基于PCA-BP神经网络的装甲车辆柴油机状态评估

针对装甲车辆柴油机摩托小时不能真实反映实际技术状况的问题,通过提取气缸压缩压力、加速时间、减速时间、供油提前角、振动能量和平均燃油流量等状态参数,运用主成分分析和BP神经网络相结合的方法构建了一种柴油机状态评估模型;该模型首先利用主成分分析方法将多个参数简化为两个综合参数,并根据综合参数的散点图对柴油机的状态进行初步划分,得到BP神经网络的训练数据;最后通过建立BP神经网络进行状态评估;评估结果表明,该模型准确度高,具有较好的应用和推广价值。     

基于混沌免疫网络的镍氢电池建模研究

针对电动汽车用镍氢电池组,提出利用计算智能算法训练的RBF网络实现电池组建模;首先采用免疫聚类的方法,通过对样本径基进行成分提取,并与并行免疫进化规划(PCEIP)相结合,形成一种更有效的RBF网络构造策略,然后基于PCIEP设计了改进的RBF网络的训练步骤;最后,在镍氢电池恒流放电和变功率放电工况下,以改进的RBF网络实现镍氢电池建模,验证建模的精度。     

基于无线通信技术的FFU风机群控系统

针对大型洁净工程实现自动化控制的需要,利用数字无线通信技术,设计了一种新型网络化的多风机过滤器单元(FFU)群控系统,详细介绍了系统的组成实现原理和软硬件设计方法;系统间采用基于射频收发芯片nRF2401实现数据的无线收发,有效地减少了系统布线和设计成本,提高了系统的组网灵活性和适用性;对设计开发的系统进行了测试实验,实验结果表明该系统数据通信正确可靠,系统具有结构简单、组网灵活、监控效果好和可扩展性强等优点。     

机载塔康设备综合检查仪设计

使用市场上成熟的模块和技术研制机载塔康设备综合检查仪,以降低成本和提高设备的可靠性;根据设备的测试需求,选用嵌入式工业平板电脑、USB-ARINC429通讯卡、USB-数字IO卡、串行接口数字表和自研的塔康信号模拟器等构成检查仪硬件,使用CVI9.0编写了测试程序;应用表明:检查仪集成度高,使用方便,能够完成对塔康设备的自动及手动测试。     

Integrating local action elements for action analysis

In this paper, we propose a framework for human action analysis from video footage. A video action sequence in our perspective is a dynamic structure of sparse local spatial–temporal patches termed action elements, so the problems of action analysis in video are carried out here based on the set of local characteristics as well as global shape of a prescribed action. We first detect a set of action elements that are the most compact entities of an action, then we extend the idea of Implicit Shape Model to space time, in order to properly integrate the spatial and temporal properties of these action elements. In particular, we consider two different recipes to construct action elements: one is to use a Sparse Bayesian Feature Classifier to choose action elements from all detected Spatial Temporal Interest Points, and is termed discriminative action elements. The other one detects affine invariant local features from the holistic Motion History Images, and picks up action elements according to their compactness scores, and is called generative action elements. Action elements detected from either way are then used to construct a voting space based on their local feature representations as well as their global configuration constraints. Our approach is evaluated in the two main contexts of current human action analysis challenges, action retrieval and action classification. Comprehensive experimental results show that our proposed framework marginally outperforms all existing state-of-the-arts techniques on a range of different datasets.     

Detection of sudden pedestrian crossings for driving assistance systems

In this paper, we study the problem of detecting sudden pedestrian crossings to assist drivers in avoiding accidents. This application has two major requirements: to detect crossing pedestrians as early as possible just as they enter the view of the car-mounted camera and to maintain a false alarm rate as low as possible for practical purposes. Although many current sliding-window-based approaches using various features and classification algorithms have been proposed for image-/video-based pedestrian detection, their performance in terms of accuracy and processing speed falls far short of practical application requirements. To address this problem, we propose a three-level coarse-to-fine video-based framework that detects partially visible pedestrians just as they enter the camera view, with low false alarm rate and high speed. The framework is tested on a new collection of high-resolution videos captured from a moving vehicle and yields a performance better than that of state-of-the-art pedestrian detection while running at a frame rate of 55 fps.     

Generalized extreme learning machine acting on a metric space

Functional data learning is an extension of traditional data learning, that is, learning the data chosen from the Euclidean space ${\mathbb{R}^{n}}$ to a metric space. This paper focuses on the functional data learning with generalized single-hidden layer feedforward neural networks (GSLFNs) acting on some metric spaces. In addition, three learning algorithms, named Hilbert parallel overrelaxation backpropagation (H-PORBP) algorithm, ν-generalized support vector regression (ν-GSVR) and generalized extreme learning machine (G-ELM) are proposed to train the GSLFNs acting on some metric spaces. The experimental results on some metric spaces indicate that GELM with additive/RBF hidden-nodes has a faster learning speed, a better accuracy, and a better stability than HPORBP algorithm and ν-GSVR for training the functional data. The idea of GELM can be used to extend those improved extreme learning machines (ELMs) that act on the Euclidean space ${\mathbb{R}^{n}, }$ such as online sequential ELM, incremental ELM, pruning ELM and so on, to some metric spaces.     

Least squares approach in measurement-dependent filtering for selective medical images

An image-processing method called measurement-dependent filtering has been introduced to improve the SNR (signal-to-noise ratio) of selective images produced by various medical imaging systems. The basic algorithm involves the combination of the low-frequency information of the selective image with the high-frequency information of a nonselective image. A spatially variant control function modulates the amount of high frequency to be added at each point. A least-mean-square (LMS) control function formed from two basis images, namely the high-passed versions of the nonselective image (M(b)) and the selective image (S(b)), is introduced. The original algorithm is now viewed as a two-stage filtering method, including the low-pass filtering noise reduction and least squares filtering for the edge restoration. An appropriate linear transformation is used to convert the original basis images M(b) and S(b) into a new pair with orthogonal noise. This allows the implementation of the LMS and control function with practically obtainable a priori knowledge.     

Floral volatiles ofTanacetum vulgare L. attractive toLobesia botrana den. et schiff. females

The European grapevine moth (EGVM),Lobesia botrana, is a major pest of grapes in Europe. Females are attracted to a nonhost plant: tansy (Tanacetum vulgare L.), which is a common weed in Slovakian vineyards. A steam distillate extract of tansy flowers was analyzed by means of a GC-EAG technique to screen constituents detected by the olfactory receptors of EGVM females. From more than 200 GC peaks, nine peaks corresponding to monoterpenoids released an EAG response in more than 70% of the females (N=15):p-cymene,d-limonene,-thujene,-thujone,-thujone, thujyl alcohol, terpinene-4-ol, (Z)-verbenol, and piperitone. The steam distillate of tansy as well as a synthetic blend of identified compounds released consistent attraction in a field cage. The use of nonhost plants and host plant odors in integrated pest management is discussed.