藏族传统村落公共开放空间分析与对策——以赤康村为例

本文对藏式传统村落公共开放空间类型进行建构,分为历史建筑、活动场所、自然、基础设施。定性分析其特点、影响因素;采用语义分析法进行定量分析;从物质、社会、精神、民俗活动的角度,寻找空间需求与活力点。进一步提出高品质空间的设计原则与对策。     

物联网环境下基于情境的语义Web服务选择

当前Web服务海量增加，物联网应用技术快速发展、不断普及，而现有的Web服务选择算法低效、用户匹配度低。针对该问题提出一种物联网环境下基于情境的语义Web服务选择方法。该方法应用QoS参数的无量纲化与语义Web服务动态选择方式，将物联网环境下服务与语义Web服务相结合，并根据用户需求针对QoS选择最优的服务集。实验表明，该方法能有效地提高用户服务动态选择的成功率。     

Effects of different nutrition labels on visual attention and accuracy of nutritional quality perception – Results of an experimental eye-tracking study

Front-of-Pack (FoP) nutrition labels are emerging as a prominent public policy tool for promoting healthy eating. In this study, we question how different FoP nutrition labels ranging from more directive (Nutriscore, NS), to semi-directive (monochromatic Guided Daily Amount, GDA) and non-directive (multiple-traffic lights, MTL), affect perceived visual attention and nutritional quality perception. The visual attention was measured by eye-tracing measures, and nutritional quality by healthiness perception and recommended frequency of consumption. Seventy-six participants (N = 76) were randomly assigned in one of three experimental conditions, where they were asked to give estimates on eight different chocolate snack bars. To test whether participants estimates were accurate, we surveyed fifty-six (N = 56) nutritionists and asked for their assessments of the same group of products. The results showed that Nutriscore required least visual attention in terms of dwell-time, number of fixations, and average fixation duration, followed by MTL and GDA. Participants in NS and MTL condition gave significantly higher estimates of nutritional quality compared to experts' estimates. Most accurate estimates came from products with GDA label. Color-coded fields (MTL) required less visual attention, compared to GDA, without adding to visual efficiency. More directive FoP nutrition labels require less visual attention but lead to inflated estimates of products' nutrition quality in the category of less healthy products. In creating public policies, removing the possibility for consumers to process nutritional information and absolute estimates of products' nutrition quality should not be disregarded.     

基于动态标签的关系抽取方法

针对远程监督数据集的关系抽取研究方法存在着大量标签噪声的问题,提出了一种作用于分层注意力机制关系抽取模型的动态标签方法。首先，提出了一种根据关系类别相似性生成动态标签的概念。由于相同的关系标签包含相似的特征信息，计算特征信息的关系类别相似性有助于生成与特征信息相对应的动态标签。其次，利用动态标签方法的评分函数来评价远程监督标签是否为噪声，以决定是否需要生成新的标签代替远程监督标签，通过调整远程监督标签来抑制标签噪声对模型的影响。最后，根据动态标签来更新分层注意力机制以关注有效实例，重新学习每个有效实例的重要性，进一步抽取关键的关系特征信息。实验结果表明，相较于原始的分层注意力机制关系抽取模型，所提方法在Micro和Macro分数上分别有1.3个百分点和1.9个百分点的提升，实现了噪声标签的动态纠正，提升了模型的关系抽取能力。     

Automatic recommendation to appropriate log levels

A log statement is one of the key tactics for a developer to record and monitor important run-time behaviors of our system in a development phase and a maintenance phase. It composes of a message for stating log contents, and a log level (eg, debug or warn) to denote the severity of a message and controlling its visibility at run time. In spite of its usefulness, a developer does not tend to deeply consider which log level is appropriate in writing source code, which causes the system to be unmaintainable. To address this issue, this paper proposes an automatic approach to validating the appropriateness of the log level in consideration of the semantic and syntactic features and recommending a proper alternative log level. We first build the semantic feature vector to quantify the semantic similarity among application log messages using the word vector space, and the syntactic feature vector to capture the application context that surrounds the log statement. Based on the feature vectors and machine learning techniques, the log level is automatically validated, and an alternative log level is recommended if the log level is invalid. For the evaluation, we collected 22 open-source projects from three application domains, and obtained the 77% of precision and 75% of recall in validating the log levels. Also, our approach showed 6% higher accuracy than that of the developer group who has 7 to 8 years of work experience, and 72% of the developers accepted our recommendation.     

伪标签置信选择的半监督集成学习视频语义检测

在视频语义检测中，有标记样本不足会严重影响检测的性能，而且伪标签样本中的噪声也会导致集成学习基分类器性能提升不足。为此，提出一种伪标签置信选择的半监督集成学习算法。首先，在三个不同的特征空间上训练出三个基分类器，得到基分类器的标签矢量；然后，引入加权融合样本所属某个类别的最大概率与次大概率的误差和样本所属某个类别的最大概率与样本所属其他各类别的平均概率的误差，作为基分类器的标签置信度，并融合标签矢量和标签置信度得到样本的伪标签和集成置信度；接着，选择集成置信度高的样本加入到有标签的样本集，迭代训练基分类器；最后，采用训练好的基分类器集成协作检测视频语义概念。该算法在实验数据集UCF11上的平均准确率到达了83.48%，与Co-KNN-SVM算法相比，平均准确率提高了3.48个百分点。该算法选择的伪标签能体现样本所属类别与其他类别的总体差异性，又能体现所属类别的唯一性，可减少利用伪标签样本的风险，有效提高视频语义概念检测的准确率。     

Manifold label prediction for low dimensional palmprint recognition

Minimum Squared Error Classification (MSEC) is a learning method for predicting the class labels of samples in real time. However, as a regression algorithm, MSEC tries its best to map the training samples into their class labels using a linear projection without considering the manifold structure of the data. In this paper, we introduce a supervised label learning framework using an effective manifold learning strategy. This method which is referred to as Manifold Supervised Label Prediction (MSLP) generalizes MSEC objective function to incorporate intra-class relationships of data. Thus, in addition to relying on the relationship between a training sample and its label, we propose to also learn the relationship between the training samples while transforming them. As a testbed for MSLP, we apply it to an image identification venue in which image samples with a very low spatial resolution (16 × 16) are used. These images have been dramatically influenced by a down-sampling process in order to reduce their size and hence, improving over computation time. We also show that the blurring process for reducing the artifacts introduced by down-sampling serendipitously results in better identification accuracies. Finally, unlike MSEC that classifies a query sample based on the deviation between the predicted and the true class labels, we compare both the training and the query samples in the label prediction space. A set of comprehensive experiments on benchmark palmprint databases including Multispectral PolyU, PolyU 2D/3D, and PolyU Contact-free I shows meaningful improvements over existing state-of-the-art algorithms.     

自然光照条件下植被几何光学四分量的提取算法

目的 几何光学四分量是指在太阳光照条件下传感器所能观测的4个光学分量，即光照植被、光照土壤、阴影植被和阴影土壤。四分量是构成遥感几何光学模型的重要内容。在近地表遥感应用中，相机俯视拍照是提取四分量的一个途径。准确快速地从图像数据中提取四分量对植被冠层结构参数反演和植被长势监测具有重要意义。方法 植被与土壤二分量的识别是四分量提取的基础。目前大多数二分类算法在自然光照条件复杂时分类误差较大。本文基于卷积神经网络（CNN）和阈值法实现了多种二分类和四分量提取算法。阈值法中，使用SHAR-LABFVC （shadow-resistant algorithm：LABFVC）实现植被与土壤的二分类，并在此基础上应用二次阈值分割获取四分量，称为二次阈值法；基于CNN的方法中，采用U-Net架构，并使用RGB和RGBV数据进行训练得到U-Net和U-Net-V模型，前者完成二分类和四分量任务，后者只完成四分量提取实验。最后，对一种结合U-Net与阈值法的混合算法进行四分量提取实验。结果 本文在18幅图像（1 800个子图）数据上进行了实验，结果表明，与目视解译得到的四分量真值相比较，U-Net-V和混合法精度最高，具有相近的均方根误差（RMSE）（0.06和0.07）和相关系数（0.95和0.94）；二次阈值法与U-Net模型精度略低于上述两种算法，RMSE分别是0.08和0.09，相关系数均为0.88。在二分类实验中，U-Net的分类正确率是91%，SHAR-LABFVC为85%。结论 通过对比实验表明，在二分类问题中，U-Net可以更好地应对复杂自然光照条件下的数字图像。在四分量提取实验中，混合法和U-Net-V的结果优于U-Net与二次阈值法，可以用于提取四分量。