Search Results (277)

Plastic waste presents a significant environmental and public health concern in Malawi, where rapid urban growth, limited waste collection services, and informal disposal practices contribute to persistent plastic waste hotspots. In Lilongwe City, the waste collection rate has been reported ranges from 10% to 30%. This means that out of the 500 to 600 tons of municipal solid waste produced each day, only about 50 to 150 tons are collected daily. These hotspots occur in settings such as drains, markets, settlement edges, riverbanks, and lakeshore environments. They intensify health-relevant exposure pathways by encouraging stagnant water, increasing flood risk, facilitating open burning, and supporting the formation of plastisphere biofilms that can contain pathogenic and antimicrobial resistant organisms. This research synthesises evidence on the main sources of plastic waste in Malawi, the mechanisms of leakage across different environments, and the associated health implications. It uses a scoping approach aligned with PRISMA-ScR guidance and is informed by the UK Research and Innovation (UKRI) funded Sustainable Plastic Attitudes to benefit Communities and their Environments (SPACES project), which highlights the influence of behavioural, governance, and environmental factors on plastic pollution. A two phase, risk-based decision framework to support targeted management of plastic waste hotspots is described. Phase 1 focuses on rapid harm reduction through the identification and ranking of hotspots according to risk severity, spatial extent, and feasibility, guiding timely interventions such as drain clearance, waste capture, and temporary stabilisation. Phase 2 addresses longer term prevention by tackling upstream drivers through policy measures, improved services, reuse and reduction schemes, and community engagement. The framework has been developed using evidence from Malawi; however, its methodology could be applied to other low- and middle-income countries that experience similar constraints and exposure pathways. The framework offers a transparent and practical tool for decision makers seeking to allocate limited resources effectively while reducing environmental and health risks associated with plastic waste. Full article

Radio-frequency identification (RFID)-based asset tracking in cabinet environments often encounters unpredictable detection caused by multipath fading, metal-induced interference, and tag placement sensitivity, which can render single-band systems unreliable under real-world conditions. This paper proposes a dual-band detection approach combining 915 MHz and 2.45 GHz to address these challenges through frequency diversity. Unlike designs confined to closely spaced UHF bands, this method uses a larger spectral gap to benefit from uncorrelated fading and distinct propagation properties. Theoretical analysis shows that dual-band detection significantly reduces joint failure probability under independent fading. The proposed framework is implemented using commercially available passive UHF tags at 915 MHz and an active RFID tag/reader at 2.45 GHz. The two systems are operated sequentially along the same guided scan path, and their detected tag-ID sets are combined offline using an OR-fusion rule without hardware-level synchronization. Across trials with varied scan speeds, power levels, reader distances, and tag placements, single-band detection fell below 50% under double-speed scanning at 200 cm, while the dual-band method remained above 70% and, in many cases, reached 100% reliability. Performance trends are further analyzed across individual scenarios, showing that 2.45 GHz links are less affected by metallic shadowing at close range, whereas 915 MHz links maintain more stable detection at longer distances. These findings are discussed in terms of deployment feasibility, indicating that the additional hardware and configuration requirements are offset by the measurable improvement in detection consistency, making the approach applicable for inventory tracking in logistics, warehousing, and industrial automation. Full article

This study develops a Pore-Prior and Progressive-Sampling Transformer architecture, termed PPFormer, for the laboratory-scale analysis of microscopic remaining-oil images acquired from photolithographic glass-micromodel displacement experiments. The architecture integrates pore-prior embedding, progressive sampling of morphology-sensitive tokens, multi-scale self-attention encoding, relative position encoding, and boundary-enhanced decoding. PPFormer identifies five microscopic remaining-oil morphologies: cluster-like remaining oil, columnar remaining oil, droplet-like remaining oil, film-like remaining oil, and blind-end remaining oil. Under the investigated experimental conditions, the model achieved an overall pixel accuracy of 93.6%. The resulting morphology identification maps were used for pore-space-normalized area characterization and displacement-efficiency analysis under three permeability conditions and four displacement strategies. Relative to conventional waterflooding, the area-reduction ranges of cluster-like remaining oil, columnar remaining oil, and droplet-like remaining oil were from 2.29% to 12.66%, from −0.46% to 21.86%, and from 0.09% to 10.75%, respectively. Film-like remaining oil and blind-end remaining oil exhibited smaller changes, ranging from −0.50% to 8.19% and from −0.59% to 5.39%, respectively. Uncertainty was evaluated across independent replicate runs and by comparing predicted masks with consensus ground-truth masks. Full article

Accurate identification of visually similar targets in Unmanned Aerial Vehicle (UAV) imagery is hindered by significant inter-class ambiguity and viewpoint variability. While hierarchical deep learning mitigates these challenges, existing architectures relieve manual design, introducing subjectivity and limiting cross-domain scalability. In this work, we propose an objective, data-driven method for the automated synthesis of hierarchical classification structures. Our approach uses a hybrid inter-class proximity metric that integrates geometric distances between latent-feature-space centroids with empirical misclassification probabilities. Using a hierarchical agglomerative clustering algorithm optimized via an inconsistency coefficient, we synthesize a coarse-to-fine cascade that deploys YOLOv11 for feature extraction and FT-Transformers for specialized identification. Experimental validation on the VisDrone2019 and UAV123 datasets demonstrates that the automatically generated hierarchy achieves a peak F1-score of 94.9%, outperforming the monolithic YOLOv11 model by 0.8% and matching human-designed cascades. Sensitivity analysis indicates an optimal hybrid weight range of 0.4–0.6. The findings confirm that our automated synthesis provides high adaptability and reliability for real-time edge AI deployments, ensuring robust performance in dynamic monitoring environments without requiring manual redesign. Full article

To improve the efficiency, accuracy, and operational stability of postharvest potato tuber sorting in the presence of mineral impurities, mainly soil clods and stones, an intelligent sorting system for potato tubers and mineral impurities was designed and developed. The system employed YOLOv10n as the baseline network and incorporated a PSA module together with a dynamic blur augmentation strategy to establish a task-adapted detection model, termed YOLOv10n-PB. Rather than treating detection accuracy alone as the optimization objective, the proposed system jointly considered detection performance, inference-latency stability, temporal–spatial coordination, and pneumatic rejection reliability. In addition, a programmable logic controller and pneumatic actuators were integrated to enable online target identification and dynamic removal. Comparative experiments involving lightweight YOLO models and $L_{25}\left(5^3\right)$ orthogonal tests were conducted to evaluate the effects of conveyor belt speed, material spacing, and classification threshold on sorting performance. The results showed that YOLOv10n-PB achieved a mAP@0.5 of 98.9% on the test set. Among the investigated factors, conveyor belt speed had the greatest effect on overall sorting accuracy, followed by material spacing and classification threshold. Range analysis identified the optimal parameter combination as a conveyor belt speed of 0.2 m/s, a material spacing of 9 cm, and a classification threshold of 0.4. Validation experiments under these conditions yielded an overall sorting accuracy of 98.3%, a combined mineral-impurity removal accuracy of 98.3%, and a potato tuber false rejection rate of 1.7%. These results demonstrate the feasibility of the proposed system for accurate and stable automatic sorting of potato tubers and mineral impurities under postharvest operating conditions. Full article

The detection technology of crop diseases and pests is transitioning from single sensor monitoring to intelligent perception and multimodal fusion. This paper follows the PRISMA 2020 standard and systematically reviews the relevant core literature. This paper systematically summarizes the development history of spectral sensing technology and analyzes the physical mechanisms of hyperspectral and multispectral imaging in early identification of crop diseases. The focus is on the architectural evolution of deep learning models, including lightweight convolutional neural networks (CNNs), vision transformers (ViTs) with long-range dependency modeling capabilities, and the efficient computing state space model Mamba. In addition, the research progress of spatial spectral joint learning, heterogeneous data fusion, and vision-language models (VLMs) in improving system robustness and interpretability are introduced. By synthesizing the integrated applications of UAV remote sensing, Internet of Things (IoT) edge computing and intelligent robots in staple and cash crops, this paper summarizes the implementation of the integrated system of perception, decision-making and execution. To address the issues of insufficient cross-domain generalization ability and uneven allocation of computing resources in existing models, this paper provides perspectives on the future development of agricultural artificial intelligence (AI) towards foundation model-driven, edge-intelligent collaboration, and green sustainable direction, which can provide theoretical reference for engineering applications in the field of intelligent plant protection. Full article

The identification of liver tumors on computed tomography (CT) scans is hindered by myriad factors, including tumor heterogeneity, anatomical variability, and the limited interpretability of deep learning models in clinical settings. The present research introduces a deep learning-based framework, referred to as the ‘form of the Transformer’, in combination with Global Context (GC) fused with Transformer (Tf) and the Quantitative Attribution (QA) module, for a first reliable, explainable liver tumor detection framework. Moving away from traditional opaque classification systems, this framework uses gradient-based attribution with a localization module and evaluates its spatial alignment with tumor annotations without requiring segmentation supervision during model training. The framework accounts for long-range spacing and leverages Tf-Encoders, which substantially improve the system’s tumor-detection performance. Integrating the Attribution, this framework significantly enhances Qualitative Evidence (QE) in clinical settings. The experimental study has shown strong classification performance with the following metrics: accuracy 96.9%, precision 96.2%, recall 95.8%, F1-score 96.0%, area under the receiver operating characteristic curve 97.6%, and Matthews correlation coefficient 0.93. The classification-based localization of the system achieves an Intersection over Union (IoU) of 71.6% and a Dice coefficient of 83.5%, underscoring the alignment of tumor regions with their attributions. The results indicated significant improvements over existing CNN- and TF-based systems. Full article

In this work, we applied Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks (ANN) to predict key performance characteristics of quantum cascade lasers (QCLs), including material gain, current density, and emission frequency. By developing a machine learning-based surrogate modeling framework that replaces computationally expensive simulations of QCLs, we enable orders-of-magnitude-faster evaluation and optimization of a high-dimensional configuration space. The training dataset was generated using a numerical simulator based on the density-matrix transport model. By combining physics simulations with machine learning, we achieved reliable predictions of device characteristics, with standardized RMSE values ranging from 0.21 to 0.55 for RF, 0.16 to 0.51 for XGBoost, and 0.04 to 0.22 for the ANN model, demonstrating the superior predictive performance of the ANN across all investigated performance characteristics. The ANN was subsequently used to analyze the full configuration space defined by possible layer thicknesses and electric fields. Approximately 44 million configurations were evaluated in about five minutes, achieving a speedup of approximately 90,000 times over the numerical simulator for a single configuration. This approach allowed the identification of designs with improved material gain and facilitated the efficient optimization of key parameters while maintaining high prediction reliability. Full article

This article considers the causes of inter-column pressures (ICP) in wells and their impact on operational reliability. The analysis of Karachaganak field well stock for the period from 2001 to 2024 demonstrates that inter-column pressures manifest in a time frame of five to six years following drilling. These pressures are characterized by a spontaneous emergence and subsequent dissipation. This study proposes a mechanism where the formation of ICP is influenced by multiple factors, including cementing defects, as well as physical and chemical processes. Additionally, the geological heterogeneity of the section has been identified as a contributing factor. The results of studies employing a mobile laboratory and pumping unit are presented. The mobile laboratory unit (MLU) operates with pressure sensors in the range of 0–100 MPa (accuracy ±0.5%), a pump rate of 0.5–20 L/min, and an injection pressure up to 70 MPa; fluid sampling is performed by a discrete sampler with a volume of 500 mL. These allow the identification of sources and channels of fluid migration into the inter-column space, as well as the carrying out of technological operations to reduce and eliminate ICP. This paper sets out a risk-oriented method of inter-column pressure assessment. The proposed risk-based method classifies wells into three risk levels (low, medium, high) based on a composite index R = (P/Pmax) + (V/Vmax) + (C/Cmax) where P is annulus pressure, V is escaped fluid volume per day, C is concentration of H₂S, CO₂, or mercaptan, respectively, and threshold values are Pmax = 35 MPa (API RP 90), Vmax = 50 m³/day, and Cmax = 10 ppm for H₂S. This method takes into account not only the pressure value, but also the volume of escaping fluid and the concentration of aggressive components. It is concluded that an integrated approach to diagnostics and management of inter-column pressures is necessary. This approach should be supported by technological solutions that ensure increased reliability and environmental safety of well operation. Full article

Background/Objectives: Recombinant adeno-associated virus (AAV) stands at the forefront of gene therapy development, requiring stable formulations to support the expanding therapeutic applications. The growing diversity of serotypes and engineered capsids often creates complex challenges for formulation development, thus demanding innovative formulation development strategies beyond traditional manual approaches to characterize a large formulation design space quickly to discover stable formulations. Methods: Here, we address this critical need through a high-throughput automation platform that dramatically enhances formulation development efficiency and capability through rapid formulation preparation and high-throughput AAV analytics. This system prepares 96 distinct formulations in 40 min and completes AAV compounding in 20 min per plate, with precise control of pH, buffer components, and AAV titers. Results: In a proof-of-concept formulation development study using AAV1, we screened 128 formulations across multiple buffer systems, pH ranges, and excipient combinations. This comprehensive approach successfully identified optimal stable high-titer AAV1 formulations (1.2 × 10¹⁴ vector genome (vg)/mL) that maintained stability under frozen, refrigerated, and room temperature storage conditions. Conclusions: Our study demonstrated that this automation platform combined with high-throughput AAV analytics significantly accelerates formulation development, conserves AAV material, and enables systematic exploration of broader formulation design space. It allows us to achieve identification of robust and stable AAV formulations within a timeframe unmatched by traditional formulation development approaches. Full article

Building damage and collapse are the main sources of serious casualties and financial losses during earthquakes, which are among the most destructive natural disasters that endanger human life and property. Therefore, quick and precise post-earthquake building damage assessment is essential for risk assessment and emergency action. Convolutional neural networks (CNNs) primarily concentrate on local features and frequently ignore global contextual information within and across buildings, despite the fact that deep learning-based techniques allow automated damage identification. Transformer-based approaches, on the other hand, are good at capturing global dependencies, but their large memory and processing costs restrict their usefulness. As a result, existing networks still struggle to achieve an effective balance between accuracy and efficiency. To address this issue, this study proposes a lightweight and efficient network for post-earthquake building damage assessment. Specifically, we develop a two-stage method based on EfficientViM with an encoder–decoder architecture. In the encoder, Mamba is introduced to extract multi-scale change features with long-range dependencies, leveraging the state space model to preserve global modeling capability while significantly reducing computational complexity. In the decoder, two lightweight modules are designed to further enhance discriminative capability and computational efficiency. The network finally outputs building localization and pixel-level building damage, respectively. Experiments were conducted on four earthquake events from the BRIGHT dataset using a three-for-training and one-for-testing cross-event rotation evaluation strategy. The results demonstrate that LEViM-Net requires only 30.94 M parameters and 27.10 G FLOPs. In addition, for the Türkiye earthquake event, the proposed method achieves an F1 score of 80.49%, an overall accuracy (OA) of 88.17%, and a mean intersection over union (mIoU) of 49.73%. The proposed model enables efficient remote-sensing-based mapping of macroscopic and image-visible building damage, providing timely support for early-stage emergency response. Full article

Light-based therapies are becoming increasingly = more mainstream, not only within the medical science space, but also within the fields of cosmetic dermatology and personal grooming. Intense Pulsed Light (IPL) harnesses the ability of the natural chromophore–melanin to absorb light energy, which is translated into heat energy and consequently results in targeted thermolysis of cells rich in melanin. This mechanistic pathway lends itself to a wide range of applications, including long-term hair removal, skin rejuvenation, the treatment of unwanted pigmentation, and the treatment of ophthalmic conditions. The development of home use devices (HUDs) for the delivery of IPL-mediated hair removal has facilitated the self-administration of photothermal treatments and reduced reliance on clinical settings. In this study, we demonstrate a pioneering approach to model aspects of IPL-induced thermal induction and selective thermolysis in a complex human skin tissue equivalent. Our approach utilised a deactivated HUD with disabled safety features that allowed for the exposure of tissue constructs to high-fluence IPL. We demonstrate an increase in biomarkers consistent with increased cellular temperature, induction of apoptosis, and increased pro-inflammatory cytokine release following extreme treatment regimens, all of which correlate with an increased fluence and/or increased number of IPL pulses delivered. This method allowed for the identification of cellular events evoked by increasing fluence and extreme-exposure regimes. Full article

Unconventional aircraft configurations are considered as potential solutions to achieve the ambitious emission reduction goals in aviation. However, the identification, selection, and synergetic combination of promising technologies remain a highly vague and uncertain process. This has been addressed in the framework for the advanced morphological approach (FAMA), which represents a structured design process for the generation and evaluation of unconventional aircraft configurations. It implies the decomposition of the task into subproblems, their analysis and the synthesis of concepts in a solution space. This general workflow has been further developed and adapted on three levels in aircraft design: (1) the qualitative idea generation; (2) the semi-quantitative concept selection from the generated ideas; and (3) the probabilistic estimation of design parameters and figures of merit for the most promising concepts from the previous level. The current paper focuses on the overview of the finalized methodology as well as levels one and two, while level three will be presented in more detail in future work. The first level is demonstrated on the concept generation for regional aerial transportation. The second level results in the percentual performance comparisons of promising technologies for the design of an energy-efficient long-range aircraft. Full article

Bayesian operational modal analysis (OMA) provides a probabilistic framework for identifying modal parameters of structures under ambient excitation while quantifying identification uncertainty. By casting modal identification as a Bayesian inference problem, it enables systematic incorporation of modeling assumptions, measurement noise, and data limitations, thereby addressing fundamental shortcomings of conventional OMA methods. This paper presents a comprehensive review of Bayesian OMA, covering its theoretical foundations, representative identification algorithms, uncertainty quantification and management, and practical applications. Emphasis is placed on frequency domain Bayesian formulations, fast Bayesian FFT-based identification algorithms, treatment of multi-setup and asynchronous data, closely spaced modes, and recent advances in both computational acceleration and capturing environmental variations. Developments on uncertainty laws are synthesized to elucidate the fundamental limits of achievable identification precision and their implications for uncertainty management and test design. A range of applications is reviewed to demonstrate how Bayesian OMA methods support robust modal identification and long-term structural health monitoring under operational and environmental variations. Finally, key challenges and future research directions are discussed to facilitate further methodological development and engineering adoption of Bayesian OMA. Full article

This paper addresses the problem of automated segmentation of plant green biomass in field crop images aimed at improving the accuracy of crop and weed identification. To construct a training dataset for neural network models, an automatic annotation algorithm is proposed, enabling the generation of polygonal object masks without human intervention. The method is based on adaptive analysis of color characteristics of plant fragments with iterative narrowing of the hue range in the HSV color space, combined with an integral quality metric that accounts for the dynamics of contour area and shape. The proposed method achieved an IoU of 93.22% and a DSC of 96.30%, demonstrating a high level of agreement between automatic and manual annotations. The generated masks are used to train segmentation models of the YOLO11-seg family. Models of different scales (n, s, m, l, x) were trained and evaluated using standard metrics, including Intersection over Union (IoU), mAP@0.5, mAP@0.5–0.95, F1-score, and Precision–Recall (PR) curves. Experimental results demonstrate that models trained on automatically generated annotations achieve stable segmentation performance of plant green biomass. The best results were obtained with the YOLO11m-seg model, achieving an F1-score of 0. 772. The results confirm the effectiveness of the proposed approach and demonstrate acceptable segmentation quality, supported by both quantitative metrics and visual analysis. The developed automatic annotation algorithm can be used to expand training datasets in computer vision tasks for agricultural applications. Full article