Semantic Agent Research Articles

Semantic agent framework for automated flood assessment using dynamic knowledge graphs

Abstract This article proposes a framework of linked software agents that continuously interact with an underlying knowledge graph to automatically assess the impacts of potential flooding events. It builds on the idea of connected digital twins based on the World Avatar dynamic knowledge graph to create a semantically rich asset of data, knowledge, and computational capabilities accessible to humans, applications, and artificial intelligence. We develop three new ontologies to describe and link environmental measurements and their respective reporting stations, flood events, and their potential impact on population and built infrastructure as well as the built environment of a city itself. These coupled ontologies are deployed to dynamically instantiate near real-time data from multiple fragmented sources into the World Avatar. Sequences of autonomous agents connected via the derived information framework automatically assess consequences of newly instantiated data, such as newly raised flood warnings, and cascade respective updates through the graph to ensure up-to-date insights into the number of people and building stock value at risk. Although we showcase the strength of this technology in the context of flooding, our findings suggest that this system-of-systems approach is a promising solution to build holistic digital twins for various other contexts and use cases to support truly interoperable and smart cities.

ChatGPT and the Writing of Philosophical Essays

Text-generative AI-systems have become important semantic agents with ChatGPT. We conducted a series of experiments to learn what teachers’ conceptions of text-generative AI are in relation to philosophical texts. In our main experiment, using mixed methods, we had twenty-four high school students write philosophical essays, which we then randomized to essays with the same command from ChatGPT. We had ten prospective teachers assess these essays. They were able to tell whether it was an AI or student essay with 78.7 percent accuracy, which is better than the Open AI Classifier. Interestingly, however, they used criteria like argumentative and logical flawlessness and neutrality. We concluded from this that they are using an inverted Turing test and are no longer looking for rationality in machines but for irrationality in humans.

Incremental sentence processing is guided by a preference for agents: EEG evidence from Basque

ABSTRACTComprehenders across languages tend to interpret role-ambiguous arguments as the subject or the agent of a sentence during parsing. However, the evidence for such a subject/agent preference rests on the comprehension of transitive, active-voice sentences where agents/subjects canonically precede patients/objects. The evidence is thus potentially confounded by the canonical order of arguments. Transitive sentence stimuli additionally conflate the semantic agent role and the syntactic subject function. We resolve these two confounds in an experiment on the comprehension of intransitive sentences in Basque. When exposed to sentence-initial role-ambiguous arguments, comprehenders preferentially interpreted these as agents and had to revise their interpretation when the verb disambiguated to patient-initial readings. The revision was reflected in an N400 component in ERPs and a decrease in power in the alpha and lower beta bands. This finding suggests that sentence processing is guided by a top-down heuristic to interpret ambiguous arguments as agents, independently of word order and independently of transitivity.

Marie and BERT-A Knowledge Graph Embedding Based Question Answering System for Chemistry.

This paper presents a novel knowledge graph question answering (KGQA) system for chemistry, which is implemented on hybrid knowledge graph embeddings, aiming to provide fact-oriented information retrieval for chemistry-related research and industrial applications. Unlike other existing designs, the system operates on multiple embedding spaces, which use various embedding methods and queries the embedding spaces in parallel. With the answers returned from multiple embedding spaces, the system leverages a score alignment model to adjust the answer scores and rerank the answers. Further, the system implements an algorithm to derive implicit multihop relations to handle the complexities of deep ontologies and improve multihop question answering. The system also implements a BERT-based bidirectional entity-linking model to enhance the robustness and accuracy of the entity-linking module. The system uses a joint numerical embedding model to efficiently handle numerical filtering questions. Further, it can invoke semantic agents to perform dynamic calculations autonomously. Finally, the KGQA system handles numerous chemical reaction mechanisms using semantic parsing supported by a Linked Data Fragment server. This paper evaluates the accuracy of each module within the KGQA system with a chemistry question data set.

Tense-aspect conditioned agent marking in Kanakanavu, an Austronesian language of Taiwan

Abstract This article examines two types of lexical effects in the voice system of Kanakanavu, an Austronesian language of Taiwan. The first concerns a well-attested phenomenon in the Austronesian literature: interactions between the semantic transitivity of verbs and their ability (or lack thereof) to undergo voice alternation. The second concerns a phenomenon that is typologically and areally rare in the western Austronesian context – differential agent marking. The pronominal agent in Kanakanavu’s patient-/undergoer-voice construction is differentially case-marked depending on the tense-aspect value of the clause. However, lexical effects are found in how the differentially marked agent is interpreted. When dynamic verbs are used, omitted agents in perfective clauses are interpreted as coreferential with a specific referent mentioned in prior discourse, but those in non-perfective clauses are interpreted as having generic reference, backgrounded, and/or not centrally involved in the situation expressed by the verb. When stative verbs are used, alternation between perfective and imperfective verb forms may have various effects on the interpretation of the agent. In some stative verbs, the agent is interpreted as a prototypical semantic agent in the perfective, but as a semantic experiencer in the imperfective. In other stative verbs, the perfective/non-perfective alternation has to do with whether a change of state is involved, without having any effects on agent interpretation. This study explores how lexical effects manifest across both elicited and natural discourse data. It also presents the phenomenon of differential agent marking in Kanakanavu as neither typical nor representative in the western Austronesian context.

A New AI-Based Semantic Cyber Intelligence Agent

The surge in cybercrime has emerged as a pressing concern in contemporary society due to its far-reaching financial, social, and psychological repercussions on individuals. Beyond inflicting monetary losses, cyber-attacks exert adverse effects on the social fabric and psychological well-being of the affected individuals. In order to mitigate the deleterious consequences of cyber threats, adoption of an intelligent agent-based solution to enhance the speed and comprehensiveness of cyber intelligence is advocated. In this paper, a novel cyber intelligence solution is proposed, employing four semantic agents that interact autonomously to acquire crucial cyber intelligence pertaining to any given country. The solution leverages a combination of techniques, including a convolutional neural network (CNN), sentiment analysis, exponential smoothing, latent Dirichlet allocation (LDA), term frequency-inverse document frequency (TF-IDF), Porter stemming, and others, to analyse data from both social media and web sources. The proposed method underwent evaluation from 13 October 2022 to 6 April 2023, utilizing a dataset comprising 37,386 tweets generated by 30,706 users across 54 languages. To address non-English content, a total of 8199 HTTP requests were made to facilitate translation. Additionally, the system processed 238,220 cyber threat data from the web. Within a remarkably brief duration of 6 s, the system autonomously generated a comprehensive cyber intelligence report encompassing 7 critical dimensions of cyber intelligence for countries such as Russia, Ukraine, China, Iran, India, and Australia.

Question answering system for chemistry—A semantic agent extension

This paper introduces an extension of a previously developed question answering (QA) system for chemistry, operating on a knowledge graph (KG) called Marie. This extension enables the automatic invocation of semantic agents to answer questions when static data is absent from the KG. The agents are semantically described using the agent ontology, OntoAgent, to enable automated agent discovery and invocation.The natural language processing (NLP) models of the QA system need to be trained in order to interpret questions to be answered by new agents. For this purpose, we extend OntoAgent so that it becomes possible to automatically create training material for the NLP models.We evaluate the extended QA system with two example chemistry-related agents and an evaluation question set. The evaluation result shows that the extension allows the QA system to discover the suitable agent and to invoke the agent by automatically constructing requests from the semantic agent description, thereby increasing the range of questions the QA system can answer.

Efficient Retrieval of Data Using Semantic Search Engine Based on NLP and RDF

With the evolution of Web 3.0, the traditional algorithm of searching Web 2.0 would become obsolete and underperform in retrieving the precise and accurate information from the growing semantic web. It is very reasonable to presume that common users might not possess any understanding of the ontology used in the knowledge base or SPARQL query. Therefore, providing easy access of this enormous knowledge base to all level of users is challenging. The ability for all level of users to effortlessly formulate structure query such as SPARQL is very diverse. In this paper, semantic web based search methodology is proposed which converts user query in natural language into SPARQL query, which could be directed to domain ontology based knowledge base. Each query word is further mapped to the relevant concept or relations in ontology. Score is assigned to each mapping to find out the best possible mapping for the query generation. Mapping with highest score are taken into consideration along with interrogative or other function to finally formulate the user query into SPARQL query. If there is no search result retrieved from the knowledge base, then instead of returning null to the user, the query is further directed to the Web 3.0. The top “k” documents are considered to further converting them into RDF format using Text2Onto tool and the corpus of semantically structured web documents is build. Alongside, semantic crawl agent is used to get <Subject-Predicate-Object> set from the semantic wiki. The Term Frequency Matrix and Co-occurrence Matrix are applied on the corpus following by singular Value decomposition (SVD) to find the results relevant for the user query. The result evaluations proved that the proposed system is efficient in terms of execution time, precision, recall and f-measures.

Real-Time Compliant Stream Processing Agents for Physical Rehabilitation.

Digital rehabilitation is a novel concept that integrates state-of-the-art technologies for motion sensing and monitoring, with personalized patient-centric methodologies emerging from the field of physiotherapy. Thanks to the advances in wearable and portable sensing technologies, it is possible to provide patients with accurate monitoring devices, which simplifies the tracking of performance and effectiveness of physical exercises and treatments. Employing these approaches in everyday practice has enormous potential. Besides facilitating and improving the quality of care provided by physiotherapists, the usage of these technologies also promotes the personalization of treatments, thanks to data analytics and patient profiling (e.g., performance and behavior). However, achieving such goals implies tackling both technical and methodological challenges. In particular, (i) the capability of undertaking autonomous behaviors must comply with strict real-time constraints (e.g., scheduling, communication, and negotiation), (ii) plug-and-play sensors must seamlessly manage data and functional heterogeneity, and finally (iii) multi-device coordination must enable flexible and scalable sensor interactions. Beyond traditional top-down and best-effort solutions, unsuitable for safety-critical scenarios, we propose a novel approach for decentralized real-time compliant semantic agents. In particular, these agents can autonomously coordinate with each other, schedule sensing and data delivery tasks (complying with strict real-time constraints), while relying on ontology-based models to cope with data heterogeneity. Moreover, we present a model that represents sensors as autonomous agents able to schedule tasks and ensure interactions and negotiations compliant with strict timing constraints. Furthermore, to show the feasibility of the proposal, we present a practical study on upper and lower-limb digital rehabilitation scenarios, simulated on the MAXIM-GPRT environment for real-time compliance. Finally, we conduct an extensive evaluation of the implementation of the stream processing multi-agent architecture, which relies on existing RDF stream processing engines.

A Transformative Concept: From Data Being Passive Objects to Data Being Active Subjects

The exploitation of potential societal benefits of Earth observations is hampered by users having to engage in often tedious processes to discover data and extract information and knowledge. A concept is introduced for a transition from the current perception of data as passive objects (DPO) to a new perception of data as active subjects (DAS). This transition would greatly increase data usage and exploitation, and support the extraction of knowledge from data products. Enabling the data subjects to actively reach out to potential users would revolutionize data dissemination and sharing and facilitate collaboration in user communities. The three core elements of the transformative DAS concept are: (1) “intelligent semantic data agents” (ISDAs) that have the capabilities to communicate with their human and digital environment. Each ISDA provides a voice to the data product it represents. It has comprehensive knowledge of the represented product including quality, uncertainties, access conditions, previous uses, user feedbacks, etc., and it can engage in transactions with users. (2) A knowledge base that constructs extensive graphs presenting a comprehensive picture of communities of people, applications, models, tools, and resources and provides tools for the analysis of these graphs. (3) An interaction platform that links the ISDAs to the human environment and facilitates transaction including discovery of products, access to products and derived knowledge, modifications and use of products, and the exchange of feedback on the usage. This platform documents the transactions in a secure way maintaining full provenance.

An agent composition framework for the J-Park Simulator - A knowledge graph for the process industry

Digital twins, Industry 4.0 and Industrial Internet of Things are becoming ever more important in the process industry. The Semantic Web, linked data, knowledge graphs and web services/agents are key technologies for implementing the above concepts. In this paper, we present a comprehensive semantic agent composition framework. It enables automatic agent discovery and composition to generate cross-domain applications. This framework is based on a light-weight agent ontology, OntoAgent, which is an adaptation of the Minimal Service Model (MSM) ontology. The MSM ontology was extended with grounding components to support the execution of an agent while keeping the compatibility with other existing web service description standards and extensibility. We illustrate how the comprehensive agent composition framework can be integrated into the J-Park Simulator (JPS) knowledge graph, for the automatic creation of a composite agent that simulates the dispersion of the emissions of a power plant within a selected spatial area.

Semantic SPA Framework for situational Student-Project Allocation in Education

Web 3.0 technologies have redefined the way classical problems in education are solved. The classical problems are constrained by interoperability challenges that can be addressed using semantic technologies. Student-project allocation (SPA) is one such classical problem in education, whose solution lies in finding a stable matching between student-project pairs. Although many methods exist to solve the SPA problem, recent developments in higher education, such as globalisation, has triggered interoperability challenge because of diversity in student and expert availability across disciplines, campuses, and universities. The author proposes the semantic SPA framework that addresses the interoperability challenge, by leveraging the existing semantic investments made by the educational institutions. The framework standardises the SPA data elements formally using semantic Web concepts, proposes reference ontology for the situational SPA problem, and adopts a semantic Web service approach, using OWL-S, for development. The OWL-S specification enables the automatic discovery, composition, and invocation of the Web services by educational Institutions or semantic agents on the Web, for situational SPA scenarios.

A systematic method for building Internet of Agents applications based on the Linked Open Data approach

The Internet of Agents (IoA) is an emerging paradigm whose objective is to mitigate the deficiencies of devices of Internet of Things (IoT) in terms of reasoning and social capabilities, in order to improve proactivity, intelligence and interoperability. This paper presents the guidelines to develop IoA applications based on described semantic agents following the Linked Open Data (LOD) approach and the specifications of the IoA-OWL ontology—a specialized full ontology that formally defines the main aspects related to a novel approach such as IoA. These guidelines have been drawn up via a systematic method created from the best practices of Agile Software Development Methodologies. This method creates smart, autonomous, collaborative IoA applications based on novel Linked Open Agents (LOAs) that are driven by Linked-Agent Contracts (LACs) and Workflows for Agent Control (WACs). From a practical perspective, our method separates the modeling of components using two levels, microscopic (at agent level) and macroscopic (at agent society level) facilitated the planning, configuring and implementation of each agent in the IoA ecosystem. Moreover, the method facilitates the agent creation automation process, reducing the time required for its development and simplifying the design complexity. These achievements were demonstrated through the modeling of an Ambient Intelligence (AmI) scenario on an office composed by a set of collaborative agents in order to provide smart comfort.

Semantic Agent Based Knowledge Discovery from Big Data on the Web

Semantic Agent Based Knowledge Discovery from Big Data on the Web

Semantical Markov Logic Network for Distributed Reasoning in Cyber-Physical Systems

The challenges associated with developing accurate models for cyber-physical systems are attributable to the intrinsic concurrent and heterogeneous computations of these systems. Even though reasoning based on interconnected domain specific ontologies shows promise in enhancing modularity and joint functionality modelling, it has become necessary to build interoperable cyber-physical systems due to the growing pervasiveness of these systems. In this paper, we propose a semantically oriented distributed reasoning architecture for cyber-physical systems. This model accomplishes reasoning through a combination of heterogeneous models of computation. Using the flexibility of semantic agents as a formal representation for heterogeneous computational platforms, we define autonomous and intelligent agent-based reasoning procedure for distributed cyber-physical systems. Sensor networks underpin the semantic capabilities of this architecture, and semantic reasoning based on Markov logic networks is adopted to address uncertainty in modelling. To illustrate feasibility of this approach, we present a Markov logic based semantic event model for cyber-physical systems and discuss a case study of event handling and processing in a smart home.

Psych verbs, the linking problem, and the acquisition of language

In acquiring language, children must learn to appropriately place the different participants of an event (e.g., causal agent, affected entity) into the correct syntactic positions (e.g., subject, object) so that listeners will know who did what to whom. While many of these mappings can be characterized by broad generalizations, both within and across languages (e.g., semantic agents tend to be mapped onto syntactic subjects), not all verbs fit neatly into these generalizations. One particularly striking example is verbs of psychological state: The experiencer of the state can appear as either the subject (Agnes fears/hates/loves Bartholomew) or the direct object (Agnes frightens/angers/delights Bartholomew). The present studies explore whether this apparent variability in subject/object mapping may actually result from differences in these verbs’ underlying meanings. Specifically, we suggest that verbs like fear describe a habitual attitude towards some entity whereas verbs like frighten describe an externally caused emotional episode. We find that this distinction systematically characterizes verbs in English, Mandarin, and Korean. This pattern is generalized to novel verbs by adults in English, Japanese, and Russian, and even by English-speaking children who are just beginning to acquire psych verbs. This results support a broad role for systematic mappings between semantics and syntax in language acquisition.

Semantic Techniques for IOT Data and Service Management on to Smart System

In 2020 more than 50 billions devices will be connected over the Internet. Every device will be connected to anything, anyone, anytime and anywhere in the world of Internet of Thing or IoT. This network will generate tremendous unstructured or semi structured data that should be shared between different devices/machines for advanced and automated service delivery in the benefits of the user's daily life. Thus, mechanisms for data interoperability and automatic service discovery and delivery should be offered. Although many approaches have been suggested in the state of art, none of these researches provide a fully interoperable, light, flexible and modular Sensing/Actuating as service architecture. Therefore, this paper introduces a new Semantic Multi Agent architecture named OntoSmart for IoT data and service management through service oriented paradigm. It proposes sensors/actuators and scenarios independent flexible context aware and distributed architecture for IoT systems, in particular smart home systems

An industrial information integration approach to in-orbit spacecraft

ABSTRACTTo operate an in-orbit spacecraft, the spacecraft status has to be monitored autonomously by collecting and analysing real-time data, and then detecting abnormities and malfunctions of system components. To develop an information system for spacecraft state detection, we investigate the feasibility of using ontology-based artificial intelligence in the system development. We propose a new modelling technique based on the semantic web, agent, scenarios and ontologies model. In modelling, the subjects of astronautics fields are classified, corresponding agents and scenarios are defined, and they are connected by the semantic web to analyse data and detect failures. We introduce the modelling methodologies and the resulted framework of the status detection information system in this paper. We discuss system components as well as their interactions in details. The system has been prototyped and tested to illustrate its feasibility and effectiveness. The proposed modelling technique is generic which can be extended and applied to the system development of other large-scale and complex information systems.

A semantic frame-based intelligent agent for topic detection

Detecting the topic of documents can help readers construct the background of the topic and facilitate document comprehension. In this paper, we propose a semantic frame-based topic detection (SFTD) that simulates such process in human perception. We take advantage of multiple knowledge sources and extracted discriminative patterns from documents through a highly automated, knowledge-supported frame generation and matching mechanisms. Using a Chinese news corpus containing over 111,000 news articles, we provide a comprehensive performance evaluation which demonstrates that our novel approach can effectively detect the topic of a document by exploiting the syntactic structures, semantic association, and the context within the text. Experimental results show that SFTD is comparable to other well-known topic detection methods.

Energy Efficient Agent Function Block: A semantic agent approach to IEC 61499 function blocks in energy efficient building automation systems

Abstract Automation plays a vital role in improving energy efficiency in buildings. Building Automation Systems (BASs) are drastically growing in size and complexity. The traditional centralized automation systems cannot suitably address this growth due to insufficient flexibility and scalability. IEC 61499 Function Block (FB) is a promising software paradigm for industrial automation that addresses these complexities because of its object-oriented, event-driven and distributed paradigm. However, efficient energy management in a heterogeneous system comprising of many energy consuming components, functioning in highly dynamic and partially predictable environments, requires a higher level of intelligence that FB currently does not possess. To cope with this issue, a software entity called 2eA-FB has been introduced by combining FB, intelligent software agent and semantic web technologies. Being capable of field-level control, communication and reasoning over semantically enriched domain knowledge, 2eA-FB bridges the gap between management and automation layers of BAS and controls the energy consumption for individual energy consuming components, separately and intelligently. This in turn results in more efficient overall energy consumption for the whole system.