Information

29 pages, 1341 KiB

Open AccessArticle

Applied Hedge Algebra Approach with Multilingual Large Language Models to Extract Hidden Rules in Datasets for Improvement of Generative AI Applications

by Hai Van Pham and Philip Moore

Information 2024, 15(7), 381; https://doi.org/10.3390/info15070381 (registering DOI) - 29 Jun 2024

Abstract

Generative AI applications have played an increasingly significant role in real-time tracking applications in many domains including, for example, healthcare, consultancy, dialog boxes (common types of window in a graphical user interface of operating systems), monitoring systems, and emergency response. This paper considers [...] Read more.

Generative AI applications have played an increasingly significant role in real-time tracking applications in many domains including, for example, healthcare, consultancy, dialog boxes (common types of window in a graphical user interface of operating systems), monitoring systems, and emergency response. This paper considers generative AI and presents an approach which combines hedge algebra and a multilingual large language model to find hidden rules in big data for ChatGPT. We present a novel method for extracting natural language knowledge from large datasets by leveraging fuzzy sets and hedge algebra to extract these rules, presented in meta data for ChatGPT and generative AI applications. The proposed model has been developed to minimize the computational and staff costs for medium-sized enterprises which are typically resource and time limited. The proposed model has been designed to automate question–response interactions for rules extracted from large data in a multiplicity of domains. The experimental results show that the proposed model performs well using datasets associated with specific domains in healthcare to validate the effectiveness of the proposed model. The ChatGPT application in case studies of healthcare is tested using datasets for English and Vietnamese languages. In comparative experimental testing, the proposed model outperformed the state of the art, achieving in the range of 96.70–97.50% performance using a heart dataset. Full article

(This article belongs to the Special Issue Applications of Information Extraction, Knowledge Graphs, and Large Language Models)

23 pages, 1552 KiB

Open AccessArticle

Improving the Selection of PV Modules and Batteries for Off-Grid PV Installations Using a Decision Support System

by Luis Serrano-Gomez, Isabel C. Gil-García, M. Socorro García-Cascales and Ana Fernández-Guillamón

Information 2024, 15(7), 380; https://doi.org/10.3390/info15070380 (registering DOI) - 29 Jun 2024

Abstract

In the context of isolated photovoltaic (PV) installations, selecting the optimal combination of modules and batteries is crucial for ensuring efficient and reliable energy supply. This paper presents a Decision Support System (DSS) designed to aid in the selection process of the development [...] Read more.

In the context of isolated photovoltaic (PV) installations, selecting the optimal combination of modules and batteries is crucial for ensuring efficient and reliable energy supply. This paper presents a Decision Support System (DSS) designed to aid in the selection process of the development of new PV isolated installations. Two different multi-criteria decision-making (MCDM) approaches are employed and compared: AHP (Analytic Hierarchy Process) combined with TOPSIS (technique for order of preference by similarity to ideal solution) and Entropy combined with TOPSIS. AHP and Entropy are used to weight the technical and economic criteria considered, and TOPSIS ranks the alternatives. A comparative analysis of the AHP + TOPSIS and Entropy + TOPSIS methods was conducted to determine their effectiveness and applicability in real-world scenarios. The results show that AHP and Entropy produce contrasting criteria weights, yet TOPSIS converges on similar top-ranked alternatives using either set of weights, with the combination of lithium-ion batteries with the copper indium gallium selenide PV module as optimal. AHP allows for the incorporation of expert subjectivity, prioritising costs and an energy yield intuitive to PV projects. Entropy’s objectivity elevates criteria with limited data variability, potentially misrepresenting their true significance. Despite these discrepancies, this study highlights the practical implications of using structured decision support methodologies in optimising renewable energy systems. Even though the proposed methodology is applied to a PV isolated system, it can effectively support decision making for optimising other stand-alone or grid-connected installations, contributing to the advancement of sustainable energy solutions. Full article

(This article belongs to the Special Issue Artificial Intelligence and Decision Support Systems)

27 pages, 561 KiB

Open AccessReview

Exploring Federated Learning Tendencies Using a Semantic Keyword Clustering Approach

by Francisco Enguix, Carlos Carrascosa and Jaime Rincon

Information 2024, 15(7), 379; https://doi.org/10.3390/info15070379 (registering DOI) - 28 Jun 2024

Viewed by 63

Abstract

This paper presents a novel approach to analyzing trends in federated learning (FL) using automatic semantic keyword clustering. The authors collected a dataset of FL research papers from the Scopus database and extracted keywords to form a collection representing the FL research landscape. [...] Read more.

This paper presents a novel approach to analyzing trends in federated learning (FL) using automatic semantic keyword clustering. The authors collected a dataset of FL research papers from the Scopus database and extracted keywords to form a collection representing the FL research landscape. They employed natural language processing (NLP) techniques, specifically a pre-trained transformer model, to convert keywords into vector embeddings. Agglomerative clustering was then used to identify major thematic trends and sub-areas within FL. The study provides a granular view of the thematic landscape and captures the broader dynamics of research activity in FL. The key focus areas are divided into theoretical areas and practical applications of FL. The authors make their FL paper dataset and keyword clustering results publicly available. This data-driven approach moves beyond manual literature reviews and offers a comprehensive overview of the current evolution of FL. Full article

(This article belongs to the Special Issue International Database Engineered Applications)

20 pages, 552 KiB

Open AccessReview

Business Model Evolution in the Age of NFTs and the Metaverse

by Mitra Madanchian and Hamed Taherdoost

Information 2024, 15(7), 378; https://doi.org/10.3390/info15070378 (registering DOI) - 28 Jun 2024

Viewed by 54

Abstract

The dynamic progression of technology has induced a profound metamorphosis within the realm of commerce, ushering in novel prospects and trials for enterprises spanning diverse sectors. In contemporary times, the rise in non-fungible tokens (NFTs) and the conception of the Metaverse have ensnared [...] Read more.

The dynamic progression of technology has induced a profound metamorphosis within the realm of commerce, ushering in novel prospects and trials for enterprises spanning diverse sectors. In contemporary times, the rise in non-fungible tokens (NFTs) and the conception of the Metaverse have ensnared the focus of corporate entities and visionary proprietors alike. This article explores the transformation of business frameworks during the era of NFTs and the Metaverse. It delves into traditional paradigms, clarifies the unique characteristics of NFTs, and examines their potential impacts on commerce. This article investigates the convergence of virtual reality (VR), augmented reality (AR), and blockchain technology within the Metaverse. To investigate these transformations, this study undertakes a comprehensive literature evaluation. The findings highlight how NFTs and the Metaverse have introduced new avenues for generating revenue and creating value. These advancements are achieved through the utilization of smart contracts and adaptable strategies that cater to evolving consumer behaviors. This article also addresses significant challenges in this landscape and provides a forward-looking perspective on the anticipated trajectory. Full article

(This article belongs to the Special Issue Feature Papers in Information in 2024–2025)

37 pages, 720 KiB

Open AccessArticle

A Survey of Computationally Efficient Graph Neural Networks for Reconfigurable Systems

by Habib Taha Kose, Jose Nunez-Yanez, Robert Piechocki and James Pope

Information 2024, 15(7), 377; https://doi.org/10.3390/info15070377 (registering DOI) - 28 Jun 2024

Viewed by 92

Abstract

Graph neural networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale and complex nature of graph data demand substantial computational resources and high [...] Read more.

Graph neural networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale and complex nature of graph data demand substantial computational resources and high performance during both training and inference stages, presenting significant challenges, particularly in the context of embedded systems. Recent studies on GNNs have investigated both software and hardware solutions to enhance computational efficiency. Earlier studies on deep neural networks (DNNs) have indicated that methods like reconfigurable hardware and quantization are beneficial in addressing these issues. Unlike DNN research, studies on efficient computational methods for GNNs are less developed and require more exploration. This survey reviews the latest developments in quantization and FPGA-based acceleration for GNNs, showcasing the capabilities of reconfigurable systems (often FPGAs) to offer customized solutions in environments marked by significant sparsity and the necessity for dynamic load management. It also emphasizes the role of quantization in reducing both computational and memory demands through the use of fixed-point arithmetic and streamlined vector formats. This paper concentrates on low-power, resource-limited devices over general hardware accelerators and reviews research applicable to embedded systems. Additionally, it provides a detailed discussion of potential research gaps, foundational knowledge, obstacles, and prospective future directions. Full article

(This article belongs to the Special Issue Artificial Intelligence on the Edge)

20 pages, 13167 KiB

Open AccessArticle

O₂SAT: Object-Oriented-Segmentation-Guided Spatial-Attention Network for 3D Object Detection in Autonomous Vehicles

by Husnain Mushtaq, Xiaoheng Deng, Irshad Ullah, Mubashir Ali and Babur Hayat Malik

Information 2024, 15(7), 376; https://doi.org/10.3390/info15070376 (registering DOI) - 28 Jun 2024

Viewed by 104

Abstract

Autonomous vehicles (AVs) strive to adapt to the specific characteristics of sustainable urban environments. Accurate 3D object detection with LiDAR is paramount for autonomous driving. However, existing research predominantly relies on the 3D object-based assumption, which overlooks the complexity of real-world road environments. [...] Read more.

Autonomous vehicles (AVs) strive to adapt to the specific characteristics of sustainable urban environments. Accurate 3D object detection with LiDAR is paramount for autonomous driving. However, existing research predominantly relies on the 3D object-based assumption, which overlooks the complexity of real-world road environments. Consequently, current methods experience performance degradation when targeting only local features and overlooking the intersection of objects and road features, especially in uneven road conditions. This study proposes a 3D Object-Oriented-Segmentation Spatial-Attention (

O_{2}

SAT) approach to distinguish object points from road points and enhance the keypoint feature learning by a channel-wise spatial attention mechanism.

O_{2}

SAT consists of three modules: Object-Oriented Segmentation (OOS), Spatial-Attention Feature Reweighting (SFR), and Road-Aware 3D Detection Head (R3D). OOS distinguishes object and road points and performs object-aware downsampling to augment data by learning to identify the hidden connection between landscape and object; SFR performs weight augmentation to learn crucial neighboring relationships and dynamically adjust feature weights through spatial attention mechanisms, which enhances the long-range interactions and contextual feature discrimination for noise suppression, improving overall detection performance; and R3D utilizes refined object segmentation and optimized feature representations. Our system forecasts prediction confidence into existing point-backbones. Our method’s effectiveness and robustness across diverse datasets (KITTI) has been demonstrated through vast experiments. The proposed modules seamlessly integrate into existing point-based frameworks, following a plug-and-play approach. Full article

(This article belongs to the Special Issue Modeling, Design, Analysis and Management of Embedded Control Systems for Automated Driving)

► Show Figures

Figure 1

13 pages, 876 KiB

Open AccessArticle

Fault Line Selection Method for Power Distribution Network Based on Graph Transformation and ResNet50 Model

by Haozhi Wang, Yuntao Shi and Wei Guo

Information 2024, 15(7), 375; https://doi.org/10.3390/info15070375 - 28 Jun 2024

Viewed by 99

Abstract

Low-current grounding systems are the main grounding method used in power distribution networks and belong to non-direct grounding systems. The most common fault in this type of system is a single-phase grounding fault, which may cause electrical fires and endanger personal safety. Due [...] Read more.

Low-current grounding systems are the main grounding method used in power distribution networks and belong to non-direct grounding systems. The most common fault in this type of system is a single-phase grounding fault, which may cause electrical fires and endanger personal safety. Due to the difficulty of troubleshooting, the selection of fault lines in low-current grounding systems has always been an important research topic in power system relay protection. This study proposes a new approach for fault identification of power lines based on the Euler transformation and deep learning. Firstly, the current signals of the distribution network are rapidly Fourier-transformed to obtain their frequencies for constructing reference signals. Then, the current signals are combined with the reference signals and transformed into images using Euler transformation in the complex plane. The images are then classified using a residual network model. The convolutional neural network in the model can automatically extract fault feature vectors, thus achieving the identification of faulty lines. The simulation was conducted based on the existing model, and extensive data training and testing were performed. The experimental results show that this method has good stability, fast convergence speed, and high accuracy. This technology can effectively accomplish fault identification in power distribution networks. Full article

(This article belongs to the Special Issue Applications of Machine Learning and Convolutional Neural Networks)

► Show Figures

Figure 1

21 pages, 3243 KiB

Open AccessArticle

Intelligent Text Mining for Ontological Knowledge Graph Refinement and Patent Portfolio Analysis—Case Study of Net-Zero Data Center Innovation Management

by Amy J. C. Trappey, Ging-Bin Lin and Li-Ping Hung

Information 2024, 15(7), 374; https://doi.org/10.3390/info15070374 - 28 Jun 2024

Viewed by 146

Abstract

Ontological knowledge graph (OKG) is a well-formed visual representation that depicts knowledge organization in formal elements (e.g., entities and attributes) and their interrelationships. OKG is crucial for innovation management analysis as it provides a clear boundary to understand complex knowledge domain in detail. [...] Read more.

Ontological knowledge graph (OKG) is a well-formed visual representation that depicts knowledge organization in formal elements (e.g., entities and attributes) and their interrelationships. OKG is crucial for innovation management analysis as it provides a clear boundary to understand complex knowledge domain in detail. In the patent analysis field, it facilitates the definition of a well-defined patent portfolio, aiming for accurate and complete patent retrievals and subsequent analyses. In recent decade, the rapid growth of the information and communication technology (ICT) sector has rendered data centers (DCs) indispensable for data processing, storage, and cloud computing, while ensuring security and privacy during DC operations. However, their energy-intensive operations pose challenges to global efforts toward achieving net-zero emissions goals. In response, this research develops a formal OKG refinement process and uses DC net-zero technology OKG as case study for in-depth OKG refinement and application in patent portfolio analysis. The net-zero DC domain covers five sub-technologies. Utilizing the proposed OKG refinement and patent portfolio analysis framework, the 1801 most recent decade’s patents related to relevant “DC net-zero technologies” are retrieved and analyzed. Particularly in this case, DC colocation and server-as-a-service perspectives are the newly discovered sub-domains for OKG refinement. Furthermore, the research also adopts the technology function matrix and technology maturity to assess current and future technology development trends, providing crucial insights supporting strategic innovation management. Full article

(This article belongs to the Special Issue Knowledge Graph Technology and its Applications II)

► Show Figures

Figure 1

18 pages, 4559 KiB

Open AccessArticle

Trends of Social Anxiety in University Students of Pakistan Post-COVID-19 Lockdown: A Healthcare Analytics Perspective

by Ikram E. Khuda, Azeem Aftab, Sajid Hasan, Samar Ikram, Sadique Ahmad, Abdelhamied Ashraf Ateya and Muhammad Asim

Information 2024, 15(7), 373; https://doi.org/10.3390/info15070373 - 28 Jun 2024

Viewed by 129

Abstract

This paper disseminates our research findings that we conducted on university students in the years 2021, 2022, and 2023, with the year 2021 taken as the base year. Our research mined and excavated a concealed prevalence of social anxiety as an important and [...] Read more.

This paper disseminates our research findings that we conducted on university students in the years 2021, 2022, and 2023, with the year 2021 taken as the base year. Our research mined and excavated a concealed prevalence of social anxiety as an important and crucial facet of study anxiety in the university students of Pakistan. Using the Liebowitz Social Anxiety Scale (LSAS), we found a significant increase in the social anxiety level among university students in the past three years after the COVID-19 lockdown. Our data showed that the ‘very severe anxiety’ level soared up to 52.94% in the year 2023 from just 5.98% in the year 2021, showing a net increase of 47.06%. Statistical analyses demonstrate noteworthy differences in the overall social anxiety levels among the students, reaching significance at the 5% level and a discernable upward trend in the social anxiety levels as study anxiety. We also employed predictive analytics, including binary classifiers and generalized linear models with a 95% confidence interval, to identify individuals at risk. This study highlights a dynamic shift with escalating social anxiety levels among the university students and thus emphasizing its awareness, which is significantly important for the timely intervention, potentially preventing symptom escalation and improving outcomes. Full article

(This article belongs to the Special Issue Health Data Information Retrieval)

► Show Figures

Figure 1

20 pages, 1066 KiB

Open AccessArticle

Mining Spatial-Temporal Frequent Patterns of Natural Disasters in China Based on Textual Records

by Aiai Han, Wen Yuan, Wu Yuan, Jianwen Zhou, Xueyan Jian, Rong Wang and Xinqi Gao

Information 2024, 15(7), 372; https://doi.org/10.3390/info15070372 - 27 Jun 2024

Viewed by 150

Abstract

Natural disasters pose serious threats to human survival. With global warming, disaster chains related to extreme weather are becoming more common, making it increasingly urgent to understand the relationships between different types of natural disasters. However, there remains a lack of research on [...] Read more.

Natural disasters pose serious threats to human survival. With global warming, disaster chains related to extreme weather are becoming more common, making it increasingly urgent to understand the relationships between different types of natural disasters. However, there remains a lack of research on the frequent spatial-temporal intervals between different disaster events. In this study, we utilize textual records of natural disaster events to mine frequent spatial-temporal patterns of disasters in China. We first transform the discrete spatial-temporal disaster events into a graph structure. Due to the limit of computing power, we reduce the number of edges in the graph based on domain expertise. We then apply the GraMi frequent subgraph mining algorithm to the spatial-temporal disaster event graph, and the results reveal frequent spatial-temporal intervals between disasters and reflect the spatial-temporal changing pattern of disaster interactions. For example, the pattern of sandstorms happening after gales is mainly concentrated within 50 km and rarely happens at farther spatial distances, and the most common temporal interval is 1 day. The statistical results of this study provide data support for further understanding disaster association patterns and offer decision-making references for disaster prevention efforts. Full article

22 pages, 1425 KiB

Open AccessArticle

Towards Reliable Healthcare LLM Agents: A Case Study for Pilgrims during Hajj

by Hanan M. Alghamdi and Abeer Mostafa

Information 2024, 15(7), 371; https://doi.org/10.3390/info15070371 - 26 Jun 2024

Viewed by 236

Abstract

There is a pressing need for healthcare conversational agents with domain-specific expertise to ensure the provision of accurate and reliable information tailored to specific medical contexts. Moreover, there is a notable gap in research ensuring the credibility and trustworthiness of the information provided [...] Read more.

There is a pressing need for healthcare conversational agents with domain-specific expertise to ensure the provision of accurate and reliable information tailored to specific medical contexts. Moreover, there is a notable gap in research ensuring the credibility and trustworthiness of the information provided by these healthcare agents, particularly in critical scenarios such as medical emergencies. Pilgrims come from diverse cultural and linguistic backgrounds, often facing difficulties in accessing medical advice and information. Establishing an AI-powered multilingual chatbot can bridge this gap by providing readily available medical guidance and support, contributing to the well-being and safety of pilgrims. In this paper, we present a comprehensive methodology aimed at enhancing the reliability and efficacy of healthcare conversational agents, with a specific focus on addressing the needs of Hajj pilgrims. Our approach leverages domain-specific fine-tuning techniques on a large language model, alongside synthetic data augmentation strategies, to optimize performance in delivering contextually relevant healthcare information by introducing the HajjHealthQA dataset. Additionally, we employ a retrieval-augmented generation (RAG) module as a crucial component to validate uncertain generated responses, which improves model performance by 5%. Moreover, we train a secondary AI agent on a well-known health fact-checking dataset and use it to validate medical information in the generated responses. Our approach significantly elevates the chatbot’s accuracy, demonstrating its adaptability to a wide range of pilgrim queries. We evaluate the chatbot’s performance using quantitative and qualitative metrics, highlighting its proficiency in generating accurate responses and achieve competitive results compared to state-of-the-art models, in addition to mitigating the risk of misinformation and providing users with trustworthy health information. Full article

(This article belongs to the Special Issue Applications of Information Extraction, Knowledge Graphs, and Large Language Models)

► Show Figures

Figure 1

13 pages, 1520 KiB

Open AccessArticle

A Study of Delayed Competitive Influence Propagation Based on Shortest Path Calculation

by Yang Li and Zhiqiang Wang

Information 2024, 15(7), 370; https://doi.org/10.3390/info15070370 - 26 Jun 2024

Viewed by 163

Abstract

In social network applications, competitive influence propagation often exhibits a certain degree of time lag. In the scenario of positive and negative competitive propagation studied in this paper, under the premise that negative nodes are activated first, how to find a set of [...] Read more.

In social network applications, competitive influence propagation often exhibits a certain degree of time lag. In the scenario of positive and negative competitive propagation studied in this paper, under the premise that negative nodes are activated first, how to find a set of positive seed nodes to participate in competitive propagation is studied, aiming to minimize the spread of negative influence. In the current study, the time complexity of the improved algorithms based on greedy strategies is high, which limits their scope of application in practical scenarios; some heuristic algorithms achieve better scalability, but there is still much room for improvement. Therefore, this paper proposes a new method to solve the influence propagation problem of delayed competition, also known as a heuristic propagation factor evaluation algorithm (HeuPFE). The main process is as follows: (1) We build a shortest path snapshot for the nearest propagation region of negative nodes and reduce the search space of competing nodes. (2) Then, we construct a node propagation factor evaluation method based on this shortest negative-oriented node path snapshot to reduce computational complexity. Comparing results with those of traditional heuristic algorithms, we carry out experiments on real datasets and verify the effectiveness of the proposed method. Full article

► Show Figures

Figure 1

23 pages, 1189 KiB

Open AccessArticle

A Data-Driven Approach to Set-Theoretic Model Predictive Control for Nonlinear Systems

by Francesco Giannini and Domenico Famularo

Information 2024, 15(7), 369; https://doi.org/10.3390/info15070369 - 23 Jun 2024

Viewed by 388

Abstract

In this paper, we present a data-driven model predictive control (DDMPC) framework specifically designed for constrained single-input single-output (SISO) nonlinear systems. Our approach involves customizing a set-theoretic receding horizon controller within a data-driven context. To achieve this, we translate model-based conditions into data [...] Read more.

In this paper, we present a data-driven model predictive control (DDMPC) framework specifically designed for constrained single-input single-output (SISO) nonlinear systems. Our approach involves customizing a set-theoretic receding horizon controller within a data-driven context. To achieve this, we translate model-based conditions into data series of available input and output signals. This translation process leverages recent advances in data-driven control theory, enabling the controller to operate effectively without relying on explicit system models. The proposed framework incorporates a robust methodology for managing system constraints, ensuring that the control actions remain within predefined bounds. By means of time sequences, the controller learns the underlying system dynamics and adapts to changes in real time, providing enhanced performance and reliability. The integration of set-theoretic methods allows for the systematic handling of uncertainties and disturbances, which are common when the trajectory of a nonlinear system is embedded inside a linear trajectory state tube. To validate the effectiveness of our DDMPC framework, we conduct extensive simulations on a nonlinear DC motor system. The results demonstrate significant improvements in control performance, highlighting the robustness and adaptability of our approach compared to traditional model-based MPC techniques. Full article

(This article belongs to the Special Issue Second Edition of Predictive Analytics and Data Science)

16 pages, 857 KiB

Open AccessArticle

Applying Machine Learning in Marketing: An Analysis Using the NMF and k-Means Algorithms

by Victor Gallego, Jessica Lingan, Alfons Freixes, Angel A. Juan and Celia Osorio

Information 2024, 15(7), 368; https://doi.org/10.3390/info15070368 - 22 Jun 2024

Viewed by 320

Abstract

The integration of machine learning (ML) techniques into marketing strategies has become increasingly relevant in modern business. Utilizing scientific manuscripts indexed in the Scopus database, this article explores how this integration is being carried out. Initially, a focused search is undertaken for academic [...] Read more.

The integration of machine learning (ML) techniques into marketing strategies has become increasingly relevant in modern business. Utilizing scientific manuscripts indexed in the Scopus database, this article explores how this integration is being carried out. Initially, a focused search is undertaken for academic articles containing both the terms “machine learning” and “marketing” in their titles, which yields a pool of papers. These papers have been processed using the Supabase platform. The process has included steps like text refinement and feature extraction. In addition, our study uses two key ML methodologies: topic modeling through NMF and a comparative analysis utilizing the k-means clustering algorithm. Through this analysis, three distinct clusters emerged, thus clarifying how ML techniques are influencing marketing strategies, from enhancing customer segmentation practices to optimizing the effectiveness of advertising campaigns. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) for Economics and Business Management)

17 pages, 3327 KiB

Open AccessArticle

Automated Knowledge Extraction in the Field of Wheat Sharp Eyespot Control

by Keyi Liu and Yunpeng Cui

Information 2024, 15(7), 367; https://doi.org/10.3390/info15070367 - 21 Jun 2024

Viewed by 371

Abstract

Wheat sharp eyespot is a soil-borne fungal disease commonly found in wheat areas in China, which can occur throughout the entire reproductive period of wheat and has a great impact on the yield and quality of wheat in China. By constructing a domain [...] Read more.

Wheat sharp eyespot is a soil-borne fungal disease commonly found in wheat areas in China, which can occur throughout the entire reproductive period of wheat and has a great impact on the yield and quality of wheat in China. By constructing a domain ontology for wheat sharp eyespot control and modeling the domain knowledge, we aim to integrate and share the knowledge in the field of wheat sharp eyespot control, which can provide important support and guidance for agricultural decision-making and disease control. In this study, the literature in the field of wheat sharp eyespot control was used as a data source, the KeyBERT keyword extraction algorithm was used to mine the core concepts of the ontology, and the hierarchical relationships among the ontology concepts were extracted through clustering. Based on the constructed ontology of wheat sharp eyespot control, the schema of knowledge extraction was formed, and the knowledge extraction model was trained using the ERNIE 3.0 knowledge enhancement pretraining model. This study proposes a model and algorithm to realize knowledge extraction based on domain ontology, describes the construction method and process framework of wheat sharp eyespot control domain ontology, and details the training and reasoning effect of the knowledge extraction model. The knowledge extraction model constructed in this study for wheat sharp eyespot control contains a more complete conceptual system of wheat sharp eyespot. The F1 value of the model reaches 91.26%, which is a 17.86% improvement compared with the baseline model, and it can satisfy the knowledge extraction needs in the field of wheat sharp eyespot control. This study can provide a reference for domain knowledge extraction and provide strong support for knowledge discovery and downstream applications such as intelligent Q&A and intelligent recommendation in the field of wheat sharp eyespot control. Full article

(This article belongs to the Special Issue Text Mining: Challenges, Algorithms, Tools and Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Information, Volume 15, Issue 7 (July 2024) – 15 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI