Next Issue
Volume 14, September
Previous Issue
Volume 14, July
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.7
5.2
Journals
Technologies
Volume 14
Issue 8
share announcement

Technologies, Volume 14, Issue 8 (August 2026) – 65 articles

Cover Story (view full-size image): Pipeline infrastructure is aging and becoming increasingly complex and demanding to manage safely and efficiently. Digital twin technology offers a promising shift from reactive inspection and maintenance toward continuous, predictive decision-making by linking physical pipelines with dynamic virtual counterparts. This review examines how digital twins are being applied across oil and gas, water, hydraulic, and subsea pipeline systems, focusing on leak detection, corrosion monitoring, condition assessment, and predictive maintenance. It compares physics-based, data-driven, hybrid, reduced-order, probabilistic, and visual approaches, while highlighting persistent challenges in data integration, validation, scalability, cybersecurity, and standardization. The review proposes a unified framework and identifies priorities for future development. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
27 pages, 1406 KB  
Systematic Review
Bridging the AI Language Divide: A Systematic Review of NMT and LLMs in Low-Resource Translation
by Sweeta Agrawal and Abayomi O. Agbeyangi
Technologies 2026, 14(8), 518; https://doi.org/10.3390/technologies14080518 - 21 Aug 2026
Viewed by 438
Abstract
The rapid evolution of AI-driven language technologies has inadvertently widened the gap between high-resource and marginalised languages. Despite significant progress in AI-driven translation for high-resource languages, low-resource languages remain underrepresented due to limited data, a lack of benchmarks, and evaluation challenges. This study [...] Read more.
The rapid evolution of AI-driven language technologies has inadvertently widened the gap between high-resource and marginalised languages. Despite significant progress in AI-driven translation for high-resource languages, low-resource languages remain underrepresented due to limited data, a lack of benchmarks, and evaluation challenges. This study presents a comprehensive systematic review of machine translation for low-resource languages, focusing on advances in neural machine translation (NMT) and large language models (LLMs) between 2017 and 2025. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 63 studies were selected from the 1696 articles in the Scopus, Web of Science, and Google Scholar databases. The review identifies five dominant methodological approaches: data augmentation, back-translation, transfer learning, pre-training, and parameter-efficient fine-tuning. The findings reveal that model performance is highly dependent on resource availability: transformer-based NMT excels in moderate data settings, while LLMs demonstrate promising zero-shot and few-shot capabilities in extremely low-resource scenarios. Hybrid NMT–LLM approaches emerge as a particularly effective paradigm. The study also highlights critical challenges, including the absence of standardised benchmarks, over-reliance on inadequate evaluation metrics such as Bilingual Evaluation Understudy (BLEU), limited human evaluation, and significant geographic and linguistic underrepresentation. Additionally, ethical concerns related to bias, cultural representation, and community engagement are increasingly relevant. The findings contribute to advancing inclusive and equitable AI-driven language technologies. Full article
►▼ Show Figures

Figure 1

25 pages, 3707 KB  
Article
ESNformer: A Hybrid Reservoir–Transformer Architecture for Interpretable, Position-Aware Classification of Structured Assessment Data, with a Braille-Literacy Case Study
by Cesar H. Valencia-Niño, Rafael A. Nuñez-Rodriguez, Marley M. B. R. Vellasco and Jeison Marin
Technologies 2026, 14(8), 517; https://doi.org/10.3390/technologies14080517 - 21 Aug 2026
Viewed by 619
Abstract
We present ESNformer, a hybrid architecture that couples an Echo State Network (ESN) reservoir with a Transformer encoder for classification of structured, multi-indicator assessment data: a fixed-order vector of complementary indicators per assessment instance rather than a repeated-measures time series. The reservoir acts [...] Read more.
We present ESNformer, a hybrid architecture that couples an Echo State Network (ESN) reservoir with a Transformer encoder for classification of structured, multi-indicator assessment data: a fixed-order vector of complementary indicators per assessment instance rather than a repeated-measures time series. The reservoir acts as a fixed nonlinear feature map over the indicator vector, while self-attention, made position-aware over the fixed column order, learns how each indicator’s evidence contributes to the final decision, so the two components, together, capture local, indicator-level detail and global, cross-indicator interactions within a single, end-to-end trainable model. Interpretability is treated as a first-class design requirement rather than an afterthought: the architecture is paired with an explainability layer combining SHAP feature attribution (reported both globally and per class), the model’s own attention weights, a deletion/insertion faithfulness test that quantitatively verifies which inputs the model actually relies on, and counterfactual maps that translate a prediction into an actionable, inspectable recommendation. We evaluate the architecture on a concrete case study, classifying Braille-literacy instructional recommendations from 15 pedagogical indicators grouped into three categories (Mangold’s, ABKL, and Progresar), using a benchmark of 900 real assessment instances (630 used, together with a class-conditional augmentation procedure, to build a 2100-instance training set) with validation and test partitions (135 instances each) kept exclusively real. On this benchmark, the tuned model reached 85.33% accuracy, 85.90% macro-precision, 85.33% macro-recall, an F1 score of 85.25%, and an AUC of 0.95 on the real test set. SHAP attribution, attention weights, and the faithfulness test converge on the same two dominant indicators (response time and error count): removing them alone collapses accuracy to chance, while retaining only them recovers most of the model’s accuracy. We report this transparently alongside a comparison against ESN-only, Transformer-only, and tabular baselines (logistic regression, decision tree, random forest, XGBoost, and an MLP) on the same data and discuss what the hybrid architecture and its explainability pipeline add beyond what the two dominant indicators already explain and how the approach generalizes to other tabular and mixed-granularity assessment settings that require both predictive accuracy and a verifiable account of what drove each decision. Full article
►▼ Show Figures

Figure 1

28 pages, 12302 KB  
Article
Enhancing Small-Object Parking-Slot Detection in UAV Images with Lightweight Multi-Scale Representation and Geometry-Aware Regression
by Yinping Li, Qing Cheng and Wenquan Huang
Technologies 2026, 14(8), 516; https://doi.org/10.3390/technologies14080516 - 21 Aug 2026
Viewed by 259
Abstract
This paper focuses on the binary task of parking-slot occupancy detection (vacant vs. occupied) from UAV aerial imagery. Accurate parking-slot detection from UAV imagery is challenged by small target sizes, highly regular rectangular shapes, large-scale variations, complex backgrounds, and perspective distortions. Compared with [...] Read more.
This paper focuses on the binary task of parking-slot occupancy detection (vacant vs. occupied) from UAV aerial imagery. Accurate parking-slot detection from UAV imagery is challenged by small target sizes, highly regular rectangular shapes, large-scale variations, complex backgrounds, and perspective distortions. Compared with fixed surveillance cameras, UAV-based detection offers flexible deployment, wide-area coverage, and no requirement for pre-installed infrastructure, making it especially suitable for large open-air parking lots and temporary parking scenarios. To address this, this study proposes a task-specific framework for UAV-based parking-slot detection, with improvements in backbone design, attention modeling, and bounding-box regression. A lightweight MnasNet-inspired backbone is used to improve multi-scale feature extraction at low computational cost. An enhanced EMA module with adaptive grouping, FFT-based frequency enhancement, and gated fusion is introduced to better model the structured patterns of parking lot scenes. In addition, a UIoU+ loss tailored to rectangular geometry is proposed to improve localization quality. Sensitivity analysis and repeated experiments show that the method is stable and statistically reliable. All main metrics are evaluated on an independent held-out test set to ensure generalization. Extensive experiments demonstrate that each component brings consistent performance gains. The proposed model achieves 99.44 ± 0.12% mAP@0.5, 90.31 ± 0.27% mAP@0.5:0.95, 99.27 ± 0.15% precision, and 99.00 ± 0.18% recall on the self-built UAV Parking Lot dataset. Its mAP@0.5:0.95 is 26.01 percentage points higher than the YOLOv11n baseline. Consistent performance improvements are also validated on two additional public benchmarks (CARPK and PKLot), confirming the generalization of the proposed method beyond the self-built dataset. Most importantly, the method supports real-time inference on embedded UAV platforms and achieves state-of-the-art performance among lightweight detectors, making it an ideal solution for practical intelligent parking management. Ablation studies further confirm the complementary synergy between the proposed backbone, attention module, and loss function. Full implementation code, pre-trained weights, and detailed reproduction guidelines are publicly available to ensure research reproducibility. Full article
(This article belongs to the Special Issue Intelligent Transportation for Integrated Mobile System: AI-Driven Technologies, Engineering Systems, and Industrial Applications)
►▼ Show Figures

Figure 1

26 pages, 5757 KB  
Article
Valorization of Pecan Shell Waste into Magnetic Fe3O4@Biocarbon for Arsenic Removal from Water: Optimization Using Fuzzy Decision Networks and RSM
by Sasirot Khamkure, Chidentree Treesatayapun, Audberto Reyes-Rosas, Alejandro Zermeño-González, Javier de Jesús Cortés-Bracho, Jose-Alexander Gil-Marin, Etelberto Cortez-Quevedo, Nakorn Tippayawong and Patiroop Pholchan
Technologies 2026, 14(8), 515; https://doi.org/10.3390/technologies14080515 - 20 Aug 2026
Viewed by 231
Abstract
This study converted pecan shell waste into magnetic Fe3O4@biocarbon for arsenic (V) removal from aqueous medium. A preliminary test was conducted on a binary system of arsenic (V) and lead. A dual-optimization approach was applied using a fuzzy decision [...] Read more.
This study converted pecan shell waste into magnetic Fe3O4@biocarbon for arsenic (V) removal from aqueous medium. A preliminary test was conducted on a binary system of arsenic (V) and lead. A dual-optimization approach was applied using a fuzzy decision network for material synthesis and response surface methodology (RSM) for adsorption performance. The fuzzy model predicted FS2 as an optimal design (particles between 0.38–0.7 mm in size, Fe ratio of 1:1) with high accuracy (R2 > 0.95). In the RSM, removal efficiency and adsorption capacity were estimated to find out the influential parameters, which turned out to be adsorbent dose and As(V) concentration. It was predicted that removal capacity would remove 90.99% As(V) at the dose of 0.95 mg L−1 As(V), pH 3.4 and 1.8 g L−1 dose. However, it was also revealed that the qe model provided a higher confidence (final conditions: 9.95 mg L−1 As(V), pH 3.0 and 0.5 g L−1 dose; qe = 3.96 mg g−1). Evaluation of Fe3O4@biocarbon was conducted at 0.217 mg L−1 As and 34.3 mg L−1 Pb. This suggests removal of lead in addition to arsenic, indicating that the method can be used in multicomponent metal removal. FTIR and XPS analysis showed that removal of As(V) took place through surface complexation with Fe-O and oxygen-containing functional groups. Full article
(This article belongs to the Special Issue Sustainable Technologies and Waste Valorisation Technologies)
►▼ Show Figures

Figure 1

26 pages, 1554 KB  
Article
Force–Depth–Stiffness Modeling of Rotary Ball-Burnished Dimples on an External Cylinder for Adaptive Guideway Stiffness Mapping
by Kirill A. Bashmur, Alexander V. Zagulyaev and Ivan S. Nekrasov
Technologies 2026, 14(8), 514; https://doi.org/10.3390/technologies14080514 - 19 Aug 2026
Viewed by 540
Abstract
This study develops a theoretical and computational mechanics framework for regular dimples produced by rotary ball burnishing on an external cylindrical surface. The model combines the local quadratic ball–cylinder gap, an effective mean indentation pressure Heff, an unloading factor λ, [...] Read more.
This study develops a theoretical and computational mechanics framework for regular dimples produced by rotary ball burnishing on an external cylindrical surface. The model combines the local quadratic ball–cylinder gap, an effective mean indentation pressure Heff, an unloading factor λ, residual dimple geometry, a Greenwood–Williamson pressure–approach law for the load-bearing lands, and an elastic spectral reference calculation. The dimple area fraction Fn is obtained from the periodic union of loaded-imprint footprints for the nominal stiffness maps, whereas the residual profile determines the specific oil capacity, defined as retained cavity volume per unit nominal area. Numerical checks include algebraic consistency, mesh-converged periodic FFT-BEM calculations, and a separate sinusoidal benchmark. For a representative 3mm ball and 25mm cylinder with Heff=2GPa, the model maps burnishing force and texture pitch to idle- and working-pressure secant stiffness. Within the stated range Fn≤0.20, the low-fidelity index preserves the ordering of all evaluated non-tied design points; the mean and maximum differences from the spectral reference are 6.6% and 15.2%. A discrete force–pitch grid yields three feasible points under illustrative stiffness windows and two candidates after non-dominated sorting and secondary selection by specific oil capacity. The selected textures reduce idle-pressure stiffness slightly more than working-pressure stiffness, increasing the nonlinearity ratio from 5.70 to 5.91. The framework provides a reproducible model-based tool for preliminary force–pitch selection; application to a specific material–process pair requires identification of Heff, λ, and the load-bearing-land response and validation against process-specific measurements. Full article
(This article belongs to the Section Manufacturing Technology)
►▼ Show Figures

Graphical abstract

30 pages, 2373 KB  
Article
Deep Robust Adaptive Beamforming via Element-Wise Manifold Calibration and Regularized Response Projection
by Wenjing Zhu, Jinhai Li, Chaosan Yang, Luqing Luo, Wenxue Liu and Xin Qiu
Technologies 2026, 14(8), 513; https://doi.org/10.3390/technologies14080513 - 19 Aug 2026
Viewed by 213
Abstract
Limited snapshots and element-wise gain–phase mismatch jointly impair covariance estimation and array manifold accuracy in uniform planar arrays. This paper proposes a deep robust adaptive beamforming framework that combines statistical base-weight generation, element-wise array manifold calibration, and regularized response projection. The base-weight network [...] Read more.
Limited snapshots and element-wise gain–phase mismatch jointly impair covariance estimation and array manifold accuracy in uniform planar arrays. This paper proposes a deep robust adaptive beamforming framework that combines statistical base-weight generation, element-wise array manifold calibration, and regularized response projection. The base-weight network extracts finite-snapshot covariance information, whereas the calibration network estimates a physically bounded element-wise complex-gain vector from covariance features and nominal direction context. Phase-aligned auxiliary supervision makes the calibration loss invariant to the unidentifiable common phase and is required only during training. The calibrated steering vectors define a closed-form minimum-distance projection that preserves the normalized base weight’s desired direction response while suppressing the calibrated interference responses. Across three training seeds, the method achieves 23.43 ± 0.06 dB output SINR and a −52.48 ± 0.09 dB average null level, improving the former by 5.64 dB and deepening the latter by 5.11 dB relative to the best-performing baseline under the main test distribution. Experiments on mismatch severity, input SNR, snapshot number, direction-of-arrival errors, controlled ablations, and computational cost characterize the performance and limitations of the method under the stated synthetic-array model. Full article
►▼ Show Figures

Figure 1

23 pages, 2875 KB  
Article
A Web-Based Digital Twin for Traffic and Air Quality Monitoring: A Prototype Study in Almaty, Kazakhstan
by Saya Sapakova, Askar Sapakov, Omirlan Auyelbekov, Lyailya Tukenova, Sakhybay Tynymbayev, Zhomart Ualiyev, Aigul Skakova and Assem Kabdoldina
Technologies 2026, 14(8), 512; https://doi.org/10.3390/technologies14080512 - 18 Aug 2026
Viewed by 289
Abstract
Urban air pollution driven by road traffic poses a significant public health challenge in cities with high vehicle density and frequent congestion, particularly in topographically constrained environments such as Almaty, Kazakhstan. This study presents a web-based digital twin prototype for the integrated monitoring [...] Read more.
Urban air pollution driven by road traffic poses a significant public health challenge in cities with high vehicle density and frequent congestion, particularly in topographically constrained environments such as Almaty, Kazakhstan. This study presents a web-based digital twin prototype for the integrated monitoring and analysis of traffic flow and air quality in Almaty, Kazakhstan. The system autonomously collects data from the TomTom Traffic, OpenWeather Air Pollution, and WAQI APIs and official population statistics for five fixed monitoring stations, computing traffic density, vehicles per hour, road congestion, estimated CO2 emissions, an air pollution index, and a population exposure index, and providing real-time dashboard visualization alongside longitudinal data accumulation. Over a 50-day deployment (26 May–16 July 2026), 4961 real co-located observations across 18 active days were analyzed; records generated by the prototype’s fallback mechanism during API outages were excluded from the scientific analysis. During this summer period, PM2.5 was low (mean ≈ 6 µg/m3) and spatially uniform, and showed no statistically significant association with traffic intensity (r ≈ −0.03). Traffic indicators were instead weakly but significantly correlated with the vehicle-emitted gases NO2 (r ≈ 0.16) and CO (r ≈ 0.10), which they preceded by up to about one hour. A short-horizon PM2.5 nowcasting task, evaluated across temporal resolutions with time-series cross-validation, was dominated by temporal persistence, with traffic-derived features contributing negligibly. The absence of a summer traffic–PM2.5 association does not preclude such a relationship during the heating season, when particulate levels are higher. The results indicate that the traffic–air-quality relationship in Almaty is season- and pollutant-dependent, and demonstrate a lightweight, reproducible platform suitable for longitudinal monitoring and future heating-season assessment. Full article
(This article belongs to the Topic Digital Twins and Artificial Intelligence for Advancing Smart Green Building and City Resilience)
►▼ Show Figures

Graphical abstract

20 pages, 1077 KB  
Systematic Review
From Algorithm Development to Clinical Implementation: A Systematic Review of Artificial Intelligence in Cardiovascular Medicine
by Lucía Osoro, Elena Arbelo, Deirdre A. Lane, Davide Antonio Mei, Nikola Kozhuharov, Maura Zylla, Brendan Collins, Panos Vardas, Giuseppe Boriani, Joseph Figueras, José Luis Merino, Helmut Pürerfellner, Haran Burri and Rubén Casado-Arroyo
Technologies 2026, 14(8), 511; https://doi.org/10.3390/technologies14080511 - 18 Aug 2026
Viewed by 498
Abstract
Artificial intelligence (AI) is transforming cardiovascular medicine through applications in disease detection, diagnosis, risk prediction, and clinical decision support. However, the clinical implementation of these technologies remains poorly characterised. This systematic review evaluated the current landscape of AI applications in cardiovascular medicine, focusing [...] Read more.
Artificial intelligence (AI) is transforming cardiovascular medicine through applications in disease detection, diagnosis, risk prediction, and clinical decision support. However, the clinical implementation of these technologies remains poorly characterised. This systematic review evaluated the current landscape of AI applications in cardiovascular medicine, focusing on implementation maturity and clinical translation. The review followed PRISMA guidelines and a prospectively registered PROSPERO protocol. Data extraction included study characteristics, cardiovascular domain, AI methodology, clinical application, validation strategy and implementation maturity, assessed using a predefined five-level framework. AI methodologies were classified as conventional machine learning, deep learning, hybrid ML/deep learning, multimodal AI, or large language models/generative AI. Seventy-four studies met the eligibility criteria. Conventional machine learning was the most frequently used methodology (47.3%), followed by deep learning (41.9%), whereas multimodal AI (5.4%), hybrid ML/deep learning (2.7%), and large language models/generative AI (2.7%) were uncommon. Applications focused mainly on screening and early detection (31.1%), risk stratification and prognosis (25.7%), treatment planning (16.2%), diagnosis (13.5%), and monitoring (12.2%). Most studies reached implementation maturity Level 3 (clinical validation, 47.3%) or Level 2 (technical validation, 35.1%), while only 13.5% achieved routine clinical implementation (Level 5) and 4.1% reached clinical deployment (Level 4). Although AI demonstrated promising diagnostic and prognostic performance across multiple cardiovascular conditions, most applications remain at the validation stage. Future research should prioritise implementation science, pragmatic evaluation, and real-world evidence to facilitate routine adoption and maximise patient benefit and healthcare value. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence in Healthcare and Information Processing)
►▼ Show Figures

Figure 1

22 pages, 1796 KB  
Article
Power Optimization and Vibration Suppression Method for Wind Farms Based on Risk Assessment Under Sandstorm Conditions
by Jun Zhao, Yuxiang Li, Xueting Cheng, Juan Wei, Weiru Wang, Lu Liu and Yu Yang
Technologies 2026, 14(8), 510; https://doi.org/10.3390/technologies14080510 - 17 Aug 2026
Viewed by 636
Abstract
In response to the severe challenges posed by extreme sandstorm weather to the operational safety of WTs and grid stability, this paper proposes an MPC-based power optimization control strategy for WFs. Simulation results indicate that, compared with the traditional PD strategy, the proposed [...] Read more.
In response to the severe challenges posed by extreme sandstorm weather to the operational safety of WTs and grid stability, this paper proposes an MPC-based power optimization control strategy for WFs. Simulation results indicate that, compared with the traditional PD strategy, the proposed MPC strategy significantly reduces the active power fluctuations of individual WTs, smoothly tracks grid dispatch orders with an overall power tracking accuracy improvement, and effectively lowers the operational risk index of turbines across the farm (ranging from 6.90% to 57.14% for the ten evaluated turbines). Furthermore, the proposed strategy substantially mitigates the angular acceleration fluctuation amplitude of the drive train components (e.g., reducing peak angular accelerations of drive-train masses by up to 35%) and reduces the fore-aft and lateral displacement oscillations of the tower top (reducing peak displacement variations by approximately 25% and 40%, respectively), providing comprehensive structural load mitigation while ensuring WF power output stability and grid safety. This study provides a theoretical basis and technical approach for the intelligent operation and risk prevention and control of WFs under extreme meteorological conditions. Full article
(This article belongs to the Special Issue Next-Generation Distribution System Planning, Operation, and Control—Second Edition)
►▼ Show Figures

Figure 1

23 pages, 6084 KB  
Article
Microstructure and Corrosion Resistance of Sn-3Ag-0.5Cu-xBi Solders
by Michaela Halmanová, Ivona Černičková, Patrícia Danišovičová, Patrik Šulhánek, Marián Drienovský, Xabier Zubizarreta Cuerda, Róbert Havlík, Libor Ďuriška and Marián Palcut
Technologies 2026, 14(8), 509; https://doi.org/10.3390/technologies14080509 - 17 Aug 2026
Viewed by 303
Abstract
Sn-3Ag-0.5Cu-xBi alloys (SAC305-xBi) represent promising lead-free alternatives for low-temperature soldering. Low Bi concentrations can strengthen SAC-based solders through solid-solution strengthening, refining β–Sn grains and transforming needle-like Ag3Sn phases into equiaxed morphologies. However, excessive Bi alloying may induce precipitation of brittle Bi [...] Read more.
Sn-3Ag-0.5Cu-xBi alloys (SAC305-xBi) represent promising lead-free alternatives for low-temperature soldering. Low Bi concentrations can strengthen SAC-based solders through solid-solution strengthening, refining β–Sn grains and transforming needle-like Ag3Sn phases into equiaxed morphologies. However, excessive Bi alloying may induce precipitation of brittle Bi particles, cause microstructural instability and interfacial degradation, thereby weakening the solder joint performance. As such, the concentration of Bi in the SAC305 alloys should be carefully controlled. In this work, the microstructure and corrosion behavior of Sn-3Ag-0.5Cu-xBi solder alloys (SAC305-xBi, where x = 0, 1, 2 and 4 wt. %) were investigated. Attention has been paid to the influence of low Bi concentration on the microstructure, morphology, and chemical composition of the phases present in the solder alloys before and after corrosion exposure. The alloys were prepared by induction melting of Sn, Ag, Cu and Bi lumps under Ar gas. The microstructure of the SAC305 and SAC305-1Bi alloys represented a hypoeutectic microstructure with dendritic (Sn) grains and the ternary eutectic, consisting of (Sn), Cu6Sn5 and Ag3Sn, located in inter-dendritic regions. In the SAC305-2Bi and SAC305-4Bi alloys, a segregation of (Bi) particles was observed in addition to dendritic (Sn) and ternary eutectic. The (Bi) particles were located at the (Sn)Ag3Sn interface in the inter-dendritic spaces of the (Sn) solid solution. The corrosion resistance of the as-cast alloys was studied in aqueous NaCl electrolyte (3.5 wt. %) using electrochemical methods. Open circuit potentials of the alloys were found to increase with increasing concentration of Bi. The highest corrosion current was found for the SAC305-1Bi alloy. It was observed that micro-galvanic cells at the Sn-Ag3Sn interface were the initiating factors of corrosion in the SAC305-1Bi alloy. The corrosion activity of the SAC305-1Bi alloy is related to the high density of fine Ag3Sn particles. The higher fraction of Ag3Sn particles provided a dense network of local galvanic interaction sites, leading to the acceleration of the corrosion rate. The presence of discrete Bi precipitates in the SAC305-2Bi and SAC305-4Bi alloys, on the other hand, partially reduced the risk of galvanic corrosion. Since Bi has a higher standard electrode potential compared to Sn, the Bi/Ag3Sn and Bi/Cu6Sn5 couples were less prone to corrosion. The corrosion mechanism of the SAC305-xBi alloys is discussed, and results are compared to previously studied SAC-Bi alloys. Full article
(This article belongs to the Section Innovations in Materials Science and Materials Processing)
►▼ Show Figures

Figure 1

45 pages, 6833 KB  
Article
Toward the Systematic Design and Study of Mixed Reality Serious Games in Higher Education: Design Recommendations and a Multi-Dimensional Methodological Framework
by Lauren Genith Isaza Dominguez, Nestor Suat-Rojas and Alfonso A. Portacio
Technologies 2026, 14(8), 508; https://doi.org/10.3390/technologies14080508 - 14 Aug 2026
Viewed by 305
Abstract
Mixed Reality (MR) serious games combine immersive technologies with game-based learning to support training, skill development, and decision-making across diverse disciplines in university education. Although previous research has demonstrated improvements in engagement, usability, and learning outcomes, less attention has been devoted to developing [...] Read more.
Mixed Reality (MR) serious games combine immersive technologies with game-based learning to support training, skill development, and decision-making across diverse disciplines in university education. Although previous research has demonstrated improvements in engagement, usability, and learning outcomes, less attention has been devoted to developing design recommendations and methodological approaches for studying MR serious games. A theory-derived Meta Quest 3-based MR serious game for diagnostic classification was developed by integrating learning theories, gameplay mechanics, and gamification features while functioning as both an educational intervention and a research instrument. The system was evaluated through two complementary studies involving undergraduate students: the first compared learning outcomes across instructional approaches, whereas the second examined learner performance and transfer using a mixed-method approach incorporating objective metrics, questionnaires, and interviews. The proposed system achieved learning outcomes comparable to expert-guided field training while significantly outperforming classroom instruction and self-directed study. Significant transfer to real-world diagnostic tasks was demonstrated, and complementary evidence was triangulated to derive preliminary design recommendations and a multi-dimensional methodological framework. These contributions provide an initial foundation for the systematic design and study of MR serious games in higher education. Full article
(This article belongs to the Special Issue Disruptive Technologies: Big Data, AI, IoT, Games, and Mixed Reality)
►▼ Show Figures

Figure 1

26 pages, 9153 KB  
Article
Biathlon Training on an Unstable Platform in Non-Immersive Virtual Reality: Exercise Intensity, Enjoyment, and Flow State in Adolescents
by Jacek Polechoński, Jakub Ryśnik, Anna Witkowska and Małgorzata Dębska-Janus
Technologies 2026, 14(8), 507; https://doi.org/10.3390/technologies14080507 - 14 Aug 2026
Viewed by 277
Abstract
Engaging adolescents in regular physical activity remains a major public health challenge; consequently, increasing attention is being directed toward technologies that make exercise more attractive, task-oriented, and engaging. Active video games and non-immersive virtual reality systems are particularly promising because they combine physical [...] Read more.
Engaging adolescents in regular physical activity remains a major public health challenge; consequently, increasing attention is being directed toward technologies that make exercise more attractive, task-oriented, and engaging. Active video games and non-immersive virtual reality systems are particularly promising because they combine physical exertion with feedback, gamification, and movement-based interaction. This study examined whether a biathlon exergame performed on an unstable ICAROS Cloud platform using the ICAROS App can elicit favorable physiological and psychological responses in adolescents, and whether these responses depend on body position. Eighty secondary school students, including 41 girls and 39 boys, completed two 10 min Biathlon trials: one in a standing position and one in a quadruped kneeling position, with the trial order counterbalanced. The percentages of maximum heart rate (%HRmax), perceived exertion, enjoyment of physical activity, and flow state were assessed. The standing condition elicited higher exercise intensity than quadrupled kneeling (71.42 ± 9.61 vs. 62.09 ± 9.04%HRmax; p < 0.001), and was also associated with higher perceived exertion, enjoyment, and flow. Similar response patterns were observed in girls and boys. These findings highlight the potential of unstable-platform exergaming as a practical and engaging approach to technology-supported physical activity promotion in developmental ages. Full article
(This article belongs to the Special Issue Emerging Technologies in Physical Activity Monitoring and Promotion for Developmental Ages)
►▼ Show Figures

Figure 1

26 pages, 1270 KB  
Article
Anomaly Score-Based Cross-Machine Wind Turbine Component Diagnosis: A Case Study and Benchmark
by Kenan Weber, Tobias Hoinka and Christine Preisach
Technologies 2026, 14(8), 506; https://doi.org/10.3390/technologies14080506 - 13 Aug 2026
Viewed by 344
Abstract
Reliable wind turbine component diagnosis requires cross-machine knowledge transfer since verified fault cases are rare. However, coarse fault interval annotations and turbine-specific operating behavior make this transfer difficult. This paper introduces a benchmark framework for cross-machine wind turbine component diagnosis on a new [...] Read more.
Reliable wind turbine component diagnosis requires cross-machine knowledge transfer since verified fault cases are rare. However, coarse fault interval annotations and turbine-specific operating behavior make this transfer difficult. This paper introduces a benchmark framework for cross-machine wind turbine component diagnosis on a new industrial dataset derived from Supervisory Control and Data Acquisition (SCADA) and vibration-derived kinematics data. The dataset is publicly available upon request and contains anomaly score-based embeddings. These embeddings are feature vectors whose entries quantify how strongly signals or component-related features deviate from learned normal behavior. The benchmark compares classical machine learning models, deep learning models, adversarial domain adaptation variants, and a simple baseline. Hyperparameter selection is performed without target labels using source classification loss, target prediction entropy, or Soft Neighborhood Density (SND). Our experiments show that, in the SCADA validation stage, source classification loss achieves the highest mean case diagnosis score among the evaluated objectives. In our evaluation, simple baselines remain highly competitive. The SCADA component score baseline achieves the highest test case diagnosis accuracy, while an ensemble of one-class support vector machines achieves the highest kinematics test case diagnosis accuracy. These findings indicate that anomaly score-based embeddings provide a useful representation for real-world component diagnosis, but that the small number of verified cases, coarse fault interval annotations, and partial label space mismatch remain major obstacles for reliable cross-machine adaptation. Full article
(This article belongs to the Special Issue Artificial Intelligence for Smart Fault Diagnosis and Fault Tolerant Control)
►▼ Show Figures

Figure 1

22 pages, 12132 KB  
Article
Improved Technology with Backfilling in Potash Mines
by Denis A. Stadnik, Nino M. Stadnik, Alexey G. Zhilin, Ruslan G. Kisnichian and Eduard E. Permyakov
Technologies 2026, 14(8), 505; https://doi.org/10.3390/technologies14080505 - 12 Aug 2026
Viewed by 368
Abstract
The development of potash deposits is generally accompanied by large losses of minerals in the subsurface. The main reason for these losses is the use of a room-and-pillar mining system, where left pillars hold the overlying rock strata and aquifers located above the [...] Read more.
The development of potash deposits is generally accompanied by large losses of minerals in the subsurface. The main reason for these losses is the use of a room-and-pillar mining system, where left pillars hold the overlying rock strata and aquifers located above the productive seams. Over time, the bearing elements of the mining system begin to deteriorate, leading to a loss of continuity of the water-protective stratum, the formation of water-conducting fractures, salt dissolution, and consequently, the flooding of the potash mine. The most effective method for solving production problems in the field of increasing mineral recovery and mine safety is the introduction of backfilling technology. The aim of the study is to identify the effect of backfilling on the stress–strain state of the rock mass in the vicinity of stopping and backfilling operations, to develop a technology for potash ore extraction with increased recovery, and also to solve the fundamental issue of the proposed technology, namely, the transport and property considerations of the backfill mixture. Numerical modeling methods and analytical derivations of calculation formulas for backfill mixture transport are used in the work. A comparison of dry, hydraulic, and hardening backfill mixtures is carried out. The study established that hardening backfill ensures a faster transition to the stage of mining the remaining reserves. A technology for pillar extraction with the leaving of technologically necessary narrow pillars is proposed, allowing for the safety of mining operations. Formulas are derived for calculating the required strength of the backfill based on the loading degree of the technological pillar. Transportability criteria are formulated, and a calculation procedure for pipeline transport parameters under gravity and gravity-pneumatic modes is developed. The proposed technology for potash ore extraction with hardening backfill allows for increased mineral recovery while maintaining safe conditions for undermining the water-protective stratum. Full article
(This article belongs to the Section Construction Technologies)
►▼ Show Figures

Figure 1

27 pages, 29684 KB  
Article
Cross-Technology Prediction of PV Cell Output Power Using a Convolutional Hierarchical Mixture of Experts Model
by Héctor Felipe Mateo-Romero, Luis Hernández-Callejo, Miguel Ángel González Rebollo, Valentín Cardeñoso-Payo, Victor Alonso Gómez, Leonardo Cardinale-Villalobos, Jose Ignacio Morales Aragonés, Sara Gallardo Saavedra, Abel Méndez Porras and Mario Carbonó dela Rosa
Technologies 2026, 14(8), 504; https://doi.org/10.3390/technologies14080504 - 12 Aug 2026
Viewed by 330
Abstract
Accurate prediction of photovoltaic (PV) cell power from electroluminescence (EL) images is a key enabler for automated quality assessment and performance estimation in PV manufacturing and diagnostics. However, most existing image-based deep learning models are developed and evaluated for a single PV cell [...] Read more.
Accurate prediction of photovoltaic (PV) cell power from electroluminescence (EL) images is a key enabler for automated quality assessment and performance estimation in PV manufacturing and diagnostics. However, most existing image-based deep learning models are developed and evaluated for a single PV cell technology, limiting their ability to generalize across the wide variety of cell types used in practice. This work investigates the impact of PV cell technology on power prediction accuracy and proposes a novel Convolutional Hierarchical Mixture of Experts (CHME) architecture to overcome these generalization limitations. First, convolutional neural networks and feature-based machine learning models are evaluated on multiple PV cell technologies. While technology-specific convolutional models achieve low mean absolute errors (MAEs) of 0.02–0.04 when tested on the same cell type, their performance deteriorates substantially (MAEs of 0.08–0.23) when applied to different technologies. Feature-based models exhibit greater robustness across technologies but at the cost of lower prediction accuracy. To address these limitations, the proposed CHME model combines multiple pretrained technology-specific convolutional experts with a discriminator network that automatically identifies the PV cell technology and selects the most appropriate expert for power prediction. Experimental results demonstrate that CHME achieves the best overall performance, reducing the MAE to 0.0262 compared with 0.0298 for the best standalone convolutional model, while preserving adaptability to heterogeneous datasets. These results demonstrate that explicitly accounting for PV cell technology significantly improves image-based power prediction and that the proposed hierarchical mixture-of-experts framework provides an accurate, scalable, and easily retrainable solution for real-world PV diagnostic systems. Full article
►▼ Show Figures

Figure 1

19 pages, 5771 KB  
Article
A Multi-Physics Continuous Integral State-Space Model for Battery Health Prognosis Under Dynamic Tropical Environments
by Uvi Desi Fatmawati, Iwa Garniwa, Faiz Husnayain, Sunarta and Pranda Mulya Putra Garniwa
Technologies 2026, 14(8), 503; https://doi.org/10.3390/technologies14080503 - 12 Aug 2026
Viewed by 343
Abstract
Tracking capacity fade and predicting the lifespan of Lithium Iron Phosphate (LiFePO4) batteries under calendar aging are crucial for the reliability of Battery Energy Storage Systems (BESSs) in tropical regions. Conventional empirical models often rely on static environmental averages and neglect [...] Read more.
Tracking capacity fade and predicting the lifespan of Lithium Iron Phosphate (LiFePO4) batteries under calendar aging are crucial for the reliability of Battery Energy Storage Systems (BESSs) in tropical regions. Conventional empirical models often rely on static environmental averages and neglect coupled thermal–hygroscopic dynamics. To address these limitations, this paper introduces a multi-physics coupled state-space-based continuous integral model for battery degradation under dynamic tropical boundary conditions. The primary novelty of this research lies in the development of a continuous-time multi-physics state-space degradation model that explicitly captures the interconnected interactions between temperature, humidity, and State of Charge (SoC) under dynamically varying tropical microclimates. Calendar aging tests were conducted for 180 days inside an environmental test chamber under tropical microclimate conditions (average of 29.91 °C, RH of 77.26%), with reference performance tests executed at a low C-rate of C/20 to extract static electrochemical capacity. Parameter identification using an Ordinary Least Squares (OLS) solver demonstrates high model fitting, with R-squared values ranging from 0.8229 to 0.9429. Extrapolation results provide realistic end-of-life projections between 8.9 and 59.8 years and successfully identify the critical physical transition points P1 and P2 at the Solid Electrolyte Interphase (SEI) layer. Overall, this research provides a prognostic instrument for optimizing the operational management of utility-scale BESS in tropical climates. Full article
►▼ Show Figures

Figure 1

32 pages, 21297 KB  
Article
HGNetV2-YOLO: An Efficient and Lightweight Framework for Mechanical Component Detection in Industrial Scenes
by Bangqiang Han, Qing Cheng, Shengbin Wang and Wenquan Huang
Technologies 2026, 14(8), 502; https://doi.org/10.3390/technologies14080502 - 11 Aug 2026
Viewed by 377
Abstract
Mechanical component detection in industrial scenes is challenged by cluttered backgrounds, large-scale variation, specular reflection, high inter-class similarity, and class imbalance. To address the above problems, this paper proposes a lightweight YOLO-style detector that integrates a PP-HGNetV2 tiny backbone, an enhanced normalization-based attention [...] Read more.
Mechanical component detection in industrial scenes is challenged by cluttered backgrounds, large-scale variation, specular reflection, high inter-class similarity, and class imbalance. To address the above problems, this paper proposes a lightweight YOLO-style detector that integrates a PP-HGNetV2 tiny backbone, an enhanced normalization-based attention module (ImNAM), and an improved complete intersection-over-union loss (ImCIoU). The HGNetV2 backbone enhances hierarchical multi-scale feature extraction and keeps the deployable computational complexity low. ImNAM has been modified to enhance discriminative representation by introducing dual-statistics channel weighting, orthogonal edge-aware spatial modeling and bipolar adaptive residual gating. ImCIoU enhances the accuracy of localization by combining quality-aware box scaling, scale-sensitive modulation and dynamic IoU-guided weighting. A class-balancing augmentation pipeline was applied to the four-category industrial dataset of Bearing, Bolt, Gear and Nut. All experimental results are reported as the mean ± standard deviation of five independent two-tailed training runs with different random seeds, and statistical significance is verified by paired t-tests (p < 0.05) with Bonferroni correction for multiple comparisons. Experimental results show that the proposed method achieves 90.82 ± 0.35% mean average precision (mAP@0.5), 91.95 ± 0.42% precision, and 82.98 ± 0.51% recall, outperforming nine mainstream lightweight detectors, including the latest YOLOv12n (2025) and RT-DETR-tiny. Extended evaluation on mAP@0.5:0.95, per-class AP and F1 score further confirms the advantages in localization accuracy and classification performance. Ablation studies confirm that the HGNetV2 family backbone provides the largest performance gain, while the improved attention mechanism and regression loss further enhance localization accuracy and robustness. With only 4.44 M parameters and 9.96GFLOPs, the proposed detector has achieved a good accuracy–efficiency trade-off and shows strong potential for intelligent industrial inspection on resource-constrained platforms, subject to further hardware-level deployment verification. Full article
(This article belongs to the Special Issue Agentic AI-Driven Optimization in Advanced Manufacturing Systems)
►▼ Show Figures

Figure 1

42 pages, 10695 KB  
Article
Efficient Techniques for Low-Rank Tensor Approximation and Applications in Robust Object Detection
by Salman Ahmadi-Asl, Naeim Rezaeian, Cesar F. Caiafa and André L. F. de Almeida
Technologies 2026, 14(8), 501; https://doi.org/10.3390/technologies14080501 - 10 Aug 2026
Viewed by 318
Abstract
This paper introduces efficient randomized fixed-precision and single-pass algorithms for low-tubal-rank approximation of third-order tensors. The proposed fixed-precision algorithms are faster and more efficient than the existing algorithms for approximating the truncated tensor SVD (T-SVD). Furthermore, unlike existing single-pass methods, which directly extend [...] Read more.
This paper introduces efficient randomized fixed-precision and single-pass algorithms for low-tubal-rank approximation of third-order tensors. The proposed fixed-precision algorithms are faster and more efficient than the existing algorithms for approximating the truncated tensor SVD (T-SVD). Furthermore, unlike existing single-pass methods, which directly extend early, unstable matrix algorithms, the proposed approach adapts enhanced and stabilized matrix techniques to the tensor setting. Through extensive numerical experiments, we identify a critical flaw in current single-pass algorithms: using sketching parameters of equal size often produces ill-conditioned tensor least-squares problems, leading to inaccurate approximations. The proposed algorithms are demonstrably robust to this issue, achieving superior performance under identical conditions. We also evaluate the robustness of existing single-pass methods on real-world data tensors, including images and videos, a topic that has not been thoroughly examined before. Numerical results confirm the effectiveness of the proposed methods. Three applications are presented: image compression, video super-resolution, and deep learning. Full article
►▼ Show Figures

Figure 1

26 pages, 10189 KB  
Article
Smart Healthcare Engineering: A Data-Driven Educational Framework for Psychrometric Analysis and Air Handling Systems in Hospitals
by Carlos Jesús Sánchez-Morales and Julia Claudia Mirza-Rosca
Technologies 2026, 14(8), 500; https://doi.org/10.3390/technologies14080500 - 10 Aug 2026
Viewed by 292
Abstract
This paper presents a data-driven educational framework for teaching psychrometry and air quality control in hospitals, developed within an international pilot project involving universities and hospitals in Spain, Romania, and Turkey. The objective of this pilot study is to examine a multidisciplinary framework [...] Read more.
This paper presents a data-driven educational framework for teaching psychrometry and air quality control in hospitals, developed within an international pilot project involving universities and hospitals in Spain, Romania, and Turkey. The objective of this pilot study is to examine a multidisciplinary framework that equips engineering students with essential technical skills for managing hospital infrastructure, particularly in critical areas like operating rooms and intensive care units. The methodology integrates theoretical instruction, analogue instruments, and digital technologies, including Arduino-based sensing and AI tools, to facilitate data interpretation and critical thinking. By bridging manual measurements with digital monitoring, the framework aims to equalize proficiency among students from diverse engineering backgrounds. Quantitative results from 23 participants provide preliminary evidence of academic growth, consistent with the hypothesis that this integrated approach may facilitate conceptual mastery. This work offers preliminary insights into the advancement of data-driven modelling in engineering education, emphasizing the significance of multidisciplinary training and international collaboration in preparing future professionals for the oversight, operational management, and maintenance of modern healthcare facilities. Full article
(This article belongs to the Collection Technology Advances in IoT Learning and Teaching)
►▼ Show Figures

Figure 1

37 pages, 5260 KB  
Article
Relation-Consistency Group Contrastive Learning for Robust Multispectral Remote Sensing Classification
by Mohcine Karroum and Noureddine En-nahnahi
Technologies 2026, 14(8), 499; https://doi.org/10.3390/technologies14080499 - 10 Aug 2026
Viewed by 279
Abstract
Multispectral remote sensing classification benefits from the complementary information carried by visible (VIS), near-infrared (NIR), and short-wave infrared (SWIR) Sentinel-2 bands, yet most deep models process them as a single stacked tensor without explicitly preserving their inter-group relationships. We propose Relation-Consistency Group Contrastive [...] Read more.
Multispectral remote sensing classification benefits from the complementary information carried by visible (VIS), near-infrared (NIR), and short-wave infrared (SWIR) Sentinel-2 bands, yet most deep models process them as a single stacked tensor without explicitly preserving their inter-group relationships. We propose Relation-Consistency Group Contrastive Learning (Group-CL-RC), a robustness-oriented framework combining group-level contrastive alignment with a relation-consistency regularizer defined over a compact VIS–NIR–SWIR similarity descriptor. The method is evaluated on EuroSAT All Bands using four backbones under radiometric drift, spatial masking, K-drop band removal, and compound spectral–spatial corruption (CS2C), and externally validated on Sentinel-2-only SEN12MS under standard and seasonal-shift protocols. Group-CL-RC preserves strong clean performance and yields statistically supported robustness gains over the multispectral-only baseline, with the largest improvements under K-drop and CS2C. SEN12MS supports the transfer of these robustness trends beyond EuroSAT, while showing that gains over standard Group-CL remain perturbation-dependent. Ablation studies further indicate that relation consistency is an effective robustness mechanism, particularly when spectral-group availability is degraded. Relation-deformation diagnostics show that Group-CL-RC primarily reduces decision-level sensitivity to relational distortions rather than uniformly minimizing raw deformation. Overall, inter-group relational geometry provides an interpretable and effective robustness target under controlled structured spectral and spectral–spatial degradation. Full article
►▼ Show Figures

Graphical abstract

36 pages, 2052 KB  
Article
A Novel Ordering Index for Evaluating Feature Selection Quality in Personalized Smart Healthcare
by Harald Rietdijk, Daniëlle Talen, Patricia Conde-Cespedes, Talko Dijkhuis, Hilbrand Oldenhuis and Maria Trocan
Technologies 2026, 14(8), 498; https://doi.org/10.3390/technologies14080498 - 8 Aug 2026
Viewed by 297
Abstract
Wearable technology and the Internet of Things have increased access to personal data, enabling applications that deliver individualized treatment and therapy within clinical pathways. To optimize coaching and interventions within such pathways, it is essential to identify all relevant factors in the available [...] Read more.
Wearable technology and the Internet of Things have increased access to personal data, enabling applications that deliver individualized treatment and therapy within clinical pathways. To optimize coaching and interventions within such pathways, it is essential to identify all relevant factors in the available data. Feature selection can be a useful tool for achieving this, but with small, high-dimensional datasets, common in healthcare, it can be challenging. The goal of this study is to develop a method for identifying the most relevant features in small, high-dimensional datasets and to introduce a new ordering index that measures the quality of the orderings produced by feature selection methods. This novel index is sensitive to the quality of feature ordering and to the prediction model’s performance metrics when combined with a feature selection method. The index reaches its maximum when the number-of-features-versus-accuracy graph has an ideal concave-downward shape, reflecting increasing accuracy with each informative feature added and decreasing accuracy with each confounding feature added. Using this index, we define six feature orderings derived from the results of four standard feature selection methods. Using the performance metrics and our new ordering index, we show that the resulting orderings can identify more relevant features and improve the overall performance of the classification models, and that the ordering index is a useful contribution to feature selection techniques. Full article
(This article belongs to the Special Issue AI-Enabled Smart Healthcare Systems)
►▼ Show Figures

Figure 1

13 pages, 4096 KB  
Article
Dual-Parameter Optical Fiber Sensors for Refractive Index and Temperature Measurements Based on a Cascaded SNS–FBG Structure
by Boyang Cui, Ying Huang, Yudong Wang, Hong Li and Haoran Wang
Technologies 2026, 14(8), 497; https://doi.org/10.3390/technologies14080497 - 8 Aug 2026
Viewed by 939
Abstract
A cascaded dual-parameter fiber-optic sensor is presented, in which a single-mode–no-core–single-mode (SNS) multimode-interference (MMI) interferometer is integrated with a fiber Bragg grating (FBG) to achieve simultaneous refractive index (RI) and temperature sensing. The SNS segment, fabricated by fusion splicing a no-core fiber (NCF) [...] Read more.
A cascaded dual-parameter fiber-optic sensor is presented, in which a single-mode–no-core–single-mode (SNS) multimode-interference (MMI) interferometer is integrated with a fiber Bragg grating (FBG) to achieve simultaneous refractive index (RI) and temperature sensing. The SNS segment, fabricated by fusion splicing a no-core fiber (NCF) between two single-mode fibers, exploits MMI to generate spectral features that are highly responsive to ambient RI changes. Meanwhile, the FBG serves as an independent temperature reference, owing to its negligible RI sensitivity. Based on the beam propagation method, the MMI characteristics in the NCF are analyzed. By combining the simulation results with the experimental spectra, the NCF length is optimized by comprehensively considering the interference-fringe visibility, free spectral range, and spectral separation from the FBG wavelength. Experimental results show that the maximum RI sensitivity of the SNS interferometric structure reaches 136.29 nm/RIU, with a corresponding temperature sensitivity of 9.14 pm/°C. The FBG exhibits a temperature sensitivity of 9.83 pm/°C while remaining virtually unresponsive to surrounding RI variations. By establishing a dual-parameter sensitivity matrix, RI and temperature variations can be simultaneously demodulated, enabling effective temperature compensation for RI sensing. The sensor requires no tapering, etching, or surface modification and can be fabricated using only conventional fiber-cleaving and fusion-splicing processes. With its simple fabrication, compact structure, low cost, and good mechanical stability, the sensor shows promising potential for temperature-compensated RI sensing, biochemical detection, liquid-concentration monitoring, and environmental sensing. Full article
(This article belongs to the Section Information and Communication Technologies)
►▼ Show Figures

Figure 1

39 pages, 2003 KB  
Article
A Hybrid Meta-Learning Framework Integrating ECG, Cine-MRI, and Biomarkers for Heart Failure Prediction
by Wafa Baccouch, Narjes Benameur, Abdulrahman Abdullah Alsayyari, Zeyad Alawaji, Amani Kallel, Abderrazak Jemai and Salam Labidi
Technologies 2026, 14(8), 496; https://doi.org/10.3390/technologies14080496 - 7 Aug 2026
Viewed by 368
Abstract
Heart failure (HF) remains a major global cause of morbidity and mortality, where early diagnosis is critical for improving patient outcomes. Conventional single-modality approaches often fail to capture the complex and multifactorial nature of HF. This study investigates the feasibility of a late-fusion [...] Read more.
Heart failure (HF) remains a major global cause of morbidity and mortality, where early diagnosis is critical for improving patient outcomes. Conventional single-modality approaches often fail to capture the complex and multifactorial nature of HF. This study investigates the feasibility of a late-fusion framework that integrates modality-specific predictions derived independently from cine-MRI, electrocardiographic signals, biomarkers and demographic data for HF prediction. Independent cine-MRI data from 281 patients, ECG recordings from the PTB-XL PhysioNet database and biomarker profiles from 157 patients were retrospectively analyzed as separate modality-specific cohorts. Twenty-five features were extracted and processed. Modality-specific models (Attention U-Net, MLP, XGBoost) were trained separately on pre-extracted features to preserve predictive accuracy while minimizing computational cost. Their outputs were combined through ensemble meta-learning (XGBoost, LightGBM, Random Forest) with sample weighting to handle missing data. The final HF prediction probability was obtained by averaging the outputs across the three meta-learners. The proposed framework achieved competitive diagnostic performance, with 98.00% (95% CI: 94.96–99.45%) accuracy, 97.80% (95% CI: 92.28–99.73%) sensitivity, 98.17% (95% CI: 93.53–99.78%) specificity, an F1-score of 97.80% (95% CI: 93.6–99.8%) and an AUC of 0.978 (95% CI: 0.945–0.996) when evaluated against state-of-the-art methods. The results highlight the potential of late-fusion strategies for integrating independently trained modality-specific predictions, offering a feasible approach for HF risk assessment under heterogeneous data availability. Full article
►▼ Show Figures

Figure 1

25 pages, 7323 KB  
Article
A Testable Three-Layer Retained-State Framework for Intelligent Energy Systems: Metrics, Public Experimental Validation, and Cross-Scale Applications
by Nikolay Hinov
Technologies 2026, 14(8), 495; https://doi.org/10.3390/technologies14080495 - 6 Aug 2026
Viewed by 247
Abstract
This paper proposes a testable three-layer retained-state framework for intelligent energy systems grounded in mem-element theory. The framework distinguishes constitutive physical memory (Layer I), distributed circuit/converter memory (Layer II), and functional operational memory (Layer III) while preventing the indiscriminate classification of any history-dependent [...] Read more.
This paper proposes a testable three-layer retained-state framework for intelligent energy systems grounded in mem-element theory. The framework distinguishes constitutive physical memory (Layer I), distributed circuit/converter memory (Layer II), and functional operational memory (Layer III) while preventing the indiscriminate classification of any history-dependent model as a mem-system. A retained variable is admissible only when it satisfies persistence, trajectory dependence, observable engineering consequence, and positive relevance beyond an instantaneous reference. Quantitative trajectory-separation, retained-state relevance, and engineering-gain indices, together with observability and falsification conditions, convert the framework from a taxonomy into a testable methodology. Layer I was partially validated using 636 experimental discharge cycles from four cells in the public NASA Ames PCoE Li-ion Battery Aging Dataset. Across 120 cycle–disjoint within-cell pairs matched at closely similar voltages, currents, temperatures, and local slopes, the median future-trajectory separation (MTS) was 0.0688, the noise-normalized separation (MNS) was 20.13, and the remaining-discharge duration differed by 150.7 s. Leave-one-battery-out prediction yielded positive retained-state relevance (MRI = 0.159 with a random-forest model; 95% bootstrap interval: 0.121–0.194). Two reduced-order cross-scale applications were then used for Layers II and III. In resonant wireless EV charging, retained-state augmentation reduced the efficiency RMSE by 29.9–32.2% and the current MAE by 27.5–27.9% in disturbed scenarios. In EV charging/V2G scheduling, history-aware operation reduced the charging cost by 3.3%, the degradation proxy by 12.0%, thermal-limit violations by 27.3%, and aggressive cycling by 17.2% while accepting lower peak reduction and V2G revenue. Same-information controls produced identical numerical outputs to the structured models by construction, showing that the framework’s novelty lies in admissibility, falsifiability, and cross-scale interpretation rather than privileged input information. The NASA study provides bounded public-experimental-data validation of Layer I; Layers II and III remain proof-of-concept demonstrations. Full article
(This article belongs to the Collection Modern Circuits, System Technologies, and Selected Papers from MOCAST)
►▼ Show Figures

Figure 1

23 pages, 4304 KB  
Article
PGA-LLM: A Probability-Guided Alignment Large Language Model Framework for Fault Diagnosis
by Tao Wang, Yanqiang Di, Shaochong Feng, Qiongyao Liu, Haohao Cui and Qing Liu
Technologies 2026, 14(8), 494; https://doi.org/10.3390/technologies14080494 - 6 Aug 2026
Viewed by 278
Abstract
Fault diagnosis for complex industrial equipment plays a crucial role in safeguarding production safety and advancing the capabilities of intelligent operation and maintenance. Current deep learning approaches have demonstrated promising accuracy in fault classification tasks; however, their signal representations alone cannot provide a [...] Read more.
Fault diagnosis for complex industrial equipment plays a crucial role in safeguarding production safety and advancing the capabilities of intelligent operation and maintenance. Current deep learning approaches have demonstrated promising accuracy in fault classification tasks; however, their signal representations alone cannot provide a transparent interface for embedded large language models. To tackle the aforementioned challenges, we propose PGA-LLM, a novel fault diagnosis framework for industrial equipment that leverages large language models via probability-guided alignment. First, a variational autoencoder (VAE)-based signal encoder embedded with reconstruction constraints is established. Joint reconstruction and classification objectives balance discriminative representation learning and signal reconstruction. Second, the probability-guided alignment (PGA) module combines fault-class probability guidance with a residual feature path; a learned gate fuses both paths before continuous soft-prompt projection. Furthermore, a progressive three-stage training scheme is adopted, encompassing encoder pre-training, interface optimization, and low-rank adaptation (LoRA) of Qwen2.5-1.5B. Extensive experiments are carried out on four standard datasets, CWRU, Gear, Mixed, and MBHM, and the Stage 2 signal-side output achieves classification accuracies of 97.1%, 99.0%, 93.4%, and 96.3%, respectively. The report-generation branch provides a schema-constrained signal-to-language interface for maintenance-oriented reporting. Full article
►▼ Show Figures

Figure 1

17 pages, 730 KB  
Article
Exploring Characteristics of High-Readiness AI–Digital Twin Studies in Mining: A Quantitative Analysis
by Shouki A. Ebad, Aws I. Abueid and Abdulbasit A. Darem
Technologies 2026, 14(8), 493; https://doi.org/10.3390/technologies14080493 - 6 Aug 2026
Cited by 1 | Viewed by 922
Abstract
Background: The mining sector’s digital transformation increasingly relies on AI-driven digital twins (AI-DTs) that integrate real-time data with intelligent analytics. A recent systematic literature review (SLR) of 68 studies identified a critical gap: which technical choices guarantee industrial success? Objective: This study extends [...] Read more.
Background: The mining sector’s digital transformation increasingly relies on AI-driven digital twins (AI-DTs) that integrate real-time data with intelligent analytics. A recent systematic literature review (SLR) of 68 studies identified a critical gap: which technical choices guarantee industrial success? Objective: This study extends that SLR by validating a Deployment Readiness Score (DRS) to identify which combinations of technical and methodological choices are associated with high readiness AI-DT studies in the literature. Methods: Each study was coded across eight dimensions and assigned to a DRS based on data source, validation method, and operational metric reporting. A random forest classifier was used as a consistency check for the DRS framework. Results: The model achieved 100% test accuracy as an internal consistency check within the coded dataset, confirming that the DRS scoring rules produce a coherent classification across the reviewed studies. The data source was the strongest association (41.2%), followed by publication year (25.6%) and validation method (22.7%). AI technique showed minimal association (0.9%). Studies using sensory data achieved 100% high readiness within the DRS framework; mixed data achieved 95.2%; and experimental validation achieved 95.7%. The proportion of high-readiness studies increased from 35.7% in 2024 to 93.5% in 2025. Conclusions: Within the reviewed literature, high-fidelity data and rigorous validation show stronger associations with high readiness than algorithmic complexity. We provide a Deployment Readiness Scorecard and propose minimal reporting standards, shifting focus from theoretical algorithms to practical data acquisition and validation. Full article
►▼ Show Figures

Figure 1

28 pages, 61410 KB  
Article
High-Temperature Tensile Behavior of Wrought and SLM-Fabricated Inconel 718: Effects of Build Orientation and Finite Element Modeling
by Miruna Ciolca, Constantin Stochioiu, Mihai Costea, Alexandru Paraschiv, Florin Baciu and Daniel Vlăsceanu
Technologies 2026, 14(8), 492; https://doi.org/10.3390/technologies14080492 - 5 Aug 2026
Viewed by 352
Abstract
Additive manufacturing enables the production of geometrically complex nickel-based superalloy components, but the high-temperature tensile response of selective laser-melted Inconel 718 remains strongly dependent on manufacturing route and build orientation. In this study, the tensile behavior of Inconel 718 specimens machined from wrought [...] Read more.
Additive manufacturing enables the production of geometrically complex nickel-based superalloy components, but the high-temperature tensile response of selective laser-melted Inconel 718 remains strongly dependent on manufacturing route and build orientation. In this study, the tensile behavior of Inconel 718 specimens machined from wrought bar stock and fabricated by selective laser melting in horizontal and vertical build orientations was investigated at 23 °C, 450 °C, 550 °C and 750 °C. The experimental values were used in a finite element simulation to create a model that can accurately predict the mechanical behavior of IN718. The results show that the X-oriented SLM specimens exhibit tensile properties comparable to those of the wrought material, whereas the Z-oriented specimens display reduced strength and increased scatter, highlighting the effect of build orientation on mechanical performance. The numerical simulations reproduced the experimental stress–strain response with good agreement within the elastic and plastic deformation regimes, demonstrating the suitability of the proposed modeling approach for high-temperature structural assessment of Inconel 718 components manufactured by conventional and additive technologies. Full article
(This article belongs to the Section Manufacturing Technology)
►▼ Show Figures

Graphical abstract

26 pages, 13814 KB  
Article
A Low-Profile Circularly Polarized Metasurface MIMO Antenna with Enhanced Axial-Ratio Bandwidth for IoT Applications
by Yahya Alsuwayyeh, Thamer Almoneef and Hamaskutty Vettikalladi
Technologies 2026, 14(8), 491; https://doi.org/10.3390/technologies14080491 - 5 Aug 2026
Viewed by 388
Abstract
This study develops and experimentally evaluates a low-profile four-port circularly polarized metasurface MIMO antenna for fixed or sectorized wireless links in the 6 GHz band. The design begins with an aperture-coupled single element incorporating a 4×4 slotted metasurface and is subsequently [...] Read more.
This study develops and experimentally evaluates a low-profile four-port circularly polarized metasurface MIMO antenna for fixed or sectorized wireless links in the 6 GHz band. The design begins with an aperture-coupled single element incorporating a 4×4 slotted metasurface and is subsequently extended to a 2×2 MIMO configuration. Mutual coupling between the closely spaced elements is controlled by a hybrid decoupling arrangement comprising metamaterial unit cells and slots etched in the common ground plane. The closely spaced metasurface resonances broaden the circular-polarization response, while the hybrid MTM and DGS decoupling structure suppresses complementary coupling paths between adjacent elements. A fabricated prototype was characterized to verify the simulated performance. The measured −10 dB impedance band extends from 5.56 to 7.85 GHz, corresponding to 34.15%, while the measured 3 dB axial-ratio band covers 5.60–7.13 GHz, corresponding to 24.03%. Across the operating region, the isolation exceeds 23 dB, and the maximum measured gain reaches 8.4 dBic. The MIMO characteristics include an envelope correlation coefficient below 0.0015, diversity gain above 9.98 dB, mean effective gain below −3 dB, and total active reflection coefficient below −10 dB. The measured results demonstrate that the proposed configuration combines wide circular-polarization bandwidth, low interelement correlation, high gain, and effective port isolation for fixed or sectorized IoT and Wi-Fi 6E applications. Full article
(This article belongs to the Section Information and Communication Technologies)
►▼ Show Figures

Figure 1

29 pages, 6568 KB  
Article
An Explainable Hybrid TabNet–Residual MLP Framework for Robust Fetal Health Prediction Using Focal Loss and Leakage-Aware Cross-Validation
by Samaa Ahmed, Doaa Saad and Ahmed Yakoub
Technologies 2026, 14(8), 490; https://doi.org/10.3390/technologies14080490 - 5 Aug 2026
Viewed by 866
Abstract
Effective fetal health prediction is crucial for early diagnosis of fetal distress and avoiding negative perinatal effects. Cardiotocography (CTG), which measures fetal heart rate and uterine contractions, is a popular method for prenatal examination; however, conventional interpretation is arbitrary and unreliable. Fetal health [...] Read more.
Effective fetal health prediction is crucial for early diagnosis of fetal distress and avoiding negative perinatal effects. Cardiotocography (CTG), which measures fetal heart rate and uterine contractions, is a popular method for prenatal examination; however, conventional interpretation is arbitrary and unreliable. Fetal health prediction continues to face challenges due to scarce and imbalanced CTG datasets and data leakage during model evaluation, which can lead to poor generalization and inaccurate performance estimates. Moreover, the absence of explainable AI reduces model clarity and restricts clinical utilization. This study offers a hybrid deep learning model that uses TabNet, Residual Multi-Layer Perceptron (Residual MLP), and Focal Loss to classify normal, suspect, and pathological fetal states. TabNet allows for attention feature learning from CTG data, Residual MLP increases predictive robustness, and Focal Loss aids minority abnormal case diagnosis. To achieve a reliable evaluation, data splitting is used to create a pipeline designed to eliminate conventional train–test data leakage by performing data partitioning before model training and evaluation. SHAP and LIME enhance interpretability by offering clear global and local explanations. The suggested model obtains 99.30% accuracy, 99.10% balanced accuracy, and 98.65% pathological recall on the augmented dataset. A comparative evaluation shows that fixing data leakage drops overinflated baseline accuracy from 96.80% to 93.14%, emphasizing the necessity of a robust experimental design. The results show that the proposed framework outperforms cutting-edge fetal health prediction approaches, offering a robust, understandable, and clinically reliable alternative for CTG-based fetal health evaluation. Full article
►▼ Show Figures

Figure 1

4 pages, 160 KB  
Editorial
Applications of Artificial Intelligence in Medical Image Analysis
by Masateru Kawakubo and Tamás Haidegger
Technologies 2026, 14(8), 489; https://doi.org/10.3390/technologies14080489 - 5 Aug 2026
Viewed by 324
Abstract
Artificial Intelligence (AI) is a transformative technology producing fundamental changes in many fields [...] Full article
(This article belongs to the Special Issue Application of Artificial Intelligence in Medical Image Analysis)
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-65
Previous Issue
Next Issue
Back to TopTop