基于kmeans-SVM的二叉树粗分类方法

针对大型数据库中进行匹配识别时存在识别速度慢、时间长、影响实时应用效果的问题,提出了一种树形层次结构的粗分类方法。通过k-means得到两类粗分类的样本,用这两类粗分类数据训练SVM分类器,找到分类超平面,再不断调整分类超平面,最后构建二叉树型结构达到粗分类的目的。三个方法相结合很好地缩小目标的搜索范围,提高了识别时候的效率。     

Steering feel improvement by mathematical modeling of the Electric Power Steering system

Currently, the Electric Power Steering (EPS) system is an essential component of the vehicle because it provides assistive steering torque to the driver. To ensure a faster steering response, the position of the EPS in some vehicles is moved closer to the tire rather than the steering wheel. The steering torque, which is provided by the EPS in the steering system, mainly affects the driver’s feel while steering. Therefore, the driver often feels uncomfortable owing to such positioning of the EPS in the steering system. In particular, the nonlinearity of the Universal Joint (UJ), which is one of parts of the steering system, can be felt at the steering wheel side.In this paper, we proposed an algorithm based on the mathematical model of the steering torque in the steering system to improve the steering feel. The mathematical model is structured using parameters that can be obtained from the information of the steering system. Moreover, the formulation of the steering torque consists of the two parts, namely the deformation part, which describes the propagation inside the steering system, and the friction part that describes the inherent friction in the UJ.Simulation and experiments were conducted to verify the proposed mathematical model with similar conditions to the real tire load during the steering motion. Furthermore, to improve the driver’s feel during steering, a torque compensation algorithm is proposed and verified through experiments.     

A Feature Selection Strategy to Optimize Retinal Vasculature Segmentation

Diabetic retinopathy (DR) is a complication of diabetes mellitus that appears in the retina. Clinitians use retina images to detect DR pathological signs related to the occlusion of tiny blood vessels. Such occlusion brings a degenerative cycle between the breaking off and the new generation of thinner and weaker blood vessels. This research aims to develop a suitable retinal vasculature segmentation method for improving retinal screening procedures by means of computer-aided diagnosis systems. The blood vessel segmentation methodology relies on an effective feature selection based on Sequential Forward Selection, using the error rate of a decision tree classifier in the evaluation function. Subsequently, the classification process is performed by three alternative approaches: artificial neural networks, decision trees and support vector machines. The proposed methodology is validated on three publicly accessible datasets and a private one provided by Hospital Sant Joan of Reus. In all cases we obtain an average accuracy above 96% with a sensitivity of 72% in the blood vessel segmentation process. Compared with the state-of-the-art, our approach achieves the same performance as other methods that need more computational power. Our method significantly reduces the number of features used in the segmentation process from 20 to 5 dimensions. The implementation of the three classifiers confirmed that the five selected features have a good effectiveness, independently of the classification algorithm.     

MRMR Based Feature Vector Design for Efficient Citrus Disease Detection

In recent times, the images and videos have emerged as one of the most important information source depicting the real time scenarios. Digital images nowadays serve as input for many applications and replacing the manual methods due to their capabilities of 3D scene representation in 2D plane. The capabilities of digital images along with utilization of machine learning methodologies are showing promising accuracies in many applications of prediction and pattern recognition. One of the application fields pertains to detection of diseases occurring in the plants, which are destroying the widespread fields. Traditionally the disease detection process was done by a domain expert using manual examination and laboratory tests. This is a tedious and time consuming process and does not suffice the accuracy levels. This creates a room for the research in developing automation based methods where the images captured through sensors and cameras will be used for detection of disease and control its spreading. The digital images captured from the field's forms the dataset which trains the machine learning models to predict the nature of the disease. The accuracy of these models is greatly affected by the amount of noise and ailments present in the input images, appropriate segmentation methodology, feature vector development and the choice of machine learning algorithm. To ensure the high rated performance of the designed system the research is moving in a direction to fine tune each and every stage separately considering their dependencies on subsequent stages. Therefore the most optimum solution can be obtained by considering the image processing methodologies for improving the quality of image and then applying statistical methods for feature extraction and selection. The training vector thus developed is capable of presenting the relationship between the feature values and the target class. In this article, a highly accurate system model for detecting the diseases occurring in citrus fruits using a hybrid feature development approach is proposed. The overall improvement in terms of accuracy is measured and depicted.     

基于预训练语言模型的关键词感知问题生成

问题生成任务是指根据给定的文本段落和答案来自动生成对应的问题。针对现有问题生成方法存在的误差累积现象以及问题生成任务固有的“一对多”情况，提出一种带有关键词感知功能的问题生成方法。在预训练语言模型的基础上，实现关键词分类模型与问题生成模型的网络结构设计。输入文本段落中蕴含关键词，为使所生成的问题中包含同样的关键词以保证问题与段落的语义一致性，利用关键词分类模型提取出文本段落中的关键词，将关键词与非关键词的区分特征融入问题生成模型的输入中，该特征作为问题生成过程的全局信息，用以消除问题生成模型仅依赖局部最优解的弊端，减少误差累积与“一对多”情况的发生。在SQuAD数据集上的实验结果表明，该方法能够提升问题生成的质量，其BLEU-4指标值可达24，优于带有复制机制、带有语义监督的问题生成模型，目前已经借助百度百科数据平台实现了大规模工业应用。     

Design of data feature-driven 1D/2D convolutional neural networks classifier for recycling black plastic wastes through laser spectroscopy

In this study, two types of convolutional neural network (CNN) classifiers are designed to handle the problem of classifying black plastic wastes. In particular, the black plastic wastes have the property of absorbing laser light coming from spectrometer. Therefore, the classification of black plastic wastes remains still a challenging problem compared to classifying other colored plastic wastes using existing spectroscopy (i.e., NIR). When it comes the classification problem of black plastic wastes, effective classification techniques by the laser spectroscopy of Fourier Transform-Infrared Radiation (FT-IR) with Attenuated Total Reflectance (ATR) and Raman to analyze the classification problem of black plastic wastes are introduced. Due to the strong ability of extracting spatial features and remarkable performance in image classification, 1D and 2D CNN through data features are designed as classifiers. The technique of chemical peak points selection is considered to reduce data redundancy. Furthermore, through the selection of data features based on the extracted 1D data with peak points is introduced. Experimental results demonstrate that 2DCNN classifier designed with the help of 2D data feature selection as well as 1DCNN classifier shows the best performance compared with other reported methods for classifying black plastic wastes.     

CT/MR-compatible physical human-robotized needle interactions: From modeling to percutaneous steering

In recent years a number of robotic steering systems have been proposed that are geared towards improving interventional radiology procedures such as tumor ablation and biopsy. These solutions have introduced new safety challenges in the physical human–robot interaction domain. This study presents a new 3D robotized needle steering algorithm compatible with CT and MR-imaging guidance. The steering algorithm is featured with an adaptive self-correction mechanism that works as a failure contingency tool that could be adapted online at each insertion step. The developed pHRI solution was designed to be compatible to ferro-magnetic issues and a reduced workspace inside the scanner bore. As far as we know, this is the first approach designed to steer rigid needles free of force sensors and which meets the challenges that prevail in our context. Our proposed approach helps overcome safety issues regarding the physical interaction between robotized needles and patients. Validation testing highlighted the feasibility of the new needle steering algorithm, while its accuracy revealed the potential of the approach under the proposed scope of application.     

矿业可持续发展的灰色动态评价

本文建立了基于灰色系统理论的矿业可持续发展动态评价模型，提出了以发展趋势和协调性评价为基本内涵的动态评价思路，并以我国有色金属矿业为例进行了矿业可持续发展动态评价实证研究。所用的方法及建模思路对其他类似产业乃至整个国民经济系统的评价也是适用的。     

导向钻进技术在地下水污染治理工程中的应用研究

水平环境井是进行地下水污染治理工程的关键,水平环境井的施工有钻进、建造井眼、完井、洗井等步骤。用导向钻进进行水平环境井施工有2种方法:连续井法和盲井法。2种方法分别适用于不同的场合,所使用的钻具也有所不同。     

仿步行式气垫车辆转向时的运动性能和动力性能分析

对仿步行式气垫车辆的转向进行了运动分析和受力分析，给出了仿步行式气垫车实现稳定转向的条件，仿步行式气垫车用双向液压马达驱动、通过分－集流阀改变双侧液压马达流量来控制内，外侧轮的下，反转，从而实现车辆的转向，提出用同步阀控制两侧半步行轮的同步运动、在气垫车前部安装导向盘等措施来保证其直线行驶性能。