基于深度学习的牙刷姿态识别方法

针对牙刷分拣中的定位问题,在确定牙刷位置的基础上采用深度学习实现牙刷姿态识别.对牙刷图像进行去噪增强,通过阈值分割提取感兴趣区域,计算图像的几何矩获得牙刷的方向角和外接矩形,以外接矩形的中心作为牙刷位置.用矩形框内的牙刷图像训练残差网络模型,当模型正确率达到要求时保存该模型,用于判断图像中牙刷的姿态.测试结果表明,该方法可以快速准确地实现牙刷的位置确定与姿态识别,为机器人分拣提供牙刷位姿信息.     

基于深度学习的中医古文献临床经验抽取

中医古文献蕴藏着丰富的临床经验，是古代中医在行医过程中对临床诊疗的经验性总结，体现了中医学形成和发展的理论框架和思想基础.然而这些宝贵的临床经验不仅量大，而且分散在不同的文献中，使得中医从业者手工很难快速全面地获取它们，文献检索工具也只能提供文档级别的信息筛选，无法为这种细粒度的信息获取提供支持.此外，古汉语相对于现代汉语的不同特点也限制了主流文本分析工具的使用效果.为此本文提出面向临床经验获取的中医古文献信息抽取任务，用于识别古文献中描述临床经验的文本片段，手工标注了样本数据用于这种抽取模型的训练和测试，并设计了基于深度学习的序列标注器用于完成该任务.考虑到标注数据量小可能带来的过度拟合问题，本文引入对抗训练和虚拟对抗训练来增强模型的泛化能力.一系列充分的实验验证了模型的有效性，表明利用信息抽取技术从古文献获取中医临床经验具有可行性，为这一新的信息抽取任务提供了有希望的研究基线和可复用的标注数据集.     

Maxwell's role in turning the concept of model into the methodology of modeling

This is a contribution towards a history and philosophy of modeling in its early stages in electromagnetism. In 1873, James Clerk Maxwell (1831–1879) hinted at the methodology of modeling at the end of his Treatise on Electricity and Magnetism. We focus on Maxwell's impact on physicists who immediately followed him, specifically Oliver Lodge (1851–1940) and George Francis FitzGerald (1851–1901). We begin with the role that the scientific concept of model played in the late nineteenth century, as assessed by Ludwig Boltzmann (1844–1906). We then discuss the role of hypothesis as a methodology, the appeal to (dynamical) illustration, and the way Maxwell applied model and working model in his studies of electromagnetism. We show that for Maxwell these key terms were kept distinct, but Lodge did not maintain these distinctions and, in this regard, FitzGerald followed Lodge. Notwithstanding Lodge's influence, Fitzgerald modified Maxwell's theory based on the mechanical model he designed, thereby implicitly taking the first step towards modeling. This methodology consists in drawing consequences from the (mechanical) model to the (electrodynamic) theory and modifying the latter in light of the functioning of the former. At the core of our argument is the thesis that it was a methodological novelty to move from the concept of model to the methodology of modeling. The introduction of modeling as a new methodology into physics in the late nineteenth century was a major event which deserves proper recognition.     

苏里格气田马家沟组膏模孔型储层特征及成因

含“膏模”孔泥粉晶云岩是鄂尔多斯盆地马家沟组上组合地层重要储集岩类型，其形成时间和成因对于该类型储层的认识具有重要意义。研究利用苏里格东区丰富的取芯资料，根据岩芯、薄片等观察手段，结合常规物性测试分析，综合研究含“膏模”孔型储层特征及其成因。结果表明，“膏模”孔主要发育于泥粉晶白云岩中，位于向上变浅序列中部，常可见未充填—半充填型与全充填型两类。储层特征方面，该类储集岩主要发育“膏模”孔充填残余孔、渗流粉砂间微孔和基岩晶间溶蚀微孔3类储集空间，物性测试显示储集性能优越，平均孔隙度可达5.34%，平均渗透率为1.02 mD。纵向沉积序列显示“膏模”孔发育受沉积旋回控制，旋回中部“膏模”孔内存在溶蚀，内为云质渗流粉砂充填，旋回顶部具有暴露特征，且可见下一次海侵泥质灌入岩溶系统内，各类特征均指示“膏模”孔形成与准同生期岩溶相关，即“膏模”孔形成于准同生期，而非传统认识的表生阶段。     

谈“十四五”生态保护与绿色发展的生态关系

 从“十四五”保护与发展的生态关系角度，探讨了生态保护与绿色发展的十大生态关系，阐述了生态保护和绿色发展中的一系列有关生态关系的生态智慧及生态技术，并对长江、黄河等流域的生态保护和修复提出了相关建议。     

基于深度学习的多STBC盲识别算法

针对空时分组码(space-time block code, STBC)识别中多种编码类型难区分的问题, 提出了一种基于卷积神经网络的STBC盲识别算法。该算法首先将接收信号采用自相关函数的频域预处理, 输入到卷积神经网络中对信号特征进行提取, 全连接层对特征进行映射, 实现对6种STBC类型的识别。仿真实验结果表明, 在无信道和噪声等先验信息的条件下, 所提算法能够有效区分3种相似度高的STBC3码, 且将STBC可识别的编码类型由目前的4种扩充到6种, 识别准确率能达到96%。该方法的复杂度较低, 不需要利用大量样本数据, 实时性高, 具有较好的工程应用价值。     

Digging with ‘hands’: observations of food capture in the flying gurnard Dactylopterus volitans (Linnaeus, 1758)

ABSTRACT

Videofilms of a foraging flying gurnard (Dactylopterus volitans) were collected at Itaipu, Niterói, RJ, Brazil. Analysis revealed details of the use of anterior parts of the pectoral fins which act as digging ‘hands’ to access infaunal prey items that are subsequently captured by oral suction feeding. Each pectoral fin has two distinct sections articulated separately on the pectoral girdle. The digging ‘anterior pectoral fin’ mainly consists of segmented and flexible fin rays but has an anterior robust unsegmented ray that provides an edge to the ‘hand’, allowing penetration of the substratum. The huge ‘posterior pectoral fins’ are supported by unsegmented rays. Most digging episodes involved one ‘hand’ and consisted of 1–7 cycles of movement with frequencies 1.15–3.74 cycles s^?1. During a cycle, the ‘hand’ is moved forwards and medially above the substratum, then is twisted medially and simultaneously depressed so that the anterior unsegmented ray impacts and enters the substratum. The hand is then drawn backwards and laterally to disturb the substratum. To prevent upward pitching of the head during digging, the ‘posterior pectoral fins’ are both moved anteriorly and laterally to shift the centre of gravity forwards while the caudal and ?second dorsal fins continue to provide propulsive force.     

A new twist to the No Miracles Argument for the success of science

J. D. Trout has recently developed a new defense of scientific realism, a new version of the No Miracles Argument. I critically evaluate Trout's novel defense of realism. I argue that Trout's argument for scientific realism and the related explanation for the success of science are self-defeating. In the process of arguing against the traditional realist strategies for explaining the success of science, he inadvertently undermines his own argument.     

Little-known and phylogenetically obscure South African estuarine microgastropods (Mollusca: Truncatelloidea) as living animals

Areas of the Knysna estuarine bay in the Western Cape are dominated by three endemic South African truncatelloid microgastropods, temporarily known as ‘Hydrobia’ knysnaensis (Krauss), ‘Assiminea’ capensis (Sowerby) and ‘Assiminea’ globulus Connolly. Although first described 80–170 years ago and present in abundance (up to 100,000 m^?2), they remain surrounded by confusion and still await taxonomic assignment, largely because they appear most atypical members of their groups by virtue of anatomy and/or biogeography and/or habitat. This study contributes in-life perspectives to morphological and phylogenetic analyses known to be on-going. At Knysna, they are syntopic: at least two occurring in >85% and all three in >40% of individual 0.0026 m² samples from their region of dominance. Nevertheless, they tend to greater abundance in divergent microhabitats; ‘A.’ globulus dominating higher tidal levels, and ‘A.’ capensis and ‘Hydrobia’ lower ones; the former especially unvegetated sediment, the latter, if anything, seagrass. Interspecific feeding interactions appear unlikely to be responsible for these patterns, other evidence suggesting that all are maintained below carrying capacity. Field biology of ‘H.’ knysnaensis generally appears equivalent to that of northern-hemisphere intertidal hydrobiids and that of ‘A.’ globulus is typically assimineid, albeit at atypically low shore height. Unlike assimineids, however, ‘A.’ capensis is truly aquatic. The success of these truncatelloids in unusual circumstances may be consequent on the absence from South Africa of other microgastropod groups that fill their niches elsewhere in the southern hemisphere.