Joint tracking and classification of extended targets with complex shapes

The high computational complexity of existing joint tracking and classification (JTC) algorithms hampers their application. After presenting a new description of the JTC problem--simultaneous tracking and classification (STC) instead of JTC, we derive two STC algorithms in both exact and approximate forms by applying Hayes' rule to the target state probability density function (pdf) and target class probability mass function (pmf) simultaneously under the assumption that the kinematic and attribute measurement processes are conditional independent. The mutual information exchange between tracker and classifier of the proposed STC algorithms is introduced by defining the simultaneous pdf-pmf of target state and class, the dependence of kinematic measurement on target class, the dependence of attribute measurement on target state and target model, class-dependent kinematic model sets, and class-dependent flight envelopes, etc. The proposed STC algorithms have four distinctive features. First, they have a modularized structure, i.e., they explicitly integrate a multiple-model filter and a Bayesian classifier. Second, the approximate versions, which follow easily from the proposed STC algorithms thanks to their modularized structure, have a closed form with a lower computational complexity and are more suitable for real-time applications. Third, the proposed exact STC algorithms are derived without the hidden approximation made in some existing multiple-model based JTC algorithms. Fourth, one of the proposed STC algorithms has the potential to further reduce the computational load since it has no redundant motion models. Simulation results suggest that the proposed STC algorithms provide a hopeful solution to a class of STC problems.

In this paper, single-target tracking using radar measurements is addressed. Recently, algorithms based on Bernoulli random finite sets have proved efficient in a cluttered environment. However, in Bayesian approaches, the choice of the motion model impacts the trajectory estimation accuracy. To select an appropriate set of motion models, a joint tracking and classification (JTC) algorithm can be used. The principle is to consider different target classes depending on their maneuvrability, each of them being associated to a set of motion models. In this context, additional information such as a target length extent measurement can improve both classification and trajectory estimation. Therefore, we propose a multiple-model Bernoulli filter to perform JTC. To jointly estimate the trajectory and the target length which is constant, a Rao-Blackwellized approach is considered. Another contribution is that a bank of probabilistic data association filters is run instead of Kalman filters to account for false detections.

In practical target tracking scenarios, targets of different sizes (or extents) may be near or far away from the sensor, which may result in targets appearing as point sources or as extended targets spanning one or more resolution cells, respectively, depending on distance and sensor resolution. In this paper, a new Gaussian Process (GP) measurement model is proposed to explicitly describe the observation about each basis point of GP by an individual dynamic Poisson measurement rate. By employing this model, a novel algorithm to track multiple point targets and extended targets, simultaneously and seamlessly, in the presence of clutter and missed detections is proposed within the Probabilistic Multi-Hypothesis Tracker (PMHT) framework. The proposed algorithm can adapt to spatio-temporally varying target sizes or extents of extended targets and temporally varying target cardinality. In addition, the posterior Cramer-Rao lower bound (PCRLB) for extended targets, which quantifies the accuracies of estimates of multiple extended target states in scenarios with clutter, is derived. Simulations with a scenario consisting of multiple extended targets and point targets are used to verify the effectiveness of the proposed algorithm and to compare its performance with the extended target PCRLB and with those of existing extended target tracking algorithms.

BackgroundReducing TB surveillance incurs significant costs, as effective control and societal impact minimization rely on robust, ongoing surveillance systems that integrate and analyze comprehensive data for prompt action. Our study supports integrating artificial intelligence (LSI) into TB and other notifiable disease monitoring frameworks to improve trackingFigure 1Binary Matrix of 125 Terms: Presence vs. Absence of Root Keywords Retrieved from the Patient ElectronicRecord for the LSI Automatic Retrieval System.Binary Matrix of 125 Terms: Presence vs. Absence of Root Keywords Retrieved from the Patient Electronic Record for the LSI Automatic Retrieval System.MethodsIn 2024, we developed a novel application within Datamart A.R.G.U.S.—Assistant for Recovery and Guarding of Urgent and Epidemiological Sentinels—a cloud-based platform hosted on AWS and developed by our team. This application integrates with hospital systems (MV) and laboratory systems (MATRIX and GAL) to enhance the surveillance of healthcare-associated infections (HAI) and notifiable diseases. Data from both hospital and outpatient care are encoded into a binary matrix of 125 terms (root keywords) extracted from patient electronic records. This matrix is then processed using Singular Value Decomposition (SVD) within an LSI-based information retrieval system (Fig. 1). In our model, each patient is represented as a point in a 125-dimensional hyperdimensional space. When projected into three-dimensional space, this framework allows for effective clustering and classification of notifiable Diseases (Fig. 2), specifically TB (Fig. 3).Figure 2:3D Visualization of High-Dimensional Data: Comparing Mandatory Notifiable Diseases versus Non-Notifiable Diseases. Both patient types are well separated in the space, enabling automatic clustering and classification.3D Visualization of High-Dimensional Data: Comparing Mandatory Notifiable Diseases versus Non-Notifiable Diseases. Both patient types are well separated in the space, enabling automatic clustering and classification.ResultsThe LSI-based matrix was constructed using data from January 2023 to February 2024, encompassing a sample of 17,895 cases (lines) across 125 presence versus absence terms, with each case classified as either a notifiable or non-notifiable disease. The 125-dimensional matrix was reduced to 28 factors using SVD. The sensitivity and specificity of the Euclidean distance were better than those of cosine similarity when automatically identifying TB cases in 1,970 independent queries (Fig. 4).Figure 3:3D Visualization of High-Dimensional Data: Comparing Tuberculosis versus Other Mandatory Notifiable Diseases versus Non-Notifiable Diseases. The three types of patients are well separated in the space, enabling automatic clustering and classification.3D Visualization of High-Dimensional Data: Comparing Tuberculosis versus Other Mandatory Notifiable Diseases versus Non-Notifiable Diseases. The three types of patients are well separated in the space, enabling automatic clustering and classification.ConclusionArtificial Intelligence (LSI), significantly enhances the surveillance of TB and other notifiable diseases by enabling real-time, automated case identification up to one day prior (D-1). This advancement allows surveillance personnel to complete their tasks more efficiently, thereby preventing outbreaks and reducing the risk of unforeseen fatalities.Figure 4:Performance Comparison of Cosine vs. Euclidean Distance Metrics in Automatically Identifying TB Cases Using LSI: Euclidean Distance Demonstrates Superior Accuracy and Has Been Integrated into Datamart A.R.G.U.S. for Real-Time Identification of TB and Other Notifiable Diseases as of the Previous Workday (D-1).Performance Comparison of Cosine vs. Euclidean Distance Metrics in Automatically Identifying TB Cases Using LSI: Euclidean Distance Demonstrates Superior Accuracy and Has Been Integrated into Datamart A.R.G.U.S. for Real-Time Identification of TB and Other Notifiable Diseases as of the Previous Workday (D-1).DisclosuresAll Authors: No reported disclosures

To enhance the tracking accuracy of multi-ellipse extended target tracking for maneuvering targets, we propose a Variational Bayesian-based Interacting Multiple Model Maneuvering Extended Target Tracking Algorithm. The algorithm leverages multiple kinematic models within an Interacting Multiple Model framework to predict the target state, enabling better adaptation to various target kinematic modes during the time update. Following the prediction step, variational Bayesian inference, which includes inference of unknown measurement noise, is applied independently within each model to estimate the target’s position and shape. Then, model probabilities are updated based on the likelihood functions, and the model transition probabilities are adaptively learned. Concurrently, an ellipsoid fusion method is employed to combine the shape estimates from different models, while kinematic states are fused using model weights, yielding a robust overall target state estimate. The feasibility and performance of the proposed algorithm are validated by comparing its target tracking simulation results with those of other algorithms under different scenarios.

The optimization of an assembly line layout can be modeled as a facility layout problem. Since an accurate representation of the real-world distances is essential for the validity of the optimization results, this paper compares the accuracy of the approximation of the real-world distances by the commonly used rectilinear and Euclidean distance metrics. Further, the influence of the size and aspect ratio of the machines on the approximation accuracy and the influence of the distance metrics on the solver runtime is studied. The results show the Euclidean distance metric being more accurate but extending computation time.

In this paper, we propose a feature combination, also known as feature fusion, for improving performance in content-based gastric image retrieval (CBGIR). This study provides a CBGIR system that retrieves images by combining ResNet-18 and ResNet-50 information and finally, the Euclidean distance metric is evaluated for similarity measurement. The proposed approach is also compared to different deep learning techniques such as AlexNet, VGGs (VGG-16 & VGG-19), GoogleNet, SqueezeNet, DarkNet-19 models. The proposed method was examined on the KVASIR database with 4000 images and S different classes. We get the optimum results as average precision of 95.44% and average recall of 19.09 on a scale of 20 using the proposed deep learning model and Euclidean distance metric.

Methods dealing with the problem of Joint Tracking and Classification (JTC) are abundant, among which Simultaneous Tracking and Classification (STC) provides a modularized scheme solving tracking and classification subproblems simultaneously. However, there is no explicit hard decision on the class label but only soft decision (class probability) is provided. This does not fit many practical cases, in which a hard decision is urgently needed. To solve this problem, this paper proposes a Hard decision-based STC (HSTC) method. HSTC takes all the decision error rate, timeliness, and estimation error into account. Specifically, for decision, the sequential probability ratio test is adopted due to its nice properties and also the adaptability to our situation. For estimation, by utilizing the two-way information exchange between the tracker and the classifier, we propose flexible three tracking schemes related to decision. The HSTC tracking result is divided into three parts according to the time of making the hard decision. In general, the proposed HSTC method takes advantage of both SPRT and STC. Finally, two illustrative JTC examples with hard decision verify the effectiveness of the the proposed HSTC method. They show that HSTC can meet the demand of the problem, and also has the performance superiority in both decision and estimation.

Decision letter for "‘Euclimatch': an R package for climate matching with Euclidean distance metrics"

Decision letter for "‘Euclimatch': an R package for climate matching with Euclidean distance metrics"

Review for "‘Euclimatch': an R package for climate matching with Euclidean distance metrics"

Author response for "‘Euclimatch': an R package for climate matching with Euclidean distance metrics"

Robust microarray data feature selection using a correntropy based distance metric learning approach

While the Euclidean distance metric is commonly utilized in most soft subspace clustering algorithms, some robust distance metrics can also be considered for soft subspace clustering. In this study, a novel soft subspace clustering algorithm called Alternative Soft Subspace Clustering (ASSC) is proposed by incorporating the alternative distance metric into the framework of entropy weighting subspace clustering. The properties of ASSC are investigated and a theoretical analysis on robustness is established accordingly. Experiments on UCI data are conducted and the experimental results show the effectiveness of the proposed algorithm.

In the extended target tracking using Gaussian process (GP) or other methods to estimate the extension state, all of them is necessary to obtain the measurement model, and the deviation from the true kinematic state affects the extension result easily. Meanwhile, with the growth of the shape complexity, the corresponding covariance matrix dimension increases, leading to a very high computational burden. To this end, we present an extended target tracking algorithm based on deep learning, which adopts Gaussian mixture (GM) probability hypothesis density (PHD) filter for extended target (ET) tracking, called the ET-GM-PHD filter, to estimate the kinematic state, and uses convolutional conditional neural process (ConvCNP) to estimate the extension state (i.e., the shape of the target) avoiding the complex computation and dependence on priors. Therefore, the proposed algorithm is named as the ConvCNP-GM-PHD filter. In our algorithm, ConvCNP lies on the neural network (NN) and GP, where the former can learn the rules from a large amount of data without any priors, while the latter uses the covariance function to express the distribution over possible functions according to a small number of context observations. Due the proposed algorithm can effectively combine the advantages of both, it is reliable to get a model via training which is able to realize function regression flexibly. Thus, ConvCNP is able to estimate the shape function by putting the angles and radial value between the kinematic state and associated measurements into the pre-trained model. The results show that the accuracy of the extension state estimation of the proposed ConvCNP-GM-PHD filter is improved and its computational complexity is also reduced. It implies that the proposed algorithm is more real-time and effective, and has a good application prospect.