scholarly journals Measurement Noise Recommendation for Efficient Kalman Filtering over a Large Amount of Sensor Data

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1168 ◽  
Author(s):  
Sebin Park ◽  
Myeong-Seon Gil ◽  
Hyeonseung Im ◽  
Yang-Sae Moon
Keyword(s):  
Kalman Filtering ◽  
Input Parameter ◽  
Original Data ◽  
Measurement Noise ◽  
Sensor Data ◽  
Noise Variance ◽  
Noise Parameters ◽  
Input Noise ◽  
Novel Method ◽  
Filtering Technique

To effectively maintain and analyze a large amount of real-time sensor data, one often uses a filtering technique that reflects characteristics of original data well. This paper proposes a novel method for recommending the measurement noise for Kalman filtering, which is one of the most representative filtering techniques. Kalman filtering corrects inaccurate values of input sensor data, and its filtering performance varies depending on the input noise parameters. In particular, if the noise parameters determined based on the user’s experience are incorrect, the accuracy of Kalman filtering may be reduced significantly. Based on this observation, this paper addresses how to determine the measurement noise variance, a major input parameter of Kalman filtering, by analyzing past sensor data and how to use the estimated noise to improve the filtering accuracy. More specifically, to estimate the measurement noise variance, two analytical methods are proposed: one a transform-based method using a wavelet transform and the other a learning-based method using a denoising autoencoder. Experimental results show that the proposed methods estimated the measurement noise variance accurately and were superior to the experience-based method in the filtering accuracy.

scholarly journals Estimation of Object Motion State Based on Adaptive Decorrelation Kalman Filtering

2019 ◽  
Vol 23 (4) ◽  
pp. 749-757
Author(s):  
Xinmei Wang ◽  
Leimin Wang ◽  
Longsheng Wei ◽  
Feng Liu ◽  
◽  
...  
Keyword(s):  
Kalman Filtering ◽  
Cross Correlation ◽  
Measurement Noise ◽  
Feature Point ◽  
Noise Variance ◽  
Filtering Method ◽  
Motion State ◽  
New Process ◽  
Object Feature ◽  
Noise Cross Correlation

To estimate the motion state of object feature point in image space, an adaptive decorrelation Kalman filtering model is proposed in this paper. The model is based on the Kalman filtering method. A first-order Markov sequence model is used to describe the colored measurement noise. To eliminate the colored noise, the measurement equation is reconstructed and then a cross-correlation between the process noise and the newly measurement noise is established. To eliminate the noise cross-correlation, a reconstructed process equation is proposed. According to the new process and measurement equations, and the noise mathematical characteristics of the standard Kalman filtering method, the parameters involved in the new process equation can be acquired. Then the noise cross-correlation can be successfully eliminated, and a decorrelation Kalman filtering model can be obtained. At the same time, for obtaining a more accurate measurement noise variance, an adaptive recursive algorithm is proposed to update the measurement noise variance based on the correlation method. It overcomes the limitations of traditional correlation methods used for noise variance estimation, thus, a relatively accurate Kalman filtering model can be obtained. The simulation shows that the proposed method improves the estimation accuracy of the motion state of object feature point.

Healing Seismic Data with Phase Corrections for Processing of Single-Sensor Data in the Desert Environment

2021 ◽  
Author(s):  
Andrey Bakulin ◽  
Ilya Silvestrov ◽  
Dmitry Neklyudov
Keyword(s):  
Speech Processing ◽  
Original Data ◽  
Sensor Data ◽  
Desert Environment ◽  
Time Frequency ◽  
Weak Reflection ◽  
Phase Corrections ◽  
Single Sensor ◽  
Efficient Processing ◽  
Novel Method

Abstract Acquiring data with single sensors or small arrays in a desert environment may lead to challenging data quality for subsequent processing. We present a new approach to effectively "heal" such data and allow efficient processing and imaging without requiring any additional acquisition. A novel method combines the power of seismic beamforming and time-frequency masking originating from speech processing. First, we create an enhanced version of the data with beamforming or local stacking. Beamforming effectively suppresses scattered noise and finds weak reflection signals, albeit sacrificing some higher frequencies. Next, we employ a seismic time-frequency masking procedure to fix the original data while using beamformed data as a guide. Time-frequency masking effectively fixes corrupt and broken phase of the original data. After such data-driven healing, prestack data can be effectively processed and imaged, while maintaining the higher frequencies lost during beamforming.

ROI Based Post Image Quality Assessment Technique on Multiple Localized Filtering Method On Kinect HD Sensor Mobile Robot

2018 ◽  
Vol 3 (2) ◽  
pp. 145
Author(s):  
Kholilatul Wardani ◽  
Aditya Kurniawan
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Similarity Index ◽  
Assessment Model ◽  
Sensor Data ◽  
Edge Region ◽  
Kinect Sensor ◽  
Image Region ◽  
Filtering Technique

 The ROI (Region of Interest) Image Quality Assessment is an image quality assessment model based on the SSI (Structural Similarity Index) index used in the specific image region desired to be assessed. Output assessmen value used by this image assessment model is 1 which means identical and -1 which means not identical. Assessment model of ROI Quality Assessment in this research is used to measure image quality on Kinect sensor capture result used in Mobile HD Robot after applied Multiple Localized Filtering Technique. The filter is applied to each capture sensor depth result on Kinect, with the aim to eliminate structural noise that occurs in the Kinect sensor. Assessment is done by comparing image quality before filter and after filter applied to certain region. The kinect sensor will be conditioned to capture a square black object measuring 10cm x 10cm perpendicular to a homogeneous background (white with RGB code 255,255,255). The results of kinect sensor data will be taken through EWRF 3022 by visual basic 6.0 program periodically 10 times each session with frequency 1 time per minute. The results of this trial show the same similar index (value 1: identical) in the luminance, contrast, and structural section of the edge region or edge region of the specimen. The value indicates that the Multiple Localized Filtering Technique applied to the noise generated by the Kinect sensor, based on the ROI Image Quality Assessment model has no effect on the image quality generated by the sensor.

scholarly journals Embedding Undersampling Rotation Forest for Imbalanced Problem

2018 ◽  
Vol 2018 ◽  
pp. 1-15 ◽  
Author(s):  
Huaping Guo ◽  
Xiaoyu Diao ◽  
Hongbing Liu
Keyword(s):  
Imbalanced Data ◽  
Feature Space ◽  
Original Data ◽  
Training Set ◽  
Data Set ◽  
Minority Class ◽  
Rotation Forest ◽  
Novel Method ◽  
Individual Classifier ◽  
The Cost

Rotation Forest is an ensemble learning approach achieving better performance comparing to Bagging and Boosting through building accurate and diverse classifiers using rotated feature space. However, like other conventional classifiers, Rotation Forest does not work well on the imbalanced data which are characterized as having much less examples of one class (minority class) than the other (majority class), and the cost of misclassifying minority class examples is often much more expensive than the contrary cases. This paper proposes a novel method called Embedding Undersampling Rotation Forest (EURF) to handle this problem (1) sampling subsets from the majority class and learning a projection matrix from each subset and (2) obtaining training sets by projecting re-undersampling subsets of the original data set to new spaces defined by the matrices and constructing an individual classifier from each training set. For the first method, undersampling is to force the rotation matrix to better capture the features of the minority class without harming the diversity between individual classifiers. With respect to the second method, the undersampling technique aims to improve the performance of individual classifiers on the minority class. The experimental results show that EURF achieves significantly better performance comparing to other state-of-the-art methods.

scholarly journals Detection and Location of Malicious Nodes Based on Homomorphic Fingerprinting in Wireless Sensor Networks

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Zhiming Zhang ◽  
Yu Yang ◽  
Wei Yang ◽  
Fuying Wu ◽  
Ping Li ◽  
...  
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Evaluation Model ◽  
Original Data ◽  
Base Station ◽  
Sensor Data ◽  
Wireless Sensor ◽  
Malicious Node ◽  
Malicious Nodes ◽  
Trust Value

The current detection schemes of malicious nodes mainly focus on how to detect and locate malicious nodes in a single path; however, for the reliability of data transmission, many sensor data are transmitted by multipath in wireless sensor networks. In order to detect and locate malicious nodes in multiple paths, in this paper, we present a homomorphic fingerprinting-based detection and location of malicious nodes (HFDLMN) scheme in wireless sensor networks. In the HFDLMN scheme, using homomorphic fingerprint and coding technology, the original data is divided into n packets and sent to the base station along n paths, respectively; the base station determines whether there are malicious nodes in each path by verifying the validity of the packets; if there are malicious nodes in one or more paths, the location algorithm of the malicious node is implemented to locate the specific malicious nodes in the path; if all the packets are valid, the original data is recovered. The HFDLMN scheme does not need any complex evaluation model to evaluate and calculate the trust value of the node, nor any monitoring nodes. Theoretical analysis results show that the HFDLMN scheme is secure and effective. The simulation results demonstrate promising outcomes with respect to key parameters such as the detection probability of the malicious path and the locating probability of the malicious node.

scholarly journals Kalman filtering for dynamic motion and model estimation

2021 ◽  
Author(s):  
Randal Schumacher.
Keyword(s):  
Kalman Filtering ◽  
Vision System ◽  
Target Position ◽  
Model Estimation ◽  
Mass Center ◽  
Extended Kalman Filtering ◽  
Dynamic Motion ◽  
Filtering Technique ◽  
Time Determination

The fundamental task of a space vision system for rendezvous, capture, and servicing of satellites on-orbit is the real-time determination of the motion of the target vehicle as observed on-board a chaser vehicle. Augmenting the architecture to incorporate the highly regarded Kalman filtering technique can synthesize a system that is more capable, more efficient and more robust. A filter was designed and testing was conducted in an inertial environment and then in a more realistic relative motion orbital rendezvous scenario. The results indicate that a Dynamic Motion Filter based on extended Kalman filtering can provide the vision system routines with excellent initialization leading to faster convergence, reliable pose estimation at slower sampling rates, and the ability to estimate target position, velocity, orientation, angular velocity, and mass center location.

Does the brain implement the Kalman filter?

2004 ◽  
Vol 27 (3) ◽  
pp. 404-405 ◽  
Author(s):  
Valeri Goussev
Keyword(s):  
Kalman Filter ◽  
Data Processing ◽  
Kalman Filtering ◽  
Brain Structures ◽  
Parameter Evaluation ◽  
Filtering Technique ◽  
Processing Techniques ◽  
The Brain

The Kalman filtering technique is considered as a part of concurrent data-processing techniques also related to detection, parameter evaluation, and identification. The adaptive properties of the filter are discussed as being related to symmetrical brain structures.

scholarly journals A Novel EM Implementation for Initial Alignment of SINS Based on Particle Filter and Particle Swarm Optimization

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Yanbing Guo ◽  
Lingjuan Miao ◽  
Yusen Lin
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Filter ◽  
Particle Swarm ◽  
The State ◽  
Nonlinear Filters ◽  
Measurement Noise ◽  
Strong Nonlinearity ◽  
Initial Alignment ◽  
Swarm Optimization ◽  
Noise Parameters

For nonlinear systems in which the measurement noise parameters vary over time, adaptive nonlinear filters can be applied to precisely estimate the states of systems. The expectation maximization (EM) algorithm, which alternately takes an expectation- (E-) step and a maximization- (M-) step, has been proposed to construct a theoretical framework for the adaptive nonlinear filters. Previous adaptive nonlinear filters based on the EM employ analytical algorithms to develop the two steps, but they cannot achieve high filtering accuracy because the strong nonlinearity of systems may invalidate the Gaussian assumption of the state distribution. In this paper, we propose an EM-based adaptive nonlinear filter APF to solve this problem. In the E-step, an improved particle filter PF_new is proposed based on the Gaussian sum approximation (GSA) and the Monte Carlo Markov chain (MCMC) to achieve the state estimation. In the M-step, the particle swarm optimization (PSO) is applied to estimate the measurement noise parameters. The performances of the proposed algorithm are illustrated in the simulations with Lorenz 63 model and in a semiphysical experiment of the initial alignment of the strapdown inertial navigation system (SINS) in large misalignment angles.

Sign in / Sign up

Export Citation Format

Share Document