Saved Queries

The Dubai Government has made significant investments in digital learning through platforms such as Al Mawrid and Bayanati, enabling widespread access to employee training and upskilling. However, there remains a major gap in translating accumulated learning into intelligent workforce restructuring. This paper proposes “SkillChain DX,” a policy-driven framework that applies artificial intelligence (AI) to dynamically map employee-acquired skills to evolving job roles across departments, developed using a conceptual design science and policy analysis approach. The framework integrates blockchain to ensure secure, tamper-proof verification of skill credentials across diverse training platforms. To validate feasibility, a pilot prototype was implemented using sentence-transformer models for semantic skill inference and cryptographic hashing mechanisms for decentralized credential verification. Experimental evaluation across six controlled scenarios demonstrated an average role-matching accuracy of approximately 82%, blockchain transaction throughput exceeding 1000 operations per second, and near-instant credential verification with over 99% performance improvement compared to manual processes. The findings demonstrate that integrating AI-driven skill inference with decentralized credential verification can significantly enhance internal mobility, role alignment, and workforce planning at a policy level. The study benchmarks international practices and outlines a practical implementation path for the Dubai Government using only publicly available technologies and case studies, positioning SkillChain DX as one of the first integrated AI–blockchain policy frameworks tailored to public sector human resources (HR) transformation in Dubai. The proposed system framework bridges the current disconnect between training access and organizational transformation, supporting a proactive, transparent, and skills-first public sector, while offering actionable policy insights for future government HR modernization. Full article

►▼ Show Figures

Figure 1

32 pages, 1475 KB

Open AccessReview

The Neuro–Bone Axis in Metastatic Progression: Innervation, Neuro-Immune–Osteoclast Crosstalk, and Therapeutic Opportunities

by Mohamad Bakir, Alhomam Dabaliz, Mohammed Raddaoui, Hala Fatash, Nourhan Elsaadany, Wael AlKattan and Khalid Said Mohammad

Biology 2026, 15(4), 364; https://doi.org/10.3390/biology15040364 (registering DOI) - 21 Feb 2026

Abstract

Bone metastases represent a major cause of morbidity in advanced cancers, yet the neural regulation of metastatic growth within bone remains largely unexplored. The skeletal system is richly innervated by sensory and sympathetic nerve fibers that influence bone remodeling, hematopoiesis, and immune surveillance. Emerging evidence suggests that disseminated tumor cells exploit these neural circuits to create a growth-permissive microenvironment. Tumor-secreted neurotrophic factors can induce nerve sprouting, while sympathetic activation via β-adrenergic receptors promotes osteoclastogenesis, immunosuppression, and tumor proliferation. Neuropeptides such as substance P and calcitonin gene-related peptide exert dual effects on bone cells and infiltrating immune populations, further shaping the metastatic niche. The interplay between neural signals, osteolytic activity, and immune modulation positions the neuro–bone axis as a critical but underappreciated driver of metastatic progression. In this review, we synthesize current evidence on the anatomy and function of bone innervation, tumor-induced neural remodeling, and neuro–immune–osteoclast interactions. We highlight preclinical and clinical data supporting neuromodulatory strategies, including β-blockers, neurotrophin inhibitors, and targeted nerve ablation, as potential adjuncts to standard bone metastasis therapies. Finally, we identify key knowledge gaps, including the need for spatial and functional mapping of nerve–tumor interfaces and for integrating neuroimaging into bone metastasis detection. By framing the neuro–bone axis as a therapeutic target, we aim to catalyze interdisciplinary research that bridges oncology, neuroscience, and bone biology, with the goal of disrupting neural support for metastatic growth Full article

(This article belongs to the Special Issue Molecular Mechanisms of Bone Metastasis in Cancer)

►▼ Show Figures

Figure 1

26 pages, 9715 KB

Open AccessArticle

Methodological Framework for Generation of Static Air Traffic Situations and Automated Complexity Data Extraction

by Tea Jurinić, Biljana Juričić, Dominik Jurinić and Petar Andraši

Appl. Sci. 2026, 16(4), 2106; https://doi.org/10.3390/app16042106 (registering DOI) - 21 Feb 2026

Abstract

Existing simulation methods and tools available for air traffic complexity research have several limitations (such as time-consuming processing and complex data extraction) that hinder the simple and flexible collection of input data acquired from air traffic controllers (ATCOs). These limitations are particularly evident in research when representative and diverse data are needed, such as research on air traffic complexity based on ATCO input. To address this research gap, we present a new methodological framework for research in air traffic complexity, which incorporates ATCO input. The proposed methodological framework consists of three major components: (1) SATSI, a user-friendly interface for creating and visualizing various static air traffic situations (airspace, traffic, and contextual data), (2) a parser that converts SATSI outputs into inputs for the trajectory prediction model, and (3) an algorithm for automated extraction of terminal air traffic complexity indicators. All together, these components present a novel flexible tool for traffic scenario development, and its integration with the existing trajectory model and automatic processing of air traffic complexity data extraction. The proposed integrated framework shortens the overall research process by using simple and flexible air traffic scenario generation, facilitates automated data collection and enables broader and more representative studies of ATCO-perceived complexity. Full article

(This article belongs to the Special Issue Novel Approaches and Trends in Aerospace Control Systems)

►▼ Show Figures

Figure 1

25 pages, 618 KB

Open AccessArticle

Ascertaining the Reasons for Escalation of Disagreements over Extension of Time Assessments from Construction Delay Claims into Disputes

by Vasil Angelov Atanasov

Buildings 2026, 16(4), 872; https://doi.org/10.3390/buildings16040872 (registering DOI) - 21 Feb 2026

Abstract

Disputes over delay assessments are costly, persistent, prevalent worldwide, often funded by taxpayers, and negatively impact productivity in the construction sector. The identified academic literature argues that the main causes of the escalation of disagreements over delay assessments from contract claims into disputes (or factors) are objective factors, particularly unavailability and/or inadequacy of relevant project data. However, those findings are not based on comprehensive investigations of all factors involved, employing research methodologies that rely upon real-life project data. This article contributes to the fulfilment of the aforementioned knowledge gap. Published literature and twenty-one case studies were evaluated to identify the factors. The research findings revealed that although data-related issues were often important factors, they were not the main and/or most frequently identified ones. Subjective factors, including manipulation of programme activity completion dates, reliance on biased assumptions when data is unavailable, misinterpretation of material records, and self-serving delay analysis, were the main factors. The findings suggest that the root cause of this issue is the exploitation of systemic flaws, including the unavailability of good/best practice guidance on assessing the impact of delays, deficient contract provisions, inadequate impartiality, divergent priority of interests, unexploited technologies, and the confidential nature of dispute resolution methods. Full article

(This article belongs to the Special Issue Selected Papers from the CIB WBC 2025—Sustainable Development and the Built Environment: Legal Challenges and Opportunities)

19 pages, 1231 KB

Open AccessArticle

Standardising Culture Medium Safety Testing for Cultivated Meat: Outputs from a Workshop and Case Study

by Ruth E. Wonfor, Kimberly J. Ong, Wei Ng, Jo Anne Shatkin, Reka Tron and Cai Linton

Foods 2026, 15(4), 783; https://doi.org/10.3390/foods15040783 (registering DOI) - 21 Feb 2026

Abstract

Cultivated meat is a novel food and therefore must undergo safety assessments and regulatory review to identify risks and establish appropriate mitigations prior to commercialisation. The culture media used within the cell cultivation process may contain components that lack a long history of use in food, necessitating safety evaluation. However, there is no clearly defined framework outlining the evaluations needed to generate robust and reliable data. The aim of this work was two-fold: first, to convene a multi-stakeholder workshop to identify knowledge gaps related to culture medium safety assessment, and second, to provide a case study addressing one knowledge gap through the evaluation of ELISAs for quantifying growth factors in culture media and cultivated meat products. The workshop findings highlighted critical needs for standardised residue measurement methods, Certificates of Analysis, characterisation of metabolites and breakdown products, as well as open databases. Our case study evaluates the use of ELISAs to quantify six commonly used growth factors for cultivated meat production, comparing their presence in cultivated meat and conventional meat. Growth factor levels varied depending on the medium formulation but were generally reduced to conventional levels or were non-detectable after simulated cooking. Several methodological challenges were identified around the use of ELISAs, such as cross-reactivity between species, limited antibody availability for non-traditional species, and a lack of reference data and standards to support validation of ELISAs and establishment of suitable limits of detection. This work therefore provides actionable guidance for future research in this field for standardisation and emphasises the need for a clearly defined framework and standardised analytical methods to ensure consistent and transparent evaluation of cultivated meat. Full article

(This article belongs to the Special Issue Alternative Protein: Sources, Bioactivities, Potential Health Benefits, and Application)

►▼ Show Figures

Figure 1

34 pages, 3113 KB

Open AccessSystematic Review

A Systematic Review of Available Multispectral UAV Image Datasets for Precision Agriculture Applications

by Andrea Caroppo, Giovanni Diraco and Alessandro Leone

Remote Sens. 2026, 18(4), 659; https://doi.org/10.3390/rs18040659 (registering DOI) - 21 Feb 2026

Abstract

The proliferation of Unmanned Aerial Vehicles (UAVs) equipped with multispectral imaging sensors has revolutionized data collection in precision agriculture. These platforms provide high-resolution, temporally dense data crucial for monitoring crop health, optimizing resource management, and predicting yield. However, the development and validation of robust data-driven algorithms, from vegetation index analysis to complex deep learning models, are contingent upon the availability of high-quality, standardized, and publicly accessible datasets. This review systematically surveys and characterizes the current landscape of available datasets containing multispectral imagery acquired by UAVs in agricultural contexts. Following guidelines for reporting systematic reviews and meta-analyses (PRISMA methodology), 39 studies were selected and analyzed, categorizing them based on key attributes including spectral bands (e.g., RGB, Red Edge, Near-Infrared), spatial and temporal resolution, types of crops studied, presence of complementary ground-truth data (e.g., biomass, nitrogen content, yield maps), and the specific agricultural tasks they support (e.g., disease detection, weed mapping, water stress assessment). However, the review underscores a critical gap in standardization, with significant variability in data formats, annotation quality, and metadata completeness, which hampers reproducibility and comparative analysis. Furthermore, we identify a need for more datasets targeting specific challenges like early-stage disease identification and anomaly detection in complex crop canopies. Finally, we discuss future directions for the creation of more comprehensive, benchmark-ready open datasets that will be instrumental in accelerating research, fostering collaboration, and bridging the gap between algorithmic innovation and practical agricultural deployment. This work serves as a foundational guide for researchers and practitioners seeking suitable data for their work and contributes to the ongoing effort of standardizing open data practices in agricultural remote sensing. Full article

(This article belongs to the Special Issue Applications of Unmanned Aerial Remote Sensing in Precision Agriculture)

16 pages, 2796 KB

Open AccessArticle

MiMics-Net: A Multimodal Interaction Network for Blastocyst Component Segmentation

by Adnan Haider, Muhammad Arsalan and Kyungeun Cho

Diagnostics 2026, 16(4), 631; https://doi.org/10.3390/diagnostics16040631 (registering DOI) - 21 Feb 2026

Abstract

Objectives: Global infertility rates are rapidly increasing. Assisted reproductive technologies combined with artificial intelligence are the next hope for overcoming infertility. In vitro fertilization (IVF) is gaining popularity owing to its increasing success rates. The success rate of IVF essentially depends on the assessment and inspection of blastocysts. Blastocysts can be segmented into several important compartments, and advanced and precise assessment of these compartments is strongly associated with successful pregnancies. However, currently, embryologists must manually analyze blastocysts, which is a time-consuming, subjective, and error-prone process. Several AI-based techniques, including segmentation, have been recently proposed to fill this gap. However, most existing methods rely only on raw grayscale intensity and do not perform well under challenging blastocyst image conditions, such as low contrast, similarity in textures, shape variability, and class imbalance. Methods: To overcome this limitation, we developed a novel and lightweight architecture, the microscopic multimodal interaction segmentation network (MiMics-Net), to accurately segment blastocyst components. MiMics-Net employs a multimodal blastocyst stem to decompose and process each frame into three modalities (photometric intensity, local textures, and directional orientation), followed by feature fusion to enhance segmentation performance. Moreover, MiMic dual-path grouped blocks have been designed, in which parallel-grouped convolutional paths are fused through point-wise convolutional layers to increase diverse learning. A lightweight refinement decoder is employed to refine and restore the spatial features while maintaining computational efficiency. Finally, semantic skip pathways are induced to transfer low- and mid-level spatial features after passing through the grouped and point-wise convolutional layers. Results/Conclusions: MiMics-Net was evaluated using a publicly available human blastocyst dataset and achieved a Jaccard index score of 87.9% while requiring only 0.65 million trainable parameters. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics: From Algorithms to Clinical Impact)

►▼ Show Figures

Figure 1

43 pages, 9596 KB

Open AccessArticle

Bridging Effect–Efficiency Gaps in Low-Carbon Resilient Cities: Evidence on Synergistic Development and Nonlinear Drivers from Chinese Cities

by Xingchen Lai, Fan Li, Yuxin Zhang, Panpan Liu, Jun Feng, Jiao Chi, Xiong Wang and Hiroatsu Fukuda

Sustainability 2026, 18(4), 2126; https://doi.org/10.3390/su18042126 (registering DOI) - 21 Feb 2026

Abstract

Advancing the low-carbon and resilient transformation of urban systems has become a crucial strategy for addressing the climate crisis. Current research predominantly focuses on either the effect of governance or the efficient utilization of urban systems, overlooking the potential structural mismatches and synergistic development governance logic between the two. This paper systematically proposes a theoretical research framework integrating the synergistic development of urban system effect and efficiency, and constructs a multi-level analytical methodology. Through an in-depth examination of 278 prefecture-level cities in China from 2010 to 2023, the following key conclusions emerge: (1) The overall level of synergistic development within urban systems has steadily increased. Specifically, the proportion of cities at low levels of synergistic development decreased from 65.11% to 17.63%, while the proportion at medium and high levels rose from 18.70% to 46.40%. (2) Spatial disparities in urban system coordination have progressively narrowed, as evidenced by the overall Gini coefficient decreasing from 0.195 to 0.153. (3) Key influencing factors for urban system coordination include foreign enterprise attraction, urban infrastructure development, and green technological innovation. Overall, this study reveals the long-standing structural mismatch between effect and efficiency in China’s urban system’s low-carbon resilience transformation, emphasizing the importance of their coordinated development. It provides theoretical foundations and empirical references for the sustainable development of urban low-carbon resilience transformation. Full article

(This article belongs to the Special Issue Sustainable Development of Construction Engineering—2nd Edition)

42 pages, 2229 KB

Open AccessArticle

Rural Tourism Development Under Weak Governance in Lebanon: Challenges and Opportunities

by Farah Mohamad and Liliane Buccianti-Barakat

Tour. Hosp. 2026, 7(2), 56; https://doi.org/10.3390/tourhosp7020056 (registering DOI) - 21 Feb 2026

Abstract

Rural tourism has been regarded as a vital approach for the development of marginalized rural regions. Against the backdrop of Lebanon’s ongoing crisis, there is a significant and increasing interest in the tourism sector that can advance key SDGs by creating decent jobs, building sustainable communities, promoting responsible resource consumption, and conserving the environment. Nevertheless, the promise of this approach is endangered by the current situation of weak governance and institutional deficiencies. This paper examines the role of tourism governance in shaping the development of sustainable rural tourism in Shouf El-Souayjani, a rural area in Lebanon. The study adopts a sequential explanatory design to integrate quantitative and qualitative viewpoints, with a quantitative survey consisting of 388 respondents for collecting data, which is further enriched by 43 interviews with different stakeholders. Quantitative results indicate statistically significant relationships between governance dimensions, participation, knowledge sharing, empowerment, community knowledge, and legislative adequacy with perceived sustainability outcomes in Lebanon. Qualitative findings show major governance gaps, balanced by rural strengths like entrepreneurship and resilience. The study proposes a comprehensive governance model that highlights how a particular governance mechanism shapes rural tourism sustainability, particularly in a country affected by successive crises like Lebanon. Full article

(This article belongs to the Special Issue Challenges and Development Opportunities for Tourism in Rural Areas)

15 pages, 1363 KB

Open AccessReview

Engineering Multifunctional Biochars for Integrated Environmental Systems: Multi-Medium Performance, Challenges, and Research Priorities

by Jelena Beljin, Marijana Kragulj Isakovski and Snežana Maletić

Processes 2026, 14(4), 714; https://doi.org/10.3390/pr14040714 (registering DOI) - 21 Feb 2026

Abstract

The valorization of agricultural and other waste residues into biochar represents a promising strategy for sustainable waste management and environmental remediation within a circular economy framework. Engineering multifunctional biochars like agricultural waste-derived biochars (AWDBs) exhibit tunable physicochemical properties governed by feedstock characteristics and thermochemical conversion conditions, enabling their application across water, soil, and sediment systems. While extensive research has demonstrated the effectiveness of biochar in isolated environmental compartments, natural systems function as interconnected water–soil–sediment continua, where pollutants, nutrients, and organic matter dynamically interact. This review critically synthesizes recent advances in the production, properties, and environmental applications of biochars, with a particular focus on their multifunctional performance in coupled environmental systems. Mechanistic insights into contaminant sequestration, nutrient cycling, and microbial interactions across media are discussed, alongside evidence of synergistic and antagonistic effects arising from cross-media processes. Despite significant progress, major knowledge gaps persist, including limited integrated multi-medium studies, lack of standardized assessment methodologies, insufficient understanding of long-term biochar stability, and challenges associated with field-scale implementation. Future research directions are proposed to address these limitations through standardized protocols, engineered multifunctional biochars, long-term monitoring, and policy integration. Advancing a system-based perspective is essential to unlock the full potential of agricultural waste-derived biochars for sustainable and scalable environmental remediation. Full article

(This article belongs to the Special Issue Waste Supermaterials: Engineered Multifunctional Composites for Dual Water-Waste Solutions)

►▼ Show Figures

Figure 1

24 pages, 6107 KB

Open AccessArticle

3D Printing Experimental Investigation and DEM Simulation on the Failure Processes of Double Tunnels Containing Fissures

by Huaijian Li, Hao Yu, Lanjing Xing, Xiangyu Deng, Xuewen Xiao, Junyang Wang, Linyun Sun, Baoming Wang, Liang Ma and Wangping Qian

Appl. Sci. 2026, 16(4), 2097; https://doi.org/10.3390/app16042097 (registering DOI) - 21 Feb 2026

Abstract

To address the current research gap where studies on the failure mechanisms of fissured tunnels mainly focus on single tunnels with insufficient research on double tunnels, and to provide a scientific basis for disaster prevention and control of the Jinan Tunnel on Jinan Ring Expressway, this study investigates the mechanical behavior and failure characteristics of tunnel structures containing fissure–hole composite systems using experimental tests and numerical simulations. The crack initiation, propagation, and coalescence mechanisms are systematically analyzed to provide engineering references for tunnel design and stability assessment. Sand-based 3D printing technology was used to fabricate double-tunnel models with prefabricated fissures of different inclination angles α. Uniaxial compression tests were conducted, and crack evolution was monitored using DIC technology. Meanwhile, numerical simulation verification was performed based on the parallel bond (PB) model of the Discrete Element Method (PFC). The results show that the mechanical response of sand-based 3D-printed models conforms to the brittle characteristics of engineering rock masses. For models without fissures, cracks are preferentially initiated at the top and bottom of the tunnels. For models with fissures, the peak strength is the highest when α = 30° and 60°, and the lowest when α = 45° and 90°. As the fissure inclination angle increases, the tensile stress concentration shifts from the top and bottom of the tunnels and the middle of the fissure to the two ends of the fissure. The numerical simulation results are consistent with the experimental results and can accurately reproduce crack evolution. This study verifies the effectiveness of combining sand-based 3D printing with discrete element simulation, providing a reference for fissure prevention and control as well as operation and maintenance optimization of similar double-tunnel projects. Full article

(This article belongs to the Special Issue Advances in Tunnel Excavation and Underground Construction)

29 pages, 961 KB

Open AccessArticle

Enhancing Sustainability Consciousness in Higher Education: Impacts of Artificial Intelligence-Integrated Sustainable Engineering Education

by Feng Liu, Hua Wang, Yuntao Guo and Tianpei Tang

Sustainability 2026, 18(4), 2124; https://doi.org/10.3390/su18042124 (registering DOI) - 21 Feb 2026

Abstract

Engineering education is increasingly shaped by two converging developments: accelerating sustainability transitions and rapid advances in artificial intelligence (AI). However, in many application-oriented undergraduate programs, sustainability learning remains fragmented, methodologically limited, and weakly connected to authentic engineering decision-making. To address this gap, this study proposes AI-SEE (Artificial Intelligence-Integrated Sustainable Engineering Education), a pedagogical framework that integrates AI across the curriculum as both a cognitive scaffold and a resource for system-level analysis. Emphasizing human–AI collaboration, AI-SEE is designed to be feasible and scalable within application-oriented higher education contexts. The framework comprises four interrelated pillars: intelligence-driven, green-empowered, responsibility-leading, and practice-integrated. Drawing on an empirical case from transportation-related programs at Nantong University, the study employs a qualitative comparative design and conducts semi-structured interviews with 144 undergraduates at the end of their eighth semester (control group n = 70; pilot group n = 74). Interview data were analyzed using thematic analysis informed by constructivist grounded theory and the Gioia coding approach. The findings suggest that participation in AI-SEE is associated with differentiated patterns of sustainability consciousness. At the knowledge level, students reported more systematic and interdisciplinary understandings that extended beyond environmentally reductionist perspectives to include life-cycle thinking, social equity, and long-term considerations. At the attitudinal level, students described enhanced ethical reflexivity and evolving professional self-concepts, shifting from a focus on technical execution toward broader value-oriented roles. At the behavioral level, students reported more extensive knowledge-to-action translation across personal, academic, and career-related domains. Overall, AI-SEE provides a transferable pedagogical pathway for integrating AI into engineering education to support the development of sustainability consciousness in higher education. Full article

►▼ Show Figures

Figure 1

38 pages, 1242 KB

Open AccessReview

An Integrated Algal Biorefinery Approach for Wastewater Treatment and Biomass Valorisation

by Faiz Ahmad Ansari, Humeira Hassan, Abdulwahab Said Salim Al-Ouweini, Mayuri Chabukdhara, Amita Shakya, Abdul Gaffar Sheik, Samar Alghamdi, Insaf Naser, Sharjeel Waqas and Irshad Ahmad

Sustainability 2026, 18(4), 2123; https://doi.org/10.3390/su18042123 (registering DOI) - 21 Feb 2026

Abstract

Biological wastewater treatment methods are considered suitable due to several advantages, such as fast processing, low operating cost, less secondary pollution, and overall, environmentally friendly. Microalgae-based wastewater treatment has promising potential, as it not only removes pollutants but also produces valuable biomass, which can be further utilised for various applications. In such systems, microalgae bacterial consortia enhance overall treatment efficiency by promoting symbiotic relationships that improve microbial activity, environmental resilience and enhance pollutant removal efficiency. The current review provides an overview of microalgae cultivation in various wastewater streams, CO₂ sequestration and the utilisation of produced microalgal biomass for multiple applications. The manuscript also focuses on the current role of molecular tools in optimisation and the integration of artificial intelligence to enhance microalgae-based wastewater treatment and management. The manuscript highlights recent progress in wastewater treatment, resource recovery, and the contribution of microalgal biomass to the emerging bioeconomy. To address the identified research gaps and promote the practical implementation of integrated algal systems, future research should focus on the combined approach of algae-based wastewater treatment and the concurrent utilisation of algal biomass. Such research should aim to optimise cultivation conditions and operational strategies to improve nutrient removal efficiency, enhance biomass valorisation for biochar, bioplastics, or feed applications, and ensure sustainable economics. This integrated perspective will help bridge the gap between laboratory-scale studies and integration at a larger scale. Overall, this review aims to guide the effective use of microalgae for treating diverse wastewater streams while supporting efforts to mitigate greenhouse gases and reduce pollution. Full article

(This article belongs to the Special Issue Advanced Research on Waste Management and Biomass Valorization)

20 pages, 32177 KB

Open AccessArticle

Communication Frame Analysis to Differentiate Between Authorized and Unauthorized Drones of the Same Model

by Angesom Ataklity Tesfay, Jonathan Villain, Virginie Deniau and Christophe Gransart

Drones 2026, 10(2), 149; https://doi.org/10.3390/drones10020149 (registering DOI) - 21 Feb 2026

Abstract

Unmanned aerial vehicle (UAV) applications are growing fast in different sectors, such as agricultural, commercial, academic, leisure, and health fields. However, drones pose a significant threat to public safety due to their ability to transmit information, particularly when used in an unauthorized or malicious manner. In fact, in order to protect citizens’ privacy and prevent accidents in high-traffic areas due to poorly controlled flights, no-fly zones for drones have been established in the legislation of a number of countries. Most common UAV detection techniques are based on radio frequencies, which identify drones and their models by monitoring radio frequency signals. However, differentiating between multiple UAVs of the same model is their main limitation. This article fills this gap by proposing a method for physically tracking the communication frames of a registered UAV in the presence of another UAV of the same model. A measurement campaign was conducted to collect real-world RF communication signals from two DJI MAVIC 2 Zoom, two DJI Air2S, and two DJI Phantom drones. This measurement was performed inside and outside an anechoic chamber in order to study the UAV’s communication without any interference and in the presence of other communications. Through detailed statistical analysis, we characterized features such as communication duration, time intervals between communications, signal strength, and patterns in communication timing sequences. Our analysis revealed unique, identifiable patterns for each UAV, even within identical models. Based on these results, we developed an automated system that links communication frames to the corresponding registered drones. The proposed method fills gaps in drone detection and surveillance models, providing valuable information for applications in the fields of security and airspace management. This research lays the foundation for drone identification solutions, thereby addressing a major limitation of current detection technologies. Full article

(This article belongs to the Section Drone Communications)

23 pages, 26789 KB

Open AccessArticle

DermaCalibra: A Robust and Explainable Multimodal Framework for Skin Lesion Diagnosis via Bayesian Uncertainty and Dynamic Modulation

by Ben Wang, Qingjun Niu, Chengying She, Jialu Zhang, Wei Gao and Lizhuang Liu

Diagnostics 2026, 16(4), 630; https://doi.org/10.3390/diagnostics16040630 (registering DOI) - 21 Feb 2026

Abstract

Background: Accurate and timely diagnosis of skin lesions, including Melanoma (MEL), Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC), Actinic Keratosis (ACK), Seborrheic Keratosis (SEK), and Nevus (NEV), is often hindered by the severe class imbalance and high morphological similarity among pathologies in clinical practice. Although multimodal learning has shown potential in resolving these issues, existing approaches often fail to address predictive uncertainty or effectively integrate heterogeneous clinical metadata. Therefore, this study proposes DermaCalibra, a robust and explainable multimodal framework optimized for small-scale, imbalanced clinical datasets. Methods: The proposed framework integrates three essential modules: First, the Attention-Based Multimodal Channel Recalibration (AMCR) module introduces a probabilistic Bayesian uncertainty estimation mechanism via Monte Carlo dropout to adjust focal loss weights, prioritizing features from underrepresented classes. Second, the Metadata-Driven Dynamic Feature Modulation and Cross-Attention Fusion (MDFM-CAF) module, designed to resolve inter-class visual ambiguity, dynamically rescales dermoscopic feature maps using non-linear clinical context transformations. Lastly, the Gradient Feature Attribution (GFA) module is implemented to provide pixel-level diagnostic heatmaps and metadata importance scores. Results: Evaluated on the PAD-UFES-20 dataset, DermaCalibra achieves a balanced accuracy (BACC) of 84.2%, outperforming current state-of-the-art (SOTA) methods by 3.6%, and a Macro Area Under the Receiver Operating Characteristic Curve (Macro AUC) of 96.9%. Extensive external validation on unseen hospital and synthetic datasets confirms robust generalizability across diverse clinical settings without the need for retraining. Conclusions: DermaCalibra effectively bridges the gap between deep learning complexity and clinical intuition through uncertainty-aware reasoning and transparent interpretability. The framework provides a reliable and scalable computer-aided diagnostic tool for early skin lesion detection, particularly in resource-limited clinical environments. Full article

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)

►▼ Show Figures

Figure 1

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 1154.

Go to page 1 2 3 4 5

Search Results (57,667)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI