Multi-path tracks of a single target exist in skywave over-the-horizon radar (OTHR) surveillance, due to the availability multiple signal propagation paths through ionosphere. Different from traditional multipath data association and estimation methods for OTHR tracking, novel scheme joint state (JMAE) is developed based on expectation-maximization (EM) framework. The proposed has iterative optimization identification (including ionospheric mode identification) path-conditional track...

Laboratories today need flexible, budget-friendly tools that can grow with their experiments. We present ModuLab, a proof-of-concept platform built to streamline environmental monitoring and pave the way for scaled-up deployments. ModuLab’s backbone is microcontroller-driven I²C bus which discrete, hot-swappable sensor modules—measuring temperature, pH, light intensity, humidity—attach via standardized headers. An MCP2221A bridge creates USB virtual COM port, onboard LEDs immediately signal...

This study introduces a new variational Bayesian adaptive estimator that enhances traditional interactive multiple model (IMM) frameworks for maneuvering target tracking. Conventional IMM algorithms struggle with rapid maneuvers due to model-switching delays and fixed structures. Our method uses inference update change-point statistics in real-time quick switching. Variational approximates the complex posterior distribution, transforming state estimation identification into an optimization...

Motivated by tracking a manoeuvring target in electronic counter environments, the authors present problem of joint estimation and identification class discrete‐time stochastic systems with unknown inputs both plant sensors. Based on expectation‐maximum criterion, optimisation scheme state estimation, parameter iteration terminate decision were derived. A numerical example accompanied range gate pull‐off is utilised to verify proposed scheme.

We consider multitarget detection and tracking problem for a class of multipath system where one target may generate multiple measurements via propagation paths, the association relationship among targets, measurements, paths is unknown. In order to effectively utilize from improve performance, tracker has handle high-dimensional estimation latent variables including existence state, kinematic data association. Based on variational Bayesian inference, we propose novel joint algorithm that...

Over-the-horizon radar (OTHR) target tracking in the presence of complicated ionospheric environment mainly faces three challenges, i.e., discrete uncertainty multipath data association, continuous heights, and coupling state estimation parameters identification. The existing OTHR algorithms demanded that heights should be exactly known or statistical properties known. However, is inaccurate due to inherent variability ionosphere, especially when deployment ionosondes unavailable sea area...

This paper considers the joint recursive estimation of dynamic state and time-varying process noise covariance for a linear space model. The conjugate prior on covariance, inverse Wishart distribution, provides latent variable. A variational Bayesian inference framework is then adopted to iteratively estimate posterior density functions state, introduced performance algorithm demonstrated with simulated data in target tracking application.

Motivated by the maneuvering target tracking with sensors such as radar and sonar, this article considers joint recursive estimation of dynamic state time-varying process noise covariance in nonlinear state-space models. Due to nonlinearity models nonconjugate prior, problem is generally intractable it involves integrals general functions unknown covariance, resulting posterior probability distribution lacking closed-form solutions. This presents a solution for model parameters...

We propose an iterative nonlinear estimator based on the technique of variational Bayesian optimization. The posterior distribution underlying system state is approximated by a solvable approached iteratively using evidence lower bound optimization subject to minimal weighted Kullback-Leibler divergence, where penalty factor considered adjust step size iteration. Based linearization, filter derived in closed-form. performance proposed algorithm compared with several filters literature...

Tracking an unknown number of targets based on multipath measurements provided by over-the-horizon radar (OTHR) network with a statistical ionospheric model is complicated, which requires solving four subproblems: Target detection, target tracking, data association, and heights identification. A joint solution desired since the subproblems are highly correlated, but suffering from intractable inference problem high-dimensional latent variables. In this article, unified message passing (MP)...

Target tracking is a hot topic for unmanned aerial vehicle surveillance. Recently, the novel random sample consensus (RANSAC) algorithm shows good performance in dense clutter environment. However, heavy computational burden limits usage (UAV). In this paper, density-based recursive (DBR-RANSAC) proposed, which utilizes density property of measurements within several steps to direct sampling. DBR-RANSAC, randomness sampling can be avoided and computation complexity reduced particularly...

In the target localization of skywave over-the-horizon radar (OTHR), error ionospheric parameters is one main source. To reduce parameters, a method using both information reference sources (e.g., terrain features, ADS-B) in ground coordinates and corresponding OTHR measurements proposed to estimate parameters. Describing electron density profile by quasi-parabolic model, estimation formulated as an inverse problem, solved Markov chain Monte Carlo due complicated ray path equations....

Over-the-horizon radar (OTHR) is of significance in persistent surveillance. To localize targets, coordinate registration (CR) has to be carried out transform the coordinates targets from slant system ground system. An alternative way improve accuracy CR utilization sea-land transitions and islands. The key novelty this paper a solution recognizing sea/land clutter based on range-Doppler spectrum OTHR. We propose deep convolutional neural network (DCNN) with multiple hidden layers learn...

Multitarget tracking in the interference environments suffers from nonuniform, unknown and time-varying clutter, resulting dramatic performance deterioration. We address this challenge by proposing a robust multitarget algorithm, which estimates states of clutter targets simultaneously message-passing (MP) approach. define non-homogeneous with finite mixture model containing uniform component multiple nonuniform components. The measured signal strength is utilized to estimate mean...

In this paper we consider the problem of distributed, joint, state estimation and identification for a class stochastic systems with unknown inputs (UI). A distributed Expectation-Maximization (EM) algorithm is presented to estimate local at each sensor node by using observations in E-step, three different consensus schemes are proposed diffuse sensor's neighbours derive global node. M-step, identifies estimate. numerical example target tracking network given verify EM algorithms compared...