Search Results (77)

Agrarian women are at the forefront of rural livelihoods increasingly affected by the frequency and severity of climate change impacts. However, their household livelihood resilience (HLR) remains limited due to gender-blind policies, scarce sex-disaggregated data, and inadequate consideration of gender-specific needs in resilience-building efforts. Grounded in participatory feminist research, this study employed a multi-method qualitative approach, including semi-structured interviews and oral history narratives, with 60 women in two climate-vulnerable provinces. Data were analyzed through thematic coding, CATWOE (Customers, Actors, Transformation, Worldview, Owners, Environmental Constraints) analysis, and descriptive statistics. The findings identify nine major climate-related events disrupting livelihoods and reveal a limited understanding of HLR as a long-term, transformative concept. Adaptation strategies remain short-term and focused on immediate survival. Barriers to HLR include financial constraints, limited access to agricultural resources and technology, and entrenched gender norms restricting women’s leadership and decision-making. While local governments, women’s associations, and community networks provide some support, gaps in accessibility and adequacy persist. Participants expressed the need for financial assistance, vocational training, agricultural technologies, and stronger peer networks. Strengthening HLR among agrarian women requires gender-sensitive policies, investment in local support systems, and community-led initiatives. Empowering agrarian women as agents of change is critical for fostering resilient rural livelihoods and achieving inclusive, sustainable development. Full article

Skin cancer is one of the most prevalent forms of cancer worldwide, and early and accurate diagnosis critically impacts patient outcomes. Given the sensitive nature of medical data and its fragmented distribution across institutions (data silos), privacy-preserving collaborative learning is essential to enable knowledge-sharing without compromising patient confidentiality. While federated learning (FL) offers a promising solution, existing methods struggle with heterogeneous and missing modalities across institutions, which reduce the diagnostic accuracy. To address these challenges, we propose an effective and flexible Personalized Multimodal Federated Learning framework (PMM-FL), which enables efficient cross-client knowledge transfer while maintaining personalized performance under heterogeneous and incomplete modality conditions. Our study contains three key contributions: (1) A hierarchical aggregation strategy that decouples multi-module aggregation from local deployment via global modular-separated aggregation and local client fine-tuning. Unlike conventional FL (which synchronizes all parameters in each round), our method adopts a frequency-adaptive synchronization mechanism, updating parameters based on their stability and functional roles. (2) A multimodal fusion approach based on multitask learning, integrating learnable modality imputation and attention-based feature fusion to handle missing modalities. (3) A custom dataset combining multi-year International Skin Imaging Collaboration(ISIC) challenge data (2018–2024) to ensure comprehensive coverage of diverse skin cancer types. We evaluate PMM-FL through diverse experiment settings, demonstrating its effectiveness in heterogeneous and incomplete modality federated learning settings, achieving 92.32% diagnostic accuracy with only a 2% drop in accuracy under 30% modality missingness, with a 32.9% communication overhead decline compared with baseline FL methods. Full article

Light Detection and Ranging(LiDAR)-inertial simultaneous localization and mapping (SLAM) is a critical component in multi-sensor autonomous navigation systems, providing both accurate pose estimation and detailed environmental understanding. Despite its importance, existing optimization-based LiDAR-inertial SLAM methods often face key limitations: unreliable feature extraction, sensitivity to noise and sparsity, and the inclusion of redundant or low-quality feature correspondences. These weaknesses hinder their performance in complex or dynamic environments and fail to meet the reliability requirements of autonomous systems. To overcome these challenges, we propose a novel and accurate LiDAR-inertial SLAM framework with three major contributions. First, we employ a robust multi-category feature extraction method based on principal component analysis (PCA), which effectively filters out noisy and weakly structured points, ensuring stable feature representation. Second, to suppress outlier correspondences and enhance pose estimation reliability, we introduce a coarse-to-fine two-stage feature correspondence selection strategy that evaluates geometric consistency and structural contribution. Third, we develop an adaptive weighted pose estimation scheme that considers both distance and directional consistency, improving the robustness of feature matching under varying scene conditions. These components are jointly optimized within a sliding-window-based factor graph, integrating LiDAR feature factors, IMU pre-integration, and loop closure constraints. Extensive experiments on public datasets (KITTI, M2DGR) and a custom-collected dataset validate the proposed method’s effectiveness. Results show that our system consistently outperforms state-of-the-art approaches in accuracy and robustness, particularly in scenes with sparse structure, motion distortion, and dynamic interference, demonstrating its suitability for reliable real-world deployment. Full article

Background: Primary malignant bone tumors among adolescent patients are most commonly associated with burdensome surgeries that can severely affect young patients’ early life. To this day, despite available autologous tissue donor sites, cement spacers or endoprostheses are still most commonly used as a form of reconstruction of post-resection defects. Methods: The study group includes 20 adolescent patients diagnosed with Osteosarcoma or Ewing Sarcoma involving the upper limbs. The inclusion criteria were as follows: primary malignant bone tumors sensitive to neoadjuvant chemotherapy, tumors not infiltrating major blood vessels and nerves, and the appliance of the microsurgical free flap as a reconstructive method. Poor tumor response to neodajuvant chemotherapy or patients with incomplete follow-up were excluded from this study. To achieve the functional reconstruction of post-resection defects, fibula free flaps were applied. In cases of resection, including the metaphysis of a long bone, a modification of the flap harvest was applied in order to prevent arthrodesis. The MSTS (Musculoskeletal Tumor Society Scoring System) scale was used as a functional outcome measurement tool. Results: The reported outcomes of this study prove the efficiency of the treatment’s approach of combining the resection of the tumor with subsequent microsurgical restoration with the use of autologous tissues. The average score on the MSTS scale, which assesses the functional outcome, was 26.8/30 points, which indicates great motor outcomes. There were no reports of local recurrence during follow-up. Conclusions: Patients with primary malignant bone tumors in the upper limbs can benefit from microsurgical techniques, which are highly customized; effective; and give sufficient functionality following extensive resection. Full article

To address the challenges of high missed detection rates for minute transmission line defects, strong complex background interference, and limited computational power on edge devices in UAV-assisted power line inspection, this paper proposes a lightweight improved YOLOv12 real-time detection model. First, a Bidirectional Weighted Feature Fusion Network (BiFPN) is introduced to enhance bidirectional interaction between shallow localization information and deep semantic features through learnable feature layer weighting, thereby improving detection sensitivity for line defects. Second, a Cross-stage Channel-Position Collaborative Attention (CPCA) module is embedded in the BiFPN’s cross-stage connections, jointly modeling channel feature significance and spatial contextual relationships to effectively suppress complex background noise from vegetation occlusion and metal reflections while enhancing defect feature representation. Furthermore, the backbone network is reconstructed using ShuffleNetV2’s channel rearrangement and grouped convolution strategies to reduce model complexity. Experimental results demonstrate that the improved model achieved 98.7% mAP@0.5 on our custom transmission line defect dataset, representing a 3.0% improvement over the baseline YOLOv12, with parameters compressed to 2.31M (8.3% reduction) and real-time detection speed reaching 142.7 FPS. This method effectively balances detection accuracy and inference efficiency, providing reliable technical support for unmanned intelligent inspection of transmission lines. Full article

Background: Intestinal metaplasia (IM) is a precancerous gastric condition that requires accurate histopathological diagnosis to enable early intervention and cancer prevention. Traditional evaluation of H&E-stained tissue slides can be labor-intensive and prone to interobserver variability. Recent advances in deep learning, particularly transformer-based models, offer promising tools for improving diagnostic accuracy. Methods: We propose ViSwNeXtNet, a novel patch-wise ensemble framework that integrates three transformer-based architectures—ConvNeXt-Tiny, Swin-Tiny, and ViT-Base—for deep feature extraction. Features from each model (12,288 per model) were concatenated into a 36,864-dimensional vector and refined using iterative neighborhood component analysis (INCA) to select the most discriminative 565 features. A quadratic SVM classifier was trained using these selected features. The model was evaluated on two datasets: (1) a custom-collected dataset consisting of 516 intestinal metaplasia cases and 521 control cases, and (2) the public GasHisSDB dataset, which includes 20,160 normal and 13,124 abnormal H&E-stained image patches of size 160 × 160 pixels. Results: On the collected dataset, the proposed method achieved 94.41% accuracy, 94.63% sensitivity, and 94.40% F1 score. On the GasHisSDB dataset, it reached 99.20% accuracy, 99.39% sensitivity, and 99.16% F1 score, outperforming individual backbone models and demonstrating strong generalizability across datasets. Conclusions: ViSwNeXtNet successfully combines local, regional, and global representations of tissue structure through an ensemble of transformer-based models. The addition of INCA-based feature selection significantly enhances classification performance while reducing dimensionality. These findings suggest the method’s potential for integration into clinical pathology workflows. Future work will focus on multiclass classification, multicenter validation, and integration of explainable AI techniques. Full article

This study presents an advanced model of thermal Resistances and heat Capacities model approach (RC model), applied to a custom-built skin calorimeter for the in vivo characterization of localized thermal behavior of the skin. The device integrates a heat flux sensor and a programmable thermostat, and is capable of measuring the heat flux, heat capacity, internal thermal resistance, and subcutaneous temperature of the skin, under both resting and exercising conditions. The model, refined through extensive experimental validation, incorporates the skin as part of the system and is adapted to three modes of operation: calibration base, ambient air, and direct skin contact. Simulations are used to analyze heat flux dynamics, optimize control parameters, and validate analytical expressions. Under resting conditions, the model enables the estimation of the skin’s heat capacity and thermal resistance. During exercise, it allows the determination of heat flux and internal temperature variations using simplified expressions. The system demonstrates high sensitivity (195.5 mV/W) and provides a robust, non-invasive method for extracting medically relevant thermal parameters from a 2 × 2 cm² skin area. Full article

High-performance flexible sensors capable of direct integration with biological tissues are essential for personalized health monitoring, assistive rehabilitation, and human–machine interaction. However, conventional devices face significant challenges in achieving conformal integration with biological surfaces, along with sufficient biomechanical compatibility and biocompatibility. This research presents an in situ 3D biomanufacturing strategy utilizing Direct Ink Writing (DIW) technology to fabricate functional bioelectronic interfaces directly onto human skin, based on a novel annealing PEDOT:PSS/PVA composite bio-ink. Central to this strategy is the utilization of a novel annealing PEDOT:PSS/PVA composite material, subjected to specialized processing involving freeze-drying and subsequent thermal annealing, which is then formulated into a DIW ink exhibiting excellent printability. Owing to the enhanced network structure resulting from this unique fabrication process, films derived from this composite material exhibit favorable electrical conductivity (ca. 6 S/m in the dry state and 2 S/m when swollen) and excellent mechanical stretchability (maximum strain reaching 170%). The material also demonstrates good adhesion to biological interfaces and high-fidelity printability. Devices fabricated using this material achieved good conformal integration onto a finger joint and demonstrated strain-sensitive, repeatable responses during joint flexion and extension, capable of effectively transducing local strain into real-time electrical resistance signals. This study validates the feasibility of using the DIW biomanufacturing technique with this novel material for the direct on-body fabrication of functional sensors. It offers new material and manufacturing paradigms for developing highly customized and seamlessly integrated bioelectronic devices. Full article

With the rapid proliferation of electric vehicles (EVs), urban logistics faces increasing challenges in optimizing vehicle routing. This paper presents a new modeling framework for the Electric Vehicle Routing Problem (EVRP), where multiple electric trucks serve a set of customers within their capacity limits. The model incorporates critical EV-specific constraints, including limited battery range, charging demand, and dynamic urban traffic conditions, with the objective of minimizing total delivery cost. To efficiently solve this problem, a Dual Population Cooperative Genetic Algorithm (DPCGA) is proposed. The algorithm employs a dual-population mechanism for global exploration, effectively expanding the search space and accelerating convergence. It then introduces local refinement operators to improve solution quality and enhance population diversity. A large number of experimental results demonstrate that DPCGA significantly outperforms traditional algorithms in terms of performance, achieving an average 3% improvement in customer satisfaction and a 15% reduction in computation time. Furthermore, this algorithm shows superior solution quality and robustness compared to the AVNS and ESA-VRPO algorithms, particularly in complex scenarios such as adjustments in charging station layouts and fluctuations in vehicle range. Sensitivity analysis further verifies the stability and practicality of DPCGA in real-world urban delivery environments. Full article

In the N$\nu$DEx collaboration, a high-pressure gas TPC is being developed to search for the neutrinoless double beta decay. The use of electronegative ⁸²SeF₆ gas mandates an ion-TPC. The reconstruction of the z coordinate is to be realized by exploiting the feature of multiple species of charge carriers. As the initial stage of the development, we studied the properties of the ${\mathrm{SF}}_6$ gas, which is non-toxic and has a similar molecular structure to ${\mathrm{SeF}}_6$. In the paper, we present the measurement of drift velocities and mobilities of the majority and minority negative charge carriers found in ${\mathrm{SF}}_6$ at a pressure of 750 Torr, slightly higher than the local atmospheric pressure. The reduced fields range between 3.0 and 5.5 Td. This was performed using a laser beam to ionize the gas inside a small TPC, with a drift length of 3.7 cm. A customized charge-sensitive amplifier was developed to read out the anode signals induced by the slowly drifting ions. The closure test of the reconstruction of the z coordinate using the difference in the velocities of the two carriers was also demonstrated. Full article

In this study, we present a proof-of-concept neuroelectronic interface (NEI) for extracellular stimulation and recording of neurophysiological activity in spiral ganglion neurons (SGNs) cultured in vitro on three-dimensional, micro-patterned substrates with customized microtopographies, integrated within a 196-channel microelectrode array (MEA). This approach enables mechanotaxis-driven neuronal contact guidance, promoting SGN growth and development, which is highly sensitive to artificial in vitro environments. The microtopography geometry was optimized based on our previous studies to enhance SGN alignment and neuron-electrode interactions. The NEI was validated using SGNs dissociated from rat pups in the prehearing period and cultured for seven days in vitro (DIV). We observed viable and proliferative cellular cultures with robust neurophysiological responses in the form of local field potentials (LFPs) resembling action potentials (APs), elicited both spontaneously and through electrical stimulation. These findings provide deeper insights into SGN behavior and neuron-microenvironment interactions, laying the groundwork for further advancements in neuroelectronic systems. Full article

Rationale: Neoadjuvant chemotherapy (NAC) is a key element of treatment for locally advanced breast cancer (LABC). Predicting the response of NAC for patients with LABC before initiating treatment would be valuable to customize therapies and ensure the delivery of effective care. Objective: Our objective was to develop predictive measures of tumor response to NAC prior to starting for LABC using machine learning and textural computed tomography (CT) features in different level of frequencies. Materials and Methods: A total of 851 textural biomarkers were determined from CT images and their wavelet coefficients for 117 patients with LABC to evaluate the response to NAC. A machine learning pipeline was designed to classify response to NAC treatment for patients with LABC. For training predictive models, three models including all features (wavelet and original image features), only wavelet and only original-image features were considered. We determined features from CT images in different level of frequencies using wavelet transform. Additionally, we conducted a comparison of feature selection methods including mRMR, Relief, Rref QR decomposition, nonnegative matrix factorization and perturbation theory feature selection techniques. Results: Of the 117 patients with LABC evaluated, 82 (70%) had clinical–pathological response to chemotherapy and 35 (30%) had no response to chemotherapy. The best performance for hold-out data splitting was obtained using the KNN classifier using the Top-5 features, which were obtained by mRMR, for all features (accuracy = 77%, specificity = 80%, sensitivity = 56%, and balanced-accuracy = 68%). Likewise, the best performance for leave-one-out data splitting could be obtained by the KNN classifier using the Top-5 features, which was obtained by mRMR, for all features (accuracy = 75%, specificity = 76%, sensitivity = 62%, and balanced-accuracy = 72%). Conclusions: The combination of original textural features and wavelet features results in a greater predictive accuracy of NAC response for LABC patients. This predictive model can be utilized to predict treatment outcomes prior to starting, and clinicians can use it as a recommender system to modify treatment. Full article

To support data-driven decision-making in a Manufacturing Execution System (MES) environment, a system that can quickly and accurately analyze a wide range of production, quality, asset, and material information must be deployed. However, existing MES data management approaches rely on predefined queries or report templates that lack flexibility and limit real-time decision support. In this paper, we proposes a domain-specific Retrieval-Augmented Generation (RAG) architecture that extends LangChain’s capabilities with Manufacturing Execution System (MES)-specific components and the Ollama-based Local Large Language Model (LLM). The proposed architecture addresses unique MES requirements including real-time sensor data processing, complex manufacturing workflows, and domain-specific knowledge integration. It implements a three-layer structure: an application layer using FastAPI for high-performance asynchronous processing, an LLM layer for natural language understanding, and a data storage layer combining MariaDB, Redis, and Weaviate for efficient data management. The system effectively handles MES-specific challenges such as schema relationships, temporal data processing, and security concerns without exposing sensitive factory data. This is an industry-specific, customized approach focusing on problem-solving in manufacturing sites, going beyond simple text-based RAG. The proposed architecture considers the specificity of data sources, real-time and high-availability requirements, the reflection of domain knowledge and workflows, compliance with security and quality control regulations, and direct interoperability with MES systems. The architecture can be further enhanced through integration with various manufacturing systems, an advanced LLM, and distributed processing frameworks while maintaining its core focus on MES domain specialization. Full article

The widespread adoption of electric vehicles (EVs) has elevated the importance of rigorous safety standards, particularly for fire resistance in post-crash scenarios. Existing testing protocols, such as Regulation No. 100, utilize petrol pool fires to simulate real-world fire hazards but lack comprehensive analysis regarding their repeatability and reliability. This study addresses this critical gap by evaluating the variability and consistency of fire-resistance tests performed on multiple battery energy storage systems (BESSs) under standardized conditions. A custom-built measurement system incorporating thermocouples, anemometers, and hygrometers provided high-resolution data on flame dynamics, ambient conditions, and pool fire efficiency. Statistical evaluations following ISO 5725 series guidelines revealed substantial inconsistencies, including unstable exposure temperatures and sensitivity to local turbulence. These findings call into question the robustness of current testing methods, and we propose an alternative approach employing LPG burners for improved precision and repeatability. By identifying significant flaws in existing standards and offering scientifically grounded enhancements, this work contributes a novel perspective to the field of EV safety, advancing global fire-resistance testing protocols. Full article

Background/Objectives: Sports-related bone fractures are a common challenge in sports medicine, requiring accurate and timely diagnosis to prevent long-term complications and enable effective treatment. Conventional diagnostic methods often rely on manual interpretation, which is prone to errors and inefficiencies, particularly for subtle and localized fractures. This study aims to develop a lightweight and efficient deep learning-based framework to improve the accuracy and computational efficiency of fracture detection, tailored to the needs of sports medicine. Methods: We proposed a novel fracture detection framework based on the DenseNet121 architecture, incorporating modifications to the initial convolutional block and final layers for optimized feature extraction. Additionally, a Canny edge detector was integrated to enhance the model ability to detect localized structural discontinuities. A custom-curated dataset of radiographic images focused on common sports-related fractures was used, with preprocessing techniques such as contrast enhancement, normalization, and data augmentation applied to ensure robust model performance. The model was evaluated against state-of-the-art methods using metrics such as accuracy, recall, precision, and computational complexity. Results: The proposed model achieved a state-of-the-art accuracy of 90.3%, surpassing benchmarks like ResNet-50, VGG-16, and EfficientNet-B0. It demonstrated superior sensitivity (recall: 0.89) and specificity (precision: 0.875) while maintaining the lowest computational complexity (FLOPs: 0.54 G, Params: 14.78 M). These results highlight its suitability for real-time clinical deployment. Conclusions: The proposed lightweight framework offers a scalable, accurate, and efficient solution for fracture detection, addressing critical challenges in sports medicine. By enabling rapid and reliable diagnostics, it has the potential to improve clinical workflows and outcomes for athletes. Future work will focus on expanding the model applications to other imaging modalities and fracture types. Full article