Electronics

Research

Jump to: Review

18 pages, 1492 KB

Open AccessArticle

FingerMarks: Robust Multi-Bit Watermarking for Remote Deep Neural Networks

by Qingguang Li, Guangluan Xu and Xiyu Qi

Electronics 2025, 14(24), 4818; https://doi.org/10.3390/electronics14244818 - 7 Dec 2025

Viewed by 130

Abstract

Existing model watermarking methods fail to provide adequate protection for edge intelligence models. This paper innovatively integrates the characteristics of model fingerprinting, proposing a model watermarking method named FingerMarks that enables both model attribution and traceability of edge node users. The method initially [...] Read more.

Existing model watermarking methods fail to provide adequate protection for edge intelligence models. This paper innovatively integrates the characteristics of model fingerprinting, proposing a model watermarking method named FingerMarks that enables both model attribution and traceability of edge node users. The method initially constructs a uniform trigger set and an encoding scheme through fingerprint extraction, which effectively distinguishes the host model from independently trained models. Based on the encoding scheme, distinct user IDs are converted and mapped into specific labels, thereby generating distinct watermark-embedded trigger sets. Watermarks are embedded using a progressive adversarial training strategy. Comprehensive evaluation across multiple datasets confirms the method’s performance, uniqueness, and robustness. Experimental results show that FingerMarks effectively identifies the watermarked model while maintaining superior robustness compared to state-of-the-art alternatives. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

24 pages, 460 KB

Open AccessArticle

An Approach Based on Granular Computing and 2-Tuple Linguistic Model to Personalize Linguistic Information in Group Decision-Making

by Aylin Estrada-Velazco, Yeleny Zulueta-Véliz, José Ramón Trillo and Francisco Javier Cabrerizo

Electronics 2025, 14(23), 4698; https://doi.org/10.3390/electronics14234698 - 28 Nov 2025

Viewed by 192

Abstract

Group decision-making is an inherently collaborative process that can become increasingly complex when addressing the uncertainty associated with linguistic assessments from experts. A crucial principle for achieving a solution of superior quality lies in the acknowledgment that the same word may bear divergent [...] Read more.

Group decision-making is an inherently collaborative process that can become increasingly complex when addressing the uncertainty associated with linguistic assessments from experts. A crucial principle for achieving a solution of superior quality lies in the acknowledgment that the same word may bear divergent meanings among different experts. Regrettably, a significant number of existing methodologies for computing with words presuppose a uniformity of meaning for linguistic assessments across all participating individuals. In response to this limitation, we propose an innovative methodology based on the 2-tuple linguistic model in conjunction with the granular computing paradigm. Given that the individual interpretations of words, when articulating preferences, are closely linked to the consistency of each expert, our proposal places particular emphasis on the modification of the symbolic translation of the 2-tuple linguistic value with the overarching objective of maximizing the consistency of their assessments. This adjustment is implemented while preserving the original linguistic preferences communicated by the experts. We address a real-world building refurbishment problem and conduct a comparative analysis to demonstrate the effectiveness of the proposal. Focusing on consistency enhances group decision-making processes and outcomes, ensuring both accuracy and alignment with individual interpretations and preferences. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

34 pages, 11286 KB

Open AccessArticle

Degradation of Multi-Task Prompting Across Six NLP Tasks and LLM Families

by Federico Di Maio and Manuel Gozzi

Electronics 2025, 14(21), 4349; https://doi.org/10.3390/electronics14214349 - 6 Nov 2025

Viewed by 788

Abstract

This study investigates how increasing prompt complexity affects the performance of Large Language Models (LLMs) across multiple Natural Language Processing (NLP) tasks. We introduce an incremental evaluation framework where six tasks—JSON formatting, English-Italian translation, sentiment analysis, emotion classification, topic extraction, and named entity [...] Read more.

This study investigates how increasing prompt complexity affects the performance of Large Language Models (LLMs) across multiple Natural Language Processing (NLP) tasks. We introduce an incremental evaluation framework where six tasks—JSON formatting, English-Italian translation, sentiment analysis, emotion classification, topic extraction, and named entity recognition—are progressively combined within a single prompt. Six representative open-source LLMs from different families (Llama 3.1 8B, Gemma 3 4B, Mistral 7B, Qwen3 4B, Granite 3.1 3B, and DeepSeek R1 7B) were systematically evaluated using local inference environments to ensure reproducibility. Results show that performance degradation is highly architecture-dependent: while Qwen3 4B maintained stable performance across all tasks, Gemma 3 4B and Granite 3.1 3B exhibited severe collapses in fine-grained semantic tasks. Interestingly, some models (e.g., Llama 3.1 8B and DeepSeek R1 7B) demonstrated positive transfer effects, improving in certain tasks under multitask conditions. Statistical analyses confirmed significant differences across models for structured and semantic tasks, highlighting the absence of a universal degradation rule. These findings suggest that multitask prompting resilience is shaped more by architectural design than by model size alone, and they motivate adaptive, model-specific strategies for prompt composition in complex NLP applications. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

20 pages, 690 KB

Open AccessArticle

VLM-as-a-Judge Approaches for Evaluating Visual Narrative Coherence in Historical Photographical Records

by Brian Keith, Claudio Meneses, Mauricio Matus, María Constanza Castro and Diego Urrutia

Electronics 2025, 14(21), 4199; https://doi.org/10.3390/electronics14214199 - 27 Oct 2025

Viewed by 777

Abstract

Evaluating the coherence of visual narrative sequences extracted from image collections remains a challenge in digital humanities and computational journalism. While mathematical coherence metrics based on visual embeddings provide objective measures, they require computational resources and technical expertise to interpret. We propose using [...] Read more.

Evaluating the coherence of visual narrative sequences extracted from image collections remains a challenge in digital humanities and computational journalism. While mathematical coherence metrics based on visual embeddings provide objective measures, they require computational resources and technical expertise to interpret. We propose using vision-language models (VLMs) as judges to evaluate visual narrative coherence, comparing two approaches: caption-based evaluation that converts images to text descriptions and direct vision evaluation that processes images without intermediate text generation. Through experiments on 126 narratives from historical photographs, we show that both approaches achieve weak-to-moderate correlations with mathematical coherence metrics (r = 0.28–0.36) while differing in reliability and efficiency. Direct VLM evaluation achieves higher inter-rater reliability (

ICC () = 0.718

vs.

0.339

) but requires

10.8 \times

more computation time after initial caption generation. Both methods successfully discriminate between human-curated, algorithmically extracted, and random narratives, with all pairwise comparisons achieving statistical significance (

p < 0.05

, with five of six comparisons at

p < 0.001

). Human sequences consistently score highest, followed by algorithmic extractions, then random sequences. Our findings indicate that the choice between approaches depends on application requirements: caption-based for efficient large-scale screening versus direct vision for consistent curatorial assessment. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

35 pages, 3157 KB

Open AccessEditor’s ChoiceArticle

Federated Unlearning Framework for Digital Twin–Based Aviation Health Monitoring Under Sensor Drift and Data Corruption

by Igor Kabashkin

Electronics 2025, 14(15), 2968; https://doi.org/10.3390/electronics14152968 - 24 Jul 2025

Cited by 2 | Viewed by 1890

Abstract

Ensuring data integrity and adaptability in aircraft health monitoring (AHM) is vital for safety-critical aviation systems. Traditional digital twin (DT) and federated learning (FL) frameworks, while effective in enabling distributed, privacy-preserving fault detection, lack mechanisms to remove the influence of corrupted or adversarial [...] Read more.

Ensuring data integrity and adaptability in aircraft health monitoring (AHM) is vital for safety-critical aviation systems. Traditional digital twin (DT) and federated learning (FL) frameworks, while effective in enabling distributed, privacy-preserving fault detection, lack mechanisms to remove the influence of corrupted or adversarial data once these have been integrated into global models. This paper proposes a novel FL–DT–FU framework that combines digital twin-based subsystem modeling, federated learning for collaborative training, and federated unlearning (FU) to support the post hoc correction of compromised model contributions. The architecture enables real-time monitoring through local DTs, secure model aggregation via FL, and targeted rollback using gradient subtraction, re-aggregation, or constrained retraining. A comprehensive simulation environment is developed to assess the impact of sensor drift, label noise, and adversarial updates across a federated fleet of aircraft. The experimental results demonstrate that FU methods restore up to 95% of model accuracy degraded by data corruption, significantly reducing false negative rates in early fault detection. The proposed system further supports auditability through cryptographic logging, aligning with aviation regulatory standards. This study establishes federated unlearning as a critical enabler for resilient, correctable, and trustworthy AI in next-generation AHM systems. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Graphical abstract

37 pages, 1029 KB

Open AccessArticle

Autonomous Reinforcement Learning for Intelligent and Sustainable Autonomous Microgrid Energy Management

by Iacovos Ioannou, Saher Javaid, Yasuo Tan and Vasos Vassiliou

Electronics 2025, 14(13), 2691; https://doi.org/10.3390/electronics14132691 - 3 Jul 2025

Cited by 1 | Viewed by 1809

Abstract

Effective energy management in microgrids is essential for integrating renewable energy sources and maintaining operational stability. Machine learning (ML) techniques offer significant potential for optimizing microgrid performance. This study provides a comprehensive comparative performance evaluation of four ML-based control strategies: deep Q-networks (DQNs), [...] Read more.

Effective energy management in microgrids is essential for integrating renewable energy sources and maintaining operational stability. Machine learning (ML) techniques offer significant potential for optimizing microgrid performance. This study provides a comprehensive comparative performance evaluation of four ML-based control strategies: deep Q-networks (DQNs), proximal policy optimization (PPO), Q-learning, and advantage actor–critic (A2C). These strategies were rigorously tested using simulation data from a representative islanded microgrid model, with metrics evaluated across diverse seasonal conditions (autumn, spring, summer, winter). Key performance indicators included overall episodic reward, unmet load, excess generation, energy storage system (ESS) state-of-charge (SoC) imbalance, ESS utilization, and computational runtime. Results from the simulation indicate that the DQN-based agent consistently achieved superior performance across all evaluated seasons, effectively balancing economic rewards, reliability, and battery health while maintaining competitive computational runtimes. Specifically, DQN delivered near-optimal rewards by significantly reducing unmet load, minimizing excess renewable energy curtailment, and virtually eliminating ESS SoC imbalance, thereby prolonging battery life. Although the tabular Q-learning method showed the lowest computational latency, it was constrained by limited adaptability in more complex scenarios. PPO and A2C, while offering robust performance, incurred higher computational costs without additional performance advantages over DQN. This evaluation clearly demonstrates the capability and adaptability of the DQN approach for intelligent and autonomous microgrid management, providing valuable insights into the relative advantages and limitations of various ML strategies in complex energy management scenarios. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

17 pages, 12204 KB

Open AccessArticle

Architectural Ambiance: ChatGPT Versus Human Perception

by Rachid Belaroussi and Jorge Martín-Gutierrez

Electronics 2025, 14(11), 2184; https://doi.org/10.3390/electronics14112184 - 28 May 2025

Viewed by 1296

Abstract

Architectural ambiance refers to the mood perceived in a built environment, assessed through human reactions to virtual drawings of prospective spaces. This paper investigates the use of a ready-made artificial intelligence model to automate this task. Based on professional BIM models, videos of [...] Read more.

Architectural ambiance refers to the mood perceived in a built environment, assessed through human reactions to virtual drawings of prospective spaces. This paper investigates the use of a ready-made artificial intelligence model to automate this task. Based on professional BIM models, videos of virtual tours of typical urban areas were built: a business district, a strip mall, and a residential area. GPT-4V was used to assess the aesthetic quality of the built environment based on keyframes of the videos and characterize these spaces shaped by subjective attributes. The spatial qualities analyzed through subjective human experience include space and scale, enclosure, style, and overall feelings. These factors were assessed with a diverse set of mood attributes, ranging from balance and protection to elegance, simplicity, or nostalgia. Human participants were surveyed with the same questions based on the videos. The answers were compared and analyzed according to these subjective attributes. Our findings indicate that, while GPT-4V demonstrates adequate proficiency in interpreting urban spaces, there are significant differences between the AI and human evaluators. In nine out of twelve cases, the AI’s assessments aligned with the majority of human voters. The business district environment proved more challenging to assess, while the green environment was effectively modeled. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Graphical abstract

21 pages, 4407 KB

Open AccessFeature PaperArticle

Large Language Model-Driven Code Compliance Checking in Building Information Modeling

by Soumya Madireddy, Lu Gao, Zia Ud Din, Kinam Kim, Ahmed Senouci, Zhe Han and Yunpeng Zhang

Electronics 2025, 14(11), 2146; https://doi.org/10.3390/electronics14112146 - 24 May 2025

Cited by 1 | Viewed by 6536

Abstract

This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling (BIM) by introducing a Large Language Model (LLM)-driven approach to semi-automate this critical process. The developed system integrates LLMs such as ChatGPT, Claude, Gemini, and Llama, [...] Read more.

This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling (BIM) by introducing a Large Language Model (LLM)-driven approach to semi-automate this critical process. The developed system integrates LLMs such as ChatGPT, Claude, Gemini, and Llama, with Revit software to interpret building codes, generate Python scripts, and perform semi-automated compliance checks within the BIM environment. Case studies on a single-family residential project and an office building project demonstrated the system’s ability to reduce the time and effort required for compliance checks while improving accuracy. It streamlined the identification of violations, such as non-compliant room dimensions, material usage, and object placements, by automatically assessing relationships and generating actionable reports. Compared to manual methods, the system eliminated repetitive tasks, simplified complex regulations, and ensured reliable adherence to standards. By offering a comprehensive, adaptable, and cost-effective solution, this proposed approach offers a promising advancement in BIM-based compliance checking, with potential applications across diverse regulatory documents in construction projects. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

18 pages, 2263 KB

Open AccessArticle

Rapid Right Coronary Artery Extraction from CT Images via Global–Local Deep Learning Method Based on GhostNet

by Yanjun Li, Takaaki Yoshimura and Hiroyuki Sugimori

Electronics 2025, 14(7), 1399; https://doi.org/10.3390/electronics14071399 - 31 Mar 2025

Cited by 1 | Viewed by 869

Abstract

The right coronary artery plays a crucial role in cardiac function and its accurate extraction and 3D reconstruction from CT images are essential for diagnosing and treating coronary artery disease. This study proposes a novel, automated, deep learning pipeline that integrates a transformer-based [...] Read more.

The right coronary artery plays a crucial role in cardiac function and its accurate extraction and 3D reconstruction from CT images are essential for diagnosing and treating coronary artery disease. This study proposes a novel, automated, deep learning pipeline that integrates a transformer-based network with GhostNet to improve segmentation and 3D reconstruction. The dataset comprised CT images from 32 patients, with the segmentation model effectively extracting vascular cross-sections, achieving an F1 score of 0.887 and an Intersection over Union of 0.797. Meanwhile, the proposed model achieved an inference speed of 7.03 ms, outperforming other state-of-the-art networks used for comparison, making it highly suitable for real-time clinical applications. Compared to conventional methods, the proposed approach demonstrates superior segmentation performance while maintaining computational efficiency. The results indicate that this framework has the potential to significantly improve diagnostic accuracy and interventional planning for coronary artery disease. Future work will focus on expanding dataset diversity, refining real-time processing capabilities, and extending the methodology to other vascular structures. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

25 pages, 7436 KB

Open AccessArticle

A Co-Optimization Method for Analog IC Placement and Routing Based on Sequence Pairs and Random Forests

by Zhouhu Huo, Niannian Sun, Chaofei Zhang, Bingbing Li and Jixin Zhang

Electronics 2025, 14(7), 1349; https://doi.org/10.3390/electronics14071349 - 28 Mar 2025

Viewed by 992

Abstract

In the physical design of integrated circuits (ICs), conventional methodologies treat placement and routing as two sequential and independent steps, resulting in placement adjustments that do not sufficiently account for routing requirements. Such decoupled optimization leads to various routing challenges, including congestion and [...] Read more.

In the physical design of integrated circuits (ICs), conventional methodologies treat placement and routing as two sequential and independent steps, resulting in placement adjustments that do not sufficiently account for routing requirements. Such decoupled optimization leads to various routing challenges, including congestion and excessive wirelength. To address these limitations, we propose a novel iterative co-optimization framework that simultaneously considers placement and routing. Our methodology establishes an interdependent relationship between placement and routing, where routing is guided by the placement results and placement is adaptively adjusted based on the routing feedback. The proposed framework comprises two key components. First, we introduce an efficient gridless routing algorithm based on line exploration, which rapidly generates routing results by leveraging the placement state and netlist connectivity. The routing connectivity ratio and wirelength are then incorporated as the primary optimization metrics for placement refinement. Second, we develop an advanced placement optimization algorithm that integrates random forest techniques with Monte Carlo-based optimization. This algorithm systematically integrates routing information to guide iterative placement refinement, with the goal of achieving a higher routing connectivity ratio and a reduction in wirelength. We evaluated our approach on a dataset provided by Empyrean. Compared to the baseline placements in the dataset, the algorithm proposed in this work achieved an average improvement of 8.03% in terms of routing connectivity ratio and an average reduction of 18.33% in wirelength. Additionally, a comparative analysis of four optimization algorithms under the proposed co-optimization framework and the traditional half-perimeter wirelength (HPWL) method reveals achieved improvements of 12.41%, 14.16%, 13.87%, and 14.02% in the routing connectivity ratio, respectively, significantly outperforming the HPWL-based method. These results substantiate the efficacy of our co-optimization approach in enhancing IC physical design outcomes. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

Review

Jump to: Research

26 pages, 14606 KB

Open AccessReview

Attribution-Based Explainability in Medical Imaging: A Critical Review on Explainable Computer Vision (X-CV) Techniques and Their Applications in Medical AI

by Kazi Nabiul Alam, Pooneh Bagheri Zadeh and Akbar Sheikh-Akbari

Electronics 2025, 14(15), 3024; https://doi.org/10.3390/electronics14153024 - 29 Jul 2025

Cited by 2 | Viewed by 3632

Abstract

One of the largest future applications of computer vision is in the healthcare industry. Computer vision tasks are generally implemented in diverse medical imaging scenarios, including detecting or classifying diseases, predicting potential disease progression, analyzing cancer data for advancing future research, and conducting [...] Read more.

One of the largest future applications of computer vision is in the healthcare industry. Computer vision tasks are generally implemented in diverse medical imaging scenarios, including detecting or classifying diseases, predicting potential disease progression, analyzing cancer data for advancing future research, and conducting genetic analysis for personalized medicine. However, a critical drawback of using Computer Vision (CV) approaches is their limited reliability and transparency. Clinicians and patients must comprehend the rationale behind predictions or results to ensure trust and ethical deployment in clinical settings. This demonstrates the adoption of the idea of Explainable Computer Vision (X-CV), which enhances vision-relative interpretability. Among various methodologies, attribution-based approaches are widely employed by researchers to explain medical imaging outputs by identifying influential features. This article solely aims to explore how attribution-based X-CV methods work in medical imaging, what they are good for in real-world use, and what their main limitations are. This study evaluates X-CV techniques by conducting a thorough review of relevant reports, peer-reviewed journals, and methodological approaches to obtain an adequate understanding of attribution-based approaches. It explores how these techniques tackle computational complexity issues, improve diagnostic accuracy and aid clinical decision-making processes. This article intends to present a path that generalizes the concept of trustworthiness towards AI-based healthcare solutions. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

48 pages, 1127 KB

Open AccessReview

Artificial Intelligence vs. Efficient Markets: A Critical Reassessment of Predictive Models in the Big Data Era

by Antonio Pagliaro

Electronics 2025, 14(9), 1721; https://doi.org/10.3390/electronics14091721 - 23 Apr 2025

Cited by 9 | Viewed by 11390

Abstract

This paper critically examines artificial intelligence applications in stock market forecasting, addressing significant gaps in the existing literature that often overlook the tension between theoretical market efficiency and empirical predictability. While numerous reviews catalog methodologies, they frequently fail to rigorously evaluate model performance [...] Read more.

This paper critically examines artificial intelligence applications in stock market forecasting, addressing significant gaps in the existing literature that often overlook the tension between theoretical market efficiency and empirical predictability. While numerous reviews catalog methodologies, they frequently fail to rigorously evaluate model performance across different market regimes or reconcile statistical significance with economic relevance. We analyze techniques ranging from traditional statistical models to advanced deep learning architectures, finding that ensemble methods like Extra Trees, Random Forest, and XGBoost consistently outperform single classifiers, achieving directional accuracy of up to 86% in specific market conditions. Our analysis reveals that hybrid approaches integrating multiple data sources demonstrate superior performance by capturing complementary market signals, yet many models showing statistical significance fail to generate economic value after accounting for transaction costs and market impact. By addressing methodological challenges including backtest overfitting, regime changes, and implementation constraints, we provide a novel comprehensive framework for rigorous model assessment that bridges the divide between academic research and practical implementation. This review makes three key contributions: (1) a reconciliation of the Efficient Market Hypothesis with AI-driven predictability through an adaptive market framework, (2) a multi-dimensional evaluation methodology that extends beyond classification accuracy to financial performance, and (3) an identification of promising research directions in explainable AI, transfer learning, causal modeling, and privacy-preserving techniques that address current limitations. Full article

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence-Driven Emerging Applications

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (12 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI