Search Results (4,187)

Due to complex underwater environments characterized by severe scattering, absorption, and color distortion, accurate restoration remains challenging. This paper proposes a hybrid approach combining dual transmission estimation, adaptive ambient light estimation with color correction, and a U-Net Transformer (Uformer) for underwater image enhancement. Our method estimates transmission maps by integrating boundary constraints and local contrast, which effectively address visibility degradation. An adaptive ambient light estimation and color correction strategy are further developed to correct color distortion robustly. Subsequently, a Uformer network enhances the restored image by capturing global and local contextual features effectively. Experiments conducted on publicly available underwater image datasets validate our approach. Performance is quantitatively evaluated using widely adopted non-reference image quality metrics, especially Underwater Image Quality Measure (UIQM) and Underwater Color Image Quality Evaluation (UCIQE). The results demonstrate that our proposed method achieves superior enhancement performance over several state-of-the-art methods. Full article

Background: Cannabis excise tax structures vary widely across the states in the United States. Standardizing taxes may improve cross-state comparisons and strengthen evaluations of how taxes and prices influence public health outcomes. This study developed category-specific standardized tax metrics for flower, vaping, and edible products by incorporating price and tax structure variations using retail scanner data. Methods: We analyzed cannabis retail scanner data from dispensary point-of-sale systems for flower, vaping, and edible products in 12 states with legal recreational markets from Q1 2020 to Q4 2024. Using retail prices and excise tax policies, we converted taxes in different forms across the supply chain into standardized measures and estimated tax incidence (ratio of standardized taxes to retail prices) for each category. We also evaluated the association between standardized taxes and retail prices. Results: Mean standardized excise taxes were USD 32.58/ounce for flower, USD 180.21/ounce for vaping, and USD 0.024/milligram THC for edible products. Corresponding tax incidences were 13.03%, 13.59%, and 13.09%. Standardized taxes and tax incidences varied considerably across states. Category-specific standardized taxes strongly predicted retail prices, supporting their use as an instrumental variable candidate. Conclusions: Category-specific standardized measures of cannabis excise taxes derived from retail scanner data may support cross-state comparisons and pricing policy evaluation. Full article

Background/Objectives: Detecting copy number variations (CNVs) from next-generation sequencing (NGS) is challenging, particularly in targeted sequencing panels, especially for cell-free DNA (cfDNA), where the signal is weak and noise is high. Methods: We present BayesCNV, a Bayesian hierarchical model for gene-level copy ratio estimation from targeted amplicon read depths compared to a CNV-neutral reference sample. The model provides posterior uncertainty for each gene and supports interpretable calling based on effect size and posterior confidence. The model also provides a principled quality-control strategy based on the marginal log likelihood of each sample, with low values indicating low confidence in the calls. BayesCNV uses thermodynamic integration, a technique to reliably estimate this quantity. We benchmark our method against two publicly available CNV callers using Seracare^® reference samples with known CNVs on the OncoReveal^® Core Lbx panel. Results: Our method achieves a sensitivity of 0.87 and specificity of 0.996, dramatically outperforming two competitor methods, IonCopy and DeviCNV. In a separate FFPE dataset using the OncoReveal^® Essential Lbx panel, we show that the marginal log likelihood cleanly separates, degraded from high-quality samples, even when conventional sequencing QC metrics do not. Conclusions: BayesCNV provides accurate and interpretable gene-level CNV estimates and uncertainty quantification, along with an evidence-based quality control metric that improves robustness in targeted cfDNA workflows. Full article

Crop production in the desert Southwest of the United States, as well as in other arid and semi-arid regions, requires tools that provide accurate crop evapotranspiration (ET) estimates to support efficient irrigation management. Such tools include the web-based OpenET platform, which provides real-time ET data generated from six satellite-based models, their Ensemble, and a field-based system (LI-710, LI-COR Inc., Lincoln, NE, USA). This study evaluated simulated ET (ET_SIM) of cotton (Gossypium hirsutum L.) derived from OpenET models (ALEXI/DisALEXI, eeMETRIC, geeSEBAL, PT-JPL, SIMS, and SSEBop), their Ensemble approach, and LI-710. Field data were utilized to estimate cotton ET using the soil water balance (SWB) method (ET_SWB) from June to October 2025 in Gila Bend, AZ, USA. Four evaluation metrics, the normalized root-mean-squared error (NRMSE), mean bias error (MBE), simulation error (S_e), and coefficient of determination (R²), were employed to evaluate the performance of OpenET models, their Ensemble, and the LI-710 in estimating cotton ET. Statistical analysis indicated that the ALEXI/DisALEXI, geeSEBAL, and PT-JPL models substantially underestimated ET_SWB, with simulation errors ranging from −26.92% to −20.57%. The eeMETRIC, SIMS, SSEBop, and Ensemble provided acceptable ET estimates (22.57% ≤ NRMSE ≤ 29.85%, −0.36 mm. day⁻¹ ≤ MBE ≤ 0.16 mm. day⁻¹, −7.58% ≤ S_e ≤ 3.42%, 0.57 ≤ R² ≤ 0.74). Meanwhile, LI-710 simulated cotton ET acceptably with a slight tendency to overestimate daily ET by 0.21 mm. A strong positive correlation was observed between daily ET_SIM from LI-710 and ET_SWB, with S_e and NRMSE of 4.40% and 23.68%, respectively. Based on our findings, using a singular OpenET model, such as eeMETRIC, SIMS, or SSEBop, the OpenET Ensemble, and the LI-710 can offer growers and decision-makers reliable guidance for efficient irrigation management of late-planted cotton in arid and semi-arid climates. Full article

The fundamental goal of a construction project is to complete the construction phase within budget, but in practice, planned cost estimates are often exceeded. The causes of overruns can be due to insufficient preparation and planning of the project, changes during construction, activation of risky events, etc. Also, construction costs are often calculated based on experience rather than scientifically based approaches. Due to the challenges, this paper investigates the potential of several different machine learning methods (linear regression, decision tree forest, support vector machine and general regression neural network) for estimating construction costs. The methods were implemented on a database of recent high-rise construction projects in the Republic of Croatia. Results confirmed the potential of the selected assessment methods; in particular, the support vector machine stands out in terms of accuracy metrics. Established machine learning models contribute to a deeper understanding of real construction costs, their optimization, and more effective cost management during the construction phase. Full article

Background/Objectives: Fibroepithelial tumors (FETs) of the breast, including fibroadenomas (FAs) and phyllodes tumors (PTs), are among the most common breast masses encountered by breast radiologists and pathologists. Differentiating FAs from benign or borderline PTs can be challenging, especially on core biopsy specimens where sampling limitations obscure key histologic features. Although imaging techniques provide useful diagnostic context, their predictive accuracy for pathologic classification remains limited. Methods: We conducted a single-institution pilot study to assess whether tumor growth rate (TGR) derived from serial imaging could serve as a noninvasive correlate of histopathologic outcomes in FETs. Thirty-two patients with serial imaging and subsequent surgical excision (January 2020–May 2025) were analyzed. TGR, expressed as percentage volume increase per month, was calculated from diameter-based volumetrics. Results: The cohort included conventional FA (n = 10), cellular FA (n = 4), benign PT (n = 8), borderline PT (n = 6), and malignant PT (n = 4). Malignant PTs demonstrated significantly higher median TGRs (180.4%/month) and shorter imaging intervals (1.1 months) compared with other groups (p = 0.0357 and p = 0.005, respectively). These large effect-size differences suggest clinically meaningful growth dynamics. Conclusions: As a pilot, this study establishes foundational variance and effect-size estimates for powering a multicenter trial. If validated, TGR may provide an objective, noninvasive metric to enhance preoperative risk stratification and guide management of breast FETs. Full article

The Atlantic horse mackerel (Trachurus trachurus) and the Mediterranean horse mackerel (T. mediterraneus) are two commercially important species whose biological traits remain insufficiently studied in the Central Mediterranean Sea. This study examines their age, growth pattern, and, for the first time, otolith morphology in both species in the Eastern Ionian Sea. The intercept of the weight–length relationship was a = 0.00599 (95% CI = 0.0050–0.0072) for T. trachurus and a = 0.00801 (95% CI = 0.0072–0.0089) for T. mediterraneus, and the slope was b = 3.121 (95% CI: 3.058–3.183) and b = 2.994 (95% CI: 2.957–3.031), respectively. Age was estimated by counting annual growth increments, visible as alternating opaque and clear bands along the axis of the left sagittal otolith from the core to the posterior margin. Von Bertalanffy growth parameters were estimated as L_∞ = 34.65 cm, k = 0.31 year⁻¹, and t₀= −1.11 years for T. trachurus and L_∞ = 35.98 cm, k = 0.23 year⁻¹, and t_o = −1.60 years for T. mediterraneus. Otolith morphometrics showed significantly higher values (ANOVA, p-value < 0.05) in T. mediterraneus for all morphometric variables, except one, indicating larger and wider otoliths than those of T. trachurus, which can be a tool to distinguish the two species. A strong correlation was observed between the total length of the body and otolith metrics in both species. This study enhanced our scientific knowledge on the studied species’ life history traits and provides information for further ecological and stock assessment studies. Full article

Cardiac arrest is a life-threatening emergency requiring immediate intervention, with bystander-initiated Cardiopulmonary resuscitation (CPR) being critical for survival, especially in out-of-hospital situations where medical help is often delayed. Given that over 70% of out-of-hospital cases occur in private residences, there is a growing imperative to provide widespread CPR training to the public. However, conventional instructor-led CPR training faces inherent limitations regarding spatiotemporal constraints and the lack of personalized feedback. To address these issues, this paper proposes an AI-integrated XR-based CPR training system designed as an advanced auxiliary tool for skill acquisition. The system integrates vision-based pose estimation with multimodal sensor data to assess the trainee’s posture and compression metrics in accordance with Korean regional CPR guidelines. Moreover, it utilizes a Large Language Model to evaluate verbal protocols, including requesting an emergency call that aligns with the guidelines. Experimental validation of the proof-of-concept reveals a verbal evaluation accuracy of 88% and a speech recognition accuracy of approximately 95%. Furthermore, the optimized concurrent architecture provides a real-time response latency under 0.5 s, and the automated marker-based tracking ensures precise spatial registration without manual calibration. These results confirm the technical feasibility of the system as a complementary solution for basic life support education. Full article

The Body Mass Index (BMI), integrating body weight and length, is a widely used metric for obesity assessment in humans. As pigs serve as crucial biomedical models, the application of BMI in swine and its genetic basis remain poorly explored. This study aimed to investigate the genetic architecture of pig BMI and compare two carcass-based BMI metrics (BMI-S and BMI-O) for breeding applicability. A total of 439 Landrace × Yorkshire crossbred pigs were genotyped with a 50 K SNP chip; heritability was estimated via a mixed linear model, and genome-wide association study (GWAS) was performed using the BLINK model. BMI-S and BMI-O exhibited moderate-to-high heritability of 0.55 and 0.47, respectively, with 17 genome-wide significant SNPs detected—including the top associated SNP rs81382440 on chromosome 4 and rs80898583 on chromosome 7. Key candidate genes (GPHN, ADAM33, KCNH8, PDCD4) and 5 SNP-trait associations validated in PigQTLdb were linked to lipid/energy metabolism and muscle development. Carcass-based BMI improved phenotypic accuracy, and our findings provide core genetic markers and a theoretical basis for molecular breeding of pig body conformation and lipid deposition traits. Full article

This paper proposes a complete cascade pipeline for accurate position and orientation estimation using a single dual-antenna UWB module. First, an extended Kalman filter (EKF) fuses distance measurements from multiple anchors to estimate the agent’s position. The estimated position is then used to derive orientation. To overcome the critical challenge of front–back ambiguity in orientation estimation, we introduce a novel method that integrates a multi-hypothesis testing (MHT) framework with a circular likelihood metric (CLM). This method enumerates all feasible angle of arrival (AoA) hypotheses via MHT and assesses their consistency using the CLM, thereby selecting the most probable hypothesis to resolve ambiguity. Comparative simulations demonstrate that this “position-first, orientation-later” cascade enhances robustness over joint optimization by preventing the propagation of AoA noise to the position estimates. Extensive evaluations, including high-precision rotary table experiment and real-world field trials, validate the system’s efficacy in providing precise location and heading information. This work delivers a complete, low-cost, and robust solution for autonomous navigation in challenging environments. Full article

Remote photoplethysmography (rPPG) enables non-contact acquisition of human physiological parameters using ordinary cameras, and has been widely applied in medical monitoring, human–computer interaction, and health management. However, most existing studies focus on estimating specific physiological metrics, such as heart rate and heart rate variability, while paying insufficient attention to reconstructing the underlying rPPG waveform. In addition, publicly available datasets typically record facial videos accompanied by fingertip PPG signals as reference labels. Since fingertip PPG waveforms differ substantially from the true photoplethysmography (PPG) signals obtained from the face, deep learning models trained on such datasets often struggle to recover high-quality rPPG waveforms. To address this issue, we collected a new dataset consisting of palm-region videos paired with wrist-based PPG signals as reference labels, and experimentally validated its effectiveness for training neural network models aimed at rPPG waveform reconstruction. Furthermore, we propose a generative adversarial network (GAN)-based pulse-wave synthesis framework that produces high-quality rPPG waveforms by denoising the mean green-channel signal. By incorporating time-domain peak-aware loss, frequency-domain loss, and adversarial loss, our method achieves promising performance, with an RMSE (Root Mean Square Error) of 0.102, an MAPE (Mean Absolute Percentage Error) of 0.028, a Pearson correlation of 0.987, and a cosine similarity of 0.989. These results demonstrate the capability of the proposed approach to reconstruct high-fidelity rPPG waveforms with improved morphological accuracy compared to noisy raw rPPG signals, rather than directly validating health monitoring performance. This study presents a high-quality rPPG waveform reconstruction approach from both data and model perspectives, providing a reliable foundation for subsequent physiological signal analysis, waveform-based studies, and potential health-related applications. Full article

Workers’ exposure to silica dust is a global occupational and public health concern and is particularly prevalent in Southern Africa, mainly because of inadequate dust control measures. It is worsened by the high prevalence of HIV/AIDS, which exacerbates tuberculosis and other occupational lung diseases. The prevalence of silicosis in the region ranges from 9 to 51%; however, silica dust exposure levels and controls, especially in the informal mining sector, particularly in artisanal small-scale mines (ASMs), leave much to be desired. This is important because silicosis is incurable and can only be eliminated by preventing worker exposure. Additionally, several studies have indicated inadequate occupational health and safety policies, weak inspection systems, inadequate monitoring and control technologies, and inadequate occupational health and hygiene skills. Furthermore, there is a near-absence of silica dust analysis laboratories in southern Africa, except in South Africa. This protocol aims to systematically evaluate the effectiveness of respirable dust and respirable crystalline silica dust exposure evaluation and control methodology for the mining industry. The study will entail testing the effectiveness of current dust control measures for controlling microscale particles using various exposure dose metrics, such as mass, number, and lung surface area concentrations. This will be achieved using a portable Fourier transform infrared spectroscope (FTIR) (Nanozen Industries Inc., Burnaby, BC, Canada), the Nanozen DustCount, which measures both the mass and particle size distribution. The surface area concentration will be analysed by inputting the particle size distribution (PSD) results into the Multiple-Path Particle Dosimetry Model (MPPD) to estimate the retained and cleared doses. The MPPD will help us understand the sub-micron dust deposition and the reduction rate using the controls. To the best of our knowledge, the proposed approach has never been used elsewhere or in our settings. The proposed approach will reduce dependence on highly skilled individuals, reduce the turnaround sampling and analysis time, and provide a reference for regional harmonised occupational exposure limit (OEL) guidelines as a guiding document on how to meet occupational health, safety and environment (OHSE) requirements in ASM settings. Therefore, the outcome of this study will influence policy reforms and protect hundreds of thousands of employees currently working without any form of exposure prevention or protection. Full article

This study presents the development and validation of a high-speed optical data acquisition system for detecting and characterizing hydrodynamic cavitation downstream of a triangular nozzle. The system integrates a PIN photodiode, a transimpedance amplifier, and a high-sampling-rate microcontroller. Its performance was first evaluated using controlled sinusoidal signals, and statistical stability was assessed as a function of the number of acquired samples. Experiments were subsequently conducted in a converging–diverging conduit under biphasic flow conditions, where mean irradiance, standard deviation, and frequency spectra were analyzed downstream of the nozzle. The optical signal distributions revealed transitions in flow behavior associated with cavitation development, which were quantified through statistical metrics and spectral features. The Strouhal number was estimated from dominant frequencies extracted from the spectra, exhibiting a non-monotonic dependence on the Reynolds number, consistent with changes in flow structure and turbulence intensity. Spectral analysis further indicated frequency bands associated with energy transfer across turbulent scales and bubble dynamics. Overall, the results demonstrate that the proposed optical system constitutes a viable and non-intrusive methodology for detecting and characterizing cavitation intensity in a way that complements other optical and acoustic methods. Full article

Efficient clustering and cluster head (CH) selection are the critical parameters of wireless sensor networks (WSNs) for their prolonged network lifetime. However, the performances of the traditional clustering algorithms like LEACH and HEED are not satisfactory when they are implemented on a dense WSN due to their unbalanced load distribution and high contention nature. In the traditional methods, the cluster heads are selected with respect to the residual energy criteria, and often create a circular cluster shape boundary with a uniform node distribution. This causes the cluster heads to become overloaded in the high-density regions and the unutilized cluster heads gather in the sparse regions. Therefore, frequent cluster head changes occur, which is not suitable for a real-time dynamic environment. In order to avoid these issues, this proposed work develops a density-aware adaptive clustering (DAAC) protocol for optimizing the CH selection and cluster formation in a dense wireless sensor network. The residual energy information, together with the local node density and link quality, is utilized as a single cluster head detection metric in this work. The local node density information assists the proposed work to estimate the sparse and dense area in the network that results in frequent cluster head congestion. DAAC is also included with a minimum inter-CH distance constraint for CH crowding, and a multi-factor cost function is used for making the clusters by inviting the nodes by their distance and an expected transmission energy. DAAC triggers re-clustering in a dynamic manner when it finds a response in the CH energy depletion or a significant change in the load density. Unlike the traditional circular cluster boundaries, DAAC utilizes dynamic Voronoi cells (VCs) for making an interference-aware coverage in the network. This makes dense WSNs operate efficiently, by providing a hierarchical extension, on making secondary CHs in an extremely dense scenario. The proposed model is implemented in MATLAB simulation, to determine and compare its efficiency over the traditional algorithms such as LEACH and HEED, which shows a satisfactory network lifetime improvement of 20.53% and 32.51%, an average increase in packet delivery ratio by 8.14% and 25.68%, and an enhancement in total throughput packet by 140.15% and 883.51%, respectively. Full article

Reconstructing hand and object shapes from a single view during interaction remains challenging due to severe mutual occlusion and the need for high physical plausibility. To address this, we propose a novel framework for hand–object interaction reconstruction based on holistic, multi-stage collaborative optimization. Unlike methods that process hands and objects independently or apply constraints as late-stage post-processing, our model progressively enforces physical consistency and geometric accuracy throughout the entire reconstruction pipeline. Our network takes an RGB-D image as input. An adaptive feature fusion module first combines color and depth information to improve robustness against sensing uncertainties. We then introduce structural priors for 2D pose estimation and leverage texture cues to refine depth-based 3D pose initialization. Central to our approach is the iterative application of a dense mutual attention mechanism during sparse-to-dense mesh recovery, which dynamically captures interaction dependencies while refining geometry. Finally, we use a Signed Distance Function (SDF) representation explicitly designed for contact surfaces to prevent interpenetration and ensure physically plausible results. Through comprehensive experiments, our method demonstrates significant improvements on the challenging ObMan and DexYCB benchmarks, outperforming state-of-the-art techniques. Specifically, on the ObMan dataset, our approach achieves hand CD_h and object CD_o metrics of 0.077 cm² and 0.483 cm², respectively. Similarly, on the DexYCB dataset, it attains hand CD_h and object CD_o values of 0.251 cm² and 1.127 cm², respectively. Full article