Browse Articles
Discover research articles across all indexed journals
Sim-to-real domain adaptation based completion level recognition for autonomous micro-drilling in biomedical application
Abstract Micron-level precision in drilling thin bone structures is essential in both surgical and neuroscience applications but remains technically challenging due to tissue fragility and anatomical variability. Traditional manual methods are slow and error-prone, while systems based on preoperative imaging lack adaptability to intraoperative changes. We previously proposed a convolutional neural network based autonomous micro-drilling system, enabling real-time control without prior bone knowledge. However, its reliance on manual annotation limited scalability and accuracy. In this study, we enhance the system through a sim-to-real domain adaptation model using synthetic data generated from a photorealistic simulator. The novelty of this work is a task-specific adversarial model that bridges the domain gap, significantly reducing annotation time (from 600 s/frame to 1.8 s/frame) while achieving a success rate of 85% (up from 80%) in 20 trials of eggshell drilling. These results demonstrate the feasibility and effectiveness of simulation-based training and domain adaptation for improving autonomous micro-drilling performance in biomedical applications.
Effectiveness of the Brush DJ app in improving oral hygiene among patients with fixed orthodontic appliances: a randomized controlled trial
ROV dynamic modeling and grasping algorithm for underwater control system of marine oil and gas
Association between triglyceride glucose-body mass index and preeclampsia risk in advanced maternal age pregnant women-a retrospective cohort study
Catalytic activity of supported Cu-Mn/fly ash geopolymer for the oxidative removal of toluene
Comparison of cNORM and LMS methods for estimating reference percentile curves from biometric data
Abstract Accurate reference curves for biometric measures are essential for population health monitoring and screening. The Lambda Mu Sigma Method (LMS) , introduced by Cole and Green, is widely used in public health for generating age-specific reference percentiles. This study compares LMS with cNORM, a distribution-free approach based on Taylor polynomials, previously validated in psychometric applications. Using publicly accessible National Health and Nutrition Examination Survey (NHANES) datasets, we compared the performance of LMS and cNORM in modelling reference curves for body mass index (BMI) and maximum oxygen consumption (VO 2max ). We repeatedly drew random samples of different size to compute the models and cross-validated these to examine accuracy and bias of both methods across different percentile ranges. Performance metrics included R 2 , root mean square error and systematic deviation (Bias) from empirical percentiles. Both cNORM and LMS achieved high accuracy across the full distributions of BMI and VO₂ max , but cNORM showed superior precision in extreme percentiles (± 2 SD), critical for identifying at-risk individuals. Accuracy improved with larger sample sizes, with a stronger effect for LMS, while interactions between method and sample size were dataset-specific and inconsistent. The distribution free approach implemented in cNORM offers a viable alternative to LMS for generating reference curves in public health applications, particularly when accurate classification in extreme ranges is crucial for screening decisions.
Prevalence and associated factors of antenatal depression among pregnant women attending Shegaw Motta general Hospital, East Gojjam Zone, Ethiopia
Dimensional validation of CubeSat structures using 3D optical scanning technology
Production and trade of specialty coffee in Brazil
An improved weighted average algorithm with Cloud-Based Risk-Conscious stochastic model for building energy optimization
Comprehensive care needs among informal cancer caregivers of patients with advanced cancer in palliative care: a cross-sectional study
Development and validation of a kinematic hindlimb cycling model for rats
Abstract Functional electrical stimulation (FES) bicycle training is a physical rehabilitation technique used to promote muscle recovery and/or cardiorespiratory health in persons with lower extremity impairment due to neurologic injury. FES cycling may also increase bone mineral density (BMD) in such populations, although no consensus exists that supports FES-induced skeletal improvement, in-part due to the extended 9–12 + month duration necessary to detect BMD gain in humans and the multitude of FES parameter permutations that require optimization to improve bone strength and/or reduce fracture risk, which may differ from those needed to improve muscle or cardiovascular fitness. Rodent models have been used in FES studies because musculoskeletal changes are phenotypically like humans but occur over an accelerated time course that permits more rapid identification of potentially efficacious FES parameters. To gain accelerated understanding of FES-cycling in humans, we performed a kinematic analysis of the rat hindlimb with a fixed hip location and variable foot location as the pedal of the bicycle rotated about the crank. Based on this analysis, an FES pattern was developed for the femoral and sciatic nerves to produce forward (clockwise) or reverse (counterclockwise) motion of the crank. These modeled FES patterns were validated in nine experiments that used 743 unique stimulation trials conducted in anesthetized male and female rodents. Such insights represent initial steps to facilitate closed-loop FES control of cycling in rats, which will help to refine rehabilitation strategies to promote bone and muscle recovery in rodent models and ultimately people.