Saved Queries

Large Language Models (LLMs) exhibit remarkable generative capabilities but remain vulnerable to hallucinations—outputs that are fluent yet inaccurate, ungrounded, or inconsistent with source material. To address the lack of methodologically grounded surveys, this paper introduces a novel method-oriented taxonomy of hallucination mitigation strategies in text-based LLMs. The taxonomy organizes over 300 studies into six principled categories: Training and Learning Approaches, Architectural Modifications, Input/Prompt Optimization, Post-Generation Quality Control, Interpretability and Diagnostic Methods, and Agent-Based Orchestration. Beyond mapping the field, we identify persistent challenges such as the absence of standardized evaluation benchmarks, attribution difficulties in multi-method systems, and the fragility of retrieval-based methods when sources are noisy or outdated. We also highlight emerging directions, including knowledge-grounded fine-tuning and hybrid retrieval–generation pipelines integrated with self-reflective reasoning agents. This taxonomy provides a methodological framework for advancing reliable, context-sensitive LLM deployment in high-stakes domains such as healthcare, law, and defense. Full article

(This article belongs to the Section AI Systems: Theory and Applications)

17 pages, 2879 KB

Open AccessArticle

Integration of Hyperspectral Imaging and Robotics: A Novel Approach to Analysing Cultural Heritage Artefacts

by Agnese Babini, Selene Frascella, Gregory Sech, Fabrizio Andriulo, Ferdinando Cannella, Gabriele Marchello and Arianna Traviglia

Heritage 2025, 8(10), 417; https://doi.org/10.3390/heritage8100417 - 3 Oct 2025

Abstract

This paper pioneers the integration of hyperspectral imaging and robotics for the automated analysis of cultural heritage, representing a measurable advancement over existing manually operated systems. For the first time in the cultural heritage domain, a compact push-broom hyperspectral camera working in the VNIR range has been successfully mounted on a robotic arm, enabling precise and repeatable acquisition trajectories without the need for manual intervention. Unlike traditional approaches that rely on fixed paths or manual repositioning, the proposed approach allows dynamic and programmable imaging of both planar and volumetric objects, greatly improving adaptability to complex geometries. The integrated system achieves spectral reliability comparable to established manual methods, while offering superior flexibility and scalability. Current limitations, particularly regarding the illumination setup, are discussed alongside planned optimisation strategies. Full article

(This article belongs to the Section Digital Heritage)

21 pages, 3223 KB

Open AccessArticle

Oxidative Degradation Mechanism of Zinc White Acrylic Paint: Uneven Distribution of Damage Under Artificial Aging

by Mais Khadur, Victor Ivanov, Artem Gusenkov, Alexander Gulin, Marina Soloveva, Yulia Diakonova, Yulian Khalturin and Victor Nadtochenko

Heritage 2025, 8(10), 419; https://doi.org/10.3390/heritage8100419 - 3 Oct 2025

Abstract

Accelerated artificial aging of zinc oxide (ZnO)-based acrylic artists’ paint, filled with calcium carbonate (CaCO₃) as an extender, was carried out for a total of 1963 h (~8 × 10⁷ lux·h), with assessments at specific intervals. The total color difference ΔE* was <2 (CIELab-76 system) over 1725 h of aging, while the human eye notices color change at ΔE* > 2. Oxidative degradation of organic components in the paint to form volatile products was revealed by attenuated total reflectance–Fourier transform infrared (ATR-FTIR) spectroscopy, micro-Raman spectroscopy, and scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDS). It appears that deep oxidation of organic intermediates and volatilization of organic matter may be responsible for the relatively small value of ΔE* color difference during aging of the samples. To elucidate the degradation pathways, principal component analysis (PCA) was applied to the spectral data, revealing: (1) the catalytic role of ZnO in accelerating photodegradation, (2) the Kolbe photoreaction, (3) the decomposition of the binder to form volatile degradation products, and (4) the relative photoinactivity of CaCO₃ compared with ZnO, showing slower degradation in areas with a higher CaCO₃ content compared with those dominated by ZnO. These results provide fundamental insights into formulation-specific degradation processes, offering practical guidance for the development of more durable artist paints and conservation strategies for acrylic artworks. Full article

►▼ Show Figures

Figure 1

25 pages, 3956 KB

Open AccessReview

Multi-Sensor Monitoring, Intelligent Control, and Data Processing for Smart Greenhouse Environment Management

by Emmanuel Bicamumakuba, Md Nasim Reza, Hongbin Jin, Samsuzzaman, Kyu-Ho Lee and Sun-Ok Chung

Sensors 2025, 25(19), 6134; https://doi.org/10.3390/s25196134 - 3 Oct 2025

Abstract

Management of smart greenhouses represents a transformative advancement in precision agriculture, enabling sustainable intensification of food production through the integration of multi-sensor networks, intelligent control, and sophisticated data filtering techniques. Unlike conventional greenhouses that rely on manual monitoring, smart greenhouses combine environmental sensors, Internet of Things (IoT) platforms, and artificial intelligence (AI)-driven decision making to optimize microclimates, improve yields, and enhance resource efficiency. This review systematically investigates three key technological pillars, multi-sensor monitoring, intelligent control, and data filtering techniques, for smart greenhouse environment management. A structured literature screening of 114 peer-reviewed studies was conducted across major databases to ensure methodological rigor. The analysis compared sensor technologies such as temperature, humidity, carbon dioxide (CO₂), light, and energy to evaluate the control strategies such as IoT-based automation, fuzzy logic, model predictive control, and reinforcement learning, along with filtering methods like time- and frequency-domain, Kalman, AI-based, and hybrid models. Major findings revealed that multi-sensor integration enhanced precision and resilience but faced changes in calibration and interoperability. Intelligent control improved energy and water efficiency yet required robust datasets and computational resources. Advanced filtering strengthens data integrity but raises concerns of scalability and computational cost. The distinct contribution of this review was an integrated synthesis by linking technical performance to implementation feasibility, highlighting pathways towards affordable, scalable, and resilient smart greenhouse systems. Full article

(This article belongs to the Section Smart Agriculture)

►▼ Show Figures

Figure 1

23 pages, 2788 KB

Open AccessArticle

Green Cores as Architectural and Environmental Anchors: A Performance-Based Framework for Residential Refurbishment in Novi Sad, Serbia

by Marko Mihajlovic, Jelena Atanackovic Jelicic and Milan Rapaic

Sustainability 2025, 17(19), 8864; https://doi.org/10.3390/su17198864 - 3 Oct 2025

Abstract

This research investigates the integration of green cores as central biophilic elements in residential architecture, proposing a climate-responsive design methodology grounded in architectural optimization. The study begins with the full-scale refurbishment of a compact urban apartment, wherein interior partitions, fenestration and material systems were reconfigured to embed vegetated zones within the architectural core. Light exposure, ventilation potential and spatial coherence were maximized through data-driven design strategies and structural modifications. Integrated planting modules equipped with PAR-specific LED systems ensure sustained vegetation growth, while embedded environmental infrastructure supports automated irrigation and continuous microclimate monitoring. This plant-centered spatial model is evaluated using quantifiable performance metrics, establishing a replicable framework for optimized indoor ecosystems. Photosynthetically active radiation (PAR)-specific LED systems and embedded environmental infrastructure were incorporated to maintain vegetation viability and enable microclimate regulation. A programmable irrigation system linked to environmental sensors allows automated resource management, ensuring efficient plant sustenance. The configuration is assessed using measurable indicators such as daylight factor, solar exposure, passive thermal behavior and similar elements. Additionally, a post-occupancy expert assessment was conducted with several architects evaluating different aspects confirming the architectural and spatial improvements achieved through the refurbishment. This study not only demonstrates a viable architectural prototype but also opens future avenues for the development of metabolically active buildings, integration with decentralized energy and water systems, and the computational optimization of living infrastructure across varying climatic zones. Full article

(This article belongs to the Special Issue Advances in Ecosystem Services and Urban Sustainability, 2nd Edition)

►▼ Show Figures

Figure 1

15 pages, 1026 KB

Open AccessArticle

Flexible, Stretchable, and Self-Healing MXene-Based Conductive Hydrogels for Human Health Monitoring

by Ruirui Li, Sijia Chang, Jiaheng Bi, Haotian Guo, Jianya Yi and Chengqun Chu

Polymers 2025, 17(19), 2683; https://doi.org/10.3390/polym17192683 - 3 Oct 2025

Abstract

Conductive hydrogels (CHs) have attracted significant attention in the fields of flexible electronics, human–machine interaction, and electronic skin (e-skin) due to their self-adhesiveness, environmental stability, and multi-stimuli responsiveness. However, integrating these diverse functionalities into a single conductive hydrogel system remains a challenge. In this study, polyvinyl alcohol (PVA) and polyacrylamide (PAM) were used as the dual-network matrix, lithium chloride and MXene were added, and a simple immersion strategy was adopted to synthesize a multifunctional MXene-based conductive hydrogel in a glycerol/water (1:1) binary solvent system. A subsequent investigation was then conducted on the hydrogel. The prepared PVA/PAM/LiCl/MXene hydrogel exhibits excellent tensile properties (~1700%), high electrical conductivity (1.6 S/m), and good self-healing ability. Furthermore, it possesses multimodal sensing performance, including humidity sensitivity (sensitivity of −1.09/% RH), temperature responsiveness (heating sensitivity of 2.2 and cooling sensitivity of 1.5), and fast pressure response/recovery times (220 ms/230 ms). In addition, the hydrogel has successfully achieved real-time monitoring of human joint movements (elbow and knee bending) and physiological signals (pulse, breathing), as well as enabled monitoring of spatial pressure distribution via a 3 × 3 sensor array. The performance and versatility of this hydrogel make it a promising candidate for next-generation flexible sensors, which can be applied in the fields of human health monitoring, electronic skin, and human–machine interaction. Full article

(This article belongs to the Special Issue Semiflexible Polymers, 3rd Edition)

18 pages, 2652 KB

Open AccessArticle

Dual Benefits of Endophytic Bacillus velezensis Amzn015: Growth Promotion and Root Rot Control in Atractylodes macrocephala

by Na Zhu, Jiongyi Wu, Sen Fan, Qingling Meng, Shijie Dai, Mingjiang Mao, Weichun Zhao and Xiaofeng Yuan

Microorganisms 2025, 13(10), 2300; https://doi.org/10.3390/microorganisms13102300 - 3 Oct 2025

Abstract

Atractylodes macrocephala Koidz. (A. macrocephala), a medicinal plant extensively used in traditional Chinese medicine, is greatly susceptible to root rot under continuous monoculture, leading to serious yield and quality losses. To develop a sustainable control strategy, we isolated the endophytic bacterium Bacillus velezensis (B. velezensis) Amzn015 from healthy A. macrocephala plants and assessed its biocontrol efficacy and underlying mechanisms. In vitro assays showed that Amzn015 significantly inhibited Fusarium oxysporum and other phytopathogenic fungi by disrupting hyphal morphology and reducing spore viability. Pot experiments confirmed its effectiveness in reducing disease incidence and promoting plant growth. Mechanistically, Amzn015 induced reactive oxygen species accumulation and upregulated key defense responsive genes involved in salicylic acid, jasmonic acid/ethylene, and phenylpropanoid signaling pathways. The findings imply that Amzn015 synchronously activates systemic acquired resistance and induced systemic resistance in A. macrocephala. This dual activation contributes to enhanced immunity and plant vigor under pathogen challenge. Our findings offer fresh perspectives on the biocontrol potential of endophytic B. velezensis Amzn015 and support its application as an eco-friendly agent for managing root rot in medicinal crops. Full article

(This article belongs to the Section Plant Microbe Interactions)

►▼ Show Figures

Figure 1

46 pages, 3204 KB

Open AccessReview

Recent Advances in Sliding Mode Control Techniques for Permanent Magnet Synchronous Motor Drives

by Tran Thanh Tuyen, Jian Yang, Liqing Liao and Nguyen Gia Minh Thao

Electronics 2025, 14(19), 3933; https://doi.org/10.3390/electronics14193933 - 3 Oct 2025

Abstract

As global industry enters the digital era, automation is becoming increasingly pervasive. Due to their superior efficiency and reliability, Permanent Magnet Synchronous Motors (PMSMs) are playing an increasingly prominent role in industrial applications. Sliding Mode Control (SMC) has emerged as a modern control strategy that is widely employed not only in PMSM drive systems, but also across broader power and industrial control domains. This technique effectively mitigates key challenges associated with PMSMs, such as nonlinear behavior and susceptibility to external disturbances, thereby enhancing the precision of speed and torque regulation. This paper provides a thorough review and evaluation of recent advancements in SMC as applied to PMSM control. It outlines the fundamentals of SMC, explores various SMC-based strategies, and introduces integrated approaches that combine SMC with optimization algorithms. Furthermore, it compares these methods, identifying their respective strengths and limitations. This paper concludes by discussing current trends and potential future developments in the application of SMC for PMSM systems. Full article

(This article belongs to the Special Issue Next-Generation Control Systems for Power Electronics in the AI Era)

36 pages, 2558 KB

Open AccessArticle

Research on Warship System Resilience Based on Intelligent Recovery with Improved Ant Colony Optimization

by Zhen Li, Luhong Wang, Lingzhong Meng and Guang Yang

Algorithms 2025, 18(10), 626; https://doi.org/10.3390/a18100626 - 3 Oct 2025

Abstract

Faced with complex, ever-changing battlefield environments and diverse attacks, enabling warship combat systems to recover rapidly and effectively after damage is key to enhancing resilience and sustained combat capability. We construct a representative naval battle scenario and propose an integrated Attack-Defense-Recovery Strategy (ADRS) grounded in warship system models for different attack types. To address high parameter sensitivity, weak initial pheromone feedback, suboptimal solution quality, and premature convergence in traditional ant colony optimization (ACO), we introduce three improvements: (i) grid-search calibration of key ACO parameters to enhance global exploration, (ii) a non-uniform initial pheromone mechanism based on the wartime importance of equipment to guide early solutions, and (iii) an ADRS-consistent state-transition rule with group-based starting points to prioritize high-value equipment during the search. Simulation results show that the improved ACO (IACO) outperforms classical ACO in convergence speed and solution optimality. Across torpedo, aircraft/missile, and UAV scenarios, ADRS-ACO improves over GRS-ACO by 7.2%, 0.3%, and 5.5%, while ADRS-IACO achieves gains of 34.9%, 17.1%, and 16.7% over GRS-ACO and 25.9%, 16.7%, and 10.6% over ADRS-ACO. Overall, ADRS-IACO consistently delivers the best solutions. In high-intensity, high-damage torpedo conditions, ADRS-IACO demonstrates superior path planning and repair scheduling, more effectively identifying critical equipment and allocating resources. Moreover, under multi-wave combat, coupling with ADRS effectively reduces cumulative damage and substantially improves overall warship-system resilience. Full article

(This article belongs to the Special Issue Evolutionary and Swarm Computing for Emerging Applications)

19 pages, 4146 KB

Open AccessArticle

Ultrastructure and Transcriptome Analysis Reveal Sexual Dimorphism in the Antennal Chemosensory System of Blaptica dubia

by Yu Zhang, Liming Liu, Haiqi Zhao, Jiabin Luo and Lina Guo

Insects 2025, 16(10), 1024; https://doi.org/10.3390/insects16101024 - 3 Oct 2025

Abstract

This study distinguished male and female individuals by wing morphology (males with long wings, females with short wings) and investigated sexual dimorphism in the chemosensory system of Blaptica dubia through integrated ultrastructural and transcriptomic analyses. Scanning electron microscopy (SEM) was used to characterize the type, number, and distribution of antennal sensilla, while Illumina HiSeq sequencing, Gene Ontology/Kyoto Encyclopedia of Genes and Genomes (GO/KEGG) annotation, and Quantitative Real-time Reverse Transcription Polymerase Chain Reaction (qRT-PCR) validation were employed to analyze sex-specific gene expression profiles. Both sexes exhibited Böhm’s bristles, chaetic, trichoid, and basiconic sensilla. Males showed significantly more chaetic sensilla on the pedicel and longer type I/II chaetic sensilla on the flagellum, whereas females had longer ST2 sensilla. Basiconic sensilla were predominantly flagellar-distributed and more abundant/longer in males. No sexual differences were observed in Böhm’s bristles. Transcriptomics revealed 5664 differentially expressed genes (DEGs) (2541 upregulated; 3123 downregulated), enriched in oxidation-reduction, extracellular space, lysosome, and glutathione metabolism. KEGG analysis identified five key pathways: lysosome, glutathione metabolism, cytochrome P450-mediated xenobiotic/drug metabolism, and ascorbate/aldarate metabolism. Among 11 chemosensory-related DEGs, chemosensory proteins (CSPs) and odorant binding proteins (OBPs) were downregulated in males, while gustatory receptors (GRs), olfactory receptors (Ors), and ionotropic receptors (IRs) were upregulated. These results demonstrate profound sexual dimorphism in both antennal sensilla morphology and chemosensory gene expression, suggesting divergent sex-specific chemical communication strategies in Blaptica dubia, with implications for understanding adaptive evolution in Blattodea. Full article

(This article belongs to the Section Insect Molecular Biology and Genomics)

►▼ Show Figures

Figure 1

18 pages, 396 KB

Open AccessArticle

Sociodemographic and Psychological Profile of Offenders in Alternative Penal Measures: A Comparative Study of the TASEVAL, PRIA-MA, and reGENER@r Programs

by Ana Isabel Sánchez, Aida Fernández, Almudena Lorite, Clotilde Berzosa Sáez, Elena Miró, María Pilar Martínez and Raúl Quevedo-Blasco

Soc. Sci. 2025, 14(10), 589; https://doi.org/10.3390/socsci14100589 - 3 Oct 2025

Abstract

Gender-based violence (GBV) and traffic offenses pose significant public health challenges and contribute to widespread social issues globally. This study examines the sociodemographic and psychological profiles of individuals who commit traffic offenses and GBV, focusing on three alternative penal programs: TASEVAL (for traffic offenses), PRIA-MA, and reGENER@r (both for GBV). The study involved 54 participants distributed across these programs, using various psychometric tests to assess their profiles. Participants across the three programs (TASEVAL, PRIA-MA, and reGENER@R) were comparable in age (mean range 39.13–40.69 years) and nationality, with roughly half having prior contact with the justice system. Educational levels varied, with TASEVAL participants mainly completing secondary education (43.8%), PRIA-MA participants primary education (43.8%), and reGENER@R participants post-secondary education (59.1%). Employment status differed slightly, with TASEVAL and reGENER@R participants mainly employed (62.5% and 63.6%, respectively), while most PRIA-MA participants were unemployed (56.3%). Family characteristics varied across groups. In TASEVAL, having a partner and no children predominated (62.5% and 31.3%); in PRIA-MA, not having a partner and having two children predominated (62.5% and 37.5%); and, in reGENER@R, not having a partner and having one child predominated (59.1% and 31.8%). No significant differences were observed in sociodemographic variables. Regarding psychological characteristics, results across all groups indicate a marked presence of psychopathological symptoms and difficulties in emotional intelligence domains, with a significant correlation between psychological traits and coping strategies. These findings highlight the importance of tailoring alternative penal measures to the specific characteristics of each group to enhance effectiveness and reduce recidivism. Full article

(This article belongs to the Special Issue Assessment and Intervention with Victims and Offenders)

19 pages, 359 KB

Open AccessReview

Antimicrobial Resistance in Immunocompromised Outpatients: A Narrative Review of Current Evidence and Challenges

by Farhood Sadeghi, Erta Rajabi, Zahra Ghanbari, Sajjad Fattahniya, Reza Samiee, Mandana Akhavan, Mohammadreza Salehi and Maryam Shafaati

Pharmacoepidemiology 2025, 4(4), 21; https://doi.org/10.3390/pharma4040021 - 3 Oct 2025

Abstract

Immunocompromised outpatients, including people living with HIV/AIDS (PLWH), diabetes, cancer, and organ transplant recipients, are at high risk of antimicrobial resistance (AMR) due to their weakened immune systems and use of immunosuppressive therapies. The high prevalence of prophylactic and therapeutic antibiotic use in this vulnerable population, coupled with frequent contact with healthcare facilities and limited outpatient antimicrobial resistance surveillance systems, contributes to the increase in antimicrobial resistance. The majority of available data pertains to inpatients, and there is a lack of comprehensive outpatient information on pathogen distribution, resistance patterns, and diagnostic challenges. Moreover, nonspecific clinical presentations, diminished inflammatory responses, and limitations of traditional diagnostic methods complicate infection diagnosis in this population. Increasing resistance surveillance, developing rapid diagnostic tools, and implementing accurate and personalized approaches are key strategies to reduce the burden of disease, mortality, and healthcare costs in the immunocompromised outpatient population. This study was designed as a narrative review based on a comprehensive search of major databases and guidelines. It aims to examine the available evidence and address the challenges associated with AMR in immunocompromised outpatients. Full article

58 pages, 3568 KB

Open AccessArticle

Investigation of Corporate Sustainability Performance Data and Developing an Innovation-Oriented Novel Analysis Method with Multi-Criteria Decision Making Approach

by Huseyin Haliloglu, Ahmet Feyzioglu, Leonardo Piccinetti, Trevor Omoruyi, Muzeyyen Burcu Hidimoglu and Akin Emrecan Gok

Sustainability 2025, 17(19), 8860; https://doi.org/10.3390/su17198860 - 3 Oct 2025

Abstract

This study addresses the growing importance of integrating innovation into corporate sustainability strategies by examining the financial and environmental performance of ten firms listed on the Borsa Istanbul Sustainability Index over a five-year period. The main objective is to develop and test a novel, data-driven analytical framework that reduces reliance on subjective expert judgments while providing actionable insights for sustainability-oriented decision-making. Within this framework, the entropy method from the Multi-Criteria Decision Making (MCDM) approach is first applied to calculate the objective weights of sustainability criteria, ensuring that the analysis is grounded in real performance data. Building on these weights, an innovative reverse Decision-Making Trial and Evaluation Laboratory (DEMATEL) model, implemented through a custom artificial neural network-based software, is introduced to estimate direct influence matrices and reveal the causal relationships among criteria. This methodological advance makes it possible to explore how environmental and financial factors interact with R&D expenditures and to simulate their systemic interdependencies. The findings demonstrate that R&D serves as a central driver of both environmental and financial sustainability, highlighting its dual role in fostering corporate innovation and long-term resilience. By positioning R&D as both an enabler and outcome of sustainability dynamics, the proposed framework contributes a novel tool for aligning innovation with strategic sustainability goals, offering broader implications for corporate managers, policymakers, and researchers. Full article

►▼ Show Figures

Figure 1

20 pages, 1777 KB

Open AccessArticle

A Classification Algorithm for Revenue Range Estimation in Ancillary Service Markets

by Alice La Fata, Giulio Caprara, Riccardo Barilli and Renato Procopio

Energies 2025, 18(19), 5263; https://doi.org/10.3390/en18195263 - 3 Oct 2025

Abstract

In the last decades, the introduction of intermittent renewable energy sources has transformed the operation of power systems. In this framework, ancillary service markets (ASMs) play an important role, due to their contribution in supporting system operators to balance demand and supply and managing real-time contingencies. Usually, ASMs require that energy is committed before actual participation, hence scheduling systems of plants and microgrids are required to compute the dispatching program and bidding strategy before needs of the market are revealed. Since possible ASM requirements are given as input to scheduling systems, the chance of accessing accurate estimates may be helpful to define reliable dispatching programs and effective bidding strategies. Within this context, this paper proposes a methodology to estimate the revenue range of energy exchange proposals in the ASM. To this end, the possible revenues are discretized into ranges and a classification pattern recognition algorithm is implemented. Modeling is performed using extreme gradient boosting. Input data to be fed to the algorithm are selected because of relationships with the production unit making the proposal, with the location and temporal indication, with the grid power dispatch and with the market regulations. Different tests are set up using historical data referred to the Italian ASM. Results show that the model can appropriately estimate rejection and the revenue range of awarded bids and offers, respectively, in more than 82% and 70% of cases. Full article

►▼ Show Figures

Figure 1

15 pages, 3332 KB

Open AccessArticle

YOLOv11-XRBS: Enhanced Identification of Small and Low-Detail Explosives in X-Ray Backscatter Images

by Baolu Yang, Zhe Yang, Xin Wang, Baozhong Mu, Jie Xu and Hong Li

Sensors 2025, 25(19), 6130; https://doi.org/10.3390/s25196130 - 3 Oct 2025

Abstract

Identifying concealed explosives in X-ray backscatter (XRBS) imagery remains a critical challenge, primarily due to low image contrasts, cluttered backgrounds, small object sizes, and limited structural details. To address these limitations, we propose YOLOv11-XRBS, an enhanced detection framework tailored to the characteristics of XRBS images. A dedicated dataset (SBCXray) comprising over 10,000 annotated images of simulated explosive scenarios under varied concealment conditions was constructed to support training and evaluation. The proposed framework introduces three targeted improvements: (1) adaptive architectural refinement to enhance multi-scale feature representation and suppress background interference, (2) a Size-Aware Focal Loss (SaFL) strategy to improve the detection of small and weak-feature objects, and (3) a recomposed loss function with scale-adaptive weighting to achieve more accurate bounding box localization. The experiments demonstrated that YOLOv11-XRBS achieves better performance compared to both existing YOLO variants and classical detection models such as Faster R-CNN, SSD512, RetinaNet, DETR, and VGGNet, achieving a mean average precision (mAP) of 94.8%. These results confirm the robustness and practicality of the proposed framework, highlighting its potential deployment in XRBS-based security inspection systems. Full article

(This article belongs to the Special Issue Advanced Spectroscopy-Based Sensors and Spectral Analysis Technology)

►▼ 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 1048.

Go to page 1 2 3 4 5

Search Results (52,364)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI