Dynamic adaptive spatio-temporal graph network for COVID-19 forecasting

Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.

Novel Retinex algorithm by interpolation and adaptive noise suppression

In order to improve image quality, a novel Retinex algorithm for image enhancement was presented. Different from conventional algorithms, it was based on certain defined points containing the illumination information in the intensity image to estimate the illumination. After locating the points, the whole illumination image was computed by an interpolation technique. When attempting to recover the reflectance image, an adaptive method which can be considered as an optimization problem was employed to suppress noise in dark environments and keep details in other areas. For color images, it was taken in the band of each channel separately. Experimental results demonstrate that the proposed algorithm is superior to the traditional Retinex algorithms in image entropy.

A NEW ALGORITHM OF THE NONLINEAR ADAPTIVE INTERPOLATION

The paper presents a new algorithm of NonLinearly Adaptive Interpolation (NLAI). NLAI is based on both the gradients and the curvature of the signals with the predicted subsection. It is characterized by adap- tive nonlinear interpolation method with extracting the characteristics of signals. Experimental research testi- fies the validity of the algorithm using the echoes of the Ground Penetrating Radar (GPR). A comparison of this algorithm with other traditional algorithms demonstrates that it is feasible.

ON THE MOVING ADAPTIVE INTERPOLATION TECHNIQUE TO IMPROVE THE VERTICAL RESOLUTION OF PICTURES IN TV

This paper deals with the method of moving adaptive interpolation technique. The interlaced scanning that structures the pictures in today’s television systems is changed into progressive scanning, which helps to greatly improve the vertical resolution of pictures.

Spatio-temporal Differentiation and Driving Factors of Industrial Ecology of Restricted Development Zone from Adaptive Perspective:A Case Study of Shandong,China

Based on the adaptive analysis paradigm,this paper constructs an evaluation index system and an evaluation model of the level of industrial ecology of a restricted development zone from the perspective of the industrial system and of the environmental system,and studies the spatial-temporal differentiation characteristics and the driving factors of the level of industrial ecology of the restricted development zone of the Shandong Province,China,by using a variety of measurement methods.The results show that:1)In the temporal dimension,the level of industrial ecology of the research area increased from 2005 to 2017,while in the regional dimension,it was higher in the eastern coastal areas,followed by the northwestern area and the southwestern area;2)In the spatial dimension,from 2005 to 2017 the level of industrial ecology of the research area had a clear spatial dependence,and the regional spatial agglomeration of the restricted development zones with similar industrial ecology levels become increasingly evident;3)On the whole,the industrial ecology level in the study area had a clear spatial differentiation pattern,as it was higher in the north and in the east and lower in the south and in the west.Moreover,its evolution model changed from a‘three-core driven model’to a‘spatial scattered mosaic distribution model’,and then to a‘single-core driven model’;4)Industrial ecology was positively correlated with economic development,foreign investment,science and technology,and negatively correlated with the government role,while industrial structure and environmental regulation failed to pass the statistical significance test.

NURBS CURVE INTERPOLATOR WITH ADAPTIVE ACCELERATION-DECELERATION CONTROL

The feedrate profile of non-uniform rational B-spline （NURBS） interpolation due to the contour errors is analyzed. A NURBS curve interpolator with adaptive acceleration-deceleration control is presented. In interpo- lation preprocessing, the sensitive zones of feedrate variations are processed with acceleration-deceleration control. By using the proposed algorithm, the machining accuracy is guaranteed and the feedrate is adaptively adjusted to he smoothed. The mechanical shock imposed in the servo system is avoided by the first and the second time derivatives of feedrates. A simulation of NURBS interpolation is given to demonstrate the validity and the effectiveness of the algorithm. The proposed interpolator can also be applied to the trajectory planning of the other parametric curves.

Study of NURBS Interpolation Algorithm Based on Self-adaptive Control

Aimed at problems such as profile error increasing and acceleration enlarging and tool machine working instability and quality decreasing of workpiece surfaces in processing complicated curved surfaces because of several variable curvatures, an improved method of NURBS interpolation is adopted. According to self-adaptive programming principles, self-adaptive control of profile errors and accelerations and speed-converting is realized with increasing or descending self-adaptive control strategy. This method meets real-time and high-precision requirements of high speed and precision processing, and solves various problems caused by several variable curvatures of a complicated surface.

Speaker Adaptation with Transformation Matrix Linear Interpolation

A transformation matrix linear interpolation (TMLI) approach for speaker adaptation is proposed. TMLI uses the transformation matrixes produced by MLLR from selected training speakers and the testing speaker. With only 3 adaptation sentences, the performance shows a 12.12% word error rate reduction. As the number of adaptation sentences increases, the performance saturates quickly. To improve the behavior of TMLI for large amounts of adaptation data, the TMLI+MAP method which combines TMLI with MAP technique is proposed. Experimental results show TMLI+MAP achieved better recognition accuracy than MAP and MLLR+MAP for both small and large amounts of adaptation data. Key words speech recognition - speaker adaptation - MLLR - MAP - maximum likelihood model interpolation (MLMI) CLC number TN 912. 34 Foundation item: Supported by the Science and Technology Committee of Shanghai (01JC14033)Biography: XU Xiang-hua (1977-), female, Ph. D. candidate, research direction: large vocabulary continuous Mandarin speech recognition and speaker adaptation

Study on Real-time Look-ahead and Adaptive Parametric Curve Interpolator

The principle of real-time look-ahead was introduced and analysed. An adaptive parametric curve interpolator with a real-time look-ahead function was developed for non-uniform rational B-spline (NURBS) curves interpolation, which considering the maximum acceleration/deceleration of the machine tool. In order to deal with the acceleration/deceleration around the feedrate sensitive corners, the look-ahead function was designed and illustrated. It can detect and adjust the feedrate adaptively. With the help of real-time look-ahead, the acceleration/deceleration can be limited to the range of the machine tool capacity. Thus, feedrate fluctuation is reduced. A NURBS curve interpolation experiment was provided to verify the feasibility and advantages of the proposed interpolator with a real-time look-ahead function.

Extraction of Laser Stripe Center Line Based on Genetic Algorithm and NURBS Interpolation

To improve the measurement accuracy of structured laser for inner surface dimensions of a deep hole, a new method to extract the laser stripe center line is proposed. An improved adaptive genetic algorithm that can converge rapidly and search the global optimum is used to determine the threshold for the laser stripe segmentation. And then NURBS interpolation which has a good local control capability is adopted to extract the laser stripe center line. Experiments show that the extracted laser stripe center line is stable and the diameter of the deep hole can be measured accurately.

Missing interpolation model for wind power data based on the improved CEEMDAN method and generative adversarial interpolation network

Randomness and fluctuations in wind power output may cause changes in important parameters(e.g.,grid frequency and voltage),which in turn affect the stable operation of a power system.However,owing to external factors(such as weather),there are often various anomalies in wind power data,such as missing numerical values and unreasonable data.This significantly affects the accuracy of wind power generation predictions and operational decisions.Therefore,developing and applying reliable wind power interpolation methods is important for promoting the sustainable development of the wind power industry.In this study,the causes of abnormal data in wind power generation were first analyzed from a practical perspective.Second,an improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)method with a generative adversarial interpolation network(GAIN)network was proposed to preprocess wind power generation and interpolate missing wind power generation sub-components.Finally,a complete wind power generation time series was reconstructed.Compared to traditional methods,the proposed ICEEMDAN-GAIN combination interpolation model has a higher interpolation accuracy and can effectively reduce the error impact caused by wind power generation sequence fluctuations.

Wavelet Optimized Adaptive Mesh for MHD Flow Problems

There are many problems in science and engineering where the solution shows a boundary layer character. Near the boundary the gradient is large in contrast with the smooth behaviour in the central core. A uniform grid is, therefore, not suitable for a numerical solution. MHD flow problems belong to this category where a velocity and induced magnetic field profiles get flattened in a transverse flow. In the present paper an optimized grid has been generated using interpo-lating wavelets. The results are compared with those obtained using uniform grid, the finite element method and also from the analytical solution.

Adaptive removal of power-line interference from high resolution ECG

The paper presents a novel approach to adaptive removal of power-line interference, taken to be at 50 Hz, from high resolution ECG sampled at 1 KHz. ECG data consists of 12 lead data. Each of the 12 leads contains power line interference at the time of acquisition. So power line interference needs to be removed from each lead. An approach that uses the power spectral density over the range of interest is used to determine the exact frequency of the interfering component and filter coefficients for the desired notch filter are determined using an interpolation technique.

Application of adaptive filter in time delay estimation——generalized quadratic interpolation method

The time delay estimation (TDE) of two different received signals from the same source has attracted many interests of researchers in the field of signal processing. A method described for precisely estimating time delay in this paper is based on the assumption that little priori knowledge on statistical characteristics is available for the received signals. The variance of the estimate is derived . The basic architecture of this method is to use the adaptive noise canceller, in the steady state , and to interpolate the weight coefficients by using a generalized quadratic interpolation matrix. The formula of the time delay estimation is presented . The method proposed by F.A. Reed is a special case of this method . The hardware implementation is much easier than that of the conventional time delay estimation method . The results of the system simulation and the experimental results at sea show a good agreement with the theoretical analysis.

Improved Adaptive Interpolation Filter for H.264/AVC

Motion compensation with adaptive interpolation filters （AIF） was developed to compensate for temporary varieties in the aliasing of video signals and improve the coding efficiency. The AIF achieves better RD performance than common static interpolation filtering by exploiting the statistics in the reference frames＇ local auto-correlation and the local cross-correlation between the current encoding frame and the reference frames. This paper presents an interpolation filter buffering structure that derives the current en- coding frame＇s interpolation filters from the filters of previous frames. The number of encoding bits for the filter coefficients is reduced by encoding only the differences between the current filter coefficients and the corresponding buffered filter coefficients. Experimental results show that in comparison with the AIF in the current ＂key technical area＂ （KTA） reference software, this interpolation filter buffering structure further improves all the test sequences （with up to 2.87% bit rate saving） with negligible computational increase.

Dynamic State Estimation for DFIG with Unknown Inputs Based on Cubature Kalman Filter and Adaptive Interpolation

Dynamic state estimation(DSE)accurately tracks the dynamics of power systems and demonstrates the evolution of the system state in real time.This paper proposes a DSE approach for a doubly-fed induction generator(DFIG)with unknown inputs based on adaptive interpolation and cubature Kalman filter(AICKF-UI).DFIGs adopt different control strategies in normal and fault conditions;thus,the existing DSE approaches based on the conventional control model of DFIG are not applicable in all cases.Consequently,the DSE model of DFIGs is reformulated to consider the converter controller outputs as unknown inputs,which are estimated together with the DFIG dynamic states by an exponential smoothing model and augmented-state cubature Kalman filter.Furthermore,as the reporting rate of existing synchro-phasor data is not sufficiently high to capture the fast dynamics of DFIGs,a large estimation error may occur or the DSE approach may diverge.To this end,in this paper,a local-truncation-error-guided adaptive interpolation approach is developed.Extensive simulations conducted on a wind farm and the modified IEEE 39-bus test system show that the proposed AICKF-UI can(1)effectively address the divergence issues of existing cubature Kalman filters while being computationally more efficient;(2)accurately track the dynamic states and unknown inputs of the DFIG;and(3)deal with various types of system operating conditions such as time-varying wind and different system faults.

A Combined Speaker Adaptation Method for Mandarin Speech Recognition

A speaker adaptation method that combines transformation matrix linear interpolation with maximum a posteriori (MAP) was proposed. Firstly this method can keep the asymptotical characteristic of MAP. Secondly, as the method uses linear interpolation with several speaker-dependent (SD) transformation matrixes, it can fully use the prior knowledge and keep fast adaptation. The experimental results show that the combined method achieves an 8.24% word error rate reduction with only one adaptation utterance, and keeps asymptotic to the performance of SD model for large amounts of adaptation data.

机械臂多目标最优轨迹的自适应惩罚MOEA/D规划

为了减少机械臂的工作时间和工作过程中的冲击量,提出了基于自适应惩罚MOEA/D算法的时间-冲击多目标规划方法。介绍了PUMA560机械臂结构,并建立了机械臂的连杆坐标系。建立了以减小机械臂工作时间和冲击为综合目标的优化模型,并分析了5次多项式插值函数。通过编码和建立适应度函数,将轨迹规划问题转化为最优基因搜索问题。根据邻域内解的密度设置了自适应惩罚因子,提出了机械臂轨迹的自适应惩罚MOEA/D规划方法。经仿真验证,自适应惩罚MOEA/D算法搜索的Pareto前沿解质量高于标准MOEA/D算法、文献[10]新型MOEA/D算法。且经过优化,机械臂工作时间减少了7.68%,冲击减少了17.32%。实验结果表明,自适应惩罚MOEA/D算法在机械臂轨迹规划中具有优越性。

基于细化等值面拓扑的病灶切片三维重建方法

脑组织病灶切片的三维重构对于了解神经胶质神经瘤状态具有重要意义,可用于鉴别诊断、手术模拟等。移动立方体(MC)算法是经典的多边形曲面重建算法,具有简单易实现的优点,但其存在低效且梯级现象明显的情况。针对该问题,本研究提出一种细化等值面拓扑的病灶切片空间堆叠重建方法(SSR-RI),旨在实现拓扑构形与运行效率的优化。SSR-RI通过构建空间坐标系对磁共振图像(MRI)切片邻近图进行处理,为了改善双线性插值法中图像分量易受损的问题,提出一种自适应空间插值法,根据灰度值变化自适应选择插值点,对周围进行扩充。在结合等法线顶点的基础上,设计了一种细化等值面提取方式的堆叠重建方法,以提高堆叠速度,并减少梯级问题。为了进一步优化SSR-RI的三维重建效果,提出一种改进的局部反射光照法(PR)以绘制三维病变,利用镜面颜色反射(SCR)与镜面指数(SE)对重建体进行渲染优化。使用公开脑肿瘤分割数据集BraTS的618例病例开展三维重建实验,以验证所提出方法性能。实验结果显示,所提算法的重建时间只需2.124 s,F-score值达到0.845,SSIM值达到0.81,相较于MC算法减少了38%的重建时间,F-score值和SSIM值分别提高了30.89%和38.4%。重构体序列间结构紧密,视觉效果更富立体感和纹理感,有效地提高了三维重建的绘制效率。

顾及地球物理效应的GNSS高程时间序列AdaBoost预测和插值方法

传统的GNSS高程时间序列预测和插值方法仅考虑时间变量,具有明显的局限性。本文顾及地球物理效应的影响,通过温度、大气压强、极移等数据和GNSS高程时间序列数据构建回归问题,使用自适应提升(AdaBoost)算法建模。为了验证模型的预测和插值性能,试验选取4个GNSS站的高程时间序列进行分析。建模试验表明,相较于Prophet模型,AdaBoost模型的拟合精度提升了约35%;预测结果表明,在12个月的预测周期内,AdaBoost模型在4个GNSS站的MAE值为4.0~4.5 mm,RMSE值约为5.0~6.0 mm;插值试验表明,相较于三次样条插值方法,AdaBoost插值模型的精度约提升了15%~28%。预测和插值试验表明,顾及地球物理效应的AdaBoost模型可以应用于GNSS高程时间序列预测与插值。