Submit to Electronics Review for Electronics Propose a Special Issue

Journal Menu

Journal Browser

Advancements in Artificial Intelligence (AI) for Engineering Applications

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Related Special Issue
Published Papers

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (31 December 2025) | Viewed by 39304

Share This Special Issue

Special Issue Editor

Dr. Hubert Zarzycki

E-Mail Website
Guest Editor

Faculty of Computer Science and Technology, Wroclaw University of Science and Technology, 50-370 Wroclaw, Poland
Interests: artificial intelligence; optimization techniques; fuzzy logic; natural language processing; reinforcement learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

We are excited to issue a call for papers for a Special Issue of Electronics focusing on the intersection of artificial intelligence (AI) with engineering applications. This Special Issue aims to explore the latest advancements and practical implementations within the realms of swarm intelligence, optimization, fuzzy logic, natural language processing (NLP), computer vision, and reinforcement learning.

The overall focus, scope, and purpose of this Special Issue are delineated as follows:

(a) Focus: The Special Issue will concentrate on exploring innovative methodologies and algorithms within the fields of swarm intelligence, optimization, fuzzy logic, NLP, computer vision, and reinforcement learning, with a specific emphasis on their application in engineering domains.

(b) Scope: We welcome contributions that present novel research findings, methodologies, case studies, and applications related to the aforementioned AI fields in engineering contexts. Topics of interest include, but are not limited to, the following:

Development of advanced AI-based optimization techniques for engineering problems;
Integration of fuzzy logic principles into engineering systems to enhance adaptability and decision-making;
Utilization of NLP for improving human–computer interaction in engineering applications;
Application of computer vision techniques for object recognition, image analysis, and visual perception in engineering tasks;
Implementation of reinforcement learning algorithms for autonomous decision-making and control in engineering systems.

(c) Purpose: The purpose of this Special Issue is to provide a platform for researchers to disseminate their latest findings, exchange insights, and foster collaborations for advancing the state of the art in AI-driven engineering applications. By showcasing practical implementations and case studies, we aim to bridge the gap between theoretical advancements in AI and their real-world applications in engineering.

This Special Issue will complement the existing literature by taking the following steps:

Offering a comprehensive overview of the latest trends and advancements in AI techniques as applied to engineering problems;
Providing in-depth discussions and analyses of practical case studies and applications, thereby offering valuable insights for both academia and industry practitioners;
Stimulating further research and innovation in this field by identifying emerging challenges and potential areas for future exploration.

We encourage researchers from academia, industry, and other relevant sectors to contribute their original research articles for publication in this Special Issue.

We eagerly anticipate your contributions to this Special Issue and advance our collective understanding of AI-driven engineering applications.

Dr. Hubert Zarzycki
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

artificial intelligence
swarm intelligence
optimization
fuzzy logic
natural language processing (NLP)
computer vision
reinforcement learning
engineering applications

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Related Special Issue

Advancements in Artificial Intelligence (AI) for Engineering Applications, 2nd Edition in Electronics

Published Papers (14 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

23 pages, 2837 KB

Open AccessArticle

Link Prediction Using Temporal Graph Neural Network Model

by Dominika Dudziak-Gajowiak, Krzysztof Juszczyszyn, Dawid Marcin Chudzicki and Dariusz Skorupka

Electronics 2026, 15(3), 662; https://doi.org/10.3390/electronics15030662 - 3 Feb 2026

Cited by 1 | Viewed by 1312

Abstract

In this work, we present a Temporal Graph Neural Network (TGNN) architecture specifically designed for link prediction in dynamic graphs. The proposed approach is evaluated on a dynamic social network constructed from internal email communication between employees of Wrocław University of Science and Technology that was collected over a continuous period of 605 days. To capture short-term fluctuations in communication behavior, we introduce the use of very short temporal aggregation windows, down to a single day, for constructing temporal graph snapshots. This fine-grained temporal resolution allows the model to accurately learn evolving interaction patterns and adapt to the dynamic nature of social communication networks. The TGNN model demonstrates consistently high predictive performance, achieving 99.28% ROC-AUC (Receiver Operating Characteristic—Area Under Curve) and 99.17% Average Precision in link prediction tasks. These results confirm that the model is able to distinguish between existing and emerging communication links with high reliability across temporal intervals. The architecture, optimized exclusively for temporal link prediction, effectively utilizes its representational capacity for modeling edge formation processes in time-dependent networks. The findings highlight the potential of focused TGNN architectures and short-time-window modeling in improving predictive accuracy and temporal resolution in link prediction applications involving evolving social or organizational structures. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

25 pages, 44747 KB

Open AccessArticle

Small-Sample Thermal Fault Diagnosis Using Knowledge Graph and Generative Adversarial Networks

by Ke Chen, Gang Xu, Yunjie Zhang and Yi Wang

Electronics 2026, 15(2), 355; https://doi.org/10.3390/electronics15020355 - 13 Jan 2026

Viewed by 402

Abstract

The scarcity of fault samples significantly impedes the generalization of data-driven diagnosis models for local thermal imbalances in integrated energy systems. To overcome this limitation, this paper proposes a novel knowledge graph-guided conditional generative adversarial network (KG-GAN) framework. The approach begins by constructing a dynamically updatable fault knowledge graph for district heating systems, which explicitly encapsulates pipeline topology, thermodynamic principles, and fault propagation mechanisms. The derived knowledge embeddings are then fused with physics-based constraints into the adversarial learning process, effectively alleviating the issue of physically implausible sample generation that plagues conventional data-centric models. Experimental validation on a district heating platform, involving four common fault types, demonstrates the superiority of our method. With only 100 samples per fault category, a diagnostic model trained on KG-GAN-generated data achieves a classification accuracy of 91.7%, outperforming a GAN-based baseline by 8.3%. Furthermore, t-Distributed Stochastic Neighbor Embedding (t-SNE) visualization reveals a 92.3% feature distribution consistency between generated and real samples, confirming the method’s capability to enhance diagnostic robustness and physical interpretability under small-sample conditions. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

28 pages, 1728 KB

Open AccessFeature PaperEditor’s ChoiceArticle

A Lightweight Learning-Based Approach for Online Edge-to-Cloud Service Placement

by Mohammadsadeq Garshasbi Herabad, Javid Taheri, Bestoun S. Ahmed and Calin Curescu

Electronics 2026, 15(1), 65; https://doi.org/10.3390/electronics15010065 - 23 Dec 2025

Cited by 1 | Viewed by 628

Abstract

The integration of edge and cloud computing is critical for resource-intensive applications which require low-latency communication, high reliability, and efficient resource utilisation. The service placement problem in these environments poses significant challenges owing to dynamic network conditions, heterogeneous resource availability, and the necessity for real-time decision-making. Because determining an optimal service placement in such networks is an NP-complete problem, the existing solutions rely on fast but suboptimal heuristics or computationally intensive metaheuristics. Neither approach meets the real-time demands of online scenarios, owing to its inefficiency or high computational overhead. In this study, we propose a lightweight learning-based approach for the online placement of services with multi-version components in edge-to-cloud computing. The proposed approach utilises a Shallow Neural Network (SNN) with both weight and power coefficients optimised using a Genetic Algorithm (GA). The use of an SNN ensures low computational overhead during the training phase and almost instant inference when deployed, making it well suited for real-time and online service placement in edge-to-cloud environments where rapid decision-making is crucial. The proposed method (SNN-GA) is specifically evaluated in AR/VR-based remote repair and maintenance scenarios, developed in collaboration with our industrial partner, and demonstrated robust performance and scalability across a wide range of problem sizes. The experimental results show that SNN-GA reduces the service response time by up to 27% compared to metaheuristics and 55% compared to heuristics at larger scales. It also achieves over 95% platform reliability, outperforming heuristics (which remain below 85%) and metaheuristics (which decrease to 90% at larger scales). Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Graphical abstract

25 pages, 25914 KB

Open AccessArticle

Permeability Index Modeling with Multiscale Time Delay Characteristics Excavation in Blast Furnace Ironmaking Process

by Yonghong Xu, Chunjie Yang and Siwei Lou

Electronics 2025, 14(23), 4670; https://doi.org/10.3390/electronics14234670 - 27 Nov 2025

Viewed by 728

Abstract

The permeability index (PI) is a key comprehensive indicator that reflects the smoothness of internal gas flow in pig iron production via blast furnace. An accurate prediction for it is essential for forecasting abnormal furnace conditions and preventing potential faults. However, developing an early prediction model for PI has been neglected in existing research, and it faces massive challenges due to the strong nonlinearity, undesirable nonstationarity, and significant multiscale time delays inherent in the blast furnace data. To bridge this gap, a new modeling paradigm for PI is proposed to explore the inherent time delay characteristics among multiple variables. First, the data are progressively decomposed into multiple components using wavelet decomposition and spike separation. Then, a novel delay extraction method based on wavelet coherence analysis is developed to obtain accurate multiscale time delay knowledge. Furthermore, the integration of Orthonormal Subspace Analysis (OSA) and wavelet neural network (WNN) achieves comprehensive modeling across time and frequency domains, incorporating global and local features. A Gauss–Markov-based fusion framework is also utilized to reduce the output error variance, ultimately enabling the early prediction of PI. Mechanism analysis and a practical case study on blast furnace production verify the effectiveness of the proposed target-oriented prediction framework. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

22 pages, 5419 KB

Open AccessFeature PaperArticle

AI at Sea, Year Six: Performance Evaluation, Failures, and Insights from the Operational Meta-Analysis of SatShipAI, a Sensor-Fused Maritime Surveillance Platform

by Ioannis Nasios and Konstantinos Vogklis

Electronics 2025, 14(18), 3648; https://doi.org/10.3390/electronics14183648 - 15 Sep 2025

Cited by 2 | Viewed by 1930

Abstract

Six years after its deployment, SatShipAI, an operational platform combining AI models with Sentinel-1 SAR imagery and AIS data, has provided robust maritime surveillance around Denmark. A meta-analysis of archived outputs, logs, and manual reviews shows stable vessel detection and classification performance over time, including successful cross-sensor application to X-band SAR data without retraining. Key operational challenges included orbit file delays, nearshore detection limits, and emerging infrastructure such as wind farms. The platform proved particularly valuable for detecting offshore “dark” vessels beyond AIS coverage, informing maritime security, traffic management, and emergency response. These findings demonstrate the feasibility, resilience, and adaptability of long-term AI–geospatial systems, offering practical guidance for future autonomous monitoring infrastructure. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

50 pages, 8041 KB

Open AccessArticle

A Sequence-Aware Surrogate-Assisted Optimization Framework for Precision Gyroscope Assembly Based on AB-BiLSTM and SEG-HHO

by Donghuang Lin, Yongbo Jian and Haigen Yang

Electronics 2025, 14(17), 3470; https://doi.org/10.3390/electronics14173470 - 29 Aug 2025

Viewed by 1105

Abstract

High-precision assembly plays a central role in aerospace, defense, and precision instrumentation, where errors in bolt preload or tightening sequences can directly degrade product reliability and lead to costly rework. Traditional finite element analysis (FEA) offers accuracy but is too computationally expensive for iterative or real-time optimization. Surrogate models are a promising alternative, yet conventional machine learning methods often neglect the sequential and constraint-aware nature of multi-bolt assembly. To overcome these limitations, this paper introduces an integrated framework that combines an Attention-based Bidirectional Long Short-Term Memory (AB-BiLSTM) surrogate with a stratified version of the Harris Hawks Optimizer (SEG-HHO). The AB-BiLSTM captures temporal dependencies in preload evolution while providing interpretability through attention–weight visualization, linking model focus to physical assembly dynamics. SEG-HHO employs an encoding–decoding mechanism to embed engineering constraints, enabling efficient search in complex and constrained design spaces. Validation on a gyroscope assembly task demonstrates that the framework achieves high predictive accuracy (Mean Absolute Error of 3.59 × 10⁻⁵), reduces optimization cost by orders of magnitude compared with FEA, and reveals physically meaningful patterns in bolt interactions. These results indicate a scalable and interpretable solution for precision assembly optimization. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

23 pages, 1614 KB

Open AccessArticle

Towards Generic Failure-Prediction Models in Large-Scale Distributed Computing Systems

by Srigoutam Jagannathan, Yogesh Sharma and Javid Taheri

Electronics 2025, 14(17), 3386; https://doi.org/10.3390/electronics14173386 - 26 Aug 2025

Cited by 2 | Viewed by 1658

Abstract

The increasing complexity of Distributed Computing (DC) systems requires advanced failure-prediction models to enhance reliability and efficiency. This study proposes a comprehensive methodology for developing generic machine learning (ML) models capable of cross-layer and cross-platform failure-prediction without requiring platform-specific retraining. Using the Grid5000 failure dataset from the Failure Trace Archive (FTA), we explored Linear and Logistic Regression, Random Forest, and XGBoost to predict three critical metrics: Time Between Failures (TBF), Time to Return/Repair (TTR), and Failing Node Identification (FNI). Our approach involved extensive exploratory data analysis (EDA), statistical examination of failure patterns, and model evaluation across the cluster, site, and system levels. The results demonstrate that XGBoost consistently outperforms the other models, achieving near-perfect 100% accuracy for TBF and FNI, with robust generalisability across diverse DC environments. In addition, we introduce a hierarchical DC architecture that integrates these failure-prediction models. In the form of a use case, we also demonstrate how service providers can use these prediction models to balance service reliability and cost. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

8 pages, 443 KB

Open AccessEditor’s ChoiceArticle

A Simple Open-Loop Control Method for Optimizing Manufacturing Control Knobs Using Artificial Intelligence

by Sarah Marzen

Electronics 2025, 14(13), 2676; https://doi.org/10.3390/electronics14132676 - 2 Jul 2025

Cited by 1 | Viewed by 912

Abstract

Manufacturing processes are collecting a wealth of data on how operational knobs affect process efficiency and product quality. Yet, optimizing the adjustment of these knobs using artificial intelligence remains a challenge. We propose a simple open-loop control method for optimizing a manufacturing process, with pharmaceutical applications in mind, using artificial intelligence. The first step involves fitting a simple supervised learning model to manufacturing data—typically an artificial neural network with universal approximation guarantees—so that operational knobs (such as concentrations and temperatures) can be used to predict process efficiency (e.g., time-to-product) and/or product quality (e.g., yield or quality score). Assuming the supervised learning model works well, we can perform typical optimization procedures, like gradient ascent, to increase efficiency and product quality. We test this on a publicly available dataset for wine and suggest new values for wine parameters that should produce a higher-quality wine with a greater probability. The result is a setting for the manufacturing knobs that optimizes the product using basic artificial intelligence. This method can be further enhanced by incorporating more advanced and recent AI applications for anomaly and defect detection in manufacturing processes. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

20 pages, 3651 KB

Open AccessArticle

A Meta-Learner Based on the Combination of Stacking Ensembles and a Mixture of Experts for Balancing Action Unit Recognition

by Andrew Sumsion and Dah-Jye Lee

Electronics 2025, 14(13), 2665; https://doi.org/10.3390/electronics14132665 - 30 Jun 2025

Cited by 2 | Viewed by 2780

Abstract

Facial action units (AUs) are used throughout animation, clinical settings, and robotics. AU recognition usually works better for these downstream tasks when it achieves high performance across all AUs. Current facial AU recognition approaches tend to perform unevenly across all AUs. Among other potential reasons, one cause is their focus on improving the overall average F1 score, where good performance on a small number of AUs increases the overall average F1 score even with poor performance on other AUs. Building on our previous success, which achieved the highest average F1 score, this work focuses on improving its performance across all AUs to address this challenge. We propose a mixture of experts as the meta-learner to combine the outputs of an explicit stacking ensemble. For our ensemble, we use a heterogeneous, negative correlation, explicit stacking ensemble. We introduce an additional measurement called Borda ranking to better evaluate the overall performance across all AUs. As indicated by this additional metric, our method not only maintains the best overall average F1 score but also achieves the highest performance across all AUs on the BP4D and DISFA datasets. We also release a synthetic dataset as additional training data, the first with balanced AU labels. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

20 pages, 3502 KB

Open AccessArticle

Explainable AI Models for IoT-Based Shaft Power Prediction and Comprehensive Performance Monitoring

by Sotiris Zikas, Katerina Gkirtzou, Ioannis Filippopoulos, Dimitris Kalatzis, Theodor Panagiotakopoulos, Zoran Lajic, Dimitris Papathanasiou and Yiannis Kiouvrekis

Electronics 2025, 14(13), 2561; https://doi.org/10.3390/electronics14132561 - 24 Jun 2025

Cited by 5 | Viewed by 1474

Abstract

This paper presents a comparative analysis of machine learning-based methods for predicting shaft power in ships, a key factor in optimizing ship performance. Accurate shaft power prediction facilitates efficient operations, reducing fuel consumption, emissions, and maintenance costs, aligning with environmental regulations and promoting sustainable maritime practices. The proposed approach evaluates three machine learning methods, analyzing 431 models to determine the most accurate and reliable option for VLCC tankers. XGBoost emerged as the top-performing model, delivering a 13% improvement in accuracy over traditional methods. Using the SHAP framework, key factors influencing shaft power predictions—such as GPS speed, draft, days from dry dock, and wave height—were identified, enhancing model transparency and decision-making clarity. This explainability fosters trust in the use of AI within marine engineering. The results demonstrate that machine learning can optimize maintenance scheduling by reducing unnecessary cleaning procedures, mitigating propulsion system wear, and improving reliability. By using predictive insights, ship operators can achieve better fuel efficiency, lower emissions, and cost savings. The study underscores the potential of explainable machine learning models as transformative tools for ship performance monitoring, supporting greener and more efficient maritime operations. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

30 pages, 1455 KB

Open AccessArticle

Automated Formative Feedback for Algorithm and Data Structure Self-Assessment

by Lourdes Araujo, Fernando Lopez-Ostenero, Laura Plaza and Juan Martinez-Romo

Electronics 2025, 14(5), 1034; https://doi.org/10.3390/electronics14051034 - 5 Mar 2025

Cited by 1 | Viewed by 3764

Abstract

Self-evaluation empowers students to progress independently and adapt their pace according to their unique circumstances. A critical facet of self-assessment and personalized learning lies in furnishing learners with formative feedback. This feedback, dispensed following their responses to self-assessment questions, constitutes a pivotal component of formative assessment systems. We hypothesize that it is possible to generate explanations that are useful as formative feedback using different techniques depending on the type of self-assessment question under consideration. This study focuses on a subject taught in a computer science program at a Spanish distance learning university. Specifically, it delves into advanced data structures and algorithmic frameworks, which serve as overarching principles for addressing complex problems. The generation of these explanatory resources hinges on the specific nature of the question at hand, whether theoretical, practical, related to computational cost, or focused on selecting optimal algorithmic approaches. Our work encompasses a thorough analysis of each question type, coupled with tailored solutions for each scenario. To automate this process as much as possible, we leverage natural language processing techniques, incorporating advanced methods of semantic similarity. The results of the assessment of the feedback generated for a subset of theoretical questions validate the effectiveness of the proposed methods, allowing us to seamlessly integrate this feedback into the self-assessment system. According to a survey, students found the resulting tool highly useful. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

20 pages, 5610 KB

Open AccessArticle

Graph Neural Network (GNN) for Joint Detection–Decoder MAP–LDPC in Bit-Patterned Media Recording Systems

by Thien An Nguyen and Jaejin Lee

Electronics 2024, 13(23), 4811; https://doi.org/10.3390/electronics13234811 - 5 Dec 2024

Cited by 4 | Viewed by 3177

Abstract

With its high area density, bit-patterned media recording (BPMR) is emerging as a leading technology for next-generation storage systems. However, as area density increases, magnetic islands are positioned closer together, causing significant two-dimensional (2D) interference. To address this, detection methods are used to interpret the received signal and mitigate 2D interference. Recently, the maximum a posteriori (MAP) detection algorithm has shown promise in improving BPMR performance, though it requires extrinsic information to effectively reduce interference. In this paper, to solve the 2D interference and improve the performance of BPMR systems, a model using low-density parity-check (LDPC) coding was introduced to supply the MAP detector with the needed extrinsic information, enhancing detection in a joint decoding model we call MAP–LDPC. Additionally, leveraging similarities between LDPC codes and graph neural networks (GNNs), we replace the traditional sum–product algorithm in LDPC decoding with a GNN, creating a new model, MAP–GNN. The simulation results demonstrate that MAP–GNN achieves superior performance, particularly when using the deep learning-based GNN approach over conventional techniques. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

23 pages, 770 KB

Open AccessArticle

Computationally Efficient Inference via Time-Aware Modular Control Systems

by Dmytro Shchyrba and Hubert Zarzycki

Electronics 2024, 13(22), 4416; https://doi.org/10.3390/electronics13224416 - 11 Nov 2024

Viewed by 2018

Abstract

Control in multi-agent decision-making systems is an important issue with a wide variety of existing approaches. In this work, we offer a new comprehensive framework for distributed control. The main contributions of this paper are summarized as follows. First, we propose PHIMEC (physics-informed meta control)—an architecture for learning optimal control by employing a physics-informed neural network when the state space is too large for reward-based learning. Second, we offer a way to leverage impulse response as a tool for system modeling and control. We propose IMPULSTM, a novel approach for incorporating time awareness into recurrent neural networks designed to accommodate irregular sampling rates in the signal. Third, we propose DIMAS, a modular approach to increasing computational efficiency in distributed control systems via domain-knowledge integration. We analyze the performance of the first two contributions on a set of corresponding benchmarks and then showcase their combined performance as a domain-informed distributed control system. The proposed approaches show satisfactory performance both individually in their respective applications and as a connected system. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

Review

Jump to: Research

54 pages, 2065 KB

Open AccessReview

Edge Intelligence: A Review of Deep Neural Network Inference in Resource-Limited Environments

by Dat Ngo, Hyun-Cheol Park and Bongsoon Kang

Electronics 2025, 14(12), 2495; https://doi.org/10.3390/electronics14122495 - 19 Jun 2025

Cited by 43 | Viewed by 14431

Abstract

Deploying deep neural networks (DNNs) in resource-limited environments—such as smartwatches, IoT nodes, and intelligent sensors—poses significant challenges due to constraints in memory, computing power, and energy budgets. This paper presents a comprehensive review of recent advances in accelerating DNN inference on edge platforms, with a focus on model compression, compiler optimizations, and hardware–software co-design. We analyze the trade-offs between latency, energy, and accuracy across various techniques, highlighting practical deployment strategies on real-world devices. In particular, we categorize existing frameworks based on their architectural targets and adaptation mechanisms and discuss open challenges such as runtime adaptability and hardware-aware scheduling. This review aims to guide the development of efficient and scalable edge intelligence solutions. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Journal Menu

Journal Browser

Advancements in Artificial Intelligence (AI) for Engineering Applications

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issue

Published Papers (14 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI