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.     

Remote Steering of Self‐Propelling Microcircuits by Modulated Electric Field

The principles and design of “active” self‐propelling particles that can convert energy, move directionally on their own, and perform a certain function is an emerging multidisciplinary research field, with high potential for future technologies. A simple and effective technique is presented for on‐demand steering of self‐propelling microdiodes that move electroosmotically on water surface, while supplied with energy by an external alternating (AC) field. It is demonstrated how one can control remotely the direction of diode locomotion by electronically modifying the applied AC signal. The swimming diodes change their direction of motion when a wave asymmetry (equivalent to a DC offset) is introduced into the signal. The data analysis shows that the ability to control and reverse the direction of motion is a result of the electrostatic torque between the asymmetrically polarized diodes and the ionic charges redistributed in the vessel. This novel principle of electrical signal‐coded steering of active functional devices, such as diodes and microcircuits, can find applications in motile sensors, MEMs, and microrobotics.     

基于多尺度双线性卷积神经网络的多角度下车型精细识别

针对多角度下车辆出现一定的尺度变化和形变导致很难被准确识别的问题，提出基于多尺度双线性卷积神经网络（MS-B-CNN）的车型精细识别模型。首先，对双线性卷积神经网络（B-CNN）算法进行改进，提出MS-B-CNN算法对不同卷积层的特征进行了多尺度融合，以提高特征表达能力；此外，还采用基于中心损失函数与Softmax损失函数联合学习的策略，在Softmax损失函数基础上分别对训练集每个类别在特征空间维护一个类中心，在训练过程中新增加样本时，网络会约束样本的分类中心距离，以提高多角度情况下的车型识别的能力。实验结果显示，该车型识别模型在CompCars数据集上的正确率达到了93.63%，验证了模型在多角度情况下的准确性和鲁棒性。     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

Word length and lexical activation: Longer is better.

Many models of spoken word recognition posit the existence of lexical and sublexical representations, with excitatory and inhibitory mechanisms used to affect the activation levels of such representations. Bottom-up evidence provides excitatory input, and inhibition from phonetically similar representations leads to lexical competition. In such a system, long words should produce stronger lexical activation than short words, for 2 reasons: Long words provide more bottom-up evidence than short words, and short words are subject to greater inhibition due to the existence of more similar words. Four experiments provide evidence for this view. In addition, reaction-time-based partitioning of the data shows that long words generate greater activation that is available both earlier and for a longer time than is the case for short words. As a result, lexical influences on phoneme identification are extremely robust for long words but are quite fragile and condition-dependent for short words. Models of word recognition must consider words of all lengths to capture the true dynamics of lexical activation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Tracking the mind during reading: The influence of past, present, and future words on fixation durations.

Reading requires the orchestration of visual, attentional, language-related, and oculomotor processing constraints. This study replicates previous effects of frequency, predictability, and length of fixated words on fixation durations in natural reading and demonstrates new effects of these variables related to 144 sentences. Such evidence for distributed processing of words across fixation durations challenges psycholinguistic immediacy-of-processing and eye-mind assumptions. Most of the time the mind processes several words in parallel at different perceptual and cognitive levels. Eye movements can help to unravel these processes. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

指纹考勤管理软件的研究与实现

针对企、事业单位原有的考勤系统，如打卡钟、磁卡、IC卡等考勤方式存在代打卡、卡丢失等不足和缺陷的实际，结合指纹识别技术，建立一套考勤、薪资、人事管理于一体的软件系统。给出了系统的体系结构和功能实现，能使企业考勤管理更加简便快捷、客观公正。并提出了进一步的发展方向和展望。     

一种新型注入剖面组合测井仪及其应用

为了提高注入剖面测井的准确性，研制了一种新型注入剖面组合测井仪。该仪器由流量处理单元、伽马处理单元、井温处理单元、磁性定位处理单元、调制式传输、电源电路六部分组成。一次下井可同时测取流量、伽马、井温、磁性定位四组参数。具有测取资料精度高、单芯电缆传输、流量可单点测量也可连续测量以厦现场监测和维修方便等特点。     

Sequential Spectrum Analysis of the Sideband Components of Digital Amplitude-Modulated Signals

It is shown that, for the spectrum analysis of digital quasi-periodic signals, one must use a procedure based on approximating the sequence of data readouts by a first-order trigonometric polynomial with a varying frequency of its harmonic functions.     

应用时频分析方法辨识时变系统的模态参数

应用Gabor展开及Hilbert变换进行时变线性系统模态参数的辨识。利用非平稳信号的Gabor变换将结构响应信号表示在时频面上，并通过Gabor展开重构分离模态分量，建立每一阶模态的时变线性模型。对单模态时变线性模型应用Hilbert变换来辨识随时间变化的模态频率和阻尼。通过对刚度和阻尼慢变的两自由度系统模态参数的仿真辨识验证辨识方法的有效性。仿真结果表明：本文方法为时变线性系统的模态参数辨识提供了一条新的途径。