Electronics

Research

Jump to: Review

18 pages, 1196 KB

Open AccessArticle

Automatic Metadata Extraction Leveraging Large Language Models in Digital Humanities

by Adriana Morejón, Borja Navarro-Colorado, Carmen García-Barceló, Alberto Berenguer, David Tomás and Jose-Norberto Mazón

Electronics 2025, 14(24), 4962; https://doi.org/10.3390/electronics14244962 - 18 Dec 2025

Viewed by 895

Abstract

DCAT-based data ecosystems, such as open data portals and data spaces, have shown their potential to foster data economy by supporting the FAIR (Findability, Accessibility, Interoperability, Reusability) principles. Nevertheless, there are domains where metadata are tailored to specific semantics of the domain, resulting [...] Read more.

DCAT-based data ecosystems, such as open data portals and data spaces, have shown their potential to foster data economy by supporting the FAIR (Findability, Accessibility, Interoperability, Reusability) principles. Nevertheless, there are domains where metadata are tailored to specific semantics of the domain, resulting in the absence of DCAT-based catalogs that adhere to FAIR principles. A particularly relevant case is that of the digital humanities, where texts encoded in TEI (Text Encoding Initiative) constitute a consolidated standard in the field of literature. However, TEI metadata are not always well aligned with the FAIR principles, nor easily integrated into interoperable catalogs that enable seamless combination with external datasets. To address this gap, our approach aims to (i) generate DCAT catalogs derived from TEI by identifying which metadata can be mapped and how, and (ii) explore the use of Large Language Models (LLMs) to assist in the generation and enrichment of metadata when transforming TEI to DCAT. Our approach contributes to catalog-level harmonization, enabling domain-specific standards such as TEI to be aligned with cross-domain standards like DCAT, thus facilitating adherence to FAIR principles. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

25 pages, 4430 KB

Open AccessArticle

NOVA: A Novel Multi-Scale Adaptive Vision Architecture for Accurate and Efficient Automated Diagnosis of Malaria Using Microscopic Blood Smear Images

by Md Nayeem Hosen, Md Ariful Islam Mozumder, Proloy Kumar Mondal and Hee Cheol Kim

Electronics 2025, 14(24), 4861; https://doi.org/10.3390/electronics14244861 - 10 Dec 2025

Viewed by 431

Abstract

Background: Malaria continues to be a significant global health concern, particularly in tropical and subtropical areas. Timely and accurate diagnosis is crucial in minimizing the disease’s mortality. The standard method, microscopic diagnosis, which represents the gold standard, is heavily reliant on skilled interpretation, [...] Read more.

Background: Malaria continues to be a significant global health concern, particularly in tropical and subtropical areas. Timely and accurate diagnosis is crucial in minimizing the disease’s mortality. The standard method, microscopic diagnosis, which represents the gold standard, is heavily reliant on skilled interpretation, labor-intensive, and prone to human error. Methods: To address these challenges, we propose the NOVA (Novel Multi-Scale Adaptive Vision Architecture) for the diagnosis of malaria. NOVA is based on an innovative dynamic channel attention and Learnable Temperature Spatial Pyramid Attention to achieve more powerful feature representation and better classification performance. In addition, adaptive feature refinement and enhanced transformer blocks are used to obtain multi-scale feature extraction and contextual reasoning. Furthermore, a multi-strategy pooling mechanism that fuses average, max, and attention-based aggregation is developed to enhance the model’s discriminative capability. Results: We conduct experiments on a publicly accessible dataset of 15,031 microscopic thin blood smear images to validate the effectiveness of the proposed approach. The model is assessed and compared on a benchmark malaria microscopy dataset, achieving an accuracy of 97.00%, a precision of 96.00%, and an F1-score of 97.00%, outperforming other existing models. Conclusions: The experimental results demonstrate the feasibility of the proposed approach as a potential research prototype for the automated diagnosis of malaria. Before clinical deployment, further multi-site clinical evaluation on a large patient cohort is required for validation. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

19 pages, 1279 KB

Open AccessArticle

Fusing a Slimming Network and Large Language Models for Intelligent Decision Support in Industrial Safety and Preventive Monitoring

by Weijun Tian, Jia Yin, Wei Wang, Zhonghua Guo, Liqiang Zhu and Jianbo Li

Electronics 2025, 14(23), 4773; https://doi.org/10.3390/electronics14234773 - 4 Dec 2025

Viewed by 410

Abstract

Intelligent personnel safety management is a critical component of smart manufacturing infrastructure. This paper presents an integrated framework combining a structurally optimized neural network (enhanced with spatial and channel feature fusion mechanisms for multi-scale detection) with an agent-based large language model (LLM) enhanced [...] Read more.

Intelligent personnel safety management is a critical component of smart manufacturing infrastructure. This paper presents an integrated framework combining a structurally optimized neural network (enhanced with spatial and channel feature fusion mechanisms for multi-scale detection) with an agent-based large language model (LLM) enhanced with retrieval-augmented generation (RAG) capabilities for factory safety monitoring. The visual detection component employs the Similarity-Aware Channel Pruning (SACP) method for automated, performance-preserving compression by identifying and suppressing redundant channels based on similarity and norm regularization, while the agent-based LLM with RAG capabilities dynamically integrates real-time violation data with established safety management protocols to generate precise diagnostic reports and operational recommendations. The optimized network achieves real-time violation detection in parallel video streams, and the LLM-powered assistant facilitates intelligent decision-making through natural language querying. Extensive evaluations on multiple benchmark datasets and a real-world safety helmet detection dataset demonstrate the scheme’s superior performance in both accuracy and practical applicability for industrial deployment. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

23 pages, 1197 KB

Open AccessArticle

Signal Surface Augmentation for Artificial Intelligence-Based Automatic Modulation Classification

by Alexander Gros, Véronique Moeyaert and Patrice Mégret

Electronics 2025, 14(23), 4760; https://doi.org/10.3390/electronics14234760 - 3 Dec 2025

Viewed by 590

Abstract

Automatic modulation recognition has regained attention as a critical application for cognitive radio, combining artificial intelligence with physical layer monitoring of wireless transmissions. This paper formalizes signal surface augmentation (SSA), a process that decomposes signals into informative subcomponents to enhance AI-based analysis. We [...] Read more.

Automatic modulation recognition has regained attention as a critical application for cognitive radio, combining artificial intelligence with physical layer monitoring of wireless transmissions. This paper formalizes signal surface augmentation (SSA), a process that decomposes signals into informative subcomponents to enhance AI-based analysis. We employ Bivariate Empirical Mode Decomposition (BEMD) to break signals into intrinsic modes while addressing challenges like adjacent trends in long sample decompositions and introducing the concept of data overdispersion. Using a modern, publicly available dataset of synthetic modulated signals under realistic conditions, we validate that the presentation of BEMD-derived components improves recognition accuracy by 13% compared to raw IQ inputs. For extended signal lengths, gains reach up to 36%. These results demonstrate the value of signal surface augmentation for improving the robustness of modulation recognition, with potential applications in real-world scenarios. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

20 pages, 695 KB

Open AccessArticle

Threshold Dynamic Multi-Source Decisive Prototypical Network

by Qibing Ma, Guangyang Pang and Xinyue Liu

Electronics 2025, 14(20), 4077; https://doi.org/10.3390/electronics14204077 - 17 Oct 2025

Viewed by 547

Abstract

To address the issue that prototypical networks in existing few-shot text classification methods suffer from performance limitations due to prototype shift and metric constraints, this paper proposes a meta-learning-based few-shot text classification method: Threshold Dynamic Multi-Source Decisive Prototypical Network (TDMP-Net) to solve these [...] Read more.

To address the issue that prototypical networks in existing few-shot text classification methods suffer from performance limitations due to prototype shift and metric constraints, this paper proposes a meta-learning-based few-shot text classification method: Threshold Dynamic Multi-Source Decisive Prototypical Network (TDMP-Net) to solve these problems. This method designs two core components: the threshold dynamic data augmentation module and the multi-source information Decider. Specifically, the threshold dynamic data augmentation module achieves the optimization of the prototype estimation process by leveraging the multi-source information of query set samples, which thereby alleviates the prototype shift problem; meanwhile, the multi-source information Decider performs classification by relying on the multi-source information of the query set, thus alleviating the metric constraint problem. The effectiveness of the proposed method is verified on four benchmark datasets: under the five-way one-shot and five-way five-shot settings, TDMP-Net achieves average accuracies of 78.3% and 86.5%, respectively, which are an average improvement of 3.3 percentage points compared with current state-of-the-art methods. Experimental results show that this TDMP-Net can effectively alleviate the prototype shift problem and metric constraint problems, and has stronger generalization ability. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

9 pages, 430 KB

Open AccessArticle

An Algorithm for the Integration of Data from Surgical Robots and Operation Room Management Systems

by Paola Picozzi, Umberto Nocco, Chiara Labate, Greta Puleo and Veronica Cimolin

Electronics 2025, 14(15), 2926; https://doi.org/10.3390/electronics14152926 - 22 Jul 2025

Viewed by 857

Abstract

This study presents an algorithm developed by the Clinical Engineering department to automatically match surgical events recorded by robotic systems with corresponding entries in the hospital’s OR management software. At ASST Grande Ospedale Metropolitano Niguarda, robotic procedures were previously identified manually by surgical [...] Read more.

This study presents an algorithm developed by the Clinical Engineering department to automatically match surgical events recorded by robotic systems with corresponding entries in the hospital’s OR management software. At ASST Grande Ospedale Metropolitano Niguarda, robotic procedures were previously identified manually by surgical staff within the operating room management system, often leading to frequent inconsistencies and data quality issues. Two heterogeneous datasets—robot logs and hospital procedure records—were aligned using common features such as date, duration, and operating room, despite the absence of a unique identifier. The matching algorithm enables accurate identification of robotic procedures within the hospital system and facilitates integration of clinical and technical data into a unified framework. This integrated approach supports more effective data utilization for clinical engineering activities, operational monitoring, and Health Technology Assessment (HTA) analyses. The work provides a practical solution to a real-world data integration challenge and lays the foundation for future developments, including the application of machine learning to enhance matching precision. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

16 pages, 1058 KB

Open AccessArticle

Multi-Scale Context Enhancement Network with Local–Global Synergy Modeling Strategy for Semantic Segmentation on Remote Sensing Images

by Qibing Ma, Hongning Liu, Yifan Jin and Xinyue Liu

Electronics 2025, 14(13), 2526; https://doi.org/10.3390/electronics14132526 - 21 Jun 2025

Cited by 1 | Viewed by 918

Abstract

Semantic segmentation of remote sensing images is a fundamental task in geospatial analysis and Earth observation research, and has a wide range of applications in urban planning, land cover classification, and ecological monitoring. In complex geographic scenes, low target-background discriminability in overhead views [...] Read more.

Semantic segmentation of remote sensing images is a fundamental task in geospatial analysis and Earth observation research, and has a wide range of applications in urban planning, land cover classification, and ecological monitoring. In complex geographic scenes, low target-background discriminability in overhead views (e.g., indistinct boundaries, ambiguous textures, and low contrast) significantly complicates local–global information modeling and results in blurred boundaries and classification errors in model predictions. To address this issue, in this paper, we proposed a novel Multi-Scale Local–Global Mamba Feature Pyramid Network (MLMFPN) through designing a local–global information synergy modeling strategy, and guided and enhanced the cross-scale contextual information interaction in the feature fusion process to obtain quality semantic features to be used as cues for precise semantic reasoning. The proposed MLMFPN comprises two core components: Local–Global Align Mamba Fusion (LGAMF) and Context-Aware Cross-attention Interaction Module (CCIM). Specifically, LGAMF designs a local-enhanced global information modeling through asymmetric convolution for synergistic modeling of the receptive fields in vertical and horizontal directions, and further introduces the Vision Mamba structure to facilitate local–global information fusion. CCIM introduces positional encoding and cross-attention mechanisms to enrich the global-spatial semantics representation during multi-scale context information interaction, thereby achieving refined segmentation. The proposed methods are evaluated on the ISPRS Potsdam and Vaihingen datasets and the outperformance in the results verifies the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

18 pages, 898 KB

Open AccessArticle

Q-Learning Approach Applied to Network Security

by Zheni Utic and Ayomide Oyemaja

Electronics 2025, 14(10), 1996; https://doi.org/10.3390/electronics14101996 - 14 May 2025

Cited by 1 | Viewed by 1070

Abstract

Network security and intrusion detection and response (IDR) are necessary issues nowadays. Enhancing our cyber defense by discovering advanced machine learning models, such as reinforcement learning and Q-learning, is a crucial security measure. This study proposes a novel intrusion response method by implementing [...] Read more.

Network security and intrusion detection and response (IDR) are necessary issues nowadays. Enhancing our cyber defense by discovering advanced machine learning models, such as reinforcement learning and Q-learning, is a crucial security measure. This study proposes a novel intrusion response method by implementing an off-policy Q-learning approach. We test the validity of our model by conducting a goodness-of-fit analysis and proving its efficiency. By performing sensitivity analysis, we prove that it is possible to protect our network successfully and establish an immediate response mechanism that could be successfully implemented in intrusion response (IR) systems. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

25 pages, 4899 KB

Open AccessArticle

Development of Machine Learning-Based Indicators for Predicting Comeback Victories Using the Bounty Mechanism in MOBA Games

by Junhyuk Lee and Namhyoung Kim

Electronics 2025, 14(7), 1445; https://doi.org/10.3390/electronics14071445 - 3 Apr 2025

Cited by 4 | Viewed by 4464

Abstract

Multiplayer Online Battle Arena (MOBA) games, exemplified by titles such as League of Legends and Dota 2, have attained global popularity and have been formally recognized as an official event in the 2022 Hangzhou Asian Games, thus establishing their significance in the esports [...] Read more.

Multiplayer Online Battle Arena (MOBA) games, exemplified by titles such as League of Legends and Dota 2, have attained global popularity and have been formally recognized as an official event in the 2022 Hangzhou Asian Games, thus establishing their significance in the esports industry. In this study, we proposed a machine learning-based model for predicting comeback victories by leveraging the object bounty mechanism, a critical yet underexplored aspect of previous research. By closely examining the game environment following the activation of the bounty system, we identified pivotal variables and constructed novel indicators that contribute to successful comebacks. Furthermore, an individualized case analysis based on SHapley Additive exPlanations (SHAP) provides new insights to support strategic in-game decision-making and enhance the player experience. The experimental results demonstrate that the indicators introduced in this study, such as the weighted team champion mastery and similarity in champion mastery among the team’s main champions, significantly influence the likelihood of a comeback victory. By capturing the intrinsic dynamism of MOBA games, the proposed model is expected to improve player engagement and satisfaction. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

18 pages, 1833 KB

Open AccessArticle

Hybrid CNN-BiGRU-AM Model with Anomaly Detection for Nonlinear Stock Price Prediction

by Jiacheng Luo, Yun Cao, Kai Xie, Chang Wen, Yunzhe Ruan, Jinpeng Ji, Jianbiao He and Wei Zhang

Electronics 2025, 14(7), 1275; https://doi.org/10.3390/electronics14071275 - 24 Mar 2025

Cited by 8 | Viewed by 2846

Abstract

To address challenges in stock price prediction including data nonlinearity and anomalies, we propose a hybrid CNN-BiGRU-AM framework integrated with deep learning-based anomaly detection. First, an anomaly detection module identifies irregularities in stock price data. The CNN component then extracts local features while [...] Read more.

To address challenges in stock price prediction including data nonlinearity and anomalies, we propose a hybrid CNN-BiGRU-AM framework integrated with deep learning-based anomaly detection. First, an anomaly detection module identifies irregularities in stock price data. The CNN component then extracts local features while filtering anomalous information, followed by nonlinear pattern modeling through BiGRU with attention mechanisms. Final predictions undergo secondary anomaly screening to ensure reliability. Experimental evaluation on Shanghai Composite (SSE) daily closing prices demonstrates superior performance with

R^{2}

= 0.9903, RMSE = 22.027, MAE = 19.043, and a Sharpe Ratio of 0.65. It is noteworthy that the MAE of this model is reduced by 14.7%, and the RMSE is decreased by 7.7% compared to its ablation model. The framework achieves multi-level feature extraction through convolutional operations and bidirectional temporal modeling, effectively enhancing model generalization via nonlinear mapping and anomaly correction. Comparative Sharpe Ratio analysis across models provides practical insights for investment decision-making. This dual-functional system not only improves prediction accuracy but also offers interpretable references for market mechanism analysis and regulatory policy formulation. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

30 pages, 7287 KB

Open AccessEditor’s ChoiceArticle

Context-Aware Tomato Leaf Disease Detection Using Deep Learning in an Operational Framework

by Divas Karimanzira

Electronics 2025, 14(4), 661; https://doi.org/10.3390/electronics14040661 - 8 Feb 2025

Cited by 14 | Viewed by 3635

Abstract

Tomato cultivation is a vital agricultural practice worldwide, yet it faces significant challenges due to various diseases that adversely affect crop yield and quality. This paper presents a novel tomato disease detection system within an operational framework that leverages an innovative deep learning-based [...] Read more.

Tomato cultivation is a vital agricultural practice worldwide, yet it faces significant challenges due to various diseases that adversely affect crop yield and quality. This paper presents a novel tomato disease detection system within an operational framework that leverages an innovative deep learning-based classifier, specifically a Vision Transformer (ViT) integrated with cascaded group attention (CGA) and a modified Focaler-CIoU (Complete Intersection over Union) loss function. The proposed method aims to enhance the accuracy and robustness of disease detection by effectively capturing both local and global contextual information while addressing the challenges of sample imbalance in the dataset. To improve interpretability, we integrate Explainable Artificial Intelligence (XAI) techniques, enabling users to understand the rationale behind the model’s classifications. Additionally, we incorporate a large language model (LLM) to generate comprehensive, context-aware explanations and recommendations based on the identified diseases and other relevant factors, thus bridging the gap between technical analysis and user comprehension. Our evaluation against state-of-the-art deep learning methods, including convolutional neural networks (CNNs) and other transformer-based models, demonstrates that the ViT-CGA model significantly outperforms existing techniques, achieving an overall accuracy of 96.5%, an average precision of 93.9%, an average recall of 96.7%, and an average F1-score of 94.2% for tomato leaf disease classification. The integration of CGA and Focaler-CIoU loss not only contributes to improved model interpretability and stability but also empowers farmers and agricultural stakeholders with actionable insights, fostering informed decision making in disease management. This research advances the field of automated disease detection in crops and provides a practical framework for deploying deep learning solutions in agricultural settings, ultimately supporting sustainable farming practices and enhancing food security. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

17 pages, 2479 KB

Open AccessArticle

A Study on the Factors Influencing Rank Prediction in PlayerUnknown’s Battlegrounds

by Ji-Na Lee and Ji-Yeoun Lee

Electronics 2025, 14(3), 626; https://doi.org/10.3390/electronics14030626 - 5 Feb 2025

Cited by 1 | Viewed by 2870

Abstract

This study analyzes the key factors influencing player rank prediction in PlayerUnknown’s Battlegrounds (PUBG), using machine learning models to evaluate in-game performance. By examining variables such as “walkDistance”, “boosts”, and “weaponsAcquired”, the study identifies these as critical predictors, with “walkDistance” emerging [...] Read more.

This study analyzes the key factors influencing player rank prediction in PlayerUnknown’s Battlegrounds (PUBG), using machine learning models to evaluate in-game performance. By examining variables such as “walkDistance”, “boosts”, and “weaponsAcquired”, the study identifies these as critical predictors, with “walkDistance” emerging as the most significant across all match types. Utilizing models including random forest (RF), gradient descent (GD), extreme gradient boosting (XGBoost), and feedforward neural network (FNN), the analysis reveals performance variation by match type: XGBoost achieves the highest accuracy in solo matches (88.07%), GD performs best in duo matches (84.75%), and RF records the highest accuracy in squad matches (78.21%). These findings provide valuable insights for game developers in balancing gameplay and offer personalized strategic recommendations for players. Future research may enhance predictive performance by incorporating additional variables and exploring alternative models applicable to PUBG and similar battle royale games. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

25 pages, 5363 KB

Open AccessArticle

Power-Optimized Field-Programmable Gate Array Implementation of Neural Activation Functions Using Continued Fractions for AI/ML Workloads

by Chanakya Hingu, Xingang Fu, Taofiki Saliyu, Rui Hu and Ramkrishna Mishan

Electronics 2024, 13(24), 5026; https://doi.org/10.3390/electronics13245026 - 20 Dec 2024

Cited by 3 | Viewed by 1334

Abstract

The increasing demand for energy-efficient hardware platforms to support artificial intelligence (AI) and machine learning (ML) algorithms in edge computing has driven the adoption of system-on-chip (SoC) architectures. Implementing neural network (NN) activation functions, such as the hyperbolic tangent (tanh), on hardware presents [...] Read more.

The increasing demand for energy-efficient hardware platforms to support artificial intelligence (AI) and machine learning (ML) algorithms in edge computing has driven the adoption of system-on-chip (SoC) architectures. Implementing neural network (NN) activation functions, such as the hyperbolic tangent (tanh), on hardware presents challenges due to computational complexity, high resource requirements, and power consumption. This paper aims to optimize the hardware implementation of the tanh function using continued fraction and polynomial approximations to minimize resource consumption and power usage while preserving computational accuracy. Five models of the tanh function, including continued fraction and quadratic approximations, were implemented on Intel field-programmable gate arrays (FPGAs) using VHDL and Intel’s ALTFP toolbox, with 32-bit floating-point outputs validated against MATLAB’s 64-bit floating-point results. Detailed analyses of resource utilization, power optimization, clock latency, and bit-level accuracy were conducted, focusing on minimizing logic elements and digital signal processing (DSP) blocks while achieving high precision and low power consumption. The most optimized model was further integrated into a four-input, two-output recurrent neural network (RNN) structure to assess real-time performance. Experimental results demonstrate that the continued fraction-based models significantly reduce resource usage, computation time, and power consumption, enhancing FPGA performance for AI/ML applications in resource-constrained and power-sensitive environments. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

24 pages, 2131 KB

Open AccessArticle

Improving Text Classification in Agricultural Expert Systems with a Bidirectional Encoder Recurrent Convolutional Neural Network

by Xiaojuan Guo, Jianping Wang, Guohong Gao, Li Li, Junming Zhou and Yancui Li

Electronics 2024, 13(20), 4054; https://doi.org/10.3390/electronics13204054 - 15 Oct 2024

Cited by 3 | Viewed by 1996

Abstract

With the rapid development of internet and AI technologies, Agricultural Expert Systems (AESs) have become crucial for delivering technical support and decision-making in agricultural management. However, traditional natural language processing methods often struggle with specialized terminology and context, and they lack the adaptability [...] Read more.

With the rapid development of internet and AI technologies, Agricultural Expert Systems (AESs) have become crucial for delivering technical support and decision-making in agricultural management. However, traditional natural language processing methods often struggle with specialized terminology and context, and they lack the adaptability to handle complex text classifications. The diversity and evolving nature of agricultural texts make deep semantic understanding and integration of contextual knowledge especially challenging. To tackle these challenges, this paper introduces a Bidirectional Encoder Recurrent Convolutional Neural Network (AES-BERCNN) tailored for short-text classification in agricultural expert systems. We designed an Agricultural Text Encoder (ATE) with a six-layer transformer architecture to capture both preceding and following word information. A recursive convolutional neural network based on Gated Recurrent Units (GRUs) was also developed to merge contextual information and learn complex semantic features, which are then combined with the ATE output and refined through max-pooling to form the final feature representation. The AES-BERCNN model was tested on a self-constructed agricultural dataset, achieving an accuracy of 99.63% in text classification. Its generalization ability was further verified on the Tsinghua News dataset. Compared to other models such as TextCNN, DPCNN, BiLSTM, and BERT-based models, the AES-BERCNN shows clear advantages in agricultural text classification. This work provides precise and timely technical support for intelligent agricultural expert systems. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

► Show Figures

Figure 1

Review

Jump to: Research

49 pages, 1910 KB

Open AccessReview

Beyond Next-Token Prediction: A Standards-Aligned Survey of Autoregressive LLM Failure Modes, Deployment Patterns, and the Potential Role of World Models

by Lorenzo Ricciardi Celsi and James McCann

Electronics 2026, 15(5), 966; https://doi.org/10.3390/electronics15050966 - 26 Feb 2026

Abstract

This paper is a focused, standards-aligned survey of where autoregressive (AR) large language models (LLMs) tend to break down when deployed inside industrial informatics workflows that must satisfy long-horizon objectives, hard constraints, traceability, and functional-safety obligations (e.g., IEC 61508/ISO 26262/ISO 21448). Rather than [...] Read more.

This paper is a focused, standards-aligned survey of where autoregressive (AR) large language models (LLMs) tend to break down when deployed inside industrial informatics workflows that must satisfy long-horizon objectives, hard constraints, traceability, and functional-safety obligations (e.g., IEC 61508/ISO 26262/ISO 21448). Rather than claiming new algorithms or experiments, we synthesize and organize prior work into (i) a control-oriented taxonomy of four AR failure modes that recur in practice (compounding error, myopic objectives, data brittleness/hallucinations, and scaling/latency inefficiencies), (ii) a catalog of standards-compatible deployment patterns that mitigate these issues (human-gated LLM-in-the-loop, retrieval + verification pipelines, planner-of-record architectures, and runtime assurance envelopes), and (iii) an operational decision framework (criteria table with observable proxies, a stepwise decision procedure, and worked examples) for deciding when token-centric mitigations are sufficient versus when state/world-model components become warranted. Joint Embedding Predictive Architectures (JEPA) and Hierarchical JEPA (H-JEPA) JEPA are proposed as representative state-predictive architectures, with discussion explicitly bounded by currently available empirical evidence; we explicitly note that the published evidence base is currently concentrated on vision/multimodal benchmarks and that industrial control validation remains limited. To make evidence boundaries transparent, we introduce (a) a survey method (scope, inclusion/exclusion criteria, and data-extraction fields), (b) a comparison matrix across representative prior systems, and (c) an evidence map that links each deployment pattern to peer-reviewed empirical findings and system reports. Full article

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition for Intelligent Systems)

Journal Menu

Journal Browser

Artificial Intelligence and Pattern Recognition for Intelligent Systems

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (15 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI