利用改进特征金字塔模型的SAR图像多目标船舶检测

深度学习模型中的特征金字塔网络（Feature Pyramid Network，FPN）常被用作合成孔径雷达（Synthetic Aperture Radar，SAR）图像中多目标船舶的检测。针对复杂场景下多目标船舶检测问题，提出了一种基于改进锚点框的FPN模型。首先将特征金字塔模型嵌入传统的RPN（Region Proposal Network）并映射成新的特征空间用于目标检测，然后利用基于形状相似度距离（Shape Similar Distance,SSD）度量的Kmeans聚类算法优化FPN的初始锚点框，并使用SAR船舶数据集测试。实验结果表明，所提算法目标检测精确率达到98.62%，在复杂场景下与YOLO、Faster RCNN、FPN based on VGG/ResNet等模型进行对比，模型准确率提高，整体性能更好。     

利用频移动态特征的辐射源目标盲分选

利用辐射源目标的频移动态特征进行盲分选时，针对已有的分选方法不能很好解决非合作接收数据非周期、间断、交叠的问题，提出了一种改进的逻辑回归分选算法,将信号分选转化为轨迹分类的问题来处理。首先，借鉴多目标航迹起始模型中的M/N逻辑法的框架，设计新的数据关联门限，以建立目标起始曲线；其次，采用最小二乘拟合方法替代卡尔曼滤波，设计新的外推规则，建立载频变化预测曲线；分析新的接收数据与预测曲线的关联性，不断迭代回归或形成新的分支，最后获得目标分选结果。仿真与实测试验表明，利用逻辑回归分选算法，对不同运动目标搭载的同频辐射源可进行自动分选，4个仿真目标与2个真实目标的分选正确率达到100%。同时，该方法拓展了辐射源目标盲分选中的动态频移特征应用，为辐射源个体识别提供了新的支持。     

基于LBPH算法的人脸识别算法研究与设计

人脸识别技术是一种根据人脸的特征信息进行身份判定的技术,此技术经过几十年的发展,由弱人工智能向强人工智能转化,论文提出了一种Python语言利用LBPH算法提取人脸特征、实现人脸识别的方法。     

Relative age effects in political selection

We exploit a regression discontinuity design to provide causal evidence of the relative age effect (RAE) on a long-run adult age outcome: Political selection. We find strong evidence of the RAE in politics in Finland. However, the effect is heterogeneous: We find that male candidates born early in the calendar year have a significantly higher probability of getting elected to the parliament but no similar RAE applies to female candidates nor to municipal elections. Moreover, this effect only takes place in the most competitive parliamentary districts and is present only for some parties. We also find that in all the groups where the RAE does not exist, early-born candidates are under-represented suggesting attrition of talent in the candidate placement. Overall, our results show that seemingly artificial cutoffs imposed by the government have persistent consequences even on the selection to the highest positions of power within a society.     

Paired comparison models with age effects modeled as piecewise quadratic splines

We propose new models for analyzing pairwise comparison data, such as that relating to sports. We focus on changes in players’ strengths and the prediction of future results. Our models are based on the Thurstone-Mosteller and Bradley–Terry models, and make use of the time variation in the parameters. Furthermore, we apply our models to data from the Japanese traditional sport sumo, and analyze this data. The proposed models perform better than the standard Thurstone-Mosteller and Bradley–Terry models according to both the Akaike information criterion and the Brier score. We compare the proposed models in detail by focusing on individual sumo wrestlers.     

基于供应链管理的供应商选择问题初探

在现阶段的发展过程中,现代化发展已经成为企业未来发展的基本方向。作为企业实现现代化发展的关键环节,供应链的管理工作在整个企业运行过程中起到了举足轻重的作用。伴随着供应链管理的发展,供应商的选择问题越来越多,选择要点和选择内容不断丰富,并逐渐发展成为企业采购过程中所有采购员共同面对的问题。根据企业的发展现状和运营情况,选择更合适更合理的采购方案和供货商,并遵循行业准则来制定企业采购规则。     

执法监测中正确使用环境标准初探

经过近四十年的发展和完善,我国的环境标准已形成了“两级五类”的完整体系。基层监测人员在执法监测中对环境标准的选择,要结合环境影响批复和污染工艺、排放去向进行综合考虑。在排污许可证上载明的污染物排放浓度与排放标准中规定的浓度限值不一致的情况下,应慎重选取排放标准规定的浓度限值。使用环境标准的基本原则是地方标准优先于国家标准,行业标准优先于综合标准,新标准优先于旧标准,地方政府文件不具有标准效力。     

Object detection based on visual memory: a feature learning and feature imagination process

ABSTRACT

Visual memory plays an important role for the human’s visual system to detect objects. The features of an object stored in the visual memory have much lower dimensions than the features contained within an image. We simulate the visual memory as a feature learning and feature imagination (FLFI) process to build an object detection algorithm. The method is constructed by a bottom-up feature learning and a top-down feature imagination. The proposed object detection method is tested using publicly available benchmark data sets, and the result indicates that it is fast and more robust.     

GIS-based fuzzy multi-criteria approach for optimal site selection of fire stations in Istanbul,Turkey

Fire stations play a central role in protection and response activities as part of emergency management services in cases of fire incidences. With the rising urban populations and city expansions, the demand for more fire services resultantly increases. It then becomes critical to effectively plan the location of emergency facilities to adequately service the population and ensure the protection of lives and infrastructure. This study, therefore proposes the use of the fuzzy extension of the Multi-Criteria Decision-Making (MCDM) method of Analytical Hierarchical Process (AHP), hence called fuzzy AHP, integrated with Geographic Information Systems (GIS) approach to optimally site new fire stations for the case of Istanbul region. This proposed fuzzy approach simulates the subjective expert judgements for the preferences of the six criteria assessed for fire station suitability mapping and thereby accounted for the uncertainty of crisp comparison values via triangular fuzzy numbers (TFNs). The criteria weights evaluated from this procedure were used in a weighted overlay analysis of the reclassified criteria map layers in ArcGIS to generate a fire station suitability map. These resultant fuzzy AHP criteria weights were validated using another MCDM technique, called Best-Worst Method (BWM) and found to be comparable and consistent. The criteria that had the strongest influence on the selection of sites for fire stations were identified to be: the density of hazardous material facilities (DHM), a high population density (HPD) and proximity to main roads (PMR) with associated weights of 33.3%, 24.4% and 15.2%, respectively. Based on a thorough assessment within the areas represented by class values ranging from 3 to 5 on the suitability map, a total of 34 new fire station sites were selected complementing the existing 121 fire stations. Further, a prioritization analysis from low, medium to high, was performed to plan the phases for the construction of new fire stations in view of competing budgetary needs and resource constraints. The methodology to achieve this was proposed and modelled for enhancing the decision-making process in urban fire station site selection studies.     

The construction of a composite index for general satisfaction in Turkey and the investigation of its determinants

The goal of public enterprises is to increase the wealth and happiness of individuals. This target lets them make the investment to fulfill these expectations. However, not all citizens in a country might have the same opportunities. This case requires comparing citizens who live in cities with regard to satisfaction levels. This study consists of two stages. In the first stage, a composite index called the General Satisfaction Index (GSI), which aims to explain the satisfaction levels of citizens living in cities, is obtained by using the Benefit of the Doubt method. Contrary to the previous studies, the satisfaction indicators based on the emotions and senses of citizens are used to construct a composite index. Satisfaction indicators’ contribution to GSI is ensured using the minimum weights. In the second stage of this study, socioeconomic determinants of GSI are investigated in both countrywide and regions by using regularized regression methods. In the result of the regression analyze, it is confirmed that there are different socioeconomic determinants of satisfaction levels for countrywide and each region. For this reason, it is proposed that policymakers should follow different politicizes in each region to increase the satisfaction levels of citizens in the country.