Kalman Filter Prediction Research Articles

Real-time facial pose estimation and tracking by coarse-to-fine iterative optimization

We present a novel and efficient method for real-time multiple facial poses estimation and tracking in a single frame or video. First, we combine two standard convolutional neural network models for face detection and mean shape learning to generate initial estimations of alignment and pose. Then, we design a bi-objective optimization strategy to iteratively refine the obtained estimations. This strategy achieves faster speed and more accurate outputs. Finally, we further apply algebraic filtering processing, including Gaussian filter for background removal and extended Kalman filter for target prediction, to maintain real-time tracking superiority. Only general RGB photos or videos are required, which are captured by a commodity monocular camera without any priori or label. We demonstrate the advantages of our approach by comparing it with the most recent work in terms of performance and accuracy.

Real-time adaptive stochastic control of smart grid data traffic for security purposes

Smart grid data traffic behaves in a similar way to computer network data traffic and they are vulnerable to the same security risks. This paper presents a methodology for the real-time determination of adaptive estimates of router traffic-rate demand every five-minutes, as well as for the evolution of the estimated demand starting from zero during a five-minute interval using a Modified Mean Reverting Stochastic Process (M-MRSP). The determination of real-time adaptive estimates is based on an autoregressive model (AR(n)), which uses a window-size of past real-time router traffic-rate data with coefficients determined by a Kalman Filter (KF). The benefit of this technique is that potential monitoring tools could be provided with future knowledge of one 5-minute interval ahead. The methodology simulations show that the range of RMS error between the KF prediction and the internet service provider (ISP) measurements is of the order of 0.03, whereas the range of RMS error between the KF prediction and the M-MRSP values is of the order of 0.07. The synthetic time-series is a combination of M-MRSP and KF methodologies and maintains all the characteristics of a real traffic-rate time-series, such as non-stationarity, non-normality, long-range dependency (LRD), self-similarity and multimodality.

Adaptive Cultural Algorithm-Based Cuckoo Search for Time-Dependent Vehicle Routing Problem with Stochastic Customers Using Adaptive Fractional Kalman Speed Prediction

For the Time-Dependent Vehicle Routing Problem with Stochastic Customers (TDVRPSC), an adaptive Cultural Algorithm-Based Cuckoo Search (CACS) has been proposed in this paper. The convergence of the new algorithm is proved. An adaptive fractional Kalman filter (AFKF) for traffic speed prediction is proposed. An adaptive mechanism for choosing the covariance of state noise is designed. Its mathematical process is proved. Several benchmark instances with different scales are tested, and new solutions are discovered, which are better than the published solutions. The effects of the parameters on the convergence and the results are studied. According to cargo weight of customers to be delivered, the customers can be divided into large, small, and retail customers. The algorithm is tested with fixed demand probability and also different customer types with stochastic demand. The traffic speeds in different business districts in Xiamen at different times are predicted by AFKF. The results show that AFKF has smaller prediction error and better prediction accuracy than fractional Kalman filter and Kalman filter. The effect of different fractional orders on prediction error is compared. The performance of the new algorithm is compared with that of the cultural algorithm and the Cuckoo Search. The result shows that the new algorithm can efficiently and effectively solve DTVRPSC and improve the accuracy of vehicle routing planning of time-varying actual urban traffic road.

Novel Extreme Learning Machine Using Kalman Filter for Performance Prediction of Aircraft Engine in Dynamic Behavior

AbstractIn this paper, a novel state-propagation extreme learning machine using a Kalman filter (KF-ELM) is proposed. In comparison with the plain extreme learning machine, the proposed algorithm t...

Assessment of Handover Prediction Models in Estimation of Cycle Times for Manual Assembly Tasks in a Human–Robot Collaborative Environment

The accuracy and fluency of a handover task affects the work efficiency of human–robot collaboration. A precise and proactive estimation of handover time points by robots when handing over assembly parts to humans can minimize waiting times and maximize efficiency. This study investigated and compared the cycle time, waiting time, and operators’ subjective preference of a human–robot collaborative assembly task when three handover prediction models were applied: traditional method-time measurement (MTM), Kalman filter, and trigger sensor approaches. The scenarios of a general repetitive assembly task and repetitive assembly under a learning curve were investigated. The results revealed that both the Kalman filter prediction model and the trigger sensor method were superior to the MTM fixed-time model in both scenarios in terms of cycle time and subjective preference. The Kalman filter prediction model could adjust the handover timing according to the operator’s current speed and reduce the waiting time of the robot and operator, thereby improving the subjective preference of the operator. Moreover, the trigger sensor method’s inherent flexibility concerning random single interruptions on the operator’s side earned it the highest scores in the satisfaction assessment.

Industrial Ultra-Short-Term Load Forecasting With Data Completion

Accurate and efficient ultra-short-term load forecasting is crucial for industrial power users to have stabilized and optimized operations. In this paper, we develop novel strategies for industrial power users to handle their challenges in ultra-short-term load forecasting. Firstly, this paper proposes a two-way Genetic Algorithm Back Propagation Neural Networks (GABPNN) missing data completion model to handle data loss, which is common power load data mining. A particle swarm optimization - supporting vector regression (PSO-SVR) algorithm is further used to integrate the two-way completion results with better accuracy. In addition, the paper introduces a combined ultra-short-term load forecasting model for industrial power users. The proposed model combines the Cubature Kalman filter (CKF) prediction model with good performance in nonlinear dynamic systems and the least square support vector machine (LS-SVM) prediction model with good performance in small-scale data prediction. The grey neural network is used to integrate the two algorithms, which further improves the accuracy of ultra-short-term load forecasting. Lastly, we test the proposed strategy in case study with real industrial data and demonstrate that the proposed model has a high degree of precision in load forecasting.

Reactive Collision Avoidance Algorithm for UAV Using Bounding Tube Against Multiple Moving Obstacles

A reactive collision avoidance algorithm is proposed to enable safe autonomous flight in the presence of multiple dynamic obstacles. A position-controlled hexacopter equipped with a visual sensor obtaining obstacle information is considered as an Unmanned Aerial Vehicle (UAV) platform. The proposed method centers on the concept of bounding tube which intrinsically extends the static bounding box to incorporate forthcoming movement of the obstacles into the collision avoidance framework. The processing pipeline consists of separate components for each of the sequential tasks in obstacle sensing and tracking. Computation of a spherical bounding box for each obstacle is followed by discrete-time Kalman filtering for prediction of obstacle trajectory to detect potential collision. If the current course of UAV turns out highly likely to end in collision with any of the obstacles, the vehicle steers to an aiming point chosen from among the bundle of candidates produced by constructing a bounding tube that takes account of predicted obstacle motion. The bounding-tube-based aiming point generation extends seamlessly to the case with multiple moving obstacles through running in series with multi-obstacle track management that combines hierarchical clustering of sensory data points for obstacle identification and a simple geometric method for data association. Numerical simulations are conducted to verify the performance of the proposed collision avoidance algorithm.

Designing of dynamic Kalman filter for prediction of mean arterial blood pressure

Presently high blood pressure or hypertension is a global heath issue. Anti-hypertension vasodilator drug are usually injected to the patient body to regulate the mean arterial blood pressure (MABP) within prescribed limit. For long term treatment, it is quite essential to estimate the prospective behaviour of MABP based on its previous data as well as present drug infusion for a subject. So, development of an appropriate MABP model for a patient with hypertension is an upcoming area of research in bio-medical engineering. Here, in the reported work, a dynamic Kalman filter is designed for estimation of the future value of the MABP where the Kalman gain is a function of instantaneous behaviour of the MABP model in relation to the drug diffusion. The main contribution of the proposed work is to get enhanced performance compared to conventional technique with the help of variable Kalman gain instead of fixed value. During simulation study, three types of MABP models are considered to justify our proposed work i.e. for sensitive, normal, and insensitive patients.

Integrated Sidelobe Cancellation and Linear Prediction Kalman Filter for Joint Multi-Microphone Speech Dereverberation, Interfering Speech Cancellation, and Noise Reduction

In multi-microphone speech enhancement, reverberation as well as additive noise and/or interfering speech are commonly suppressed by deconvolution and spatial filtering, e.g., using multi-channel linear prediction (MCLP) on the one hand and beamforming, e.g., a generalized sidelobe canceler (GSC), on the other hand. In this paper, we consider several reverberant speech components, whereof some are to be dereverberated and others to be canceled, as well as a diffuse (e.g., babble) noise component to be suppressed. In order to perform both deconvolution and spatial filtering, we integrate MCLP and the GSC into a novel architecture referred to as integrated sidelobe cancellation and linear prediction (ISCLP), where the sidelobe-cancellation (SC) filter and the linear prediction (LP) filter operate in parallel, but on different microphone signal frames. Within ISCLP, we estimate both filters jointly by means of a single Kalman filter. We further propose a spectral Wiener gain post-processor, which is shown to relate to the Kalman filter's posterior state estimate. The presented ISCLP Kalman filter is benchmarked against two state-of-the-art approaches, namely first a pair of alternating Kalman filters respectively performing dereverberation and noise reduction, and second an MCLP+GSC Kalman filter cascade. While the ISCLP Kalman filter is roughly $M^2$ times less expensive than both reference algorithms, where $M$ denotes the number of microphones, it is shown to perform similarly as compared to the former, and to outperform the latter.

Low Elevation Angle Estimation Using an Iterative Array Processing Method

Multipath phenomenon reduces the performance of elevation angle estimation, intensively. In this study, a precise even symmetry relation and novel iterative array processing method have been presented based on the fixed beam method for estimating the elevation angle of low-altitude targets in specular and diffuse multipath environment. We propose an iterative beamforming process for retaining antenna aperture with precise even symmetry to eliminate multipath. The Kalman filter (KF) prediction have been used to reduce the computational load of the proposed method, and the frequency diversity and KF estimation to smooth sudden fluctuations in angle estimation. The proposed method estimates the elevation angle with very high precision as shown in simulation results in the multipath environment without the need for any advance knowledge.

On-Line Learning of Linear Dynamical Systems: Exponential Forgetting in Kalman Filters

The Kalman filter is a key tool for time-series forecasting and analysis. We show that the dependence of a prediction of Kalman filter on the past is decaying exponentially, whenever the process noise is non-degenerate. Therefore, Kalman filter may be approximated by regression on a few recent observations. Surprisingly, we also show that having some process noise is essential for the exponential decay. With no process noise, it may happen that the forecast depends on all of the past uniformly, which makes forecasting more difficult.Based on this insight, we devise an on-line algorithm for improper learning of a linear dynamical system (LDS), which considers only a few most recent observations. We use our decay results to provide the first regret bounds w.r.t. to Kalman filters within learning an LDS. That is, we compare the results of our algorithm to the best, in hindsight, Kalman filter for a given signal. Also, the algorithm is practical: its per-update run-time is linear in the regression depth.

Novel diffusion tractography methodology using Kalman filter prediction to improve preoperative benefit-risk analysis in pediatric epilepsy surgery.

In this study the authors investigated the clinical reliability of diffusion weighted imaging maximum a posteriori probability (DWI-MAP) analysis with Kalman filter prediction in pediatric epilepsy surgery. This approach can yield a suggested resection margin as a dynamic variable based on preoperative DWI-MAP pathways. The authors sought to determine how well the suggested margin would have maximized occurrence of postoperative seizure freedom (benefit) and minimized occurrence of postoperative neurological deficits (risk). The study included 77 pediatric patients with drug-resistant focal epilepsy (age 10.0 ± 4.9 years) who underwent resection of their presumed epileptogenic zone. In preoperative DWI tractography from the resected hemisphere, 9 axonal pathways, Ci=1-9, were identified using DWI-MAP as follows: C1-3 supporting face, hand, and leg motor areas; C4 connecting Broca's and Wernicke's areas; C5-8 connecting Broca's, Wernicke's, parietal, and premotor areas; and C9 connecting the occipital lobe and lateral geniculate nucleus. For each Ci, the resection margin, di, was measured by the minimal Euclidean distance between the voxels of Ci and the resection boundary determined by spatially coregistered postoperative MRI. If Ci was resected, di was assumed to be negative (calculated as -1 × average Euclidean distance between every voxel inside the resected Ci volume, ri). Kalman filter prediction was then used to estimate an optimal resection margin, d*i, to balance benefit and risk by approximating the relationship between di and ri. Finally, the authors defined the preservation zone of Ci that can balance the probability of benefit and risk by expanding the cortical area of Ci up to d*i on the 3D cortical surface. In the whole group (n = 77), nonresection of the preoperative preservation zone (i.e., actual resection margin d*i greater than the Kalman filter-defined d*i) accurately predicted the absence of postoperative motor (d*1-3: 0.93 at seizure-free probability of 0.80), language (d*4-8: 0.91 at seizure-free probability of 0.81), and visual deficits (d*9: 0.90 at seizure-free probability of 0.75), suggesting that the preservation of preoperative Ci within d*i supports a balance between postoperative functional deficit and seizure freedom. The subsequent subgroup analyses found that preservation of preoperative Ci =1-4,9 within d*i =1-4,9 may provide accurate deficit predictions independent of age and seizure frequency, suggesting that the DWI-based surgical margin can be effective for surgical planning even in young children and across a range of epilepsy severity. Integrating DWI-MAP analysis with Kalman filter prediction may help guide epilepsy surgery by visualizing the margins of the eloquent white matter pathways to be preserved.

Adaptive square-root unscented Kalman filter for position and pose prediction of UAV

Adaptive square-root unscented Kalman filter for position and pose prediction of UAV

A Method of Modal Parameter Identification for Wind Turbine Blade Based on Binocular Dynamic Photogrammetry

The identification of operational modal parameters of a wind turbine blade is fundamental for online damage detection. In this paper, we use binocular photogrammetry technology instead of traditional contact sensors to measure the vibration of blade and apply the advanced stochastic system identification technique to identify the blade modal frequencies automatically when only output data are available. Image feature extraction and target point tracking (PT) are carried out to acquire the displacement of labeled targets on the wind turbine blade. The vibration responses of the target points are obtained. The data‐driven stochastic subspace identification (SSI‐Data) method based on the Kalman filter prediction sequence is explored to extract modal parameters from vibration response under unknown excitation. Hankel matrixes are reconstructed with different dimensions, so different modal parameters are produced. Similarity of these modal parameters is compared and used to cluster modes into groups. Under appropriate tolerance thresholds, spurious modes can be eliminated. Experiment results show that good effects and stable accuracy can also be achieved with the presented photogrammetry vibration measurement and automatic modal identification algorithm.

Adaptive Dynamic Programming-Based Multi-Sensor Scheduling for Collaborative Target Tracking in Energy Harvesting Wireless Sensor Networks.

Collaborative target tracking is one of the most important applications of wireless sensor networks (WSNs), in which the network must rely on sensor scheduling to balance the tracking accuracy and energy consumption, due to the limited network resources for sensing, communication, and computation. With the recent development of energy acquisition technologies, the building of WSNs based on energy harvesting has become possible to overcome the limitation of battery energy in WSNs, where theoretically the lifetime of the network could be extended to infinite. However, energy-harvesting WSNs pose new technical challenges for collaborative target tracking on how to schedule sensors over the infinite horizon under the restriction on limited sensor energy harvesting capabilities. In this paper, we propose a novel adaptive dynamic programming (ADP)-based multi-sensor scheduling algorithm (ADP-MSS) for collaborative target tracking for energy-harvesting WSNs. ADP-MSS can schedule multiple sensors for each time step over an infinite horizon to achieve high tracking accuracy, based on the extended Kalman filter (EKF) for target state prediction and estimation. Theoretical analysis shows the optimality of ADP-MSS, and simulation results demonstrate its superior tracking accuracy compared with an ADP-based single-sensor scheduling scheme and a simulated-annealing based multi-sensor scheduling scheme.

Incremental predictive Kalman filter for alignment of inertial navigation system

In this paper, a new filter called incremental predictive Kalman filter is developed and employed for the alignment of inertial navigation system using zero velocity updates method. Utilizing the incremental model error, a well posed cost function is presented for incremental predictive Kalman filter that leads to bias-free predictions. Besides, a weighted incremental term of past and present states is evident in the model error solution. This term, in conjunction with an integral action, has substantial effects on the robust performance of the alignment process against intense model uncertainty. Due to the horizon extension of the predictions and of the model errors to more than one-step ahead in the incremental predictive Kalman filter, this filter has a very flexible structure which enables it to implement the available references in the zero velocity updates method as a whole over its wide prediction horizon. The Monte Carlo simulations indicate that the alignment accuracy is noticeably affected due to use of the incremental predictive Kalman filter.

Novel dual vector quaternions based adaptive extended two-step filter for pose and inertial parameters estimation of a free-floating tumbling space target

Estimating the parameters of an uncooperative space target is essential to the on-orbit service missions. A good parameter estimation can provide sufficient prior knowledge for the further operations. This paper proposes a novel dual vector quaternions based adaptive extended two-step filter (DVQ-AETSF) to estimate the pose and inertial parameters of a free-floating tumbling space target. Firstly, both of the rotational and translational motions are modeled by the dual vector quaternions (DVQ). Then, by using the DVQ-based system model, the DVQ-AETSF is designed. The proposed DVQ-AETSF mainly consists of a traditional Kalman filter prediction procedure in the first step and an adaptive regularized Newton iteration technique in the second step. The new proposed two-step filter aims to deal with the high nonlinearities in the measurements equations. By using the proposed DVQ-AETSF, both of the pose and initial parameters of a free floating tumbling space target under large errors of initial guesses and high measurement noise can be well estimated. Finally, the proposed DVQ-AETSF is validated by mathematical simulations to show its performance.

Phase-Aware Single-Channel Speech Enhancement With Modulation-Domain Kalman Filtering

We present a speech enhancement algorithm that performs modulation-domain Kalman filtering to track the speech phase using circular statistics, along with the spectral log-amplitudes of speech and noise. In the proposed algorithm, the speech phase posterior is used to create an enhanced speech phase spectrum for the signal reconstruction of speech. The Kalman filter prediction step separately models the temporal inter-frame correlation of the speech and noise spectral log-amplitudes and of the speech phase, while the Kalman filter update step models their nonlinear relations under the assumption that speech and noise add in the complex short-time Fourier transform domain. The phase-sensitive enhancement algorithm is evaluated with speech quality and intelligibility metrics, using a variety of noise types over a range of SNRs. Instrumental measures predict that tracking the speech log-spectrum and phase with modulation-domain Kalman filtering leads to consistent improvements in speech quality, over both conventional enhancement algorithms and other algorithms that perform modulation-domain Kalman filtering.

Potential improvements of lung and prostate MLC tracking investigated by treatment simulations.

Intrafraction tumor motion during external radiotherapy is a challenge for the treatment accuracy. A novel technique to mitigate the impact of tumor motion is real-time adaptation of the multileaf collimator (MLC) aperture to the motion, also known as MLC tracking. Although MLC tracking improves the dosimetric accuracy, there are still residual errors. Here, we investigate and rank the performance of five prediction algorithms and seven improvements of an MLC tracking system by extensive tracking treatment simulations. An in-house-developed MLC tracking simulator that has been experimentally validated against an electromagnetic-guided MLC tracking system was used to test the prediction algorithms and tracking system improvements. The simulator requires a Dicom treatment plan and a motion trajectory as input and outputs all motion of the accelerator during MLC tracking treatment delivery. For lung tumors, MLC tracking treatments were simulated with a low and a high modulation VMAT plan using 99 patient-measured lung tumor trajectories. For prostate, tracking was also simulated with a low and a high modulation VMAT plan, but with 695 prostate trajectories. For each simulated treatment, the tracking error was quantified as the mean MLC exposure error, which is the sum of the overexposed area (irradiated area that should have been shielded according to the treatment plan) and the underexposed area (shielded area that should have been irradiated). First, MLC tracking was simulated with the current MLC tracking system without prediction, with perfect prediction (Perfect), and with the following five prediction algorithms: linear Kalman filter (Kalman), kernel density estimation (KDE), linear adaptive filtering (LAF), wavelet-based multiscale autoregression (wLMS), and time variant seasonal autoregression (TVSAR). Next, MLC tracking was simulated using the best prediction algorithm and seven different tracking system improvements: no localization signal latency (a), doubled maximum MLC leaf speed (b), halved MLC leaf width (c), use of Y backup jaws to track motion perpendicular to the MLC leaves (d), dynamic collimator rotation for alignment of the MLC leaves with the dominant target motion direction (e), improvements 4 and 5 combined (f), and all improvements combined (g). All results are presented as the mean residual MLC exposure error compared to no tracking. In the prediction study, the residual MLC exposure error was 47.0% (no prediction), 45.1% (Kalman), 43.8% (KDE), 43.7% (LAF), 42.1% (wLMS), 40.1% (TVSAR), and 36.5% (Perfect) for lung MLC tracking. For prostate MLC tracking, it was 66.0% (no prediction), 66.9% (Kalman), and 63.4% (Perfect). For lung with TVSAR prediction, the residual MLC exposure error for the seven tracking system improvements was 37.2%(1), 38.3%(2), 37.4%(3), 34.2%(4), 30.6%(5), 27.7%(6), and 20.7%(7). For prostate with no prediction, the residual MLC exposure error was 61.7%(1), 61.4%(2), 55.4%(3), 57.2%(4), 47.5%(5), 43.7%(6), and 38.7%(7). For prostate, MLC tracking was slightly better without prediction than with linear Kalman filter prediction. For lung, the TVSAR prediction algorithm performed best. Dynamic alignment of the collimator with the dominant motion axis was the most efficient MLC tracking improvement except for lung tracking with the low modulation VMAT plan, where jaw tracking was slightly better.

Assimilating Doppler radar observations with an ensemble Kalman filter for convection-permitting prediction of convective development in a heavy rainfall event during the pre-summer rainy season of south China

This study examines the effectiveness of an ensemble Kalman filter based on the weather research and forecasting model to assimilate Doppler-radar radial-velocity observations for convection-permitting prediction of convection evolution in a high-impact heavy-rainfall event over coastal areas of South China during the pre-summer rainy season. An ensemble of 40 deterministic forecast experiments (40 DADF) with data assimilation (DA) is conducted, in which the DA starts at the same time but lasts for different time spans (up to 2 h) and with different time intervals of 6, 12, 24, and 30 min. The reference experiment is conducted without DA (NODA).To show more clearly the impact of radar DA on mesoscale convective system (MCS) forecasts, two sets of 60-member ensemble experiments (NODA EF and exp37 EF) are performed using the same 60-member perturbed-ensemble initial fields but with the radar DA being conducted every 6 min in the exp37 EF experiments from 0200 to 0400 BST. It is found that the DA experiments generally improve the convection prediction. The 40 DADF experiments can forecast a heavy-rain-producing MCS over land and an MCS over the ocean with high probability, despite slight displacement errors. The exp37 EF improves the probability forecast of inland and offshore MCSs more than does NODA EF. Compared with the experiments using the longer DA time intervals, assimilating the radial-velocity observations at 6-min intervals tends to produce better forecasts. The experiment with the longest DA time span and shortest time interval shows the best performance. However, a shorter DA time interval (e.g., 12 min) or a longer DA time span does not always help. The experiment with the shortest DA time interval and maximum DA window shows the best performance, as it corrects errors in the simulated convection evolution over both the inland and offshore areas. An improved representation of the initial state leads to dynamic and thermodynamic conditions that are more conducive to earlier initiation of the inland MCS and longer maintenance of the offshore MCS.