真空粉末绝热低温贮罐制造的部分工艺方法

在真空粉末绝热低温贮罐的制造过程中、通过吸附器分子筛的活化、夹层真空系统的处理和充装珠光砂等工艺方法的改进,可较大地缩短产品的制造周期并提高产品的质量。     

提高MG2×150/700-WD型采煤机截割部轴承寿命周期的设计改进

通过改进结构及轴承类型,提高MG2×150/700-WD型交流电牵引采煤机截割部轴承使用周期。     

Adaptive Safety Motion Control for Underactuated Hovercraft Using Improved Integral Barrier Lyapunov Function

International Journal of Control, Automation and Systems - In this paper, we investigate the problem of safety motion control for an underactuated hovercraft from subject to safety constraint on...     

Deformation transition of intact coal induced by gas injection

Gas migration in coal bed is a multiple-physical process, of which not only includes gas desorption/diffusion through coal matrix and gas Darcy flow through the cleat system, but also results in deform...     

Effect of Al in Ti－microalloyed Mn－Ni－Mo welding wire on microstructure and toughness of deposited metal

ＥｆｆｅｃｔｏｆＡｌｉｎＴｉ－ｍｉｃｒｏａｌｌｏｙｅｄＭｎ－Ｎｉ－Ｍｏｗｅｌｄｉｎｇｗｉｒｅｏｎｍｉｃｒｏｓｔｒｕｃｔｕｒｅａｎｄｔｏｕｇｈｎｅｓｓｏｆｄｅｐｏｓｉｔｅｄｍｅｔａｌ￥ＴａｎＣｈａｎｇｙｉｎｇ；ＺｈａｎｇＸｉａｎｈｕｉａｎｄＳｕｎＷｅｉ...     

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.     

Learning Image-Text Associations

Web information fusion can be defined as the problem of collating and tracking information related to specific topics on the World Wide Web. Whereas most existing work on Web information fusion has focused on text-based multidocument summarization, this paper concerns the topic of image and text association, a cornerstone of cross-media Web information fusion. Specifically, we present two learning methods for discovering the underlying associations between images and texts based on small training data sets. The first method based on vague transformation measures the information similarity between the visual features and the textual features through a set of predefined domain-specific information categories. Another method uses a neural network to learn direct mapping between the visual and textual features by automatically and incrementally summarizing the associated features into a set of information templates. Despite their distinct approaches, our experimental results on a terrorist domain document set show that both methods are capable of learning associations between images and texts from a small training data set.