Knowledge-based Applications Research Articles

CLKR: Conditional Logic and Knowledge Representation

AbstractCLKR (Conditional Logic and Knowledge Representation) is an online repository of conditional logic resources for knowledge representation and reasoning. The question which entailments should follow from a conditional knowledge base consisting of a set of conditionals “If A then usually B“ is central in logic-based AI. In order to support the practical side of this question, CLKR provides various collections of conditional knowledge bases and related resources. All knowledge bases available in CLKR can be processed directly with a corresponding reasoning system like InfOCF-Web. The sets of knowledge bases include examples as they are used in the literature for illustration, application knowledge bases from different domains, and systematically generated knowledge bases for evaluating implementations of nonmonotonic reasoning. A main emphasis of the current version of CLKR is on providing collections of knowledge bases in various normal forms that have been proposed for conditional knowledge bases, e.g., conditional normal form, antecedent normal form, and renaming normal form.

Ontology-Driven Computer Systems

This article delves into the evolving frontier of ontology-driven natural language information processing. Through an in-depth examination, we put forth a novel linguistic processor architecture, uniquely integrating linguistic and ontological paradigms during semantic analysis. Distancing from conventional methodologies, our approach showcases a profound merger of knowledge extraction and representation techniques. A central highlight of our research is the development of an ontology-driven information system, architected with an innate emphasis on self-enhancement and adaptability. The system’s salient capability lies in its adept handling of elementary knowledge, combined with its dynamic aptitude to foster innovative concepts and relationships. A particular focus is accorded to the system’s application in scientific information processing, signifying its potential in revolutionising knowledge-based applications within scientific domains. Through our endeavours, we aim to pave theway for more intuitive, precise, and expansive ontology-driven tools in the realm of knowledge extraction and representation.

A distribution-based representation of Knowledge Quality

In recent times, a multitude of knowledge-based applications draw knowledge from diverse sources to cater to escalating task demands. However, the presence of errors or contradictions within these acquired knowledge, originating from different sources, can significantly impact the performance of downstream tasks. As a parameter quantifying the alignment of knowledge with facts, Knowledge Quality (KQ) plays an essential role in many tasks. It serves as a metric for selecting high-quality knowledge and filtering out incorrect ones. Traditional methods typically amalgamate information from different domains to evaluate KQ, representing it as a numerical metric. However, these methods may struggle to accurately reflect the quality of knowledge and may face challenges in generalizing across different domains. Addressing these issues, this paper introduces a generalized KQ evaluation method, grounded on the consistency of multi-source knowledge. This method uses the congruence between knowledge pieces from varied sources to evaluate the KQ. Our proposed method represents knowledge quality as a normal distribution, thereby quantifying the uncertainty involved in KQ evaluation and reflecting the credibility of the knowledge. Additionally, an iterative method is devised to update the quality of knowledge, taking into account the credibility of the knowledge source. To tackle situations where the investigated knowledge is only found in a sparse number of sources, a sparsely represented constraint operator is proposed. Experimental studies conducted on several datasets show that our proposed method can effectively measure KQ and offer valuable support for downstream applications.

Modern Teaching Methods in Action in Statistics Classes in West Bengal

The overall research study has focused on the current teaching methods in the statistics domain in the Indian state of West Bengal. Different teaching styles have been evaluated in this study along with existing gaps in the current teaching method. It has been observed that traditional teaching method is still practiced by teachers and professors in WB. However, the participants accepted that “project-based learning” can be more effective in terms of technical skill development. In addition, teachers should move forward from lecture-based classes to active learning techniques that can optimise students' engagement and the standard of learning. In this study, it has been founded that the usage of modern teaching approaches primarily leads to knowledge-based application that depends on both students and educators so that their time can be utilized effectively.

Construction and Application of a Complex Network-Based Case Knowledge Base in an Assisted Instruction System

With the development of the business administration major, case teaching has become an effective teaching method. However, a lot of case resources exist in the business administration field, and the correlation between these cases is complex, which poses challenges to teachers and students in terms of information overload and knowledge organization. Existing case knowledge bases in assisted instruction systems often have shortcomings in terms of knowledge relationship strength calculation, text semantic similarity calculation, hierarchical knowledge clustering, and propagation evolution. To solve these problems, this study proposed a method of constructing and applying a case knowledge base in an assisted instruction system based on a complex network. This method mainly includes three aspects: calculation and reasoning of ontology relationship strength, calculation of ontology text semantic similarity, and hierarchical knowledge clustering and propagation evolution in complex networks. Through a comprehensive study of these three aspects, a more efficient and intelligent case knowledge base in an assisted instruction system was constructed, which not only improved the teaching efficiency and quality of the business administration major but also had the potential to promote teaching in other disciplines and fields. In addition, this study also provided new perspectives and methods in related fields, which is of great significance for efficiently organizing and utilizing knowledge.

Self-supervised contrastive graph representation with node and graph augmentation

Graph representation is a critical technology in the field of knowledge engineering and knowledge-based applications since most knowledge bases are represented in the graph structure. Nowadays, contrastive learning has become a prominent way for graph representation by contrasting positive–positive and positive–negative node pairs between two augmentation graphs. It has achieved new state-of-the-art in the field of self-supervised graph representation. However, existing contrastive graph representation methods mainly focus on modifying (normally removing some edges/nodes) the original graph structure to generate the augmentation graph for the contrastive. It inevitably changes the original graph structures, meaning the generated augmentation graph is no longer equivalent to the original graph. This harms the performance of the representation in many structure-sensitive graphs such as protein graphs, chemical graphs, molecular graphs, etc. Moreover, there is only one positive–positive node pair but relatively massive positive–negative node pairs in the self-supervised graph contrastive learning. This can lead to the same class, or very similar samples are considered negative samples. To this end, in this work, we propose a Virtual Masking Augmentation (VMA) to generate an augmentation graph without changing any structures from the original graph. Meanwhile, a node augmentation method is proposed to augment the positive node pairs by discovering the most similar nodes in the same graph. Then, two different augmentation graphs are generated and put into a contrastive learning model to learn the graph representation. Extensive experiments on massive datasets demonstrate that our method achieves new state-of-the-art results on self-supervised graph representation. The source code of the proposed method is available at https://github.com/DuanhaoranCC/CGRA.

Graph matching for knowledge graph alignment using edge-coloring propagation

Knowledge graph (KG) is a kind of structured human knowledge of modeling the relationships between real-world entities. High quality KG is of crucial importance for many knowledge-based applications, e.g., question answering, recommender systems, etc. This paper studies the problem of entity alignment in KGs to promote knowledge fusion. Existing methods model the semantic representation of entities by using graph structural information or attribute information of the KG and then align the entities across different domains by calculating the distances between entities’ embeddings. However, these methods only consider the node-to-node similarity in the alignment procedure while the edge-to-edge similarity is ignored. Our research hypothesis is that the graph edge alignment information is critical in entity alignment. We reformulate the knowledge entity alignment as a quadratic assignment problem (QAP) by adding relation alignment under the one-to-one mapping constraint. To solve the notorious QAP in a large-scale heterogeneous graph like KG, we propose a model, dual neighborhood consensus network (DNCN), which approximately decomposes the QAP into two small-scale linear assignment problems, i.e., entity alignment and relation alignment. After that, an edge-coloring propagation method is proposed to refine the coarse entity alignment result using the relation correspondence. Theoretical proof shows that this method can guarantee the isomorphism between local sub-graphs. The performance of DNCN is evaluated using the DBP15K and DWY100K benchmarks. Experimental results show that DNCN achieves the best performance on the DBP15K benchmark, and is computationally efficient. Ablation studies verify the importance of graph edge alignment information.

Research on Intelligentization of Cloud Computing Programs Based on Self-awareness

Abstract Through the research of MapReduce programming framework of cloud computing, the current MapReduce program only solves specific problems, and there is no design experience or design feature summary of MapReduce program, let alone formal description and experience inheritance and application of knowledge base. In order to solve the problem of intelligent cloud computing program, a general MapReduce program generation method is designed. This paper proposes the architecture of intelligent cloud computing by studying AORBCO model and combining cloud computing technology. According to the behavior control mechanism in AORBCO model, a program generation method of MapReduce in intelligent cloud computing is proposed. This method will extract entity information in input data set and entity information in knowledge base in intelligent cloud computing for similarity calculation, and extract the entity in the top order as key key-value pair information in intelligent cloud computing judgment data set. The data processing types are divided, and then aligned with each specific MapReduce capability, and the MapReduce program generation experiment is verified in the AORBCO model development platform. The experiment shows that the complexity of big data MapReduce program code is simplified, and the generated code execution efficiency is good.

PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction

Link prediction in knowledge hypergraphs is essential for various knowledge-based applications, including question answering and recommendation systems. However, many current approaches simply extend binary relation methods from knowledge graphs to n-ary relations, which does not allow for capturing entity positional and role information in n-ary tuples. To address this issue, we introduce PosKHG, a method that considers entities’ positions and roles within n-ary tuples. PosKHG uses an embedding space with basis vectors to represent entities’ positional and role information through a linear combination, which allows for similar representations of entities with related roles and positions. Additionally, PosKHG employs a relation matrix to capture the compatibility of both information with all associated entities and a scoring function to measure the plausibility of tuples made up of entities with specific roles and positions. PosKHG achieves full expressiveness and high prediction efficiency. In experimental results, PosKHG achieved an average improvement of 4.1% on MRR compared to other state-of-the-art knowledge hypergraph embedding methods. Our code is available at https://anonymous.4open.science/r/PosKHG-C5B3/.

Graph-based algorithm for the understanding of failures in the ATLAS infrastructure

The ATLAS Technical Coordination Expert System is a knowledge-based application which describes and simulates the ATLAS experiment based on its components and their relationships with differing levels of granularity but with an emphasis on general infrastructure. It facilitates the sharing of knowledge and improves the communication among experts with different backgrounds and domains of expertise. The developed software has become essential for the planning of interventions as it gives easily insight into their consequences. Furthermore, it has also proven to be useful for exploring the most effective ways to improve the ATLAS operation and reliability by identifying points of failure with significant impact. The underlying database describes more than 13,000 elements with 89,000 relationships among them. It combines information from diverse domains such as detector control and safety systems, gas and water supplies, cooling, ventilation, cryogenics, and electricity distribution. As the most recent addition, a tool to identify the most probable cause of a failure state has been developed. This paper discusses the graph-based algorithm currently implemented by that tool and shows its behaviour based on the parameters entered by the user. An example in form of a real failure event is given which demonstrates the potential of the Expert System for understanding major failures faster in urgent situations.

Approximate Reasoning for Large-Scale ABox in OWL DL Based on Neural-Symbolic Learning

The ontology knowledge base (KB) can be divided into two parts: TBox and ABox, where the former models schema-level knowledge within the domain, and the latter is a set of statements of assertions or facts about instances. ABox reasoning is a process of discovering implicit knowledge in ABox based on the existing KB, which is of great value in KB applications. ABox reasoning is influenced by both the complexity of TBox and scale of ABox. The traditional logic-based ontology reasoning methods are usually designed to be provably sound and complete but suffer from long algorithm runtimes and do not scale well for ontology KB represented by OWL DL (Description Logic). In some application scenarios, the soundness and completeness of reasoning results are not the key constraints, and it is acceptable to sacrifice them in exchange for the improvement of reasoning efficiency to some extent. Based on this view, an approximate reasoning method for large-scale ABox in OWL DL KBs was proposed, which is named the ChunfyReasoner (CFR). The CFR introduces neural-symbolic learning into ABox reasoning and integrates the advantages of symbolic systems and neural networks (NNs). By training the NN model, the CFR approximately compiles the logic deduction process of ontology reasoning, which can greatly improve the reasoning speed while ensuring higher reasoning quality. In this paper, we state the basic idea, framework, and construction process of the CFR in detail, and we conduct experiments on two open-source ontologies built on OWL DL. The experimental results verify the effectiveness of our method and show that the CFR can support the applications of large-scale ABox reasoning of OWL DL KBs.

Malaysian Women's Viewpoint on HPV Screening and Vaccination: A Study on Barriers.

Cervical cancer is the second most common cancer in low-income countries and the third most common cancer in Malaysia among women aged 15 to 44. This is a huge concern because of the high mortality rate compared to other countries. Cervical cancer is caused by a common sexually transmitted human papillomavirus (HPV). Of cervical cancer cases, 80% are attributed to serotypes 16 and 18; therefore, early detection of premalignant lesions and infections from these viruses is important. Diagnosis can be carried out by polymerase chain reaction (PCR)-based HPV DNA analysis and Pap smear, which act as a viable preventive strategy. (1) Background: This study determined the adoption of the human papillomavirus (HPV) vaccine and the willingness to get vaccinated in Malaysian women. (2) Methods: An online survey was conducted with women from across Malaysia to gather their views on the barriers that prevent them from accessing HPV services. Sentiment analysis was performed to detect and classify the comments into three groups (positive, neutral, and negative). (3) Results: A total of 449 opinions were received, and the findings revealed that 41.3% were not afraid to be diagnosed early, and were prepared to accept positive or negative screening results. In addition, 18.6% of those surveyed indicated that they feared a Pap smear and were very concerned that they would not get good results. Of the respondents, 36% believed in vaccination and preferred to know more about it; 43.24% claimed that their family members were very supportive towards screening and vaccination; and 21.3% felt embarrassed and were afraid to undergo the screening procedure, as they had no prior experience and were unsure of how the procedure was conducted. In addition, 40.5% indicated that they had no concerns about HPV testing and related procedures, as this information is widely available. Only a few respondents (8.1%) talked about the time constraints and busy work schedules that prevented them from going to medical appointments. The survey also revealed that women are prevented from participating in cervical cancer screening and vaccination programs due to a lack of knowledge, shyness, personal rumors, privacy issues, financial issues, a lack of access to medical services, and ignorance and beliefs about rumors spreading online. (4) Conclusion: Results indicate that awareness of HPV and related prevention measures among women is vague and that negative perceptions continue to exist. It is strongly advised to develop a well-designed and knowledge-based application on the efficacy of screening and vaccination among Malaysian women.

Development of a Knowledge System for Data Management of the Pre-Production Stages

Preparation of projects introducing new production takes into account all aspects related to development and technical preparation of production, production of prototypes, familiarization with production, processing marketing sales support, as well as preparation of service support. PLM systems represent the tools for automating engineering activities in the product life cycle. These solutions are based on the idea of a close cooperation between individual areas involved in the final product, from its design to the end of its technical life. Collecting a large amount of data and information about the product under observation is typical for this kind of activity. PLM integrates the areas of computer aid, database and information systems, and computer networks. This article points to the creation of a knowledge-based application environment for data management of a small business with a description of its functions and possibilities of use.

Solving Ontology Metamatching Problem through Improved Multiobjective Particle Swarm Optimization Algorithm

In recent years, knowledge representation in the Artificial Intelligence (AI) domain is able to help people understand the semantics of data and improve the interoperability between diverse knowledge-based applications. Semantic Web (SW), as one of the methods of knowledge representation, is the new generation of World Wide Web (WWW), which integrates AI with web techniques and dedicates to implementing the automatic cooperations among different intelligent applications. Ontology, as an information exchange model that defines concepts and formally describes the relationships between two concepts, is the core technique of SW, implementing semantic information sharing and data interoperability in the Internet of Things (IoT) domain. However, the heterogeneity issue hampers the communications among different ontologies and stops the cooperations among ontology-based intelligent applications. To solve this problem, it is vital to establish semantic relationships between heterogeneous ontologies, which is the so-called ontology matching. Ontology metamatching problem is commonly a complex optimization problem with many local optima. To this end, the ontology metamatching problem is defined as a multiobjective optimization model in this work, and a multiobjective particle swarm optimization (MOPSO) with diversity enhancing (DE) (MOPSO-DE) strategy is proposed to better trade off the convergence and diversity of the population. The well-known benchmark of the Ontology Alignment Evaluation Initiative (OAEI) is used in the experiment to test MOPSO-DE’s performance. Experimental results prove that MOPSO-DE can obtain the high-quality alignment and reduce the MOPSO’s memory consumption.

Bousi[formula omitted]Prolog: Design and implementation of a proximity-based fuzzy logic programming language

The fuzzy logic programming language Bousi∼Prolog extends Prolog with a weak unification algorithm based on proximity relations and truth degree annotations. The weak unification algorithm makes the search for answers more flexible, while rule annotations make possible knowledge-based applications where the rules may be uncertain. In this paper, after recalling the main concepts supporting this language, we detail its design and implementation. We describe the implementation of its operational semantics, which is based on compiling programs and queries into Prolog, and those important features that makes it more applicable: fuzzy sets, integration with WordNet and efficiency techniques. The result is a high-level open-source implementation of the Bousi∼Prolog system, written on top of SWI-Prolog, and publicly available. We also summarise some experiments measuring its performance compared to other systems.

Abrasive wear behavior of EN42 steel used in agricultural discs in field conditions

Comprehension wear mechanisms in worn portion is an important area of thermo-mechanical and microstructural research, especially in agricultural knowledge-based applications of abrasive micro-mechanisms of soil engaging tools is scarce. In the current study, wear in different makes (M1, M2, M3, and M4) of EN42 agricultural discs was to see whether there's a difference in weight, radius, thickness, and microstructure with the goal of extending the lifespan. The tests were conducted in a rice-harvested field using a 7 × 7-disc harrow having a speed of 4.5 km/h, soil moisture content was 12–14 % and depth of operation was 10 cm, and duration of operation was 100 h. The cumulative weight, radius, and thickness reduction on M4 make was 547.75 g, 1.78 mm, and 0.55 mm respectively. The make M4 showing minimum wear and maximum working life (3.14 times more than the life of disc M1) was found the best suitable for farm operations followed by M3, M2, and M1.

Property Assertion Constraints for ontologies and knowledge graphs

PurposeThe curation of ontologies and knowledge graphs (KGs) is an essential task for industrial knowledge-based applications, as they rely on the contained knowledge to be correct and error-free. Often, a significant amount of a KG is curated by humans. Established validation methods, such as Shapes Constraint Language, Shape Expressions or Web Ontology Language, can detect wrong statements only after their materialization, which can be too late. Instead, an approach that avoids errors and adequately supports users is required.Design/methodology/approachFor solving that problem, Property Assertion Constraints (PACs) have been developed. PACs extend the range definition of a property with additional logic expressed with SPARQL. For the context of a given instance and property, a tailored PAC query is dynamically built and triggered on the KG. It can determine all values that will result in valid property value assertions.FindingsPACs can avoid the expansion of KGs with invalid property value assertions effectively, as their contained expertise narrows down the valid options a user can choose from. This simplifies the knowledge curation and, most notably, relieves users or machines from knowing and applying this expertise, but instead enables a computer to take care of it.Originality/valuePACs are fundamentally different from existing approaches. Instead of detecting erroneous materialized facts, they can determine all semantically correct assertions before materializing them. This avoids invalid property value assertions and provides users an informed, purposeful assistance. To the author's knowledge, PACs are the only such approach.

A study on application programming interface recommendation: state-of-the-art techniques, challenges and future directions

PurposeThis study aims to identify the developer’s objectives, current state-of-the-art techniques, challenges and performance evaluation metrics, and presents outlines of a knowledge-based application programming interfaces (API) recommendation system for the developers. Moreover, the current study intends to classify current state-of-the-art techniques supporting automated API recommendations.Design/methodology/approachIn this study, the authors have performed a systematic literature review of studies, which have been published between the years 2004–2021 to achieve the targeted research objective. Subsequently, the authors performed the analysis of 35 primary studies.FindingsThe outcomes of this study are: (1) devising a thematic taxonomy based on the identified developers’ challenges, where mashup-oriented APIs and time-consuming process are frequently encountered challenges by the developers; (2) categorizing current state-of-the-art API recommendation techniques (i.e. clustering techniques, data preprocessing techniques, similarity measurements techniques and ranking techniques); (3) designing a taxonomy based on the identified objectives, where accuracy is the most targeted objective in API recommendation context; (4) identifying a list of evaluation metrics employed to assess the performance of the proposed techniques; (5) performing a SWOT analysis on the selected studies; (6) based on the developer’s challenges, objectives and SWOT analysis, presenting outlines of a recommendation system for the developers and (7) delineating several future research dimensions in API recommendations context.Research limitations/implicationsThis study provides complete guidance to the new researcher in the context of API recommendations. Also, the researcher can target these objectives (accuracy, response time, method recommendation, compatibility, user requirement-based API, automatic service recommendation and API location) in the future. Moreover, the developers can overcome the identified challenges (including mashup-oriented API, Time-consuming process, learn how to use the API, integrated problem, API method usage location and limited usage of code) in the future by proposing a framework or recommendation system. Furthermore, the classification of current state-of-the-art API recommendation techniques also helps the researchers who wish to work in the future in the context of API recommendation.Practical implicationsThis study not only facilitates the researcher but also facilitates the practitioners in several ways. The current study guides the developer in minimizing the development time in terms of selecting relevant APIs rather than following traditional manual selection. Moreover, this study facilitates integrating APIs in a project. Thus, the recommendation system saves the time for developers, and increases their productivity.Originality/valueAPI recommendation remains an active area of research in web and mobile-based applications development. The authors believe that this study acts as a useful tool for the interested researchers and practitioners as it will contribute to the body of knowledge in API recommendations context.

Regulatory Approval With Real-World Data From Regulatory Science Perspective in Japan

Recently, there has been a growing trend in clinical development to utilize real-world data (RWD) to improve the efficiency of drug/medical device development. Especially, the use of RWD to generate real-world evidence (RWE) in regulatory approval is currently undergoing a period of great change with an increasing degree of active discussion. In Japan, RWE has been used in the control arms of clinical trials, observational studies, post-marketing surveillance, and public knowledge-based applications for regulatory approval. However, the exclusive use of RWE applications has still not been applied. In this paper, we summarize the history and the current situation of RWE and focus on the utilization for the purpose of regulatory approval. In addition, we will discuss the issues and perspectives for registry research in the utilization for regulatory approval in Japan.

IFGAN: Information fusion generative adversarial network for knowledge base completion

AbstractKnowledge base completion (KBC) aims to predict missing information in a knowledge base. From a data governance perspective, KBC is an important task not only in knowledge management but also in downstream knowledge base applications. The prosperity of mobile applications and online systems enables devices to generate an enormous volume of data containing valuable knowledge. However, these data are vast and contain noise, so utilizing them in KBC requires particular skill. In this paper, we propose information fusion generative adversarial network (IFGAN) to handle heterogeneous data. We design a bidirectional learning architecture including a graph convolutional neural network and graph attention network to learn contextual embeddings that fuse knowledge from a knowledge base and data generated by an application. For efficient negative sampling, we employ different kinds of convolution structures, such as depthwise separable convolution and involution in the generator of the network. The convolution structure is known to be suitable for collaborative computing and promises great potential with the progress of technology since the structure is extensible. We demonstrate the effectiveness of the proposed model on KB4Rec dataset, the evaluation metrics MRR and H@10 were improved compared with previous models; the code is available at https://github.com/Tianchen627/IFGAN.