关键词： 天文选址   云图分类   模式识别   卷积神经网络  

摘要： 全天相机拍摄的全天空地基云图能够实时反映当地的云量信息,而云量是天文选址首先考虑的因素之一。因此,对全天空地基云图根据图像质量、应用背景等因素进行自动化分类,实现鲁棒性高、适应性强的自动化分类算法,为天文选址提供重要帮助。基于雪龙号全天相机数据对卷积神经网络模型进行训练,并使用丽江观测站全天相机数据进行测试,取得了较好的应用效果,实现了可迁移性高的全天空地基云图自动化分类方法。

关键词： Seismic multiples   wave propagation   pattern recognition   membership functions   multiple attenuation   FDTD   CPML  

摘要： It is well known that high impedance contrasts between salt bodies and their surroundings yield blurriness in seismic images which does not allow adequate interpretation;some of the artifacts generated by this process are multiple reflections and diffractions. In this work we propose a novel method of detection and attenuation of multiples from seismic gathers which is based on pattern recognition and fuzzy logic. In order to corroborate the effectiveness of this new approach, we use synthetic models which mimic a region intensely affected by salt tectonics in deep-water Gulf of Mexico. We obtained synthetic seismic sections by simulating wave propagation with an FDTD-CPML formulation. Detection of seismic events is performed through the mapping of parabolic shapes in shot gathers that approximate the recorded wavefronts. Undesired multiple events are then surgically attenuated by using fuzzy threshold criteria. Results show an optimal attenuation of multiple events, even when they are not directly related to salt structures.

关键词： Ageing   Inflammaging   Receptor for advanced glycation end-products (RAGE)   Pattern recognition receptor  

摘要： The receptor for advanced glycation end-products (RAGE) was initially characterized and named for its ability to bind to advanced glycation end-products (AGEs) that form upon the irreversible and non-enzymatic interaction between nucleophiles, such as lysine, and carbonyl compounds, such as reducing sugars. The concentrations of AGEs are known to increase in conditions such as diabetes, as well as during ageing. However, it is now widely accepted that RAGE binds with numerous ligands, many of which can be defined as pathogen-associated molecular patterns (PAMPs) or damage-associated molecular patterns (DAMPs). The interaction between RAGE and its ligands mainly results in a pro-inflammatory response, and can lead to stress events often favouring mitochondrial dysfunction or cellular senescence. Thus, RAGE should be considered as a pattern recognition receptor (PRR), similar to those that regulate innate immunity. Innate immunity itself plays a central role in inflammaging, the chronic low-grade and sterile inflammation that increases with age and is a potentially important contributory factor in ageing. Consequently, and in addition to the age-related accumulation of PAMPs and DAMPs and increases in pro-inflammatory cytokines from senescent cells and damaged cells, PRRs are therefore important in inflammaging. We suggest here that, through its interconnection with immunity, senescence, mitochondrial dysfunction and inflammasome activation, RAGE is a key contributor to inflammaging and that the pro-longevity effects seen upon blocking RAGE, or upon its deletion, are thus the result of reduced inflammaging.

关键词： Psychosis   Prodrome   Motor learning   Implicit learning   Pattern recognition  

关键词： Machine learning   Incremental clustering   Pattern recognition   Neural network   Decision tree   SVM  

摘要： The most effective well-known methods in the context of static machine learning offer no alternative to evolution and dynamic adaptation to integrate new data or to restructure problems already partially learned. In this area, the incremental learning represents an interesting alternative and constitutes an open research field, becoming one of the major concerns of the machine learning and classification community. In this paper, we study incremental supervised learning techniques and their applications, especially in the field of pattern recognition. This article presents an overview of the main concepts and supervised algorithms of incremental learning, including a synthesis of research studies done in this field and focusing on neural networks, decision trees and support vector machines.

关键词： Algebra   Algorithms   Applied mathematics   Cluster analysis   Distance measurement   Eigenvalues   Eigenvectors   Engineering and technology   Euclidean geometry   Geometry   Linear algebra   Markov models   Mathematical and statistical techniques   Mathematical models   Mathematics   Measurement   Physical sciences   Probability theory   Random walk   Research and analysis methods   Research Article   Simulation and modeling   Spectral clustering  

摘要： Clustering large and complex data sets whose partitions may adopt arbitrary shapes remains a difficult challenge. Part of this challenge comes from the difficulty in defining a similarity measure between the data points that captures the underlying geometry of those data points. In this paper, we propose an algorithm, DCG++ that generates such a similarity measure that is data-driven and ultrametric. DCG++ uses Markov Chain Random Walks to capture the intrinsic geometry of data, scans possible scales, and combines all this information using a simple procedure that is shown to generate an ultrametric. We validate the effectiveness of this similarity measure within the context of clustering on synthetic data with complex geometry, on a real-world data set containing segmented audio records of frog calls described by mel-frequency cepstral coefficients, as well as on an image segmentation problem. The experimental results show a significant improvement on performance with the DCG-based ultrametric compared to using an empirical distance measure. © 2019 Guan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： 模式识别   机器学习  

ISBN: (纸本)9787502481308

摘要： 模式识别与机器学习是计算机科学与技术的重要研究内容之一。本书较为全面地论述了模式识别与机器学习的基本概念、基础原理、基本方法和基本技术, 强调理论和实际相结合, 尽量避免涉及繁琐的数学推导。力求通俗易懂, 深入浅出, 注重实用。目的是让使用者掌握模式识别与机器学习的基本知识, 并能运用所学知识解决实际应用的问题。为研究新的模式识别与机器学习的理论和方法打下基础。本书首先讲解了贝叶斯分类、支持向量机和人工神经网络等常见的机器学习算法, 简要讲解了深度学习常见的模型和计算机视觉的基本知识。详细介绍了基于卷积神经网络的树木识别和基于对抗生成网络的玉米病害图像生成的实际应用案例。最后介绍了模式识别与机器学习涉及到的数学基础知识。书中配有模式识别与机器学习相应算法的Python源代码。

关键词： Hubel Wiesel's hypothesis   Selective attention   Invariant pattern recognition   Deep learning   Steep learning  

摘要： Hubel and Wiesel's study about low areas of the visual cortex (VC) inspired deep models for invariant pattern recognition. In such models, simple and complex layers alternate local feature extraction with subsampling to add invariance to distortion or transformations. However, it was shown that to tolerate large changes between examples of the same category, the subsampling operation has to discard so much information that the model loses the capability to discriminate between categories. So, in practice, small changes are tolerated by these layers and, afterwards, a powerful classifier is introduced to do the rest. By incorporating insights from higher areas of the VC, we add to the already used retinotopic step an object-centered step which increases invariance capabilities without losing so much information. By doing so, we reduce the need for a powerful, data hungry classification layer and, thus, are able to introduce a simple classification mechanism which is based on selective attention. The resulting model is tested with an invariant pattern recognition task in the MNIST and ETL-1 datasets. We verify that the model is able to achieve better accuracies with less training examples. More specifically, on the MNIST test set, the model achieves a 100% accuracy when trained with little more than 10% of the training set. (c) 2019 Elsevier Ltd. All rights reserved.

关键词： PRRs   TLRs   Cancer cells   Agonists   Nucleic-acid sensing   RLRs   cGAS-STING pathway  

摘要： Pattern recognition receptors (PRRs) are members of innate immunity, playing pivotal role in several immunological reactions. They are known to act as a bridge between innate and adaptive immunity. They are expressed on several normal cell types but have been shown with increasing frequency on/in tumor cells. Significance of this phenomenon is largely unknown, but it has been shown by several authors that they, predominantly Toll-like receptors (TLRs), act in the interest of tumor, by promotion of its growth and spreading. Preparation of artificial of TLRs ligands (agonists) paved the way to use them as a therapeutic agents for cancer, so far in a limited scale. Agonists may be combined with conventional anti-cancer modalities with apparently promising results. PRRs recognizing nucleic acids such as RIG-1 like receptors (sensing RNA) and STING (sensing DNA) constitute a novel promising approach for cancer immunotherapy.

关键词： myoelectric pattern recognition   spinal cord injury   exoskeleton   hand function  

摘要： Objective. The objective of this study was to investigate the feasibility of applying myoelectric pattern recognition for controlling a robotic hand in individuals with spinal cord injury (SCI). Approach. Surface electromyogram (sEMG) signals of six hand motion patterns were recorded from 12 subjects with SCI. Online and offline classification performance of two classifiers (Gaussian Naive Bayes classifier, GNB, and support vector machine, SVM) were investigated. An exoskeleton hand was then controlled in real-time using the classification results. The control accuracy and its correlation with function assessments were investigated. Main results. Average offline classification accuracy of all tested SCI subjects was (73.6 +/- 14.0)% for GNB and (77.6 +/- 11.6)% for SVM, respectively. Average online classification accuracy was significantly lower, (64.3 +/- 15.0)% for GNB and (70.2 +/- 13.2)% for SVM. Average control accuracy of (81.0 +/- 16.3)% was achieved in real-time control of the robotic hand using myoelectric pattern recognition. Correlation between control accuracy and grip/pinch force was observed. Significance. The results show that it is feasible to extract hand motion intent from individuals with SCI and control a robotic hand device using myoelectric pattern recognition. The performance of real-time control can be predicted based on functional assessments.