Search Results (2,510)

Colorectal cancer (CRC) remains a leading global health challenge, with early and accurate diagnosis crucial for effective treatment. Histopathological evaluation, the current diagnostic gold standard, faces limitations including subjectivity, delayed results, and reliance on well-prepared tissue slides. Mass spectrometry imaging (MSI) offers a complementary approach by providing molecular-level information, but its high dimensionality and the scarcity of labeled data present unique challenges for traditional supervised learning. In this study, we present the first implementation of foundation models for MSI-based cancer classification using desorption electrospray ionization (DESI) data. We evaluate multiple architectures adapted from other domains, including a spectral classification model known as FACT, which leverages audio–language pretraining. Compared to conventional machine learning approaches, these foundation models achieved superior performance, with FACT achieving the highest cross-validated balanced accuracy ($93.27\%\pm 3.25\%$) and AUROC ($98.4\%\pm 0.7\%$). Ablation studies demonstrate that these models retain strong performance even under reduced data conditions, highlighting their potential for generalizable and scalable MSI-based cancer diagnostics. Future work will explore the integration of spatial and multi-modal data to enhance clinical utility. Full article

The medical imaging domain frequently encounters the dual challenges of annotation scarcity and class imbalance. A critical issue lies in effectively extracting information from limited labeled data while mitigating the dominance of head classes. The existing approaches often overlook in-depth modeling of sample relationships in low-dimensional spaces, while rigid or suboptimal dynamic thresholding strategies in pseudo-label generation are susceptible to noisy label interference, leading to cumulative bias amplification during the early training phases. To address these issues, we propose a semi-supervised medical image classification framework combining labeled data-contrastive learning with class-adaptive pseudo-labeling (CLCP-MT), comprising two key components: the semantic discrimination enhancement (SDE) module and the class-adaptive pseudo-label refinement (CAPR) module. The former incorporates supervised contrastive learning on limited labeled data to fully exploit discriminative information in latent structural spaces, thereby significantly amplifying the value of sparse annotations. The latter dynamically calibrates pseudo-label confidence thresholds according to real-time learning progress across different classes, effectively reducing head-class dominance while enhancing tail-class recognition performance. These synergistic modules collectively achieve breakthroughs in both information utilization efficiency and model robustness, demonstrating superior performance in class-imbalanced scenarios. Extensive experiments on the ISIC2018 skin lesion dataset and Chest X-ray14 thoracic disease dataset validate CLCP-MT’s efficacy. With only 20% labeled and 80% unlabeled data, our framework achieves a 10.38% F1-score improvement on ISIC2018 and a 2.64% AUC increase on Chest X-ray14 compared to the baselines, confirming its effectiveness and superiority under annotation-deficient and class-imbalanced conditions. Full article

With the rise of 6G, the exponential growth of data traffic, the proliferation of emerging applications, and the ubiquity of smart devices, the demand for spectral resources is unprecedented. Terahertz communication (100 GHz–3 THz) plays a key role in alleviating spectrum scarcity through ultra-broadband transmission. In this study, terahertz optical carrier-based systems are employed, where fiber-optic components are used to generate the optical signals, and the signal is transmitted via direct detection in the receiver side, without relying on fiber-optic transmission. In these systems, deep learning-based equalization effectively compensates for nonlinear distortions, while probability shaping (PS) enhances system capacity under modulation constraints. However, the probability distribution of signals processed by PS varies with amplitude, making it challenging to extract useful information from the minority class, which in turn limits the effectiveness of nonlinear equalization. Furthermore, in IM-DD systems, optical multipath interference (MPI) noise introduces signal-dependent amplitude jitter after direct detection, degrading system performance. To address these challenges, we propose a lightweight neural network equalizer assisted by the Synthetic Minority Oversampling Technique (SMOTE) and a clustering method. Applying SMOTE prior to the equalizer mitigates training difficulties arising from class imbalance, while the low-complexity clustering algorithm after the equalizer identifies edge jitter levels for decision-making. This joint approach compensates for both nonlinear distortion and jitter-related decision errors. Based on this algorithm, we conducted a 3.75 Gbaud W-band PAM4 wireless transmission experiment over 300 m at Fudan University’s Handan campus, achieving a bit error rate of 1.32 × 10⁻³, which corresponds to a 70.7% improvement over conventional schemes. Compared to traditional equalizers, the proposed new equalizer reduces algorithm complexity by 70.6% and training sequence length by 33%, while achieving the same performance. These advantages highlight its significant potential for future optical carrier-based wireless communication systems. Full article

Frequent and severe droughts intensify water scarcity in arid and semi-arid regions, creating an urgent need for alternative water resources in agriculture. Treated wastewater (TWW) has emerged as a sustainable option; however, its long-term use may alter soil properties and pose risks if not carefully managed. This study tested the hypothesis that long-term TWW irrigation increases soil salinity, alters fertility, and affects microbial quality, with rainfall partially mitigating these effects. Soil samples (n = 96 at each time point) were collected from two calcareous soils in Jordan, silt loam (Mafraq) and silty clay loam (Ramtha), under four treatments (control and 2, 5, and 10 years of TWW irrigation) at three depths (0–30, 30–60, and 60–90 cm). Sampling was conducted at two intervals, before and after rainfall, to capture the seasonal variation. Soil indicators included the pH, electrical conductivity (EC), sodium (Na⁺), chloride (Cl⁻), calcium (Ca²⁺), magnesium (Mg²⁺), exchangeable sodium percentage (ESP), sodium adsorption ratio (SAR), organic matter (OM), total nitrogen (TN), and microbial parameters (total coliforms (TC), fecal coliforms (FC), and Escherichia coli). Data were analyzed using a linear mixed-effects model with repeated measures, and significant differences were determined using Tukey’s Honest Significant Difference (HSD) test at p < 0.05. The results showed that rainfall reduced Na⁺ by 70%, Cl⁻ by 86%, EC by 73%, the ESP by 28%, and the SAR by 30%. Furthermore, the TC and FC concentrations were diminished by almost 96%. Moderate TWW irrigation (5 years) provided the most balanced outcomes across both sites. This study provides one of the few long-term field-based assessments of TWW irrigation in semi-arid calcareous soils of Jordan, underscoring its value in mitigating water scarcity while emphasizing the need for monitoring to ensure soil sustainability. Full article

Facing global pressures such as population growth, shrinking arable land, and climate change, intelligent agriculture has emerged as a critical pathway toward sustainable and efficient agricultural production. Control algorithms serve as the core enabler of this transition, finding applications in crop production, pest management, agricultural machinery, and resource optimization. This review systematically examines the performance and applications of both traditional (e.g., PID, fuzzy logic) and advanced control algorithms (e.g., neural networks, model predictive control, adaptive control, active disturbance rejection control, and sliding mode control) in agriculture. While traditional methods are valued for simplicity and robustness, advanced algorithms better handle nonlinearity, uncertainty, and multi-objective optimization, enhancing both precision and resource efficiency. However, challenges such as environmental heterogeneity, hardware limitations, data scarcity, real-time requirements, and multi-objective conflicts hinder widespread adoption. This review contributes a structured, critical synthesis of these algorithms, highlighting their comparative strengths and limitations, and identifies key research gaps that distinguish it from prior reviews. Future directions include lightweight algorithms, digital twins, multi-sensor integration, and edge computing, which together promise to enhance the scalability and sustainability of intelligent agricultural systems. Full article

The scarcity of explicit feedback data is a major challenge in the design of recommender systems. Although such data are of a high quality due to users’ voluntary provision of numerical ratings, collecting a sufficient amount in real-world service environments is typically infeasible. As an alternative, implicit feedback data are extensively used. However, because implicit feedback represents observable user actions rather than direct preference statements, it inherently suffers from ambiguity as a signal of true user preference. To address this issue, this study reinterprets the ambiguity of implicit feedback signals as a problem of epistemic uncertainty regarding user preferences and proposes a latent factor model that incorporates this uncertainty within a Bayesian framework. Specifically, the behavioral vector of a user, which is learned from implicit feedback, is restructured within the embedding space using attention mechanisms applied to the user’s interaction history, forming an implicit preference representation. Similarly, item feature vectors are reinterpreted in the context of the target user’s history, resulting in personalized item representations. This study replaces the deterministic attention scores with stochastic attention weights treated as random variables whose distributions are modeled using a Bayesian approach. Through this design, the proposed model effectively captures the uncertainty stemming from implicit feedback within the vector representations of users and items. The experimental results demonstrate that the proposed model not only effectively mitigates the ambiguity of preference signals inherent in implicit feedback data but also achieves better performance improvements than baseline models, particularly on datasets characterized by high user–item interaction sparsity. The proposed model, when integrated with an attention module, generally outperformed other MLP-based models in terms of NDCG@10. Moreover, incorporating the Bayesian attention mechanism yielded an additional performance gain of up to 0.0531 compared to the model using a standard attention module. Full article

The existing literature estimating the additional costs of living faced by people with disabilities is still scarce, despite its relatively long existence. At the moment, existing studies have focused mainly on EU, Anglo-Saxon countries, Malaysia, the Philippines, Ghana, Vietnam, Cambodia, one state in India, sub-Saharan Africa, and China. This limited geographical coverage provides certain estimates for a large fraction of the OECD countries, along with non-representative samples from most other countries, leaving behind more than 75% of the countries worldwide. The main disadvantage of the scarcity of studies relates to the difficulty in estimation and the unavailability of data on disability and related costs. This study surveys the literature on the additional costs of living for people with disabilities. It summarizes the models of disability, the categorization of different costs, the cost assessment methods, and the reasons for difficulty in measuring/estimating costs. We present all studies in the literature received estimating the additional costs of living for people with disabilities, along with the methods used and the geographical areas investigated. The main conclusions drawn from the present survey point to significant additional costs of living for people with disabilities, depending on the type and intensity of disability, which in all cases are not less than 20% of household income, and increase significantly depending on the specifics. Full article

Perovskites (ABX₃) exhibit remarkable potential in optoelectronic conversion, catalysis, and diverse energy-related fields. However, the tunability of A, B, and X-site compositions renders conventional screening methods labor-intensive and inefficient. This review systematically synthesizes the roles of physical simulations and machine learning (ML) in accelerating perovskite discovery. By harnessing existing experimental datasets and high-throughput computational results, ML models elucidate structure-property relationships and predict performance metrics for solar cells, (photo)electrocatalysts, oxygen carriers, and energy-storage materials, with experimental validation confirming their predictive reliability. While data scarcity and heterogeneity inherently limit ML-based prediction of material property, integrating high-throughput computational methods as external mechanistic constraints—supplementing standardized, large-scale training data and imposing loss penalties—can improve accuracy and efficiency in bandgap prediction and defect engineering. Moreover, although embedding high-throughput simulations into ML architectures remains nascent, physics-embedded approaches (e.g., symmetry-aware networks) show increasing promise for enhancing physical consistency. This dual-driven paradigm, integrating data and physics, provides a versatile framework for perovskite design, achieving both high predictive accuracy and interpretability—key milestones toward a rational design strategy for functional materials discovery. Full article

Background: Using fish collagen supplements in daily nutrition may positively influence health and healthy aging. However, their systemic, molecular-level effects on humans are not well characterized. Therefore, given the scarcity of proteomic data, this study aimed to assess the serum proteomic changes during the fish collagen supplementation in healthy women. Methods: This was a crossover interventional study. Thirty healthy women received either 5 mL of fish gel collagen (from silver carp: Hypophthalmichthys molitrix) supplementation with 200 mL of pure water for 40 days or 200 mL of pure water for 40 days only. The washout between the fish collagen and pure water supplementation was 40 days. The nutritional status and dietary intake were assessed. Proteome analyses were conducted using a MALDI-TOF mass spectrometer in a positive linear mode in the m/z 1000–10,000 range. Results: The diet of the women in this study was not well-balanced. Supplementation did not affect nutritional status. Only water content significantly increased. During the fish collagen supplementation, the following discriminative proteins were identified: Filamin-A, Filamin-B, actin, Vimentin, Tropomyosin beta chain, 40S ribosomal protein S8, ATP-dependent RNA helicase DHX8, and FERM domain-containing protein 4A. Conclusions: Changes in serum proteins may reflect broader cytoskeletal remodeling and cellular adaptation resulting from collagen intake. Full article

Multi-view data, captured from various perspectives, is crucial for training view-invariant human action recognition models, yet its acquisition is hindered by spatio-temporal constraints and high costs. This study aims to develop the Pose Scene EveryWhere (PSEW) framework, which automatically generates temporally consistent, multi-view 3D human action data from a single monocular video. The proposed framework first predicts 3D human parameters from each video frame using a deep learning-based Human Mesh Recovery (HMR) model. Subsequently, it applies tracking, linear interpolation, and Kalman filtering to refine temporal consistency and produce naturalistic motion. The refined human meshes are then reconstructed into a virtual 3D scene by estimating a stable floor plane for alignment, and finally, novel-view videos are rendered using user-defined virtual cameras. As a result, the framework successfully generated multi-view data with realistic, jitter-free motion from a single video input. To assess fidelity to the original motion, we used Root Mean Square Error (RMSE) and Mean Per Joint Position Error (MPJPE) as metrics, achieving low average errors in both 2D (RMSE: 0.172; MPJPE: 0.202) and 3D (RMSE: 0.145; MPJPE: 0.206) space. PSEW provides an efficient, scalable, and low-cost solution that overcomes the limitations of traditional data collection methods, offering a remedy for the scarcity of training data for action recognition models. Full article

Accurate and efficient detection of underwater targets in sonar imagery is critical for applications such as marine exploration, infrastructure inspection, and autonomous navigation. However, sonar-based object detection remains challenging due to low resolution, high noise, cluttered backgrounds, and the scarcity of annotated data. To address these issues, we propose UWS-YOLO, a novel detection framework specifically designed for underwater sonar images. The model integrates three key innovations: (1) a C2F-Ortho module that enhances multi-scale feature representation through orthogonal channel attention, improving sensitivity to small and low-contrast targets; (2) a DySnConv module that employs Dynamic Snake Convolution to adaptively capture elongated and irregular structures such as pipelines and cables; and (3) a cross-modal transfer learning strategy that pre-trains on large-scale optical underwater imagery before fine-tuning on sonar data, effectively mitigating overfitting and bridging the modality gap. Extensive evaluations on real-world sonar datasets demonstrate that UWS-YOLO achieves a mAP@0.5 of 87.1%, outperforming the YOLOv8n baseline by 3.5% and seven state-of-the-art detectors in accuracy while maintaining real-time performance at 158 FPS with only 8.8 GFLOPs. The framework exhibits strong generalization across datasets, robustness to noise, and computational efficiency on embedded devices, confirming its suitability for deployment in resource-constrained underwater environments. Full article

Background: Engineered nanoparticles (NPs)—titanium dioxide, silver, zinc oxide and silica—are widely used in cosmetics for UV protection, antimicrobial activity and texturising effects. Chronic consumer-level exposure may impair skin-barrier integrity, disturb microbiome composition and dysregulate immune signalling via the gut–skin axis. Current regulatory frameworks typically omit chronic- or microbiome-focused safety assessments, leaving potential gaps. Objectives: This study aimed to evaluate the long-term effects of cosmetic-relevant NPs (titanium dioxide, silver, zinc oxide, silica) on skin and gut microbiota, epithelial-barrier integrity and immune signalling—including telocyte- and exosome-mediated pathways—and to identify regulatory shortcomings, particularly the absence of microbiome endpoints, validated chronic models and consideration of vulnerable populations. Methods: Following PRISMA 2020, PubMed, Scopus and Web of Science were searched for English-language in vivo animal or human studies (December 2014–April 2025) meeting chronic-exposure criteria (≥90 days in rodents or >10% of lifespan in other species; for humans, prolonged, repetitive application over months to years consistent with cosmetic use). Although not registered in PROSPERO, the review adhered to a pre-specified protocol. Two independent reviewers screened studies; risk of bias was assessed using a modified SYRCLE tool (animal) or adapted NIH guidance (zebrafish). Owing to heterogeneity, findings were synthesised narratively. Results: Of 600 records, 450 unique articles were screened, 50 full texts were assessed and 12 studies were included. Oral exposure predominated and was associated with dysbiosis, barrier impairment, immune modulation and metabolic effects. Dermal models showed outcomes from minimal change to pronounced immune activation, contingent on host susceptibility. Comparative human–animal findings are summarised; telocyte and exosome pathways were largely unexplored. Regulatory reviews (EU SCCS, US FDA and selected Asian frameworks) revealed no requirements for chronic microbiome endpoints. Limitations: Evidence is limited by the small number of eligible studies, heterogeneity in NP characteristics and exposure routes, predominance of animal models and a scarcity of longitudinal human data. Conclusions: Cosmetic nanoparticles may disrupt the microbiome, compromise barrier integrity and trigger immune dysregulation—risks amplified in vulnerable users. Existing regulations lack requirements for chronic exposure, microbiome endpoints and testing in vulnerable groups, and neglect mechanistic pathways involving telocytes and exosomes. Long-term, real-world exposure studies integrating gut–skin microbiome and immune outcomes, and harmonised global nanomaterial-safety standards, are needed to ensure safer cosmetic innovation. Full article

Mobile Cognitive Radio Networks (MCRNs) have emerged as a promising solution to address spectrum scarcity by enabling dynamic access to underutilized frequency bands assigned to Primary or Licensed Users (PUs). These networks rely on Cooperative Spectrum Sensing (CSS) to identify available spectrum, but this collaborative approach also introduces vulnerabilities to security threats—most notably, Spectrum Sensing Data Falsification (SSDF) attacks. In such attacks, malicious nodes deliberately report false sensing information, undermining the reliability and performance of the network. This paper investigates the application of machine learning techniques to detect and mitigate SSDF attacks in MCRNs, particularly considering the additional challenges introduced by node mobility. We propose a hybrid detection framework that integrates a reputation-based weighting mechanism with Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers to improve detection accuracy and reduce the influence of falsified data. Experimental results on software defined radio (SDR) demonstrate that the proposed method significantly enhances the system’s ability to identify malicious behavior, achieving high detection accuracy, reduces the rate of data falsification by approximately 5–20%, increases the probability of attack detection, and supports the dynamic creation of a blacklist to isolate malicious nodes. These results underscore the potential of combining machine learning with trust-based mechanisms to strengthen the security and reliability of mobile cognitive radio networks. Full article

Ultrasound imaging is widely employed for breast cancer detection; however, its diagnostic reliability is often constrained by operator dependence and subjective interpretation. Deep learning-based computer-aided diagnosis (CADx) systems offer potential to improve diagnostic consistency, yet their effectiveness is frequently limited by the scarcity of annotated medical images. This work introduces a training framework to enhance the performance and training stability of a YOLO-based object detection model for breast tumor localization, particularly in data-constrained scenarios. The proposed method integrates a detail-to-context curriculum learning scheme using hierarchically zoomed-in B-mode images, with progression difficulty determined by the tumor-to-background area ratio. A preprocessing step resizes all images to 640 × 640 pixels while preserving aspect ratio to improve intra-dataset consistency. Our evaluation indicates that aspect ratio-preserving resizing is associated with a 2.3% increase in recall and a reduction in the standard deviation of stability metrics by more than 20%. Moreover, the curriculum learning approach reached 97.2% of the final model performance using only 35% of the training data required by conventional methods, while achieving a more balanced precision–recall profile. These findings suggest that the proposed framework holds potential as an effective strategy for developing more robust and efficient tumor detection models, particularly for deployment in resource-limited clinical environments. Full article

Tool wear is a major challenge in sheet-metal forming, as it directly affects product quality and process stability. Reliable monitoring of tool-wear conditions is therefore essential, yet it remains challenging due to limited data availability and uncertainties in manufacturing conditions. To this end, this study evaluates different strategies for developing robust machine learning models under data scarcity for fluctuating manufacturing conditions: a 1D-CNN using time-series data (baseline model), a 1D-CNN with signal fusion of force and acceleration signals, and a 2D-CNN based on Gramian Angular Field (GAF) transformation. Experiments are conducted using inline data from a blanking process with varying material thicknesses and varying availability of training data. The results show that the fusion model achieved the highest improvement (up to 93.2% with the least training data) compared to the baseline model (78.3%). While the average accuracy of the 2D-CNN was comparable to that of the baseline model, its performance was more consistent, with a reduced standard deviation of 5.4% compared to 9.2%. The findings underscore the benefits of sensor fusion and structured signal representation in enhancing classification robustness. Full article