、风机转速、输送链耙转速、割刀频率以及逐稿器振动频率,并将采集的数据集作为系统的输入。利用SDAE提取输入信号的深层次特征,并由BP神经网络辨识收割机作业状态,实现联合收割机故障监测。在SDAE-BP模型训练过程中,去噪自动编码器(Denoising Auto Encode, DAE)依次经带有不同分布中心噪声的原始数据进行训练,然后将其堆叠,并通过误差反向传播算法对模型参数进行优化,以提升模型识别故障性能和泛化能力。试验结果表明,对于2018年联合收割机田间试验数据,模型的故障诊断准确率达到99.00%,与SDAE和BP神经网络相比,分别提高了1.5和4.5个百分点。将SDAE-BP故障诊断模型用2019年的试验数据进行更新,并用2018年和2019年试验数据进行测试,结果表明,更新后的模型对2018年试验数据的故障识别准确率为99.25%,对2019年试验数据的故障识别准确率为98.74%,更新后模型在2019试验数据集上的故障识别准确率较未更新模型提高了6.52个百分点。该文所建模型能够准确识别联合收割机的故障类型,且具有较好的鲁棒性,对旋转型机械故障监测及预警具有参考价值。     

缓释肥侧位深施及用量对油菜产量和肥料利用率的影响

为明确红壤稻田直播油菜缓释肥（N-P2O5-K2O:25-7-8）侧位深施效果及适宜用量，该研究连续2 a在两熟制和三熟制2种种植模式下开展缓释肥侧位深施效果对比试验（设置不施肥、土表撒施和侧位深施3个施肥方式）和施用量试验（设置0、300、450、600、750和900 kg/hm2 共6个施肥水平），研究缓释肥侧位深施及不同用量对油菜产量形成和肥料利用率的影响。结果表明，施肥方式对红壤稻田油菜产量形成和肥料利用率均有显著影响，且对两熟制油菜影响更为显著。相比传统土表撒施，侧位深施显著促进了油菜产量和肥料利用率的提高。缓释肥侧位深施明显提高了各时期油菜干物质量，尤其是显著增加了初花期至成熟期的干物质积累量，促进了花后根部与地上部干物质同步增长；促进了根系对N、P、K的吸收，提高了油菜产量和肥料利用率。菜籽产量与缓释肥用量呈线性加平台关系，适宜施肥量可保证较大的收获密度，并协同产生较多的每株角果数和每角粒数，从而提高籽粒产量、肥料利用率和经济效益。两熟制和三熟制油菜缓释肥侧位深施的适宜用量分别为715和585 kg/hm2，产量潜力可分别达2 450和1 700 kg/hm2。研究表明，侧位深施适量缓释肥可显著提高红壤稻田直播油菜生产力，建议结合机械化种植因地制宜推广应用。     

基于改进极限学习机的水体溶解氧预测方法

为了有效地指导水产养殖生产，提高溶解氧浓度预测的精度，提出了基于因子筛选和改进极限学习机（Extreme Learning Machine，ELM）的水产养殖溶解氧预测模型。首先，利用皮尔森相关系数法计算各影响因子与溶解氧浓度间的相关系数，提取强关联因子，降低预测模型的输入量维度；采用偏最小二乘算法（Partial Least Square, PLS）优化传统ELM神经网络，避免网络中隐含层共线性问题，保障输出权值的稳定性；然后，结合新型激活函数，构建水体溶解氧浓度预测模型。最后，将SPLS-ELM（Selection Based Partial Least Square Optimized Extreme Learning Machine）预测模型应用到江苏省无锡市南泉基地某试验池塘的水体溶解氧预测中。试验结果表明：该模型的预测均方根误差为0.3232，与最小二乘支持向量机（Least Square Support Vector Machine，LSSVM）、BP神经网络、粒子群（Particle Swarm Optimization，PSO）优化LSSVM和遗传算法（Genetic Algorithm, GA）优化BP神经网络相比分别降低40.98%、44.48%、34.73%和44.18%。且该模型的运行时间仅0.6231s，预测精度和运行效率明显优于其他模型。该模型的溶解氧预测曲线接近真实溶解氧变化曲线，能够满足水产养殖实际生产对水体溶解氧预测的要求。     

一种改进深度卷积神经网络的海岛识别方法

受不规律潮汐的影响,现有的海岛地物类别自动识别方法存在精度低和时效性差等问题,通过改进深度卷积神经网络提出了一种基于遥感影像的海岛快速识别方法:(1)在深度卷积神经网络的卷积层中增设1×1的卷积核作为瓶颈单元,对多波段的遥感影像进行降维;(2)在池化层引入了重采样方法,基于灰度值对海量的遥感影像进行特征压缩。以300景Landsat-8遥感影像为源数据,分别采用CNN、RCNN和本文改进的深度卷积神经网络对遥感影像中的海岛进行识别,实验结果表明:(1)改进的深度卷积神经网络降低了海岛识别的计算耗时,其计算耗时仅为CNN的4.56%和RCNN的5.60%;(2)改进的深度卷积神经网络较CNN和RCNN提高了海岛识别的精度,识别精度分别为96.0%、93.3%和95.0%。结果说明,改进的深度卷积神经网络适用于面向遥感影像的海岛自动识别。     

基于氨基酸分子中侧链基极性性质的DNA序列分类(英文)

从DNA序列片段个案中密码子分布密度角度出发,提取出DNA序列片段的特征,基于氨基酸分子中侧链基极性性质把氨基酸分成5大类,计算5大类出现的频率,这种考虑生物意义的特征提取方法不仅考虑碱基的含量,还在一定程度上考虑碱基的排列顺序,应用层次聚类分析方法和BP神经网络法对DNA序列片段进行分类。结果表明,2类算法分类结果精度较高,且一致性也较高。说明这种特征提取法比传统的单纯考虑碱基的特征提取法效果更优。     

Asterosaponins: Structures,Taxonomic Distribution,Biogenesis and Biological Activities

Asterosaponins are a class of steroid oligoglycosides isolated from starfish with characteristic structures and diverse biological activities. In this review, we have attempted to combine the most important data concerning asterosaponins and give a list of these secondary metabolites with their structural peculiarities. The purpose of this review is to provide a brief but as complete as possible principal information about their chemical structures, taxonomic distribution in the marine environment, distribution in different geographical areas and depths, some properties, biological activities, and functions. Some other rare steroid metabolites from starfish, closely related in structures and probably biogenesis to asterosaponins, are also discussed.     

Evaluation of Dynamic Structural Disorders in the Upper Airways and Applied Rein Tension in Healthy Dressage Horses During Riding in Different Gaits and Head–Neck Positions

Flexion of the horse’s head and neck during dressage riding reduces the pharyngeal lumen with the risk of increased upper airway resistance and upper airway obstructions. According to the Fédération Equestre Internationale, hyperflexion is achieved through force, whereas the position low–deep–round is nonforced. The objectives of this study were to evaluate (1) applied rein tension and (2) dynamic structural disorders in the upper airways in dressage horses in different gaits and different head–neck positions (HNPs). Overground endoscopy (OGE) and rein tension were evaluated in 13 clinically healthy and high-performance Warmblood dressage horses while being ridden in a standardized program comprised of four different gaits (halt, walk, trot, and canter) and in four HNPs (unrestrained, competition frame, hyperflexion, and low–deep–round). All included horses were able to achieve the desired HNPs. The HNP low–deep–round showed significantly lower rein tension than competition frame (P < .001) and hyperflexion (P < .001). An association was found between dynamic structural disorders in the upper airway tract evaluated by OGE and head–neck flexion, but this association was not linked to the degree of flexion. The HNP hyperflexion was neither associated with greater rein tension nor severe dynamic structural disorders than the HNP competition frame. This study confirms that low–deep–round is a nonforced position, in contrast to hyperflexion. Further studies are needed to evaluate whether dynamic structural disorders are a result of flexion or if the degree of flexion has an impact.     

Yield Performance of Wheat Isolines with Different Dosages of the Short Arm of Rye Chromosome 1

Translocations of the short arm of rye (Secale cereale L.) chromosome 1 (1RS) in wheat (Triticum aestivum L. cv. Pavon 76) are known to increase root biomass. Such an increase enhances water and nutrient uptake and may improve grain yield. Two greenhouse experiments and a field experiment were carried out at the University of California, Riverside, in 2012 and 2013 under well‐watered and terminal drought treatments to evaluate phenotypic characters associated with varying dosages of 1RS, including grain yield. The genotypes used were cultivar Pavon 76 (R₀), Pavon 76/Pavon1RS.1AL (F₁ hybrid) with a single dosage of 1RS (R₁A), Pavon 1RS.1AL with two dosages of 1RS (R₂A), Pavon 1RS.1DL (R₂D) also with two dosages of 1RS and Pavon 1RS.1AL‐1RS.1DL (R₄AD) with four dosages of 1RS. There was a significant positive correlation between number of dosages of 1RS and root biomass. However, no correlation was found between root biomass and grain yield per plant. Drought in the field experiment reduced grain yield significantly. Under well‐watered field conditions, grain yield of R₂A (215.9 g plant^?1) was significantly greater than those of R₂D (191.8 g plant^?1) and R₄AD (161.7 g plant^?1). Also, grain yield of R₄AD was significantly less than those of F₁, Pavon 76 and R₂D under well‐watered conditions. Under drought field conditions, no significant differences were found among the genotypes for grain yield was found between F₁ (14.7 g plant^?1) and R₄AD (12.4 g plant^?1). Harvest index was significantly greater in well‐watered (44.2 %) than in drought (34.6 %) field conditions. On average, genotypes F₁ (42.3 %) and R₂A (40.6 %) had higher harvest index than R₂D (38.3 %) and R₄AD (35.5 %) in the field. Also, Pavon 76 (40.2) and R₂D (38.3) had higher harvest index than R₄AD. Drought tolerance was lowest for R₄AD due to its relatively lower grain yield potential. In general, Pavon 1RS.1AL carrying two dosages of 1RS showed higher grain yield under wet treatments. Pavon 1RS.1AL‐1RS.1DL carrying four dosages of 1RS produced the largest shoot and root biomasses, but the least grain yield.     

基于LM算法的BP神经网络的电力负荷短期预测

清代书院课艺总集多为连续出版物，或具有连续出版物的刊行初衷。刊期短则一季，多则一年或数年。经费充足与否，会影响刊期。发表周期多为一年至五年，也有十余年的。用稿率以10%~20%居多，偶见“关系稿”。时文的用稿标准是“清真雅正”。题目多为官师所拟。一般全文刊登，也偶有“论点摘编”。多经润色，并附录评点。有的以袖珍本刊行，有的宣称“翻刻必究”，标出定价，附载广告。稿费已在膏火费中预支，优秀作品可被转载。从本质属性和诸多要素来看，书院课艺总集实开今日“大学学报”、“学术集刊”之先河。