Effective Knowledge Representation Research Articles

Effective knowledge representation and utilization for sustainable collaborative learning across heterogeneous systems

AbstractThe increasingly decentralized and private nature of data in our digital society has motivated the development of collaborative intelligent systems that enable knowledge aggregation among data owners. However, collaborative learning has only been investigated in simple settings. For example, clients are often assumed to train solution models de novo, disregarding all prior expertise. The learned model is typically represented in task‐specific forms that are not generalizable to unseen, emerging scenarios. Finally, a universal model representation is enforced among collaborators, ignoring their local compute constraints or input representations. These limitations hampers the practicality of prior collaborative systems in learning scenarios with limited task data that demand constant knowledge adaptation and transfer across information silos, tasks, and learning models, as well as the utilization of prior solution expertise. Furthermore, prior collaborative learning frameworks are not sustainable on a macro scale where participants desire fairness allocation of benefits (e.g., access to the combined model) based on their costs of participation (e.g., overhead of model sharing and training synchronization, risk of information breaches, etc.). This necessitates a new perspective of collaborative learning where the server not only aggregates but also conducts valuation of the participant's contribution, and distribute aggregated information to individuals in commensurate to their contribution. To substantiate the above vision, we propose a new research agenda on developing effective and sustainable collaborative learning frameworks across heterogeneous systems, featuring three novel computational capabilities on knowledge organization: model expression, comprehension, and valuation.

Simona: a comprehensive R package for semantic similarity analysis on bio-ontologies

BackgroundBio-ontologies are keys in structuring complex biological information for effective data integration and knowledge representation. Semantic similarity analysis on bio-ontologies quantitatively assesses the degree of similarity between biological concepts based on the semantics encoded in ontologies. It plays an important role in structured and meaningful interpretations and integration of complex data from multiple biological domains.ResultsWe present simona, a novel R package for semantic similarity analysis on general bio-ontologies. Simona implements infrastructures for ontology analysis by offering efficient data structures, fast ontology traversal methods, and elegant visualizations. Moreover, it provides a robust toolbox supporting over 70 methods for semantic similarity analysis. With simona, we conducted a benchmark against current semantic similarity methods. The results demonstrate methods are clustered based on their mathematical methodologies, thus guiding researchers in the selection of appropriate methods. Additionally, we explored annotation-based versus topology-based methods, revealing that semantic similarities solely based on ontology topology can efficiently reveal semantic similarity structures, facilitating analysis on less-studied organisms and other ontologies.ConclusionsSimona offers a versatile interface and efficient implementation for processing, visualization, and semantic similarity analysis on bio-ontologies. We believe that simona will serve as a robust tool for uncovering relationships and enhancing the interoperability of biological knowledge systems.

Multigranulation variable-scale fuzzy neighborhood measures and corresponding Choquet-like integrals for feature selection

Choquet-like integrals, a nonlinear fuzzy aggregation function, are diffusely applied in several real problems. However, the corresponding fuzzy measures in them are provided by human intervention and not by data-driven methods. As an effective knowledge representation tool, rough set models in different approximation spaces are established for data processing. Particularly, the multigranulation fuzzy β-covering approximation space has been concerned with only a single scale β∈(0,1]. However, different granulation structures should have different scales. Therefore, establishing a multigranulation approximation space with a variable scale by inducing fuzzy measures through data-driven methods and using corresponding Choquet-like integrals in practical problems is a significant challenge. To address this challenge, the notion of multigranulation variable-scale fuzzy Θ-covering group approximation space is presented here, as well as multigranulation variable-scale fuzzy neighborhood measures in it. Furthermore, Choquet-like integrals with the presented measures are constructed to solve the issue of feature selection (i.e., attribute reduction) under the new approximation spaces. Firstly, the concept of multigranulation variable-scale fuzzy Θ-covering group approximation space is presented, where different fuzzy β-coverings have different scales β∈Θ. Moreover, multigranulation variable-scale fuzzy neighborhood measures in it, as fuzzy measures, are presented. Subsequently, Choquet-like integrals with multigranulation variable-scale fuzzy neighborhood measures are constructed. A novel attribute reduction method under Choquet-like integrals with multigranulation variable-scale fuzzy neighborhood measures is proposed for any decision information table. Finally, the presented method is selected for solving problems of classification and diagnosis of rolling bearing faults. Several public data sets are used to demonstrate the effectiveness and feasibility of the presented methods mentioned above.

Target Detection and Segmentation Technology for Zero-shot Learning

Zero-shot learning (ZSL) in the field of computer vision refers to enabling the model to recognize and understand categories that have not been encountered during the training phase. It is particularly critical for object detection and segmentation tasks, because these tasks require the model to have good generalization capabilities to unknown categories. Object detection requires the model to determine the location of the object, while segmentation further requires the precise demarcation of the object's boundaries. In ZSL research, knowledge representation and transfer are core issues. Researchers have tried to use semantic attributes as a knowledge bridge to connect categories seen during the training phase and categories not seen during the testing phase. These attributes may be color, shape, etc., but this method requires accurate attribute annotation, which is often not easy to achieve in practice. Therefore, researchers have begun to explore the use of non-visual information such as knowledge maps and text descriptions to enrich the recognition capabilities of models, but this also introduces the challenge of information integration and alignment. At present, ZSL has made certain progress in target detection and segmentation tasks, but there is still a significant gap compared with traditional supervised learning. This is mainly due to the limited ability of ZSL models to generalize to new categories. To this end, researchers have begun to explore combining ZSL with other technologies, such as generative adversarial networks (GANs) and reinforcement learning, to enhance the model's detection and segmentation capabilities for new categories. Future research needs to focus on several aspects. The first is how to design a more effective knowledge representation and transfer mechanism so that the model can better utilize existing knowledge. The second step is to develop new algorithms to improve the performance of ZSL in complex environments. In addition, research should focus on how to reduce the dependence on computing resources so that the ZSL method can run effectively in resource-limited environments. In summary, the research on target detection and segmentation technology of zero-shot learning is a cutting-edge topic in the field of computer vision. Despite the challenges, with the deepening of research, we expect these technologies to contribute to improving the generalization ability and intelligence level of computer vision systems.

Strategies of Content Knowledge Representation and EFL Learners‘ English Writing Proficiency: Mediating Role of Critical Thinking Skills

The exploration of optimizing content knowledge representation and enhancing critical thinking capabilities in English as Foreign Language (EFL) learners’ writing still needs to be improved. Cultivating adept critical thinking skills and effective content knowledge representation is paramount for EFL learners, given its correlation with heightened writing proficiency. This study sought to examine critical thinking skills as a mediator in the correlation between strategies of content knowledge representation and writing proficiency among EFL learners. A total of 360 English as foreign language participants engaged in the California Critical Thinking Skills Test and responded to a questionnaire on strategies of content knowledge representation conducted at Kaifeng Science Technology and Communication College, China. Subsequently, participants undertook a writing task, and the outcomes underwent analysis using SPSS 26.0, incorporating descriptive analysis, correlational analysis, and AMOS 24.0 for mediating analysis. The findings unveiled a correlation between critical thinking skills and EFL learners’ writing proficiency, echoing the association observed between content knowledge representation strategies and writing proficiency. Furthermore, critical thinking skills were identified as a mediator, linking content knowledge representation strategies to writing proficiency among EFL learners. The combination of content knowledge representation and critical thinking skills emerged as a positive role in the writing process. This research underscored the paramount significance of critical thinking skills within a specialized discipline, highlighting their transformative potential for EFL learners’ writing competency and accentuating their functions in the broader writing pedagogy.

Knowledge representation of the state of a cloud-native application

Cloud Computing has revolutionized the way applications are developed, deployed, and maintained. Over the past decade, we have observed dynamically growing interest in Cloud Computing. The benefits of the cloud approach caused the increasing popularity of Cloud-native applications. Cloud-native is an approach to developing and deploying applications according to the concepts of DevOps, Continuous Integration/Continuous Delivery (CI/CD), containers and microservices. The knowledge about Cloud Computing has become extensive and complex. Fortunately, before Cloud-native applications development, there was a great deal of effort to develop tools for effective knowledge representation. Ontologies are a convenient way to show the relations between domain-specific concepts. In this paper, we propose an ontology named CNOnt that describes the state-of-the-art of Cloud-native applications. CNOnt covers aspects from the clusterization perspective. First, this paper presents the engineering perspective of building the CNOnt ontology. Second, we demonstrate a use case of our ontology that proves the correctness of CNOnt development. This ontology is exhausted in CNOnt Broker. It is a system that applies the information in the OWL file into the Kubernetes cluster and in reverse. The knowledge representation makes Cloud-native applications understandable to third-party systems and increases interoperability between different microservices.

Adapting Neural Turing Machines for linguistic assessments aggregation in neural-symbolic decision support systems

Introduction: The construction of integrated neurosymbolic systems is an urgent and challenging task. Building neurosymbolic decision support systems requires new approaches to represent knowledge about a problem situation and to express symbolic reasoning at the subsymbolic level. Purpose: Development of neural network architectures and methods for effective distributed knowledge representation and subsymbolic reasoning in decision support systems in terms of algorithms for aggregation of fuzzy expert evaluations to select alternative solutions. Methods: Representation of fuzzy and uncertain estimators in a distributed form using tensor representations; construction of a trainable neural network architecture for subsymbolic aggregation of linguistic estimators. Results: The study proposes two new methods of representation of linguistic assessments in a distributed form. The first approach is based on the possibility of converting an arbitrary linguistic assessment into a numerical representation and consists in converting this numerical representation into a distributed one by converting the number itself into a bit string and further forming a matrix storing the distributed representation of the whole expression for aggregating the assessments. The second approach to translating linguistic assessments to a distributed representation is based on representing the linguistic assessment as a tree and coding this tree using the method of tensor representations, thus avoiding the step of translating the linguistic assessment into a numerical form and ensuring the transition between symbolic and subsymbolic representations of linguistic assessments without any loss of information. The structural elements of the linguistic assessment are treated as fillers with their respective positional roles. A new subsymbolic method of aggregation of linguistic assessments is proposed, which consists in creating a trainable neural network module in the form of a Neural Turing Machine. Practical relevance: The results of the study demonstrate how a symbolic algorithm for aggregation of linguistic evaluations can be implemented by connectionist (or subsymbolic) mechanisms, which is an essential requirement for building distributed neurosymbolic decision support systems.

Operads for complex system design specification, analysis and synthesis.

As the complexity and heterogeneity of a system grows, the challenge of specifying, documenting and synthesizing correct, machine-readable designs increases dramatically. Separation of the system into manageable parts is needed to support analysis at various levels of granularity so that the system is maintainable and adaptable over its life cycle. In this paper, we argue that operads provide an effective knowledge representation to address these challenges. Formal documentation of a syntactically correct design is built up during design synthesis, guided by semantic reasoning about design effectiveness. Throughout, the ability to decompose the system into parts and reconstitute the whole is maintained. We describe recent progress in effective modelling under this paradigm and directions for future work to systematically address scalability challenges for complex system design.

Knowledge Representation and Reasoning — A History of DARPA Leadership

A fundamental goal of artificial intelligence research and development is the creation of machines that demonstrate what humans consider to be intelligent behavior. Effective knowledge representation and reasoning methods are a foundational requirement for intelligent machines. The development of these methods remains a rich and active area of artificial intelligence research in which advances have been motivated by many factors, including interest in new challenge problems, interest in more complex domains, shortcomings of current methods, improved computational support, increases in requirements to interact effectively with humans, and ongoing funding from the Defense Advanced Research Projects Agency and other agencies. This article highlights several decades of advances in knowledge representation and reasoning methods, paying particular attention to research on planning and on the impact of the Defense Advanced Research Projects Agency's support.

A Semantic Expansion Model for VGI Retrieval

OpenStreetMap (OSM) is a representative volunteered geographic information (VGI) project. However, there have been difficulties in retrieving spatial information from OSM. Ontology is an effective knowledge organization and representation method that is often used to enrich the search capabilities of search systems. This paper constructed an OSM ontology model with semantic property items. A query expansion method is also proposed based on the similarity of properties of the ontology model. Moreover, a relevant experiment is conducted using OSM data related to China. The experimental results demonstrate that the recall and precision of the proposed method reach 80% and 87% for geographic information retrieval, respectively. This study provides a method that can be used as a reference for subsequent research on spatial information retrieval.

Hybrid Technique for Effective Knowledge Representation in Normal Life

Knowledge is essential for daily life. People can gather knowledge from their routine work like reading newspaper, watching T.V, discussions, experience and many more are the source of knowledge. An artificial intelligent (AI) system must be able to do the same. So there is a requirement of effective knowledge representation (KR) technique that is able to represent the knowledge from above defined sources and works for daily life. An inference mechanism is also required for reasoning the knowledge from artificial intelligent system. The purpose of this paper is to present the implemented conceptual view of hybrid KR technique that works for representing the knowledge required for daily life.

A Survey of Knowledge Representation in Service Robotics

Within the realm of service robotics, researchers have placed a great amount of effort into learning, understanding, and representing motions as manipulations for task execution by robots. The task of robot learning and problem-solving is very broad, as it integrates a variety of tasks such as object detection, activity recognition, task/motion planning, localization, knowledge representation and retrieval, and the intertwining of perception/vision and machine learning techniques. In this paper, we solely focus on knowledge representations and notably how knowledge is typically gathered, represented, and reproduced to solve problems as done by researchers in the past decades. In accordance with the definition of knowledge representations, we discuss the key distinction between such representations and useful learning models that have extensively been introduced and studied in recent years, such as machine learning, deep learning, probabilistic modeling, and semantic graphical structures. Along with an overview of such tools, we discuss the problems which have existed in robot learning and how they have been built and used as solutions, technologies or developments (if any) which have contributed to solving them. Finally, we discuss key principles that should be considered when designing an effective knowledge representation.

Adversarial Distillation for Efficient Recommendation with External Knowledge

Integrating external knowledge into the recommendation system has attracted increasing attention in both industry and academic communities. Recent methods mostly take the power of neural network for effective knowledge representation to improve the recommendation performance. However, the heavy deep architectures in existing models are usually incorporated in an embedded manner, which may greatly increase the model complexity and lower the runtime efficiency. To simultaneously take the power of deep learning for external knowledge modeling as well as maintaining the model efficiency at test time, we reformulate the problem of recommendation with external knowledge into a generalized distillation framework . The general idea is to free the complex deep architecture into a separate model, which is only used in the training phrase, while abandoned at test time. In particular, in the training phrase, the external knowledge is processed by a comprehensive teacher model to produce valuable information to teach a simple and efficient student model. Once the framework is learned, the teacher model is abandoned, and only the succinct yet enhanced student model is used to make fast predictions at test time. In this article, we specify the external knowledge as user review, and to leverage it in an effective manner, we further extend the traditional generalized distillation framework by designing a Selective Distillation Network (SDNet) with adversarial adaption and orthogonality constraint strategies to make it more robust to noise information. Extensive experiments verify that our model can not only improve the performance of rating prediction, but also can significantly reduce time consumption when making predictions as compared with several state-of-the-art methods.

Simplifying humanitarian assistance/disaster relief analytic models using activity-based intelligence

PurposeThe purpose of this paper is to propose an effective knowledge elicitation method and representation scheme that empowers humanitarian assistance/disaster relief (HA/DR) analysts and experts to create analytic models without the aid of data scientists and methodologists while addressing the issues of complexity, collaboration, and emerging technology across a diverse global network of HA/DR organizations.Design/methodology/approachThe paper used a mixed-methods research approach, with qualitative research and analysis to select the model elicitation method, followed by quantitative data collection and evaluation to test the representation scheme. A simplified analytic modeling approach was created based on emerging activity-based intelligence (ABI) analytic methods.FindingsUsing open source data on the Syrian humanitarian crisis as the reference mission, ABI analytic models were proven capable in modeling HA/DR scenarios of physical systems, nonphysical systems, and thinking.Practical implicationsAs a data-agnostic approach to develop object and network knowledge, ABI aligns with the objectives of modeling within multiple HA/DR organizations.Originality/valueUsing an analytic method as the basis for model creation allows for immediate adoption by analysts and removes the need for data scientists and methodologists in the elicitation phase. Applying this highly effective cross-domain ABI data fusion technique should also supplant the accuracy weaknesses created by traditional simplified analytic models.

Generating automatic linguistic descriptions with big data

In highly connected world, the volume and variety of data is growing and growing. The Big Data era opens new challenges to address. Dealing with Big Data, we have identified and analyzed seven issues: (1) scalability, (2) efficient processing, (3) incomplete and inaccurate data, (4) specific domains, (5) relevance of information, (6) levels of detail, and (7) intuitive and effective knowledge representation. The analysis reveals that five of these issues are related to knowledge representation and human perception. Linguistic Descriptions of Complex Phenomena is a technology aimed to compute and generate linguistic reports customized to the user needs. In this paper, we present and describe an approach to Big Data based on this technology that faces the seven issues under study. Namely, we generate linguistic reports from Big Data that fulfill with the user requirements. To evaluate the generated linguistic reports we propose specific evaluation criteria based on the maxims of Grice. We illustrate the usefulness of the proposed solution by presenting a practical experiment based on the census data of the United States of America.

Design and evaluation of a cognitive approach for disseminating semantic knowledge and content in opportunistic networks

In cyber-physical convergence scenarios information flows seamlessly between the physical and the cyber worlds. Here, users’ mobile devices represent a natural bridge through which users process acquired information and perform actions. The sheer amount of data available in this context calls for novel, autonomous and lightweight data-filtering solutions, where only relevant information is finally presented to users. Moreover, in many real-world scenarios data is not categorised in predefined topics, but it is generally accompanied by semantic descriptions possibly describing users’ interests. In these complex conditions, user devices should autonomously become aware not only of the existence of data in the network, but also of their semantic descriptions and correlations between them. To tackle these issues, we present a set of algorithms for knowledge and data dissemination in opportunistic networks, based on simple and very effective models (called cognitive heuristics) coming from cognitive sciences. We show how to exploit them to disseminate both semantic data and the corresponding data items. We provide a thorough performance analysis, under various different conditions comparing our results against non-cognitive solutions. Simulation results demonstrate the superior performance of our solution towards a more effective semantic knowledge acquisition and representation, and a more tailored content acquisition.

Development of Ontology in Laptop Domain for Knowledge Representation

Large amount of information is available on the World Wide Web(WWW), which when searched through major search engines provides a lot of unwanted information, requiring relevant information to be extracted, consuming a lot of effort and time. Ontologies prove to be a technique for effective knowledge representation and information retrieval, which is the core concept in semantic web applications. Knowledge representation with ontologies helps in effective information retrieval as compared to other technologies of representation.This paper discusses about the requirement for ontology development, different tools for ontology development and the query languages to handle the knowledge. Three ontologies are created in the domain of laptop to deal with the problem of effective information retrieval and its coverage domain is validated with a set of queries executed with DL (Description logic) language on the developed ontologies.

Variational learning of finite Dirichlet mixture models using component splitting

Finite Dirichlet mixture models have proved to be an effective knowledge representation and inference engine in several machine learning and data mining applications. In this paper, we address the task of learning and selecting finite Dirichlet mixture models in an incremental variational way. A learning algorithm based on component splitting and local model selection is proposed. The merits of the proposed approach are illustrated using synthetic data as well as real challenging applications involving object detection, text documents clustering and distinguishing photographic images from computer graphics.

Knowledge Representation

Substantial work in knowledge engineering has focused on eliciting knowledge and representing it in a computational form. However, before elicited knowledge can be represented, it must be integrated and transformed so the knowledge engineer can understand it. This research identifies the need to separate knowledge representation into human comprehension and computational reasoning and shows that this will lead to better knowledge representation. Modeling of human comprehension is called conceptual knowledge representation. The Conceptual Knowledge Representation Scheme is developed and validated by conducting a combined qualitative/quantitative repeated-measures experiment comparing the Conceptual Knowledge Representation Scheme to two computation-oriented ones. The results demonstrate that the Conceptual Knowledge Representation Scheme better facilitates human comprehension than existing representation schemes. Four principles of the Conceptual Knowledge Representation Scheme emerge that help to attain effective knowledge representation. These are: (1) a focus on human comprehension only, (2) design around natural language, (3) addition of constructs common in the domain, and (4) constructs for representing abstract versions of detailed concepts.

Mining sequential patterns with extensible knowledge representation

Mining sequential patterns is an important activity in computerized data analysis, and further analysis of discovered patterns can lead to more important findings in a post mining stage. Methods that integrate the traditional mining tasks with a knowledge representation facilitating such as post pruning are therefore needed. In this paper a set-based approach to mining frequent sequential patterns in customer transactional databases is described which includes an extensible knowledge representation. This knowledge representation is a byproduct of the set-based approach which contributes to facilitate post data mining and analysis. The proposed approach employs a set based knowledge representation and improves the performance of Apriori based algorithms while preserving a complete set of sequential patterns. It takes advantage of an incremental mining methodology and provides a rich knowledge representation. Performance results of the proposed approach are compared to the performance of existing sequential pattern mining algorithms including GSP Generalized Sequential Pattern and PrefixSpan. The effective knowledge representation inferred from the set based approach can be extended to other data mining tasks and data analysis models. Such extension is demonstrated by two instances of enriched knowledge representations in sequential databases, namely Set Occurrence Tables and Set Distance computations, along with their use of association rules generation, feature selection and ad hoc analysis in the post mining stage.