Brain age estimation:premise,promise,and problems

Premise:The com bined effects of modern healthcare practices which prolong lifespan and declining birthrates have created unprecedented changes in age demographics worldwide that are especially pronounced in Japan,South Korea,Europe,and North America.Since old age is the most significant predictor of dementia,global healthcare systems must rise to the challenge of providing care for those with neurodegenerative disorders.

A Novel Self-Supervised Learning Network for Binocular Disparity Estimation

Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.

Bioinspired Polarized Optical Flow Enables Turbid Underwater Target Motion Estimation

Underwater target motion estimation is a challenge for ocean military and scientific research.In this work,we propose a method based on the combination of polarization imaging and optical flow for turbid underwater target detection.Polarization imaging can reduce the influence of backscattered light and obtain high-quality images underwater.The optical flow shows the motion and structural information of the target.We use polarized optical flow to obtain the optical flow field and estimate the target motion.The experimental results of different targets under varying water turbidity levels illustrate that our method is realizable and robust.The precision is verified by comparing the results with the precise displacement data and calculating two error measures.The proposed method based on polarized optical flow can obtain accurate displacement information and a good recognition effect.Moving target segmentation based on the Otsu method further proves the superiority of the polarized optical flow under turbid water.This study is valuable for target detection and motion estimation in scattering environments.

Nonparametric Estimation of the Trend Function for Stochastic Processes Driven by Fractional Brownian Motion of the Second Kind

The present paper deals with the problem of nonparametric kernel density estimation of the trend function for stochastic processes driven by fractional Brownian motion of the second kind.The consistency,the rate of convergence,and the asymptotic normality of the kernel-type estimator are discussed.Besides,we prove that the rate of convergence of the kernel-type estimator depends on the smoothness of the trend of the nonperturbed system.

Differential-geometry-based multi-dimensional joint position-velocity estimation using Crab pulsar profile distortion

The traditional orbit determination method based on pulsar profile distortion can determine the six elements of the orbit.However,the estimation accuracies of these methods are limited and the computational load of a six-dimensional search is huge.To solve this problem,the differential-geometry-based Multi-dimensional Joint Position-Velocity Estimation(MJPVE)using Crab pulsar profile distortion is proposed in this paper.Firstly,through theoretical analysis,it is found that the pulsar profile distortion caused by the initial state error in some joint positionvelocity directions is very small.In other words,the accuracies of estimation in these directions are very low.Namely,the search dimension can be reduced,which in turn greatly reduces the computational load.Then,we construct the chi-squared function of the pulsar profile with respect to the estimation error in joint position-velocity direction and use differential geometry to find the joint position-velocity directions corresponding to different degrees of distortion.Finally,we utilize the grid search based on directory folding in these joint position-velocity directions corresponding to large degrees of distortion to obtain the joint position-velocity estimation.The experimental results show that compared with the grouping bi-chi-squared inversion method,MJPVE has high precision and extensive navigation information.

Improving cutoff frequency estimation via optimized π-pulse sequence

The cutoff frequency is one of the crucial parameters that characterize the environment. In this paper, we estimate the cutoff frequency of the Ohmic spectral density by applying the π-pulse sequences(both equidistant and optimized)to a quantum probe coupled to a bosonic environment. To demonstrate the precision of cutoff frequency estimation, we theoretically derive the quantum Fisher information(QFI) and quantum signal-to-noise ratio(QSNR) across sub-Ohmic,Ohmic, and super-Ohmic environments, and investigate their behaviors through numerical examples. The results indicate that, compared to the equidistant π-pulse sequence, the optimized π-pulse sequence significantly shortens the time to reach maximum QFI while enhancing the precision of cutoff frequency estimation, particularly in deep sub-Ohmic and deep super-Ohmic environments.

Phase-matching enhanced quantum phase and amplitude estimation of a two-level system in a squeezed reservoir

Squeezed reservoir engineering is a powerful technique in quantum information that combines the features of squeezing and reservoir engineering to create and stabilize non-classical quantum states. In this paper, we focus on the previously neglected aspect of the impact of the squeezing phase on the precision of quantum phase and amplitude estimation based on a simple model of a two-level system(TLS) interacting with a squeezed reservoir. We derive the optimal squeezed phase-matching conditions for phase φ and amplitude θ parameters, which are crucial for enhancing the precision of quantum parameter estimation. The robustness of the squeezing-enhanced quantum Fisher information against departures from these conditions is examined, demonstrating that minor deviations from phase-matching can still result in remarkable precision of estimation. Additionally, we provide a geometric interpretation of the squeezed phase-matching conditions from the classical motion of a TLS on the Bloch sphere. Our research contributes to a deeper understanding of the operational requirements for employing squeezed reservoir engineering to advance quantum parameter estimation.

Underdetermined direction of arrival estimation with nonuniform linear motion sampling based on a small unmanned aerial vehicle platform

Uniform linear array(ULA)radars are widely used in the collision-avoidance radar systems of small unmanned aerial vehicles(UAVs).In practice,a ULA's multi-target direction of arrival(DOA)estimation performance suffers from significant performance degradation owing to the limited number of physical elements.To improve the underdetermined DOA estimation performance of a ULA radar mounted on a small UAV platform,we propose a nonuniform linear motion sampling underdetermined DOA estimation method.Using the motion of the UAV platform,the echo signal is sampled at different positions.Then,according to the concept of difference co-array,a virtual ULA with multiple array elements and a large aperture is synthesized to increase the degrees of freedom(DOFs).Through position analysis of the original and motion arrays,we propose a nonuniform linear motion sampling method based on ULA for determining the optimal DOFs.Under the condition of no increase in the aperture of the physical array,the proposed method obtains a high DOF with fewer sampling runs and greatly improves the underdetermined DOA estimation performance of ULA.The results of numerical simulations conducted herein verify the superior performance of the proposed method.

MOVING OBJECT TRACKING IN DYNAMIC IMAGE SEQUENCE BASED ON ESTIMATION OF MOTION VECTORS OF FEATURE POINTS

An improved estimation of motion vectors of feature points is proposed for tracking moving objects of dynamic image sequence. Feature points are firstly extracted by the improved minimum intensity change （MIC） algorithm. The matching points of these feature points are then determined by adaptive rood pattern searching. Based on the random sample consensus （RANSAC） method, the background motion is finally compensated by the parameters of an affine transform of the background motion. With reasonable morphological filtering, the moving objects are completely extracted from the background, and then tracked accurately. Experimental results show that the improved method is successful on the motion background compensation and offers great promise in tracking moving objects of the dynamic image sequence.

Fast global motion estimation and moving object extraction algorithm in image sequences

A novel and effective approach to global motion estimation and moving object extraction is proposed. First, the translational motion model is used because of the fact that complex motion can be decomposed as a sum of translational components. Then in this application, the edge gray horizontal and vertical projections are used as the block matching feature for the motion vectors estimation. The proposed algorithm reduces the motion estimation computations by calculating the onedimensional vectors rather than the two-dimensional ones. Once the global motion is robustly estimated, relatively stationary background can be almost completely eliminated through the inter-frame difference method. To achieve an accurate object extraction result, the higher-order statistics （HOS） algorithm is used to discriminate backgrounds and moving objects. Experimental results validate that the proposed method is an effective way for global motion estimation and object extraction.

RESPIRATORY MOTION ESTIMATION USING VIBRATION MODEL AND REDUCING MOTION BLUR THROUGH DECONVOLUTION

The respiratory motion leads to significant motion artifacts of the positron emission tomography （PET） image, thus influencing diagnoses and treatments in the radiation oneology. The existing approaches to correct motion artifacts involve using gating devices and/or four-dimensional （4-D） computed tomography （CT）. However, they have the disadvantages of high CT dose and high computational burden. Hence, a sinusoid vibration model is presented to simulate the respiratory motion. The motion extent and the direction are derived from the Radon transform of the cepstrum of the blurred image. Then, two typical deeonvolution algorithms, i.e. , Wiener filter （WF） and the Richardson-Lucy （RL） algorithms are used to eliminate the motion blur according to the estimated parameters and their de-blurring results are compared. Experiments on both synthetic and phantom images show good performance of the presented model for identifying vibration modeled respiration motion and reducing the motion blur. The method has advantages of safety, convenience, and economy. And it is promising to correct the motion artifacts of the non-gated PET image.

Model-driven full system dynamics estimation of PMSM-driven chain shell magazine

Based on the system dynamic model, a full system dynamics estimation method is proposed for a chain shell magazine driven by a permanent magnet synchronous motor(PMSM). An adaptive extended state observer(AESO) is proposed to estimate the unmeasured states and disturbance, in which the model parameters are adjusted in real time. Theoretical analysis shows that the estimation errors of the disturbances and unmeasured states converge exponentially to zero, and the parameter estimation error can be obtained from the extended state. Then, based on the extended state of the AESO, a novel parameter estimation law is designed. Due to the convergence of AESO, the novel parameter estimation law is insensitive to controllers and excitation signal. Under persistent excitation(PE) condition, the estimated parameters will converge to a compact set around the actual parameter value. Without PE signal, the estimated parameters will converge to zero for the extended state. Simulation and experimental results show that the proposed method can accurately estimate the unmeasured states and disturbance of the chain shell magazine, and the estimated parameters will converge to the actual value without strictly continuous PE signals.

6-DOF MOTION AND CENTER OF ROTATION ESTIMATION BASED ON STEREO VISION

A new motion model and estimation algorithm is proposed to compute the general rigid motion object＇s 6-DOF motion parameters and center of rotation based on stereo vision. The object＇s 6-DOF motion model is designed from the rigid object＇s motion character under the two defined reference frames. According to the rigid object＇s motion model and motion dynamics knowledge, the corresponding motion algorithm to compute the 6-DOF motion parameters is worked out. By the rigid object pure rotation motion model and space sphere geometry knowledge, the center of rotation may be calculated after eliminating the translation motion out of the 6-DOF motion. The motion equations are educed based on the motion model and the closed-form solutions are figured out. To heighten the motion estimation algorithm＇s robust, RANSAC algorithm is applied to delete the outliers. Simulation and real experiments are conducted and the experiment results are analyzed. The results prove the motion model＇s correction and algorithm＇s validity.

Permanent Magnet Temperature Estimation for PMSMs Using Virtual Position-offset Injection

This paper proposes a virtual position-offset injection based permanent magnet temperature estimation approach for permanent magnet synchronous machines(PMSMs). The concept of virtual position-offset injection is mathematically transforming the machine model to a virtual frame with a position-offset. The virtual frame temperature estimation model is derived to calculate the permanent magnet temperature(PMT) directly from the measurements with computation efficiency. The estimation model involves a combined inductance term, which can simplify the establishment of saturation compensation model with less measurements. Moreover, resistance and inverter distorted terms are cancelled in the estimation model, which can improve the robustness to the winding temperature rise and inverter distortion. The proposed approach can achieve simplified computation in temperature estimation and reduced memory usage in saturation compensation. While existing model-based approaches could be affected by either the need of resistance and inverter information or complex saturation compensation. Experiments are conducted on the test machine to verify the proposed approach under various operating conditions.

Deep learning for joint channel estimation and feedback in massive MIMO systems

The great potentials of massive Multiple-Input Multiple-Output(MIMO)in Frequency Division Duplex(FDD)mode can be fully exploited when the downlink Channel State Information(CSI)is available at base stations.However,the accurate CsI is difficult to obtain due to the large amount of feedback overhead caused by massive antennas.In this paper,we propose a deep learning based joint channel estimation and feedback framework,which comprehensively realizes the estimation,compression,and reconstruction of downlink channels in FDD massive MIMO systems.Two networks are constructed to perform estimation and feedback explicitly and implicitly.The explicit network adopts a multi-Signal-to-Noise-Ratios(SNRs)technique to obtain a single trained channel estimation subnet that works well with different SNRs and employs a deep residual network to reconstruct the channels,while the implicit network directly compresses pilots and sends them back to reduce network parameters.Quantization module is also designed to generate data-bearing bitstreams.Simulation results show that the two proposed networks exhibit excellent performance of reconstruction and are robust to different environments and quantization errors.

A comparative study of data-driven battery capacity estimation based on partial charging curves

With its generality and practicality, the combination of partial charging curves and machine learning(ML) for battery capacity estimation has attracted widespread attention. However, a clear classification,fair comparison, and performance rationalization of these methods are lacking, due to the scattered existing studies. To address these issues, we develop 20 capacity estimation methods from three perspectives:charging sequence construction, input forms, and ML models. 22,582 charging curves are generated from 44 cells with different battery chemistry and operating conditions to validate the performance. Through comprehensive and unbiased comparison, the long short-term memory(LSTM) based neural network exhibits the best accuracy and robustness. Across all 6503 tested samples, the mean absolute percentage error(MAPE) for capacity estimation using LSTM is 0.61%, with a maximum error of only 3.94%. Even with the addition of 3 m V voltage noise or the extension of sampling intervals to 60 s, the average MAPE remains below 2%. Furthermore, the charging sequences are provided with physical explanations related to battery degradation to enhance confidence in their application. Recommendations for using other competitive methods are also presented. This work provides valuable insights and guidance for estimating battery capacity based on partial charging curves.

Motion estimation in wide band synthetic aperture sonar based on the raw echo data using the method of displaced phase center antenna

Phase errors in synthetic aperture sonar (SAS) imaging must be reduced to less than one eighth of a wavelength so as to avoid image destruction. Most of the phase errors occur as a result of platform motion errors, for example, sway yaw and surge that are the most important error sources. The phase error of a wide band synthetic aperture sonar is modeled and solutions to sway yaw and surge motion estimation based on the raw sonar echo data with a Displaced Phase Center Antenna (DPCA) method are proposed and their implementations are detailed in this paper. It is shown that the sway estimates can be obtained from the correlation lag and phase difference between the returns at coincident phase centers. An estimate of yaw is also possible if such a technique is applied to more than one overlapping phase center positions. Surge estimates can be obtained by identifying pairs of phase centers with a maximum correlation coefficient. The method works only if the platform velocity is low enough such that a number of phase centers from adjacent pings overlap.

A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.

6-DOF motion estimation using optical flow based on dual cameras

Because of its characteristics of simple algorithm and hardware, optical flow-based motion estimation has become a hot research field, especially in GPS-denied environment. Optical flow could be used to obtain the aircraft motion information, but the six-(degree of freedom)(6-DOF) motion still couldn't be accurately estimated by existing methods. The purpose of this work is to provide a motion estimation method based on optical flow from forward and down looking cameras, which doesn't rely on the assumption of level flight. First, the distribution and decoupling method of optical flow from forward camera are utilized to get attitude. Then, the resulted angular velocities are utilized to obtain the translational optical flow of the down camera, which can eliminate the influence of rotational motion on velocity estimation. Besides, the translational motion estimation equation is simplified by establishing the relation between the depths of feature points and the aircraft altitude. Finally, simulation results show that the method presented is accurate and robust.

Efficient Unsupervised Image Stitching Using Attention Mechanism with Deep Homography Estimation

Traditional feature-based image stitching techniques often encounter obstacles when dealing with images lackingunique attributes or suffering from quality degradation. The scarcity of annotated datasets in real-life scenesseverely undermines the reliability of supervised learning methods in image stitching. Furthermore, existing deeplearning architectures designed for image stitching are often too bulky to be deployed on mobile and peripheralcomputing devices. To address these challenges, this study proposes a novel unsupervised image stitching methodbased on the YOLOv8 (You Only Look Once version 8) framework that introduces deep homography networksand attentionmechanisms. Themethodology is partitioned into three distinct stages. The initial stage combines theattention mechanism with a pooling pyramid model to enhance the detection and recognition of compact objectsin images, the task of the deep homography networks module is to estimate the global homography of the inputimages consideringmultiple viewpoints. The second stage involves preliminary stitching of the masks generated inthe initial stage and further enhancement through weighted computation to eliminate common stitching artifacts.The final stage is characterized by adaptive reconstruction and careful refinement of the initial stitching results.Comprehensive experiments acrossmultiple datasets are executed tometiculously assess the proposed model. Ourmethod’s Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) improved by 10.6%and 6%. These experimental results confirm the efficacy and utility of the presented model in this paper.