基于CNN与Transformer的医学图像分割

医学图像对疾病的诊断、治疗和评估均有所帮助,准确分割医学图像中的器官对于辅助医生的诊断具有重要的实际意义.由于医学图像中各器官部位与周围组织的图像对比度低,不同器官的边缘和形状也会存在很大差异,从而增加了分割的难度.针对这些问题,本文提出了一种基于卷积神经网络和Transformer的医学图像语义分割网络,有效提高了医学图像语义分割的精度.特征提取部分使用ResNet-50网络结构,在特征提取后使用Transformer模块来扩大感受野.在上采样过程中加入多个跳跃连接层,充分利用各阶段的特征提取信息,来恢复至与输入图像相近的分辨率.在胃肠道医学图像分割数据集上的实验结果证明本文的方法可以有效分割医学图像中的器官组织,提升分割准确率.     

基于改进多嵌入空间的实时语义数据流推理

将语义数据流处理引擎与知识图谱嵌入表示学习相结合,可以有效提高实时数据流推理查询性能,但是现有的知识表示学习模型更多关注静态知识图谱嵌入,忽略了知识图谱的动态特性,导致难以应用于实时动态语义数据流推理任务。为了使知识表示学习模型适应知识图谱的在线更新并能够应用于语义数据流引擎,建立一种基于改进多嵌入空间的动态知识图谱嵌入模型PUKALE。针对传递闭包等复杂推理场景,提出3种嵌入空间生成算法。为了在进行增量更新时更合理地选择嵌入空间,设计2种嵌入空间选择算法。基于上述算法实现PUKALE模型,并将其嵌入数据流推理引擎CSPARQL-engine中,以实现实时语义数据流推理查询。实验结果表明,与传统的CSPARQL和KALE推理相比,PUKALE模型的推理查询时间分别约降低85%和93%,其在支持动态图谱嵌入的同时能够提升实时语义数据流推理准确率。     

Efficient processing of spatial joins with DOT-based indexing

A spatial join is a query that searches for a set of object pairs satisfying a given spatial relationship from a database. It is one of the most costly queries, and thus requires an efficient processing algorithm that fully exploits the features of the underlying spatial indexes. In our earlier work, we devised a fairly effective algorithm for processing spatial joins with double transformation (DOT) indexing, which is one of several spatial indexing schemes. However, the algorithm is restricted to only the one-dimensional cases. In this paper, we extend the algorithm for the two-dimensional cases, which are general in Geographic Information Systems (GIS) applications. We first extend DOT to two-dimensional original space. Next, we propose an efficient algorithm for processing range queries using extended DOT. This algorithm employs the quarter division technique and the tri-quarter division technique devised by analyzing the regularity of the space-filling curve used in DOT. This greatly reduces the number of space transformation operations. We then propose a novel spatial join algorithm based on this range query processing algorithm. In processing a spatial join, we determine the access order of disk pages so that we can minimize the number of disk accesses. We show the superiority of the proposed method by extensive experiments using data sets of various distributions and sizes. The experimental results reveal that the proposed method improves the performance of spatial join processing up to three times in comparison with the widely-used R-tree-based spatial join method.     

Parallelization of a dynamic SVD clustering algorithm and its application in information retrieval

We describe an implementation of a parallel document clustering scheme based on latent semantic indexing, which uses singular value decomposition. Given a set of documents, the clustering algorithm is dynamic in the sense that it automatically infers the number of clusters to be output. The parallel version has been implemented on a LAN and on a dual‐core system. Experimental evaluation of the algorithm shows an average speed‐up of 6.22 for the LAN implementation and an average speed‐up of 3.71 for the dual‐core implementation, while still maintaining a precision and recall in the range [0.85, 1]. To put these implementations in the context of information retrieval, we use the parallel clustering algorithm and develop a document similarity search system. The similarity search system shows good performance in terms of precision and recall. Copyright © 2010 John Wiley & Sons, Ltd.     

基于CIDOC概念参考模型的Web服务注释

在Web服务所提供的基本功能的基础上,应用语义注释的思想,给出一种对Web服务进行语义说明的方法。应用CIDOC CRM标准对Web数据规范进行注释,可为该规范加入语义信息,反映数据的含义,并揭示出数据之间的层次关系,从而使Web服务使用者更好地理解数据,并将所获取的数据准确地应用到数据处理中。     

基于本体的查询扩展研究

查询扩展是优化信息检索的一种有效方法。基于关键词的查询扩展对语义信息的忽略为结果带来了不好的影响,因而提出一种基于本体的查询扩展方法。首先建立本体模型,通过计算本体中的概念语义相似度和实例语义相似度,实现语义查询扩展。     

刍议马头琴的设计形态语义

马头琴不仅是蒙古族音乐文化的典型代表,它的外观形态设计同样也承载了蒙古人的信仰、历史和美学观念等,聚合了丰富的蒙古文化内涵。本文着重分析了马头琴的设计形态语义及情感形态语义,旨在引发人们对马头琴的蒙古形态语言的再思考。     

Slicing the metric space to provide quick indexing of complex data in the main memory

Searching in a dataset for elements that are similar to a given query element is a core problem in applications that manage complex data, and has been aided by metric access methods (MAMs). A growing number of applications require indices that must be built faster and repeatedly, also providing faster response for similarity queries. The increase in the main memory capacity and its lowering costs also motivate using memory-based MAMs. In this paper, we propose the Onion-tree, a new and robust dynamic memory-based MAM that slices the metric space into disjoint subspaces to provide quick indexing of complex data. It introduces three major characteristics: (i) a partitioning method that controls the number of disjoint subspaces generated at each node; (ii) a replacement technique that can change the leaf node pivots in insertion operations; and (iii) range and k-NN extended query algorithms to support the new partitioning method, including a new visit order of the subspaces in k-NN queries. Performance tests with both real-world and synthetic datasets showed that the Onion-tree is very compact. Comparisons of the Onion-tree with the MM-tree and a memory-based version of the Slim-tree showed that the Onion-tree was always faster to build the index. The experiments also showed that the Onion-tree significantly improved range and k-NN query processing performance and was the most efficient MAM, followed by the MM-tree, which in turn outperformed the Slim-tree in almost all the tests.