基于VMD和BSA-KELM的高陡边坡位移预测模型研究

边坡位移的时间序列曲线存在复杂的非线性特性,传统的预测模型精度不足以满足预测要求。为此提出了基于变分模态分解的鸟群优化-核极限学习机的预测模型,并用于河北省某水泥厂的边坡位移预测。该方法首先采用VMD把边坡位移序列分解为一系列的有限带宽的子序列,再对各子序列分别采用相空间重构并用核极限学习机预测,采用鸟群算法优化相空间重构的嵌入维度和KELM中惩罚系数和核参数三个数值,以取得最优预测模型。最后将各个子序列预测值叠加,得到边坡位移的最终预测值。结果表明：和KELM、BSA-KELM、EEMD-BSA-KELM模型相比,基于VMD的BSA-KELM预测精度更高,为边坡位移的预测提供一种有效的方法。     

Structure-sensitive semantic matching for aggregate question answering over knowledge base

Aggregate question answering essentially returns answers for given questions by obtaining query graphs with unique dependencies between values and corresponding objects. Word order dependency, as the key to uniquely identify dependency of the query graph, reflects the dependencies between the words in the question. However, due to the semantic gap caused by the expression difference between questions encoded with word vectors and query graphs represented with logical formal elements, it is not trivial to match the correct query graph for the question. Most existing approaches design more expressive query graphs for complex questions and rank them just by directly calculating their similarities, ignoring the semantic gap between them. In this paper, we propose a novel Structure-sensitive Semantic Matching(SSM) approach that learns aligned representations of dependencies in questions and query graphs to eliminate their gap. First, we propose a cross-structure matching module to bridge the gap between two modalities(i.e., textual question and query graph). Then, we propose an entropy-based gated AQG filter to remove the structural noise caused by the uncertainty of dependencies. Finally, we present a two-channel query graph representation that fuses the semantics of abstract structure and grounding content of the query graph explicitly. Experimental results show that SSM could learn aligned representations of questions and query graphs to eliminate the gaps between their dependencies, and improves up to 12% (F1 score) on aggregation questions of two benchmark datasets.     

Feature selection methods for root-cause analysis among top-level product attributes

Manufacturing companies not only strive to deliver flawless products but also monitor product failures in the field to identify potential quality issues. When product failures occur, quality engineers must identify the root cause to improve any affected product and process. This root-cause analysis can be supported by feature selection methods that identify relevant product attributes, such as manufacturing dates with an increased number of product failures. In this paper, we present different methods for feature selection and evaluate their ability to identify relevant product attributes in a root-cause analysis. First, we compile a list of feature selection methods. Then, we summarize the properties of product attributes in warranty case data and discuss these properties regarding the challenges they pose for machine learning algorithms. Next, we simulate datasets of warranty cases, which emulate these product properties. Finally, we compare the feature selection methods based on these simulated datasets. In the end, the univariate filter information gain is determined to be a suitable method for a wide range of applications. The comparison based on simulated data provides a more general result than other publications, which only focus on a single use case. Due to the generic nature of the simulated datasets, the results can be applied to various root-cause analysis processes in different quality management applications and provide a guideline for readers who wish to explore machine learning methods for their analysis of quality data.     

Efficient Flexible M-Tree Bulk Loading Using FastMap and Space-Filling Curves

Many database applications currently deal with objects in a metric space. Examples of such objects include unstructured multimedia objects and points of interest (POIs) in a road network. The M-tree is a dynamic index structure that facilitates an efficient search for objects in a metric space. Studies have been conducted on the bulk loading of large datasets in an M-tree. However, because previous algorithms involve excessive distance computations and disk accesses, they perform poorly in terms of their index construction and search capability. This study proposes two efficient M-tree bulk loading algorithms. Our algorithms minimize the number of distance computations and disk accesses using FastMap and a space-filling curve, thereby significantly improving the index construction and search performance. Our second algorithm is an extension of the first, and it incorporates a partitioning clustering technique and flexible node architecture to further improve the search performance. Through the use of various synthetic and real-world datasets, the experimental results demonstrated that our algorithms improved the index construction performance by up to three orders of magnitude and the search performance by up to 20.3 times over the previous algorithm.     

Tactile colour pictogram to improve artwork appreciation of people with visual impairments

A recent development in tactile technology enables an improvement in the appreciation of the visual arts for people with visual impairment (PVI). The tactile sense, in conjunction with, or a possibly as an alternative to, the auditory sense, would allow PVIs to approach artwork in a more self‐driven and engaging way that would be difficult to achieve with just an auditory stimulus. Tactile colour pictograms (TCPs), which are raised geometric patterns, are ideographic characters that are designed to enable PVIs to identify colours and interpret information by touch. In this article, three TCPs are introduced to code colours in the Munsell colour system. Each colour pattern consists of a basic cell size of 10 mm × 10 mm to represent the patterns consistently in terms of regular shape. Each TCP consists of basic geometric patterns that are combined to create primary, secondary, and tertiary colour pictograms of shapes indicating colour hue, intensity and lightness. Each TCP represents 29 colours including six hues; they were then further expanded to represent 53 colours. Two of them did not increase the cell size, the other increased the cell size 1.5 times for some colours, such as yellow‐orange, yellow, blue, and blue‐purple. Our proposed TCPs use a slightly larger cell size compared to most tactile patterns currently used to indicate colour, but code for more colours. With user experience and identification tests, conducted with 23 visually impaired adults, the effectiveness of the TCPs suggests that they were helpful for the participants.     

Categorical observers for metamerism

A method is proposed to generate categorical colour observer functions (individual colour matching functions) for any field size based on the CIE 2006 system of physiological observer functions. The method combines proposed categorical observer techniques of Sarkar et al with a physiologically-based individual observer model of Asano et al and a clustering technique to produce the optimal set of categorical observers. The number of required categorical observers varies depending on an application with as many as 50 required to predict individual observers' matches when a laser projector is viewed. However, 10 categorical observers are sufficient to represent colour-normal populations for personalized colour imaging. The proposed and recommended categorical observers represent a robust and inclusive technique to examine and quantify observer metamerism in any application of colorimetry.     

基于三维胞元空间的MA双向并行路由算法

针对传统移动代理(MA)在监测无线传感器网络(WSNs)的感兴趣信息时产生的延迟较大和能耗较多问题,提出了基于三维胞元空间的MA双向并行(3D-BPMA)路由算法.3D-BPMA将MA与传统的客户/服务器(c/S)模式相结合,在胞元内利用C/S模式搜集信息,在单层胞元系统和路由器与路由器之间采用MA双向并行的策略进行传输.仿真结果表明:3D-BPMA与LCF,DSG-MIP算法相比减少了平均响应时间和网络平均能耗,提高了MA发送率.     

中医学视角下城市物质空间的生命要素探析

通过借鉴中医学整体观和生命观的相关理论,从认识城市有机体的生命属性入手,发现并提炼能够产生和传递城市运营所需各种能量的生命要素:廊道和功能体。阐释了其多层级、多性质和多形态的特点,提出了功能体有动力、廊道成系统、敏感点有活力的疏通策略,旨在促进城市各种能量的有机循环,从而维护城市的健康与安全,提高城市生活的效率与质量。