Hierarchical Knowledge Research Articles

Deductive Synthesis of Networks Hierarchical Knowledge Graphs

The article focuses on developing of a deductive synthesis method for building telecommunications networks (TN) hierarchical knowledge graphs (KG). Synthesized KGs can be used to solve search, analytical, and recommendation (forecast) problems. TNs are complex heterogeneous objects. The synthesis of knowledge graphs of such objects requires much computational resources. The proposed method provides a low complexity of the synthesis of KG of TN by taking into account their hierarchical structure. The authors propose to do synthesis by direct downward multilevel inference and reverse multilevel inference. The article analyses existing graph models of TNs and methods for their building. Detailed description of the proposed method of networks hierarchical KGs synthesis is given. In order to evaluate the deductive synthesis method, a prototype of the system is developed. The provided real-world example shows how telecommunications networks hierarchical knowledge graphs are synthesized and used in practice. Finally, conclusions are formulated, and the areas of further research are identified.

Merits of Hierarchical Story and Discourse Planning with Merged Languages

A hierarchical, bipartite model can characterize many complex narrative phenomena associated with coordinating plot and communication in storytelling (e.g., cinematography), but the predominant pipeline-based strategy for generating narratives has inadvertently limited the expressiveness of storytelling systems. We introduce computational steps for merging story and discourse languages in plan-based storytelling systems with hierarchical knowledge which avoids this problem and motivates more expressive narrative discourse reasoning.

A hierarchical knowledge guided backtracking search algorithm with self-learning strategy

To improve the performance of the backtracking search optimization algorithm (BSA), a multi-population cooperative evolution strategy guided BSA with hierarchical knowledge (HKBSA) is proposed in this paper. According to the domain knowledge of the candidates in objective space, the population is divided into the dominant population, the ordinary population and the inferior population. The information between the sub-populations has interacted with the evolution processes of the three sub-populations. The individuals in the dominant population are maintained as the optimal solutions and are utilized to guide the evolution of the other two sub-populations. A multi-strategy mutation mechanism is applied to solve non-separable problems. The distribution vector of inferior individuals is constructed by sampling, and a mechanism of the individual generation with feedback is proposed by combining self-learning strategy and elite learning strategy. The convergence of HKBSA is analyzed with the Markov model. Compared with the state-of-the-art BSA variants, HKBSA outperforms other algorithms in terms of the speed of convergence, solution accuracy and stability.

Adaptive Cognitive Management and Knowledge Discovery Framework Based on Internet of Things Big Data

In the future of large-scale industrial automation applications in the Internet of Things big data management and knowledge discovery, the importance of the industrial Internet is increasing day by day. The Internet of Things (IoT), computing intelligence, machine type communication, big data and sensor technology and other diversification. Technology can be combined to improve the efficiency of data management and knowledge discovery for large-scale automated applications. To this end, we need to propose a cognitive-oriented IoT big data framework (COIB-framework) and its implementation architecture, IoT big data hierarchical architecture, data organization and knowledge exploration subsystems to achieve effective data management and knowledge discovery suitable for large-scale industrial automation applications. In this work, we need to propose a cognitive-oriented IoT big data framework (COIB-framework), as well as implementation architecture, IoT big data layered architecture, data organization and knowledge mining subsystems, to meet the needs of large-scale industrial automation applications. Discussion and analysis show that the proposed framework and architecture are based on the intelligent industrial application of IoT big data provides a reasonable solution.

Developing a Product Knowledge Graph of Consumer Electronics to Manage Sustainable Product Information

Transformational computing paradigms, such as artificial intelligence, home automation, and the Internet of Things, are being rapidly applied to consumer electronics products, thus aiding in the development of integrated and innovative features. Hence, ubiquitous computing and electronic devices are increasingly becoming essential to everyday life. In this context, a wide gulf often exists between the capabilities and technical features of consumer electronic devices and the consumers’ understanding of such devices and ability to operate them correctly and effectively. This study proposes a machine-readable knowledge model representing technical terms in product specifications along with a product knowledge graph to discover semantic relationships among various products. Formal concept analysis is applied to conceptually analyze the specification terms of heterogeneous electronic products and design a hierarchical knowledge structure of extracted concepts, to elaborate the proposed knowledge model.

Imagining daylight: Evaluating participants' perception of daylight in work environments

This paper presents an experimental research study intended to evaluate daylight perception in work environments. The current metrics for assessing daylight in work environments involve quantifying daylight and do not provide insight into the actual appearance of the space, thus overlooking the qualitative aspects of light and their effect on occupants. Conceptual content cognitive mapping (3CM), a mixed methodology, was used to obtain participants' hierarchical knowledge structure and mental model of daylight in work environments. This method was selected to understand the end users' perception of an environment rather than measuring the physical environment. A cognitive map of 50 participants, half architects and half non-architects, was created using 3CM. The results present a list of daylight lexicon and a vast selection of concepts related to physical and psychological comfort among all participants. This experiment reveals that connectivity and emotional reactions are the two dominant underlying dimensions describing daylight in work environments. The results illustrate both similarities and disjunctions between two groups of participants regarding the selected daylight terms and characterizations. The results also indicate the need to augment current planning practices with a qualitative multi-disciplinary approach to create more pleasant working environments.

The method of inductive synthesis of hierarchical knowledge graphs of telecommunication networks based on statistical data

The article is devoted to the development of the method for synthesizing hierarchical knowledge graphs of telecommunication networks using network statistical data and available models or their fragments. Existing graphs or their fragments, monitoring data, descriptions of data structures, reverse engineering artifacts, etc. can be used as initial data. The paper presents analysis of relevance of the problem for telecommunication network operators and considers the advantages of the proposed method of inductive synthesis for building integrated network models. The method allows restore hierarchical graph models from source data, including the elements of the models and the relations between them. Based on extracted elements and relations hierarchical knowledge graphs are build. The mathematical models and algorithms that describe the considered method for synthesizing hierarchical knowledge graphs and quality indicators of the resulting model are presented in the paper. To confirm the method, the program was developed. This program uses a sample of initial data as a source, restores an integral fragment of a hierarchical knowledge graph of a telecommunication network. Also, as results of this work, the areas of its application and directions for further research are formulated.

THE CORRELATION BETWEEN HIERARCHICAL AUTHORITY AND KNOWLEDGE AUTHORITY

In order to reveal the relationship between hierarchical authority and knowledge authority, the most important issues of management, authority, power and influence are examined in the examination of the concepts. Unfortunately, apart from the issue of authority, issues of power, power and influence are among the most neglected issues of management and organization. The subject of authority is generally dealt with in the context of the organization. However, the management application is completely related to the use of power. Authority is only one type of power use. It can be said that the main difference between knowledge and hierarchical authority is the structure of the organization. As organizations become more complex in the information age, the problems that managers have to solve have become more complex. In addition, knowledge-based parameters have increased in management processes. It is not possible for a single manager to solve all the problems under the most optimum solution. Because today, one of the important powers of the rulers, and perhaps the information as a source of authority should be to benefit from.

Anatomy of the Italian occupational structure: concentrated power and distributed knowledge

AbstractWhich type of work do Italians perform? In this contribution, we aim at detecting the anatomy of the Italian occupational structure by taking stock of a micro-level dataset registering the task content, the execution of procedures, the knowledge embedded in the work itself, called ICP (Indagine Campionaria sulle Professioni), the latter being comparable to the U.S. O*NET dataset. We perform an extensive empirical investigation moving from the micro to the macro level of aggregation. Our results show that the Italian occupational structure is strongly hierarchical, with the locus of power distinct by the locus of knowledge generation. It is also weak in terms of collaborative and worker involvement practices, and possibility to be creative. Our analysis allows to pinpoint the role exerted by hierarchical structures, decision-making autonomy, and knowledge as the most relevant attributes characterizing the division of labor.

MapOnLearn: The Use of Maps in Online Learning Systems for Education Sustainability

Online learning and teaching have become the primary forms of education during the global pandemic, and online learning systems, which can provide fair educational opportunities for everyone, are increasingly important for sustainability in education. The amount of time a student spends on online learning systems affects the fairness and persistence of sustainability in education. To support personalized learning opportunities, interactive learning, and easy-to-access resources, we propose a map organization and visualization method called MapOnLearn for online learning systems. First, we converted tree-like hierarchical course units (HCUs) and knowledge points (KPs) into a fundamental two-dimensional (2D) map of hierarchically divided polygons and used the map to form containers to manage all learning resources. Then, we used the zoom feature of the map to express the hierarchical structures of knowledge and formulated corresponding rules for displaying information at different levels. Path analysis was applied to express the learning process, and topological processing was adapted to represent the relationships among HCUs and KPs. We developed maps for a high-level math course, a course on data structures, and an English course at a university in China and investigated 264 students and 27 teachers for a semester by using the technology acceptance model (TAM). We found that the map visualization and organization method had a positive impact on the way teachers and students use online learning systems and improved the online learning experience. To attract more students to spend more time on online learning, we hope our method can promote the sustainable development of education.

Transductive Zero-Shot Action Recognition via Visually Connected Graph Convolutional Networks.

With the explosive growth of action categories, zero-shot action recognition aims to extend a well-trained model to novel/unseen classes. To bridge the large knowledge gap between seen and unseen classes, in this brief, we visually associate unseen actions with seen categories in a visually connected graph, and the knowledge is then transferred from the visual features space to semantic space via the grouped attention graph convolutional networks (GAGCNs). In particular, we extract visual features for all the actions, and a visually connected graph is built to attach seen actions to visually similar unseen categories. Moreover, the proposed grouped attention mechanism exploits the hierarchical knowledge in the graph so that the GAGCN enables propagating the visual-semantic connections from seen actions to unseen ones. We extensively evaluate the proposed method on three data sets: HMDB51, UCF101, and NTU RGB + D. Experimental results show that the GAGCN outperforms state-of-the-art methods.

Co-constructed Documentary Film: collaboration, dialogue, and performance in researching gender and contemporary art in Vietnam

ABSTRACT How can documentary as visual research method create a relay between feminist scholarship and the goals of feminist struggle? The use of co-constructed documentary responds to the three key concerns of feminist research: the situated nature of knowledge; the critique of hierarchical knowledge; and the intention towards emancipatory action. In other words, documentary-making opens out from a “discourse of sobriety” or representation of historical truth to encompass material transformative potential not merely through representational instruments but re-organized methods, relationships, and practices which critique documentary’s social relations of power. The methodological challenge and opportunity involve the re-framing of documentary participant as collaborator with a stake in decision-making and documentary construction. Taken further, this agenda complicates the notion of documentary authorship and related concepts of creative autonomy, individuality and artist “voice.” In this paper, I take up these questions to argue that dialogic authoring in contemporary art theory and practice drawing upon Mikhail Bakhtin and Grant Kester) provides the theoretical foundation of an interactional concept of art generated between co-participants.

Exception-Tolerant Hierarchical Knowledge Bases for Forward Model Learning

This article provides an overview of the recently proposed forward model approximation framework for learning games of the general video game artificial intelligence (GVGAI) framework. In contrast to other general game-playing algorithms, the proposed agent model does not need a full description of the game but can learn the game's rules by observing game state transitions. Based on hierarchical knowledge bases, the forward model can be learned and revised during game-play, improving the accuracy of the agent's state predictions over time. This allows the application of simulation-based search algorithms and belief revision techniques to previously unknown settings. We show that the proposed framework is able to quickly learn a model for dynamic environments in the context of the GVGAI framework.

An intellectual system for supporting decision making in the control of the borring process

The problem of development of the method of identification of complications arising in the process of drilling of oil and gas wells, which operates under the conditions of a priori and current uncertainty under the influence of various perturbations based on methods of fuzzy set theory and fuzzy logic, is considered. A methodological approach to the estimation of the level of complications in the drilling of oil and gas wells, based on the principles of linguistic parameters of the drilling process, linguistic and hierarchical knowledge about the complications in the drilling of wells is proposed. Mathematical models of a controlled object have been developed that, unlike deterministic mathematical models, allow to describe in natural language the cause and effect relationships between the parameters of the drilling process and the possible complication. These models reflect the logic of the operator's reasoning with the involvement of non-numerical and fuzzy information from an expert to formalize Fuzzy Logic decision-making procedures using the parameters and indicators of the oil and gas drilling process. The structure of the decision support system for controlling the drilling of wells in the conditions of complications is proposed. The results of simulation modeling of the developed methods of modeling of complications based on the methods of fuzzy set theory and fuzzy logic are presented. Their advantages over the well-known in accuracy of the tasks of identification of an estimation and control in the conditions of uncertainty concerning structure and parameters of object are shown. The real complications have been identified, the elimination of which will increase the level of safety of the drilling process. It is shown that the developed methods and models can find application for modeling and identification of a wide class of complications on drilling rigs operating under the conditions of a priori and current uncertainty regarding their structure, parameters and geographic environment.

Hierarchical main path analysis to identify decompositional multi-knowledge trajectories

Purpose The purpose of this paper is to propose a quantitative method for identifying multiple and hierarchical knowledge trajectories within a specific technological domain (TD). Design/methodology/approach The proposed method as a patent-based data-driven approach is basically based on patent classification systems and patent citation information. Specifically, the method first analyzes hierarchical structure under a specific TD based on patent co-classification and hierarchical relationships between patent classifications. Then, main paths for each sub-TD and overall-TD are generated by knowledge persistence-based main path approach. The all generated main paths at different level are integrated into the hierarchical main paths. Findings This paper conducted an empirical analysis by using Genome sequencing technology. The results show that the proposed method automatically identifies three sub-TDs, which are major functionalities in the TD, and generates the hierarchical main paths. The generated main paths show knowledge flows across different sub-TDs and the changing trends in dominant sub-TD over time. Originality/value To the best of the authors’ knowledge, the proposed method is the first attempt to automatically generate multiple hierarchical main paths using patent data. The generated main paths objectively show not only knowledge trajectories for each sub-TD but also interactive knowledge flows among sub-TDs. Therefore, the method is definitely helpful to reduce manual work for TD decomposition and useful to understand major trajectories for TD.

Querying of several DL-Lite knowledge bases from various information sources-based polynomial response unification approach

The inconsistency in the hierarchical knowledge base is due to the fact that the assertions (ABoxes) come from several sources with different levels of reliability. We introduce the management of this inconsistency problem to query the inconsistent DL-Lite knowledge bases. Most of the approaches studied in the literature first repair all of the inconsistent assertions in the DL-Lite incoherent knowledge base and then question it. In this article, we proceed directly to a knowledge base query to retrieve an exhaustive list of responses and then, once these responses are retrieved, we repair them. The main contribution of this work therefore consists of studying several response strategies to queries from various data sources using a recurrent function to calculate the rank of coherence which will allow us to manage inconsistencies in the set of responses. We study these strategies from different points of view: productivity, precision, recall, F-measure, Accuracy, G-mean and computational complexity. The experiments carried out, on different corpora, and the analysis of the results, which we carried out, show encouraging results in productivity since our approach is much more productive, providing the greatest number of responses, while remaining the best in time compared to the other studied approaches.

Zero-shot Handwritten Chinese Character Recognition with hierarchical decomposition embedding

Handwritten Chinese Character Recognition (HCCR) is a challenging topic in the field of pattern recognition due to large-scale character vocabulary, complex hierarchical structure, various writing styles, and scarce training samples. In this paper, we explored the hierarchical knowledge of Chinese characters and presented a novel zero-shot HCCR method. First, we handled the relations between the characters and their primitives, such as radicals and structures, to obtain a tree layout of primitives. Then, we presented a novel zero-shot hierarchical decomposition embedding method to encode the tree layout into a semantic vector. Next, we devised a Convolutional Neural Network (CNN) based framework to learn both radicals and structures of characters via the semantic vector. As different Chinese characters share some common radicals and structures, our method is able to recognize new categories without any labeled samples from them. Moreover, our method is effective in both traditional HCCR and zero-shot HCCR tasks. It achieves competitive performance on the traditional experiment setting and significantly surpasses the state-of-the-art methods on the zero-shot experiment setting.

The Visual Search Strategies Underpinning Effective Observational Analysis in the Coaching of Climbing Movement.

Despite the importance of effective observational analysis in coaching the technical aspects of climbing performance, limited research informs this aspect of climbing coach education. Thus, the purpose of the present research was to explore the feasibility and the utility of a novel methodology, combining eye tracking technology and cued retrospective think-aloud (RTA), to capture the cognitive–perceptual mechanisms that underpin the visual search behaviors of climbing coaches. An analysis of gaze data revealed that expert climbing coaches demonstrate fewer fixations of greater duration and fixate on distinctly different areas of the visual display than their novice counterparts. Cued RTA further demonstrated differences in the cognitive–perceptual mechanisms underpinning these visual search strategies, with expert coaches being more cognizant of their visual search strategy. To expand, the gaze behavior of expert climbing coaches was underpinned by hierarchical and complex knowledge structures relating to the principles of climbing movement. This enabled the expert coaches to actively focus on the most relevant aspects of a climber’s performance for analysis. The findings demonstrate the utility of combining eye tracking and cued RTA interviewing as a new, efficient methodology of capturing the cognitive–perceptual processes of climbing coaches to inform coaching education/strategies.

Improving the robustness of machine reading comprehension model with hierarchical knowledge and auxiliary unanswerability prediction

Machine Reading Comprehension (MRC) aims to understand a passage and answer a series of related questions. With the development of deep learning and the release of large-scale MRC datasets, many end-to-end MRC neural networks have achieved remarkable success. However, these models are fragile and lack of robustness when there are some imperceptible adversarial perturbations in the input. In this paper, we propose an MRC model which has two main components to improve the robustness. On the one hand, we enhance the representation of the model by leveraging hierarchical knowledge from external knowledge bases. On the other hand, we introduce an auxiliary unanswerability prediction module and perform supervised multi-task learning along with a span prediction task. Experimental results on benchmark datasets show that our model can achieve consistent improvement compared with other strong baselines.

Deep embedding of concept ontology for hierarchical fashion recognition

The natural concept ontology structure of clothes has enabled easy management of large quantities of fashion images for online retailers and it is meaningful to study how to automatically recognize fashion images for both commercial promotion and academic research. In this paper, a new hierarchical approach is developed for large-scale fashion recognition. We first embed concept ontology into deep convolutional neural network (CNN) by adopting multiple deep CNN branches to learn node-specific features and classifiers explicitly. Then, we introduce a hierarchical knowledge distillation method to further improve the performance of fashion recognition. Finally, we employ the proposed approach for fashion recommendation. To deal with hierarchical deep learning constrains, we leverage back propagation to simultaneously refine the shared deep CNNs and the diverse CNN branches for relevant node features and classifiers by using our joint objective function. The main advantages of this paper lie in (1) providing an effective way for recognizing rich semantic explanations of fashion images without training large or multiple networks, and (2) saving the storage&time costs by learning personalized features and classifiers for each tree node. The experimental results on both our organized fashion dataset and the public DeepFashion dataset have verified the effectiveness and efficiency of the proposed approach on both hierarchical fashion recognition and within category fine-grained fashion recommendation.