Hierarchical Structure Information Research Articles

Named-Entity Recognition in Sports Field Based on a Character-Level Graph Convolutional Network

Traditional methods for identifying naming ignore the correlation between named entities and lose hierarchical structural information between the named entities in a given text. Although traditional named-entity methods are effective for conventional datasets that have simple structures, they are not as effective for sports texts. This paper proposes a Chinese sports text named-entity recognition method based on a character graph convolutional neural network (Char GCN) with a self-attention mechanism model. In this method, each Chinese character in the sports text is regarded as a node. The edge between the nodes is constructed using a similar character position and the character feature of the named-entity in the sports text. The internal structural information of the entity is extracted using a character map convolutional neural network. The hierarchical semantic information of the sports text is captured by the self-attention model to enhance the relationship between the named entities and capture the relevance and dependency between the characters. The conditional random fields classification function can accurately identify the named entities in the Chinese sports text. The results conducted on four datasets demonstrate that the proposed method improves the F-Score values significantly to 92.51%, 91.91%, 93.98%, and 95.01%, respectively, in comparison to the traditional naming methods.

The Research of Autonomous In-orbit Health Management System for China’s Manned Spacecrafts

The development trend of manned spacecraft is long-term in-orbit flight and long-term astronaut’s residency. Under the condition of limited TT&C resource, the autonomous health management of spacecraft is a critical and mandatory system to ensure the safety of the astronauts and platform. Based on the discussion of the autonomous health management objectives and management modes of manned spacecraft and combining the distribution and hierarchical information structure of China’s manned spacecraft, this paper elaborates an autonomous health management system. This autonomous health management system adopts a by-level safety threshold management method by establishing a mapping database between different important risk safety thresholds and system safety modes. When the key parameters reach different pre-set thresholds, the system autonomously downgrades and reconstructs the aircraft functionalities in the event of failure to realize optimal auto-processing and solves the issue between randomness of auto-processing and task continuity. The research has been applied to the China’s Space Station.

HSEM: highly scalable node embedding for link prediction in very large-scale social networks

Very large-scale social networks are typically sparse and dynamic and often have millions of nodes and billions of links. Link prediction in very large-scale networks is a challenging task for most existing methods. This paper investigates the link prediction problem in very large-scale networks. We propose a model, namely, a very large-scale network co-occurrence embedding algorithm (Hsem), which learns the co-occurrence features of node pairs to embed nodes into a vector with a lower and fixed dimension. A damping-based random walk algorithm is also developed to extract the hierarchical structural information of node pairs. Moreover, we design an incremental learning algorithm based on Hsem to meet the requirements of highly dynamic evolution in very large-scale networks, which significantly improves learning speed while maintaining accuracy. Finally, we present controlled experiments employing the proposed and baseline methods on eight challenging real-world large-scale datasets with a fixed dropout percentage and calculate the time overhead and receiver operating characteristics. The results show that Hsem performs comparably to current state-of-the-art methods and consistently outperforms the baselines in different experimental settings.

Estimating state-industry employment, with an application to industrial localization

ABSTRACTWe describe a method to construct an industry-by-state repeated cross-section of employment at the most disaggregated level publicly available, covering 1963–2012. Nondisclosed data are estimated with a procedure using the hierarchical information structure. To illustrate the usefulness of the procedure, the resulting estimated data are tested to determine if industrial localization of the processed food sector has changed over the last 50 years in the United States. Our findings suggest it has not changed systemically despite variation in levels of localization within industries.

Elasticity Analysis of Hierarchical Road Network Performance Based on Modified Logit Models

This paper investigates the impact of Variable Message Sign (VMS), stochasticity and hierarchy on the performance of a road network in the context of four typical Logit model types. These models are multinomial Logit (MNL), C-Logit (CL), Path Size Logit (PSL) and Cross-nested Logit (CNL). We quantify the road hierarchy and use the quantified hierarchy to calculate generalized path costs. Then, VMS information is quantified and integrated with the hierarchical property to calculate road “length. Furthermore, these calculation methods are applied to propose modified versions of the MNL, CL, PSL and CNL. Numerical calculations produce negative values of the dispersion elasticity and hierarchical elasticity of total travel time costs obtained from each Logit model. The results also show that the dispersion parameter, hierarchical structure and VMS information have significant and different impacts on the elasticity. The quantitative interactions among these factors, models and performance are practically useful for network design and management.

A hierarchical linguistic information-based model of English prosody: L2 data analysis and implications for computer-assisted language learning

The paper presents a prosody model of native English (L1) continuous speech as corrective prosodic feedback for non-native learners. The model incorporates both hierarchical discourse association and information structure to (1) pinpoint the prosodic features of multi-phrase continuous speech, and (2) simulate native-like expressive speech using corpus of North American and Taiwan L2 English. The bottom-up, additive, data-driven model aims to generate L1-like expressive continuous speech with built-in phonetic and phonological specifications at the lexical level, syntactic/semantic specifications at the next higher phrase and sentence levels, and completed with patterned paragraph associations and prosodic projections of information allocation at higher levels. The hierarchical model successfully allows us to identify L1-L2 differences by prosodic modules/patterns as novel additional features “discourse structure” and “information density” reliably nail down L1-L2 prosodic differences related to phrase association as well as information placement. Our L1 prosodic model with the proposed predictors and optimized model trained from L1 speech corpus showed increase of prediction over existing methods. As a corrective feedback for L2 learners, these predicted L1 prosodic features were compared with a baseline model by objective evaluation (RMS error and correlation) then superimposed onto the L2 speech tokens. Resynthesized L2 tokens were subsequently compared with the original L2 tokens for degrees of perceived accent using subjective evaluation (native-listener perception test). We believe the proposed model can be an effective alternative for implementing computer-assisted language learning (CALL) systems that helps generate L1-like prosody from text, and at the same time serves as corrective feedback for L2 learners.

Classification of Hyperspectral Images by SVM Using a Composite Kernel by Employing Spectral, Spatial and Hierarchical Structure Information

In this paper, we introduce a novel classification framework for hyperspectral images (HSIs) by jointly employing spectral, spatial, and hierarchical structure information. In this framework, the three types of information are integrated into the SVM classifier in a way of multiple kernels. Specifically, the spectral kernel is constructed through each pixel’s vector value in the original HSI, and the spatial kernel is modeled by using the extended morphological profile method due to its simplicity and effectiveness. To accurately characterize hierarchical structure features, the techniques of Fish-Markov selector (FMS), marker-based hierarchical segmentation (MHSEG) and algebraic multigrid (AMG) are combined. First, the FMS algorithm is used on the original HSI for feature selection to produce its spectral subset. Then, the multigrid structure of this subset is constructed using the AMG method. Subsequently, the MHSEG algorithm is exploited to obtain a hierarchy consist of a series of segmentation maps. Finally, the hierarchical structure information is represented by using these segmentation maps. The main contributions of this work is to present an effective composite kernel for HSI classification by utilizing spatial structure information in multiple scales. Experiments were conducted on two hyperspectral remote sensing images to validate that the proposed framework can achieve better classification results than several popular kernel-based classification methods in terms of both qualitative and quantitative analysis. Specifically, the proposed classification framework can achieve 13.46–15.61% in average higher than the standard SVM classifier under different training sets in the terms of overall accuracy.

A Two-Step Resume Information Extraction Algorithm

With the rapid growth of Internet-based recruiting, there are a great number of personal resumes among recruiting systems. To gain more attention from the recruiters, most resumes are written in diverse formats, including varying font size, font colour, and table cells. However, the diversity of format is harmful to data mining, such as resume information extraction, automatic job matching, and candidates ranking. Supervised methods and rule-based methods have been proposed to extract facts from resumes, but they strongly rely on hierarchical structure information and large amounts of labelled data, which are hard to collect in reality. In this paper, we propose a two-step resume information extraction approach. In the first step, raw text of resume is identified as different resume blocks. To achieve the goal, we design a novel feature, Writing Style, to model sentence syntax information. Besides word index and punctuation index, word lexical attribute and prediction results of classifiers are included in Writing Style. In the second step, multiple classifiers are employed to identify different attributes of fact information in resumes. Experimental results on a real-world dataset show that the algorithm is feasible and effective.

Design and Research of an Image File Format with Rich Information

The effect of image processing is determined by the amount of information provided by the image files. With the development of integrated circuit and sensor technology, the image information acquisition technology has been greatly improved, we can obtain higher and higher image quality, and it is possible that image files contain more and more abundant information. The realization of technologies such as image target detection and recognition, image and video retrieval, image segmentation, matching and understanding has a high dependence on image quality. By use of a series of sensors or instruments, we collect relevant data and add relevant information in image files, adding some information to traditional image files, such as: complex environmental information (smoke, fog, rain, clouds, snow, etc.), feature targets Distance, brightness, etc., are conducive to the processing of graphic feature data. The paper analyzes the hierarchical structure of image information, the necessity and feasibility of the increase of image file information, how to increase the relevant information in the image file format, and the significance of the rich information image file format.

Application of Hierarchical Visualization Techniques in Meta-Analysis Data

The meta-analysis is a probabilistic technique that groups the results of several studies, approaches the same subject and produces a result that summarizes the whole. The results that are displayed in graphical form neither offer interactivity with the user, nor a user-friendly interface and easy comprehension. In order to obtain a visual exploratory analysis with more satisfactory results, there are information visualization techniques applied to map the data in graphical form to broaden the user cognition. This article performs the execution of the meta-analysis, through R software, in order to determine the efficiency of fungicide fluquinconazole when combating Asian soy rust and applies the Technique for the Visualization of Hierarchical Information Structure; the Bifocal Tree, to improve the results displayed by the R through the forest plot graphic.

A Tree Regularized Classifier—Exploiting Hierarchical Structure Information in Feature Vector for Human Action Recognition

Bag of visual words is a popular model in human action recognition, but usually suffers from loss of spatial and temporal configuration information of local features, and large quantization error in its feature coding procedure. In this paper, to overcome the two deficiencies, we combine sparse coding with spatio-temporal pyramid for human action recognition, and regard this method as the baseline. More importantly, which is also the focus of this paper, we find that there is a hierarchical structure in feature vector constructed by the baseline method. To exploit the hierarchical structure information for better recognition accuracy, we propose a tree regularized classifier to convey the hierarchical structure information. The main contributions of this paper can be summarized as: first, we introduce a tree regularized classifier to encode the hierarchical structure information in feature vector for human action recognition. Second, we present an optimization algorithm to learn the parameters of the proposed classifier. Third, the performance of the proposed classifier is evaluated on YouTube, Hollywood2, and UCF50 datasets, the experimental results show that the proposed tree regularized classifier obtains better performance than SVM and other popular classifiers, and achieves promising results on the three datasets.

Hierarchical Structure Information and Its Expression for Image Features Extraction and Processing of GRIN Lens End

In this paper, hierarchical structure and its expressional method of image information are described based on the image processing experiments of gradient-index (GRIN) lens end face. The principle and methodology of image information processing for feature extraction in GRIN lens end face are introduced, on the basis of information relation. In the method, the determination process of information is described as two aspects of calculations abstractedly, and the features expression is completed in the two aspects respectively, including the pre-processing, determination and classification. Innovative experiment methods and promising results are presented in this paper.

Ideas rise from chaos: Information structure and creativity

Is structure good or bad for creativity? When it comes to organizing information, management scholars have long advocated for a hierarchical information structure (information organized around higher-order categories as opposed to a flat information structure where there is no higher-order category) to reduce complexity of information processing and increase efficiency of work. However, a hierarchical information structure can be a double-edged sword that may reduce creativity, defined as novel and useful combination of existing information. This is because a hierarchical information structure might obstruct combining information from distal conceptual categories. Thus, the current research investigates whether information structure influences creativity. We theorize that a hierarchical information structure, compared to a flat information structure, will reduce creativity because it reduces cognitive flexibility. Three experiments using a sentence construction task and a LEGO task supported our prediction.

Refine BING using effective cascade ranking

As an important pre-filtering procedure for object detection, objectness estimation now draws lots of attentions from both the video analysis and computer vision communities. Among the existing approaches, BING [1] (binarized normed gradients) is the recently proposed one that possesses the advantages of high object detection rate, ultra fast computational speed (i.e. 300fps), small number of proposals, and good generalization ability. However, within BING's framework, only the uniform hierarchical ranking structure and gradient information are employed for objectness characterization, which leads to high false positive rate. To address this issue, an effective and efficient cascade ranking method is proposed to refine BING, in this paper. It declares three main contributions. First, the concept of scale-sets histogram is novelly introduced. It helps to analyze the potential sizes of the objects. Secondly, more descriptive visual features (i.e. the color-texture consistence) are considered simultaneously for objectness characterization. Lastly, we propose hierarchical sorting to further leverage the ranking performance, according to the local contrast analysis between the inside and straddling superpixels of the object proposal windows. The experimental results on four challenging datasets PASCAL VOC2007, PASCAL VOC2010, PASCAL VOC2012 and ILSVRC2014 demonstrate that, the refined BING can achieve good balance between high detection rate (DR) (e.g. 96.7% DR with 1000 proposal windows on VOC2007), and low time consumption (e.g. 75ms per image on VOC2007). It is also worth noting that, with a relatively small number of proposals (e.g. fewer than 200 proposals), our approach generally outperforms the state-of-the-art methods on the detection rate, on all the testing datasets.

A Human Right to Internet Access: A Confucian Perspective

In this paper, I discussed the possibility to argue for a human right to internet access in Confucian society. I argued firstly that Confucianism could properly accommodate the concept of human rights, even though it does not have an explicit term for it. Secondly, Confucian concept of min xin (the will of people), as a similar concept of democracy with differences, is used in Confucianism as a normative concept to lay the foundation of the state and legitimatize the governance. Last but not least, I argued that the roles that min xin are supposed to play in reality are never fully carried out due to the specific hierarchical information structure of Confucian society. I proposed that with internet, the concept of min xin would have to be able to play its roles properly. As such, the arguments that disregard internet access by referting to the protection of the Confucian values might not stand.

Adaptive Visualization of Complex Networks with FocalPoint

Maintaining situational awareness of a dynamic global computer network that consists of ten to hundreds of thousands of computers is a complex task for cyber administrators and operators looking to understand, plan and conduct operations in real time. Currently, cyber specialists must manually navigate complex networks by continuous cycles of overviews, drilldowns and manually mapping network incidents to mission impact. This is inefficient as manually maneuvering of network data is laborious, induces cognitive overload, and is prone to errors caused by distractive information resulting in important information and impacts not being seen. We are investigating “FocalPoint” an adaptive level of detail (LOD) recommender system tailored for hierarchical network information structures. FocalPoint reasons about contextual information associated with the network, user task, and user cognitive load to tune the presentation of network visualization displays to improve user performance in perception, comprehension and projection of current situational awareness. Our system is applied to two complex information constructs important to dynamic cyber network operations: network maps and attack graphs. The key innovations include: (a) context-aware automatic tailoring of complex network views, (b) multi-resolution hierarchical graph aggregation, (c) incorporation of new computational models for adaptive-decision making on user tasks, cost/benefit utility and human situation awareness, and (d) user interaction techniques to integrate recommendations into the network viewing system. Our aim is to have a direct impact on planning and operations management for complex networks by; overcoming information overload, preventing tunnel vision, reducing cognitive load, and increasing time available to focus on optimum level of details of the global network space and missions.

Information Through Peers: Coordination Impacts on Network Formation

We study information acquisition from peers when agents' actions balance adaptation and coordination motives. Agents acquire information personally and may obtain additional information by connecting to other agents. Although equally informative regarding adaptation, the source's relative position in the information structure is relevant to form expectations about actions of other players. In our setting, information sources are not perfectly substitutable, and the information of an maker --- an agent whose information is more public --- is more informative of how others act. We show that, when players choose their connections, (i) it is always preferable to connect to opinion makers, and (ii) opinion makers have less incentives to form links. These two results characterize the endogenous shape of the network: Any strict equilibrium of the network formation game generates a hierarchical information structure. Furthermore, if the marginal cost of acquiring information is increasing, the information structure is core-periphery. We take advantage of the simplicity of the equilibrium information structure to provide two applications. First, we use data on earnings-per-share forecasts to provide an example of how much of the aggregate volatility of forecast can the information structure account for. Second, we focus on the origins of leadership: how individual characteristics influence the role of the agent in the information structure.

Prediction of missing links based on multi-resolution community division

The investigation of link prediction in networks is an important issue in many disciplines. The research of prediction algorithms which required short time but high accuracy is still a challenging task. Most of the existing algorithms are based on the topological information of the networks, including the local or global similarity indices. It is found that the hierarchical organization and community structure information may indeed provide insights for link prediction. In this paper, we propose a simple link prediction method, which fully explore the community structure information of the networks. Firstly, the community structure of the networks under different resolutions is extracted. Then, a simple frequency statistical model is applied to calculate how many times that a pair of nodes divided into the same community under different resolutions. Finally, the probability of the missing links is calculated. The performance of our algorithm is demonstrated by comparing with other seven well-known methods on two kinds of networks in different scales. The results indicate that our approach not only has a good performance on the accuracy, but also has a lower time complexity than any other algorithms which are based on hierarchical structure of the network.

Realization of Information Model in a Virtual Maintenance System for some Missile Launch Guidance Equipment

This article starts with basic features of assembly-disassembly model of a virtual maintenance system, and hierarchical organizational structure necessary for virtual maintenance of the model is established. Further, method for establishing hierarchical information model is defined in light of the characteristics of hierarchical structure and necessary information for this purpose. And said method is employed to construct the model for launch guidance of some missile warhead.

A scalable approach for ideation in biologically inspired design

AbstractThis paper presents a bioinspiration approach that is able to scalably leverage the ever-growing body of biological information in natural-language format. The ideation tool AskNature, developed by the Biomimicry 3.8 Institute, is expanded with an algorithm for automated classification of biological strategies into the Biomimicry Taxonomy, a three-level, hierarchical information structure that organizes AskNature's database. In this way, the manual work entailed by the classification of biological strategies can be alleviated. Thus, the bottleneck is removed that currently prevents the integration of large numbers of biological strategies. To demonstrate the feasibility of building a scalable bioideation system, this paper presents tests that classify biological strategies from AskNature's reference database for those Biomimicry Taxonomy classes that currently hold sufficient reference documents.