Root Mean Square Error Results Research Articles

Comparison of TLS and SLAM technologies for 3D reconstruction of objects with different geometries

Technological advances have made the 3D mapping process easily available and simpler. However, there are still aspects that need to be improved and enhanced. The efficient acquisition of 3D data and reconstruction of objects with high accuracy continues to be a challenge for the scientific community. One of the most frequently used 3D mapping methods is Terrestrial Laser Scanning (TLS), which allows the collection of high-resolution and precise data. Another method gaining popularity among researchers and professionals is mobile scanning technology, which enables real-time data capture. Its mobility and speed make it an effective alternative to traditional scanning technologies. This article compares two mapping technologies: SLAM (Simultaneous Localization and Mapping) and TLS taking into account the technical aspects of the instruments, processing methods, time and cost, and concluding with an assessment of the final accuracy. The geometry of several selected objects was analyzed. The resulting root mean square error (RMSE) for the compared distances on the two point clouds was 5 cm, which proves that the SLAM technology can be successfully applied for scenarios requiring centimeter-level accuracy.

IMPROVING MODEL ACCURACY OF THE "LUNG AGE” ESTIMATION THROUGH MACHINE LEARNING

IMPROVING MODEL ACCURACY OF THE "LUNG AGE” ESTIMATION THROUGH MACHINE LEARNING

Multi-IMU Based Alternate Navigation Frameworks: Performance & Comparison for UAS

On-board state estimation is a persistent challenge to fielding unmanned aerial systems (UAS), particularly when global positioning system (GPS) measurements are not available. The dominant estimation tool remains the extended Kalman filter (EKF) applied to an inertial measurement unit (IMU). The growing availability of low-cost commercial-grade IMUs raises questions about how to best improve sensor readings into an estimate when measurements are available from multiple IMUs. This paper evaluates four different approaches to attitude estimation from multiple IMU measurements and their application in high dynamic motion. The four approaches are fusion of measurements (virtual IMU), fusion of state estimates (Federated KF), feedback fusion state estimate (Feedback Federated KF), and an EKF design incorporating the additional measurements (Augmented KF); these correspond to fusion before, within, or after state estimation. The performance of the approaches are quantified for varying IMU number theoretically and experimentally. The experiments use on-board autopilot hardware implementations of the estimators during maneuvers in a motion capture volume and flights on-board an Unmanned Aerial Systems (UAS) implementation, with the peak and root-mean-square (RMS) errors used to quantify accuracy. The RMS error results indicate that the feedback federated Kalman Filter using five IMUs returns 38% compared to general federated Kalman Filter using 37% accuracy improvement over a single IMU. This improvement compares to a 19% improvement for virtual IMU and 9% improvement for the Augmented KF respectively. These results indicate that both the Federated KF approach achieves the lowest RMS error relative to the virtual IMU and augmented KF approaches and inform the design of multi-IMU UAS pose estimators.

Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis

Hyperspectral imaging has recently emerged in the geosciences as a technology that provides rapid, accurate, and high-resolution information from lake sediment cores. Here we introduce a new methodology to infer particle size distribution, an insightful proxy that tracks past changes in aquatic ecosystems and their catchments, from laboratory hyperspectral images of lake sediment cores. The proposed methodology includes data preparation, spectral preprocessing and transformation, variable selection, and model fitting. We evaluated random forest regression and other commonly used statistical methods to find the best model for particle size determination. We tested the performance of combinations of spectral transformation techniques, including absorbance, continuum removal, and first and second derivatives of the reflectance and absorbance, along with different regression models including partial least squares, multiple linear regression, principal component regression, and support vector regression, and evaluated the resulting root mean square error (RMSE), R-squared, and mean relative error (MRE). Our results show that a random forest regression model built on spectra absorbance significantly outperforms all other models. The new workflow demonstrated herein represents a much-improved method for generating inferences from hyperspectral imagery, which opens many new opportunities for advancing the study of sediment archives.

Adaptive Heart Rate Regulation Using Implantable Pacemaker with Artificial Neural Network-Based Backstepping Controller

Implantable cardiac pacemaker is a standard medical device totreat heart rhythm disorders. In this paper, a new adaptivebackstepping controller is developed to enhance the performanceof dual-sensor pacemakers for regulating the heart rate, based onradial basis function neural networks. The robust design ofadaptive backstepping controller using Lyapunov functions allowsguaranteeing the stability and performance of the rate-adaptivepacing system for accurately accomplishing the heart rateregulation at different preset values. This developed controlsystem has been retrospectively tested on six datasets of twopatients with a pacemaker during three body activities of the rest,walking, and exercising. The resulting root mean square error(RMSE) and maximum error are less than 0.36 and 0.50 %,respectively. In addition, comparative results of this study showedthat the performance of developed backstepping controller issuperior to other pacemaker controllers in the previous studies.

Bio-Inspired Adaptive Control for Active Knee Exoprosthetics.

On the quest to bring function of prosthetic legs closer to their biological counterparts, the intuitive interplay of their control with the user's impedance modulation is key. We present two control features to enable more physiological and more user-adaptive control of prosthetic legs: a neuromusculoskeletal impedance model ( ) including a reflexive component, and a human model reference adaptive controller ( ), which can be combined with the former. In stance-phase simulations, the allowed to control a prosthetic leg with physiological knee joint angle and moment. When perturbations were applied, the reduced the resulting root mean square error (RMSE) between simulated and physiological reference angle by 96%. In a pilot experiment with two unimpaired and one amputee subject, gait with the deviated more from a physiological reference than with a conventional visco-elastic impedance controller. Subjects, however, preferred the . When adding the to either of the two impedance controllers, the RMSE between the actual and the physiological reference angle was reduced by up to 54%. Subjects confirmed this finding and reported an easier stance-to-swing transition. Simulation and pilot experiment suggest that a reflex-based impedance controller combined with an adaptive controller may improve user-cooperative behavior of active knee exoprostheses.

On improving the accuracy of the M2 barotropic tides embedded in a high-resolution global ocean circulation model

The ocean tidal velocity and elevation can be estimated concurrently with the ocean circulation by adding the astronomical tidal forcing, parameterized topographic internal wave drag, and self-attraction and loading to the general circulation physics. However, the accuracy of these tidal estimates does not yet match accuracies in the best data-assimilative barotropic tidal models. This paper investigates the application of an augmented state ensemble Kalman Filter (ASEnKF) to improve the accuracy of M2 barotropic tides embedded in a 1/12.5° three-dimensional ocean general circulation model. The ASEnKF is an alternative to the techniques typically used with linearized tide-only models; such techniques cannot be applied to the embedded tides in a nonlinear eddying circulation. An extra term, meant to correct for errors in the tide model due to imperfectly known topography and damping terms, is introduced into the tidal forcing. Ensembles of the model are created with stochastically generated forcing correction terms. The discrepancies for each ensemble member with TPXO, an existing data-assimilative tide model, are computed. The ASEnKF method yields an optimal estimate of the model forcing correction terms, that minimizes resultant root mean square (RMS) tidal sea surface elevation error with respect to TPXO, as well as an estimate of the tidal elevation. The deep-water, global area-averaged RMS sea surface elevation error of the principal lunar semidiurnal tide M2 is reduced from 4.4 cm in a best-case non-assimilative solution to 2.6 cm. The largest elevation errors in both the non-assimilative and ASEnKF solutions are in the North Atlantic, a highly resonant basin. Possible pathways for achieving further reductions in the RMS error are discussed.

Parameter sensitivity of three Kalman filter schemes for assimilation of water levels in shelf sea models

In applications of data assimilation algorithms, a number of poorly known assimilation parameters usually need to be specified. Hence, the documented success of data assimilation methodologies must rely on a moderate sensitivity to these parameters. This contribution presents a parameter sensitivity study of three well known Kalman filter approaches for the assimilation of water levels in a three dimensional hydrodynamic modelling system. The filters considered are the ensemble Kalman filter (EnKF), the reduced rank square root Kalman filter (RRSQRT) and the steady Kalman filter. A sensitivity analysis of key parameters in the schemes is undertaken for a setup in an idealised bay. The sensitivity of the resulting root mean square error (RMSE) is shown to be low to moderate. Hence the schemes are robust within an acceptable range and their application even with misspecified parameters is to be encouraged in this perspective. However, the predicted uncertainty of the assimilation results are sensitive to the parameters and hence must be applied with care. The sensitivity study further demonstrates the effectiveness of the steady Kalman filter in the given system as well as the great impact of assimilating even very few measurements.

Image Stabilization and Registration for Tracking Cells in the Microvasculature

We propose a registration system to be used for tracking cells in intravital video microscopy that 1) stabilizes jitter-the undesired translational displacement of frames due to respiratory movement, etc., and 2) registers frames in a moving field of view (FOV) to allow for cell tracking over an extended range. For the first time, tracking of rolling leukocytes in vivo over a moving FOV is demonstrated. In a fixed FOV, stable background regions are located using a morphological approach. Template subregions are then selected from the stable regions and matched to corresponding locations in a reference frame. We show the effectiveness of the stabilization algorithm by using an active contour to track 15 leukocytes previously untrackable due to jitter. For 30 fixed FOV sequences containing rolling leukocytes, the resulting root-mean-square error (RMSE) is less than 0.5 microm. To align frames in a moving FOV, we present a modified correlation approach to estimate the common region between two consecutive fixed FOVs. We correlate the overlapping regions of the initial frame of the current fixed FOV and the final frame of the previous fixed FOV to register the images in the adjoining moving FOV. The RMSE of our moving FOV registration technique was less than 0.6 mmicrom. In 10 sequences from different venules, we were able to track 11 cells using an active contour approach over moving FOVs.

Optical‐microwave synergy for estimating surface sensible heat flux over a semi‐arid rangeland

This study reports the first results of the Walnut Gulch’ 92 experiment concerning the combined use of radar backscattering (ERS‐1) and thermal infrared (Landsat TM) data to estimate surface sensible heat flux. The purpose is to use the radar/thermal synergy to retrieve both vegetation and soil temperatures required by a two‐layer type model. The first step investigates the potential use of ERS‐1 SAR images for surface soil moisture monitoring of the watershed using five calibrated images acquired during the year 1992 (dry to wet conditions). Results show that despite the typical low level of biomass of semi‐arid rangeland, an attenuation of the soil backscatter (up to 2 dB) can occur during the rainy season mainly due to the vegetation characteristics. A statistical relationship is then used to retrieve the volumetric surface soil moisture from ERS‐1 backscattering (sensitivity of 0.23 dB/% moisture) with a resulting root mean square error (RMSE) of 1.3% of soil moisture. In a second step a semi‐empirica...