A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

基于卷积神经网络的食品图像识别

目的 探究一种基于Inception_V3-CNN模型的食品图像识别和分类方法。方法 选取包含20类食品和19609张的食品图像建立数据集Food-101, 通过卷积神经网络(convolutional neural networks, CNN)提取图像候选区域的视觉特征, 并自动进行分类, 使其具有较高的识别率; 此外, 采集来自kaggle库中已标注的食品图像集做预测对比实验, 以保证Inception_V3-CNN模型检测的准确度。结果 该方法能够去除背景噪音, 且仅需部分提取视觉特征, 可以有效解决网络食品图像的分类问题, 与多视图支持向量机(support vector machine, SVM)+方向梯度直方图(histogram of oriented gradients, HOG)和传统CNN方法相比, 在测试时间相近、设备计算能力相同的条件下, 该方法识别率更高, 迭代次数为15000次时, Loss值降至4.92, 准确率可达93.89%。结论 此方法可以快速识别食品图像, 在实际网络图片中能有较好的可移植性。将算法移植到移动设备中实现APP的模块化操作也将成为后续工作探索的重点方向。     

近距离煤层群采空区漏风规律及防控措施研究

贵州地区煤层赋存条件复杂,煤层间距小,相邻采空区存在漏风通道的问题。采用SF6示踪法及重点区域指标气体数据分析法,对发耳煤矿采空区漏风规律及其治理措施进行研究。分析结果表明,由于相邻密闭效果欠佳,导致31004开切眼联络巷及31004工作面回风巷密闭漏风严重。31004采空区漏风通道主要是31004开切眼联络巷密闭及10^#煤层开采过程中对上部7^#煤层采空区造成二次扰动形成的纵向漏风通道;漏风量为83 m^3/min,采空区风速约为0.17 m/s。对存在的煤自燃隐患采取了注水降温措施,CO体积分数显著下降至(5~9)×10^-6。为即将开采的50105、50107工作面的煤自燃防控提供了科学依据和管控措施方案。     

In-situ deflectometic measurement of transparent optics in precision robotic polishing

In the ultra-precision manufacturing of large optics, industrial robots have the potential to become an intelligent and economical choice of surface polishing. However, the transport of the workpieces between the polishing platform and the measurement instrument seriously limits the manufacturing efficiency. Therefore, an in-situ measurement system based on the monoscopic deflectometry is developed to determine the form quality of the optical lenses during rough polishing. Stray light reflected from the lower surface of transparent lenses may degrade the measuring quality, thus an effective absolute phase retrieval algorithm is developed to decouple the superposed fringes associated with the upper and lower surfaces. Then, the form of the upper surface under polishing can be reconstructed to guide the subsequent polishing. Experimental results demonstrate that the accuracy of the method is comparable to that of the coordinate measuring machine, consequently the manufacturing efficiency and reliability of large optical workpieces can be greatly improved.     

两种多层穿梭车系统的性能比较分析

物流配送中心订单响应速度的加快,对订单拣选系统提出了更高的要求。多层穿梭车系统因其柔性强、效率高等特点,近年来得到了广泛应用。多层穿梭车系统具有两种形式--基于转载车和基于环形输送线,二者均可实现货物的快速拣选,但在系统吞吐量和订单完成周期方面存在差异,致使企业决策者难以进行系统选择。基于上述原因,本文比较两种多层穿梭车系统的性能差异。建立两个系统的开环排队网络模型,然后求解系统吞吐量、订单完成周期,通过仿真验证了排队论模型的准确性,通过试验对两种系统的性能进行对比分析。结果表明,系统吞吐量与层数、巷道数相关,层数越多,巷道数越少,转载车系统相对于环线系统优势越显著;订单完成周期与层数、订单到达率相关,层数越多,订单到达率越低,转载车系统相对于环线系统越具优势。     

基于文本与语义相关性分析的图像检索

为了更加有效地检索到符合用户复杂语义需求的图像，提出一种基于文本描述与语义相关性分析的图像检索算法。该方法将图像检索分为两步：基于文本语义相关性分析的图像检索和基于SIFT特征的相似图像扩展检索。根据自然语言处理技术分析得到用户文本需求中的关键词及其语义关联，在选定图像库中通过语义相关性分析得到“种子”图像；接下来在图像扩展检索中，采用基于SIFT特征的相似图像检索，利用之前得到的“种子”图像作为查询条件，在网络图像库中进行扩展检索，并在结果集上根据两次检索的图像相似度进行排序输出，最终得到更加丰富有效的图像检索结果。为了证明算法的有效性，在标准数据集Corel5K和网络数据集Deriantart8K上完成了多组实验，实验结果证明该方法能够得到较为精确地符合用户语义要求的图像检索结果，并且通过扩展算法可以得到更加丰富的检索结果。     

结合细粒度特征与深度卷积网络的手绘图检索

目的 传统的手绘图像检索方法主要集中在检索相同类别的图像，忽略了手绘图像的细粒度特征。对此，提出了一种新的结合细粒度特征与深度卷积网络的手绘图像检索方法，既注重通过深度跨域实现整体匹配，也实现细粒度细节匹配。方法 首先构建多通道混合卷积神经网络，对手绘图像和自然图像分别进行不同的处理；其次通过在网络中加入注意力模型来获取细粒度特征；最后将粗细特征融合，进行相似性度量，得到检索结果。结果 在不同的数据库上进行实验，与传统的尺度不变特征（SIFT）、方向梯度直方图（HOG）和深度手绘模型Deep SaN（sketch-a-net）、Deep 3DS（sketch）、Deep TSN（triplet sketch net）等5种基准方法进行比较，选取了Top-1和Top-10，在鞋子数据集上，本文方法Top-1正确率提升了12%，在椅子数据集上，本文方法Top-1正确率提升了11%，Top-10提升了3%，与传统的手绘检索方法相比，本文方法得到了更高的准确率。在实验中，本文方法通过手绘图像能在第1幅检索出绝大多数的目标图像，达到了实例级别手绘检索的目的。结论 提出了一种新的手绘图像检索方法，为手绘图像和自然图像的跨域检索提供了一种新思路，进行实例级别的手绘检索，与原有的方法相比，检索精度得到明显提升，证明了本文方法的可行性。