Unsupervised constellation model learning algorithm based on voting weight control for accurate face localization

In this paper, we propose a novel unsupervised constellation model learning algorithm based on voting weight control for accurate scale, rotation, and translation invariant face localization without manual selection of feature points. The constellation model is learned by controlling the expected voting weights of the local features to obtain their perceptual boundaries and the distribution of voting weights, and selecting most common features as the representative features among them. The proposed constellation model can be learned incrementally to successfully localize faces when the previously learned model fails to localize them accurately. Through experiments, it is shown that the proposed constellation model can accurately localize faces of various size, orientation, and location.     

基于C/S体系结构的报到表决管理信息系统

以C／S体系结构为基础，设计并实现了电子报到表决管理信息系统。对其中包括门口报到子系统、电子表决子系统、会务管理子系统、视频显示子系统等各子系统的功能进行分析，提出各功能模块的设计方案。实践证明该电子报到表决管理信息系统运行安全可靠。     

Fuzzy social choice: a selective retrospect

One of the founders of social choice theory, Marquis de Condorcet, assigned truth degrees to propositions expressing preferences over options. Although his work is often discussed in terms of probability theory, it is arguable that his truth degree lends itself to a more natural interpretation as a fuzzy preference. We shall review some of Condorcet’s results in the light of this interpretation. The first twentieth century applications of fuzzy concepts to social choice appeared rather shortly after the introduction by L. A. Zadeh of the concept of fuzzy binary relation in early 1970s. The early applications dealt with experimental anomalies and their accountability with the aid of fuzzy preference relations and fuzzy goal states. Considerable literature now exists on various solution concepts in fuzzy voting games and many important theorems of traditional social choice theory have found their counterpart in fuzzy social choice. The natural next step would seem to be the design of fuzzy mechanisms and institutions. The author wishes to thank—without implicating—Didier Dubois, Javier Montero and Rudolf Seising for useful comments on an earlier draft.     

基于公共利益的城中村规划票决制探讨

根据《物权法》和《城乡规划法》的规定,城中村规划只有符合公共利益,才能成为征收土地、房屋及不动产的依据。在目前公共利益内容不确定、城市政府主导城中村规划的情况下,应引入票决制,解决城中村规划中的公共利益判断难题,为城中村改造的合法性提供法理上的保障;同时,应对票决制进行功能分析和制度设计,构建相应的救济程序,减少票决制度在操作过程中对少数人权益的损害。     

The design of novel distributed protocols from differential equations

This paper proposes a framework to translate certain subclasses of differential equation systems into practical protocols for distributed systems. The generated protocols are intended for large-scale distributed systems that contain several hundreds to thousands of processes. The synthesized protocols are state machines containing probabilistic transitions and actions, and they are proved to show equivalent stochastic behavior to the original equations. The protocols are probabilistically scalable and reliable, and have practical applications in large-scale distributed systems, e.g., peer to peer systems. In order to illustrate the usefulness of the framework, it is used to generate new solutions for the problems of (a) responsibility migration (giving rise to a novel model of dynamic replication), and (b) majority selection. We present mathematical analysis of these two protocols, and experimental results from our implementations. These two protocols are derived from natural analogies that are represented as differential equations—endemics and the Lotka–Volterra model of competition, respectively. We believe the design framework could be effectively used in transforming, in a very systematic manner, well-known natural phenomena into protocols for distributed systems.     

Application of voting to fusion of purposive modules: An experimental investigation

Control in behavior-based systems is distributed among a set of specialized behaviors. To achieve efficient implementation, behaviors exploit specific assumptions about a given task and environment. Thus they become vulnerable to deviations that render these assumptions invalid. Yet it is important to provide appropriate responses to unforeseen situations.

We demonstrate that, using voting techniques, a model-free approach may be provided to construct reliable behaviors from a multitude of less reliable ones. A team of complementary behaviors vote for the set of possible actions, and the action which is most favored is selected for controlling the system. We conjecture that selecting actions according to this scheme can improve the probability of success.

Our conjecture is investigated through two sets of experiments. In the first, a team of obstacle avoidance behaviors vote to guide a mobile robot platform in the most appropriate direction. In the second, four object tracking modules are integrated to perform smooth pursuit with a camera head.     

Towards a dichotomy for the Possible Winner problem in elections based on scoring rules

To make a joint decision, agents (or voters) are often required to provide their preferences as linear orders. To determine a winner, the given linear orders can be aggregated according to a voting protocol. However, in realistic settings, the voters may often only provide partial orders. This directly leads to the Possible Winner problem that asks, given a set of partial votes, whether a distinguished candidate can still become a winner. In this work, we consider the computational complexity of Possible Winner for the broad class of voting protocols defined by scoring rules. A scoring rule provides a score value for every position which a candidate can have in a linear order. Prominent examples include plurality, k-approval, and Borda. Generalizing previous NP-hardness results for some special cases, we settle the computational complexity for all but one scoring rule. More precisely, for an unbounded number of candidates and unweighted voters, we show that Possible Winner is NP-complete for all pure scoring rules except plurality, veto, and the scoring rule defined by the scoring vector (2,1,…,1,0), while it is solvable in polynomial time for plurality and veto.     

基于文本挖掘的高速铁路动车组故障多级分类研究

针对高速铁路信号设备故障发生后记录的文本数据,提出基于文本挖掘方式的高速铁路信号设备故障多级分类模型研究。提出TF-IDF词汇权重与词汇字典结合的特征表示方法实现信号设备故障文本数据的特征提取。多级分类模型中,基于Stacking集成学习思想设计单层分类模型,将循环神经网络BiGRU和BiLSTM作为初级学习器,设计权重组合计算方法作为次级学习器,将多级分类任务分解为各层单分类任务,并采用K折交叉验证训练Stacking模型。采用高速铁路自开通至十年的信号转辙机故障数据,通过对故障原因文本数据的分析,实现故障部位和故障原因的二级分类,经过K=5次训练,BiGRU较BiLSTM各评价指标都较高,经实验BiGRU分配权重为0.7,BiLSTM权重为0.3,组合加权对两个网络的输出计算,准确率提高为0.8814,召回率提高为0.8642。实验表明多级分类模型能够有效提升信号设备故障多级分类任务的分类评价指标,并能够保证分类结果隶属关系的正确性。     

基于投票人影响因子的投票预测模型

投票预测是计算政治学的应用之一,目前绝大多数预测模型都忽视投票过程中投票人之间的相互影响.针对此问题,文中提出基于投票人影响因子的投票预测模型.首先,提出投票人影响因子,用于刻画某位投票人在投票过程中对于其他投票人投票选择的影响,同时结合预训练模型提取的投票人特征,形成影响因子图,再输入图卷积神经网络中,学习投票人的相互影响,在一定程度上模拟真实的投票博弈过程.然后,考虑到法案文本中上下文信息的关联性,利用BiLSTM(Bi-directional Long Short-Term Memory)获得法案特征向量.鉴于法案文本的规范性导致的行文近似、用词重复,使用引入TF-IDF(Term-Frequency-Inverse Document Frequency)因子的TextRank,得到法案的关键词.在国外议会网站数据集上的实验表明文中模型性能较优,消融实验也验证每个模块对文中模型的性能均有一定程度的提升.     

Unified detection of skewed rotation,reflection and translation symmetries from affine invariant contour features

Symmetry detection is significant for object detection and recognition since symmetries are salient cues for distinguishing geometrical structures from cluttered backgrounds. This paper proposes a unified framework to detect rotation, reflection and translation symmetries simultaneously on unsegmented real-world images. The detection is performed based on affine invariant contour features, and is applicable under skewed imaging with distortions. Contours on a natural image are first matched to each other to find affine invariant matching pairs, which are then classified into three groups using a sign change criterion corresponding to the three types of symmetries. The three groups are used to vote for the corresponding symmetries: the voting for rotation utilizes a scheme of short line segments; the voting for reflection is based on a parameterization of axis equation, and the voting for translation uses a cascade-like approach. Experimental results of real-world images are provided with quantitative evaluations, validating that the proposed framework achieves desired performance.