A new reverse reduce-error ensemble pruning algorithm

Although greedy algorithms possess high efficiency, they often receive suboptimal solutions of the ensemble pruning problem, since their exploration areas are limited in large extent. And another marked defect of almost all the currently existing ensemble pruning algorithms, including greedy ones, consists in: they simply abandon all of the classifiers which fail in the competition of ensemble selection, causing a considerable waste of useful resources and information. Inspired by these observations, an interesting greedy Reverse Reduce-Error (RRE) pruning algorithm incorporated with the operation of subtraction is proposed in this work. The RRE algorithm makes the best of the defeated candidate networks in a way that, the Worst Single Model (WSM) is chosen, and then, its votes are subtracted from the votes made by those selected components within the pruned ensemble. The reason is because, for most cases, the WSM might make mistakes in its estimation for the test samples. And, different from the classical RE, the near-optimal solution is produced based on the pruned error of all the available sequential subensembles. Besides, the backfitting step of RE algorithm is replaced with the selection step of a WSM in RRE. Moreover, the problem of ties might be solved more naturally with RRE. Finally, soft voting approach is employed in the testing to RRE algorithm. The performances of RE and RRE algorithms, and two baseline methods, i.e., the method which selects the Best Single Model (BSM) in the initial ensemble, and the method which retains all member networks of the initial ensemble (ALL), are evaluated on seven benchmark classification tasks under different initial ensemble setups. The results of the empirical investigation show the superiority of RRE over the other three ensemble pruning algorithms.     

指纹细节特征提取与剪枝

指纹图像经预处理后，由于各种原因，会产生数以百计的特征。为了图像匹配的精确和快速，提出一套在细化后的指纹点线图上提取细节特征并对其剪枝的方法，并根据细节特征的拓扑特性，设计了验证其可靠性的算法。通过实验，证明了该后处理过程在去除指纹图像伪特征方法面具有良好的效果。     

Scheduling in or-parallel Prolog systems: Survey and open problems

Implementation of or-parallel Prolog systems offers a number of interesting scheduling problems. The main issues are the interaction between memory models and scheduling, ordering of multiple solutions, and scheduling of speculative work. The problems occur partly because of the design choices (e.g. the choice of a memory model), and partly because of the desire to maintain observational equivalence between parallel and sequential implementations of Prolog, while achieving high efficiency. In the first part of this paper a common framework for discussing scheduling in or-parallel systems is introduced, and also a collection of issues that must be addressed in such systems is presented. In the second part of the paper we survey a number of solutions to these problems comparing their efficiency whenever possible. We close the survey with a short discussion of open problems.Current association: Carlstedt Elektronik AB     

Aeromagnetic compensation using neural networks

Airborne magnetic surveys in geophysical exploration can be subject to interference effects from the aircraft. Principal sources are the permanent magnetism of various parts of the aircraft, induction effects created by the earth's magnetic field and eddy-current fields produced by the aircraft's manoeuvres. Neural networks can model these effects as functions of roll, pitch, heading and their time derivatives, together with vertical acceleration, charging currents to the generator, etc., without assuming an explicit physical model. Separation of interference effects from background regional and diurnal fields can also be achieved in a satisfactory way.     

选择性集成算法分类与比较

选择性集成是当前机器学习领域的研究热点之一。由于选择性集成属于NP"难"问题,人们多利用启发式方法将选择性集成转化为其他问题来求得近似最优解,因为各种算法的出发点和描述角度各不相同,现有的大量选择性集成算法显得繁杂而没有规律。为便于研究人员迅速了解和应用本领域的最新进展,本文根据选择过程中核心策略的特征将选择性集成算法分为四类,即迭代优化法、排名法、分簇法、模式挖掘法;然后利用UCI数据库的20个常用数据集,从预测性能、选择时间、结果集成分类器大小三个方面对这些典型算法进行了实验比较;最后总结了各类方法的优缺点,并展望了选择性集成的未来研究重点。     

基于逐层剪枝的中文高频重复模式快速提取算法

为了从大规模语料中快速提取高频重复模式,以递增n-gram模型为基础,使用散列数据结构提取重复串,并提出了一种基于低频字符和层次剪枝的逐层剪枝算法,用于过滤低频垃圾字串,减少I/O读写次数。在此基础上,应用改进的字串排序算法,使字符串排序可在O(n)时间内完成,从而有效提高重复模式的提取效率。实验表明,该算法是一种有效的重复模式提取算法,其I/O读写次数同语料规模呈线性关系,远小于使用首字符进行语料划分的方法,能快速有效地从规模远大于内存容量的文本语料中提取重复模式,特别适合于大规模语料的高频重复模式提取,对以重复模式为基础的新词识别、术语抽取等具有重要的支撑作用。     

面向边缘端的施工人员实时检测方法

施工人员检测在施工管理工作中有重要的应用价值。施工现场图像背景复杂且视角多样,给施工人员检测任务带来难度,同时施工现场大多基础配套设施不完善,并且网络条件较差,不适合在大型GPU工作站上进行模型部署。针对以上问题,以YOLOv3检测网络为基础,加入特征金字塔池化模块,增加多尺度特征融合并改进候选框,提升检测精度,同时采用通道剪枝算法对检测网络进行轻量化处理以适应边缘端设备算力,提出一种面向边缘端的施工人员实时检测方法。该方法在自制的施工人员数据集上平均准确率可达到88.23%,较YOLOv3检测方法提升4.89个百分点,且将模型大小压缩至原来的1/13,检测速度提升一倍,在嵌入式设备Jetson Xavier NX上检测速度可达到69.08帧/s,满足在施工现场进行实时边缘端检测的要求。     

一种高效二进前馈神经网络学习算法

为解决二进前馈神经网络(BFNN)缺乏高效实用学习算法的问题,提出一种新的融合自适应调节结构和权值的BFNN学习算法.该算法借鉴并改进了极限学习机(ELM)方法,可以高效地训练单隐层的BFNN来解决分类问题.为了满足网络的训练精度,算法可以自动增加隐层神经元个数和调节网络隐层及输出层神经元权值;同时为了提高网络的泛化精度,算法通过建立二进神经元敏感性作为度量隐层神经元重要性的尺度,自动地裁剪重要性小的神经元,并对裁剪损失的信息进行补偿.实验结果验证了该算法在处理离散分类问题时的可行性和有效性.     

基于B-list的最大频繁项集挖掘算法

针对现有的最大频繁项集挖掘算法挖掘时间过长、内存消耗较大的问题,提出了一种基于构造链表B-list的最大频繁项集挖掘算法BMFI,该算法利用B-list数据结构来挖掘频繁项集并采用全序搜索树作为搜索空间,然后采用父等价剪枝技术来缩小搜索空间,最后再结合基于MFI-tree的投影策略实现超集检测来提高算法的效率。实验结果表明,BMFI算法在时间效率与空间效率方面均优于FPMAX算法与MFIN算法。该算法在稠密数据集与稀疏数据集中进行最大频繁项集挖掘时均有良好的效果。     

改进的序列模式挖掘在医院转诊中的应用

为了研究患者在不同医院间的转诊行为模式, 可以使用序列模式挖掘算法. 类Apriori算法是序列模式挖掘中的常用算法, 但该算法存在一些不足之处, 如产生候选序列的数目较多、需要频繁扫描数据库. 针对类Apriori算法存在的不足, 本文提出了相应的改进措施, 采用新的剪枝策略并减少不必要的数据库扫描操作. 实验证明, 改进后的算法能更高效地挖掘频繁转诊序列.