An interactive lung field segmentation scheme with automated capability

Feasible clinical application of any automated segmenting methodology demands more than just accuracy. Amendment to the automated delineation is necessary when the algorithm fails, however, integrated solution to such a scenario is largely absent in literature. Hence in this survey we devised an architecture that does both the automated and interactive lung field localizations using a single segmenting engine—random walker algorithm—so that intuitive amendment is only necessary when the automated generated delineation is unsatisfactory. The algorithm proceeds by first extracting 18 intensity profiles running horizontally, each of them equally spacing apart, and in each intensity profile three extreme points denoting the two lungs and the esophagus are determined through profile matching. This done, the algorithm removes profiles that do not intersect with the lung, and the rest of the extreme points are plugged into random walker algorithm to perform segmentation. The achieved accuracy in localization by the above was 0.8875 in terms of overlap measure (the maximum value for this parameter is 1) over 341 images. In the case where unsatisfactory delineation prompts amendment necessary, the user can interactively segment the lung by just a shift on some of the previous-determined points to the desired locations, and random walker algorithm is run again with the amended input. By such a fusion, the benefits of both the automated and interactive segmentation are shared in a single architecture.     

Efficient bidirectional quantum secure communication with two-photon entanglement

An efficient bidirectional quantum secure communication protocol is proposed with two-photon entanglement. Compared with the previous protocol proposed by Shi et al., our protocol can achieve higher efficiency. Meanwhile, for the same length secret messages, only half of entangled photon pairs need to be prepared in our protocol. And the number of classical bits in public classical communication is also a half of that in the previous protocol. Moreover, the information leakage does not exist in our scheme.     

光学薄膜元器件外观特性机器视觉检测系统

本系统利用工业级摄像头及开发包的机器视觉功能与计算软件编程控制技术相结合,通过与输入控制系统中的标准膜片模板外观品质进行对比,实现高速高效、准确识别检测光学薄膜器件中滤光片的外观缺陷。可在生产线上根据外观品质标准模板中设定的类别进行自动分类装盒。     

计算机技术在档案管理中的运用浅析

随着信息技术的快速发展,计算机技术在人们的日常生活与工作中发挥着越来越重要的作用,对于档案管理工作来言也是如此.本文首先分析了计算机技术在档案管理中运用的必要性,然后分析、总结了目前计算机技术在档案管理中的一些具体运用及其运用过程中存在的问题,并在文章最后提出了几点加强计算机技术在档案管理工作中运用的对策与建议.     

浅谈LED电子显示屏在幕墙系统中的应用

随着计算机技术、光学、电子技术、视频技术、传送技术的发展,各种电子屏幕设备的应用日益增多.在众多的影像设备中,LED电子显示屏是集光电子技术、视频技术、计算机技术和微电子技术为一体的科技产品.LED因其强大的功能在各行各业中得到了广泛的应用.     

Supervised classification of share price trends

Share price trends can be recognized by using data clustering methods. However, the accuracy of these methods may be rather low. This paper presents a novel supervised classification scheme for the recognition and prediction of share price trends. We first produce a smooth time series using zero-phase filtering and singular spectrum analysis from the original share price data. We train pattern classifiers using the classification results of both original and filtered time series and then use these classifiers to predict the future share price trends. Experiment results obtained from both synthetic data and real share prices show that the proposed method is effective and outperforms the well-known K-means clustering algorithm.     

Two computational regimes of a single-compartment neuron separated by a planar boundary in conductance space

Recent in vitro data show that neurons respond to input variance with varying sensitivities. Here we demonstrate that Hodgkin-Huxley (HH) neurons can operate in two computational regimes: one that is more sensitive to input variance (differentiating) and one that is less sensitive (integrating). A boundary plane in the 3D conductance space separates these two regimes. For a reduced HH model, this plane can be derived analytically from the V nullcline, thus suggesting a means of relating biophysical parameters to neural computation by analyzing the neuron's dynamical system.     

A scalable kernel-based semisupervised metric learning algorithm with out-of-sample generalization ability

In recent years, metric learning in the semisupervised setting has aroused a lot of research interest. One type of semisupervised metric learning utilizes supervisory information in the form of pairwise similarity or dissimilarity constraints. However, most methods proposed so far are either limited to linear metric learning or unable to scale well with the data set size. In this letter, we propose a nonlinear metric learning method based on the kernel approach. By applying low-rank approximation to the kernel matrix, our method can handle significantly larger data sets. Moreover, our low-rank approximation scheme can naturally lead to out-of-sample generalization. Experiments performed on both artificial and real-world data show very promising results.