Target Distribution Research Articles

Satellite constellation method for ground targeting optimized with K-means clustering and genetic algorithm

This study proposed a satellite constellation method to cluster targets using machine learning and achieve the desired revisit performance for each target in an area of interest. Because a typical satellite constellation, such as the Walker method, does not consider the geometrical dynamics between the satellite and Earth's surface target, the target-oriented revisit performance analysis and the application of optimization method are limited. To overcome these limitations, this study developed a satellite constellation method that is customized according to the target using a repeating ground track orbit and machine learning techniques. The proposed model groups aim to maximize satellite revisit performance via K-means clustering and determine the optimal number of satellites required to achieve the desired revisit performance for each target through a quick and accurate accessibility analysis of various target distributions. This study revealed that three to five target clusters are more effective in improving the satellite revisit performance than a typical single target cluster, while identifying that the density of the target distribution is a significant influencing factor. Finally, the proposed model achieved the desired revisit performance, guaranteeing a timely response for 30 major disaster locations in East Asia and validating the model's optimal performance.

Research on the Cleaning Method of Unmanned Sweeper Based on Target Distribution Situation Analysis

Replacing traditional manual sweeping with unmanned sweepers in closed parks can not only greatly reduce labor costs, but also improve sweeping efficiency. Efficient path planning is the key technology for unmanned sweepers to complete the sweeping task. Existing unmanned sweepers are often based on fixed path sweeping or completely traversing the sweeping mode, this mode does not have the environmental adaptability, in the actual sweeping is often high energy cost, and sweeping is not complete. In this paper, an environment-adaptive sweeping path planning method is proposed to improve the sweeping intelligence and environmental adaptability of unmanned sweepers, reduce the energy consumption of sweeping and improve the efficiency of sweeping. Specifically, in this paper, we first use YOLOv5 to complete the accurate identification of individual garbage and obstacles in the road, and then work with LIDAR and Gaussian Mixture Model(GMM) to remove redundant targets. We also propose a Permutation Entropy(PE) value-based discrimination method to complete the target distribution posture analysis of each complex garbage pile. Finally, the traditional path planning problem is transformed into a combinatorial optimization problem of garbage areas, and a sweeping path accurate method based on Simulated Annealing(SA) algorithm is proposed. Through comprehensive theoretical analysis and simulation study, the optimality and effectiveness of the proposed method are proved by comparing A star and Coverage Path Planning(CPP) algorithms in a variety of experimental scenarios.

Bayesian model updating for bridge engineering applications based on DREAMKZS algorithm and Kriging model

The Differential Evolution Adaptive Metropolis (DREAM) based Bayesian model updating suffers from low convergence speed and high computational cost. This study proposes a Bayesian updating framework based on the DREAM and KZS strategies (DREAMKZS) assisted with the Kriging model to enhance the algorithm’s convergence speed and computational efficiency. The KZS strategies represent the Kalman-inspired proposal distribution, sampling from the past states, and snooker updates. The model updating of a numerical beam and a full-scale bridge were employed to test the DREAMKZS algorithm’s performance. The results demonstrated that DREAMKZS accelerates the chain exploration in high-dimensional target distributions and improves the convergence speed. The DREAMKZS outperforms the DREAM in achieving rapid convergence of the Markov chains while maintaining the precision of the posterior distribution. In the two case studies, the efficiency of model evaluation is improved by 3.66 times and 1.72 times, respectively. Compared with the traditional Bayesian approach without a surrogate model, the computational cost is reduced by 80.04% and 95.37%, respectively.

Improved Method for Apple Fruit Target Detection Based on YOLOv5s

Images captured using unmanned aerial vehicles (UAVs) often exhibit dense target distribution and indistinct features, which leads to the issues of missed detection and false detection in target detection tasks. To address these problems, an improved method for small target detection called YOLOv5s is proposed to enhance the detection accuracy for small targets such as apple fruits. By applying improvements to the RFA module, DFP module, and Soft-NMS algorithm, as well as integrating these three modules together, accurate detection of small targets in images can be achieved. Experimental results demonstrate that the integrated, improved model achieved a significant improvement in detection accuracy, with precision, recall, and mAP increasing by 3.6%, 6.8%, and 6.1%, respectively. Furthermore, the improved method shows a faster convergence speed and lower loss value during the training process, resulting in higher recognition accuracy. The results of this study indicate that the proposed improved method exhibits a good performance in apple fruit detection tasks involving UAV imagery, which is of great significance for fruit yield estimation. The research findings demonstrate the effectiveness and feasibility of the improved method in addressing small target detection tasks, such as apple fruit detection.

Causal Factor Disentanglement for Few-Shot Domain Adaptation in Video Prediction.

An important challenge in machine learning is performing with accuracy when few training samples are available from the target distribution. If a large number of training samples from a related distribution are available, transfer learning can be used to improve the performance. This paper investigates how to do transfer learning more effectively if the source and target distributions are related through a Sparse Mechanism Shift for the application of next-frame prediction. We create Sparse Mechanism Shift-TempoRal Intervened Sequences (SMS-TRIS), a benchmark to evaluate transfer learning for next-frame prediction derived from the TRIS datasets. We then propose to exploit the Sparse Mechanism Shift property of the distribution shift by disentangling the model parameters with regard to the true causal mechanisms underlying the data. We use the Causal Identifiability from TempoRal Intervened Sequences (CITRIS) model to achieve this disentanglement via causal representation learning. We show that encouraging disentanglement with the CITRIS extensions can improve performance, but their effectiveness varies depending on the dataset and backbone used. We find that it is effective only when encouraging disentanglement actually succeeds in increasing disentanglement. We also show that an alternative method designed for domain adaptation does not help, indicating the challenging nature of the SMS-TRIS benchmark.

Bayesian design of measurements for magnetorelaxometry imaging *

The aim of magnetorelaxometry imaging is to determine the distribution of magnetic nanoparticles inside a subject by measuring the relaxation of the superposition magnetic field generated by the nanoparticles after they have first been aligned using an external activation magnetic field that has subsequently been switched off. This work applies techniques of Bayesian optimal experimental design to (sequentially) selecting the positions for the activation coil in order to increase the value of data and enable more accurate reconstructions in a simplified measurement setup. Both Gaussian and total variation (TV) prior models are considered for the distribution of the nanoparticles. The former allows simultaneous offline computation of optimized designs for multiple consecutive activations, while the latter introduces adaptability into the algorithm by using previously measured data in choosing the position of the next activation. The TV prior has a desirable edge-enhancing characteristic, but with the downside that the computationally attractive Gaussian form of the posterior density is lost. To overcome this challenge, the lagged diffusivity iteration is used to provide an approximate Gaussian posterior model and allow the use of the standard Bayesian A- and D-optimality criteria for the TV prior as well. Two-dimensional numerical experiments are performed on a few sample targets, with the conclusion that the optimized activation positions lead, in general, to better reconstructions than symmetric reference setups when the target distribution or region of interest are nonsymmetric in shape.

Markov chain stochastic DCA and applications in deep learning with PDEs regularization

This paper addresses a large class of nonsmooth nonconvex stochastic DC (difference-of-convex functions) programs where endogenous uncertainty is involved and i.i.d. (independent and identically distributed) samples are not available. Instead, we assume that it is only possible to access Markov chains whose sequences of distributions converge to the target distributions. This setting is legitimate as Markovian noise arises in many contexts including Bayesian inference, reinforcement learning, and stochastic optimization in high-dimensional or combinatorial spaces. We then design a stochastic algorithm named Markov chain stochastic DCA (MCSDCA) based on DCA (DC algorithm) - a well-known method for nonconvex optimization. We establish the convergence analysis in both asymptotic and nonasymptotic senses. The MCSDCA is then applied to deep learning via PDEs (partial differential equations) regularization, where two realizations of MCSDCA are constructed, namely MCSDCA-odLD and MCSDCA-udLD, based on overdamped and underdamped Langevin dynamics, respectively. Numerical experiments on time series prediction and image classification problems with a variety of neural network topologies show the merits of the proposed methods.

Lévy Langevin Monte Carlo

Analogously to the well-known Langevin Monte Carlo method, in this article we provide a method to sample from a target distribution π\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varvec{\\pi }$$\\end{document} by simulating a solution of a stochastic differential equation. Hereby, the stochastic differential equation is driven by a general Lévy process which—unlike the case of Langevin Monte Carlo—allows for non-smooth targets. Our method will be fully explored in the particular setting of target distributions supported on the half-line (0,∞)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(0,\\infty )$$\\end{document} and a compound Poisson driving noise. Several illustrative examples conclude the article.

The Split Gibbs Sampler Revisited: Improvements to Its Algorithmic Structure and Augmented Target Distribution

The Split Gibbs Sampler Revisited: Improvements to Its Algorithmic Structure and Augmented Target Distribution

Comparison of Discrete Choice and Machine Learning Models for Simultaneous Modeling of Mobility Tool Ownership in Agent-Based Travel Demand Models

Individual travel behavior, such as mode choice, is determined to a distinct degree by the respective portfolio of available mobility tools, such as the number of cars, public transit pass ownership, or a carsharing membership. However, the choice of different mobility tools is interdependent, and individuals weigh alternatives against each other. This process of parallel trade-offs is currently not reflected in typically used sequential logit models of agent-based travel demand models. This study fills this research gap by applying discrete choice and neural network models on a synthetic population to model multiple mobility tool ownership simultaneously. Using data from a national household travel survey, both model types approximated the given target distributions of mobility tools more accurately than the sequence of three corresponding logit models. Owing to its greater flexibility, the tested shallow and deep neural network exhibited higher predictive accuracy than simultaneous discrete choice models. The results indicated that neural networks with only one hidden layer were more robust and easier to formulate and interpret than deep networks with three hidden layers. Finally, the flat neural network was applied to a different synthetic population resulting in equally accurate results.

Multi-Hypothesis Marginal Multi-Target Bayes Filter for a Heavy-Tailed Observation Noise

A multi-hypothesis marginal multi-target Bayes filter for heavy-tailed observation noise is proposed to track multiple targets in the presence of clutter, missed detection, and target appearing and disappearing. The proposed filter propagates the existence probabilities and probability density functions (PDFs) of targets in the filter recursion. It uses the Student’s t distribution to model the heavy-tailed non-Gaussian observation noise, and employs the variational Bayes technique to acquire the approximate distributions of individual targets. K-best hypotheses, obtained by minimizing the negative log-generalized-likelihood ratio, are used to establish the existence probabilities and PDFs of targets in the filter recursion. Experimental results indicate that the proposed filter achieves better tracking performance than other filters.

Dimension-independent spectral gap of polar slice sampling

Polar slice sampling, a Markov chain construction for approximate sampling, performs, under suitable assumptions on the target and initial distribution, provably independent of the state space dimension. We extend the aforementioned result of Roberts and Rosenthal (Stoch Model 18(2):257–280, 2002) by developing a theory which identifies conditions, in terms of a generalized level set function, that imply an explicit lower bound on the spectral gap even in a general slice sampling context. Verifying the identified conditions for polar slice sampling yields a lower bound of 1/2 on the spectral gap for arbitrary dimension if the target density is rotationally invariant, log-concave along rays emanating from the origin and sufficiently smooth. The general theoretical result is potentially applicable beyond the polar slice sampling framework.

Theoretical limits on the speed of learning inverse models explain the rate of adaptation in arm reaching tasks

An essential aspect of human motor learning is the formation of inverse models, which map desired actions to motor commands. Inverse models can be learned by adjusting parameters in neural circuits to minimize errors in the performance of motor tasks through gradient descent. However, the theory of gradient descent establishes limits on the learning speed. Specifically, the eigenvalues of the Hessian of the error surface around a minimum determine the maximum speed of learning in a task. Here, we use this theoretical framework to analyze the speed of learning in different inverse model learning architectures in a set of isometric arm-reaching tasks. We show theoretically that, in these tasks, the error surface and, thus the speed of learning, are determined by the shapes of the force manipulability ellipsoid of the arm and the distribution of targets in the task. In particular, rounder manipulability ellipsoids generate a rounder error surface, allowing for faster learning of the inverse model. Rounder target distributions have a similar effect. We tested these predictions experimentally in a quasi-isometric reaching task with a visuomotor transformation. The experimental results were consistent with our theoretical predictions. Furthermore, our analysis accounts for the speed of learning in previous experiments with incompatible and compatible virtual surgery tasks, and with visuomotor rotation tasks with different numbers of targets. By identifying aspects of a task that influence the speed of learning, our results provide theoretical principles for the design of motor tasks that allow for faster learning.

Optimal Transport-Embedded Neural Network for Fairness Transfer Problem

Research on neuromorphic computing has gained popularity in recent years. In particular, regularized embedded neural systems have been applied in several significant real-world situations, such as recommendation systems and transfer learning. This paper deals with the fairness transfer learning problem, which has been insufficiently explored. In fairness transfer settings, the source domain has limit-tagged training samples, which may lead to performance degradation in the target domain. To solve such problems, a linear data-augmentation-based optimal transport-embedded neural network is proposed in this paper. It can augment the source samples to make the distribution of the source domain balanced and can align the source and target distributions simultaneously. Moreover, the distribution of the augmented data by mixup is limited to a certain bound that can avoid the abnormal samples generated. The effectiveness of the proposed method has been demonstrated in several transfer learning tests, including regression and classification. In 1-shot and 3-shot classification tasks on the Office dataset, our method’s accuracy is 4.8 and 3.9% better, respectively, than the second-best model. Additionally, our model’s performance is about 2–3 percentage points superior to the second-best model in the OfficeHome dataset. It is simple yet effective, making it perfect for low-power edge AI applications.

Single-Agent Reinforcement Learning for Scalable Earth-Observing Satellite Constellation Operations

This work explores single-agent reinforcement learning for the multi-satellite agile Earth-observing scheduling problem. The objective of the problem is to maximize the weighted sum of imaging targets collected and downlinked while avoiding resource constraint violations on board the spacecraft. To avoid the computational complexity associated with multi-agent deep reinforcement learning while creating a robust and scalable solution, a policy is trained in a single satellite environment. This policy is then deployed on board each satellite in a Walker-delta constellation. A global set of targets is distributed to each satellite based on target access. The satellites communicate with one another to determine whether an imaging target is imaged or downlinked. Free communication, line-of-sight communication, and no communication are explored to determine how the communication assumptions and constellation design impact performance. Free communication is shown to produce the best performance, and no communication is shown to produce the worst performance. Line-of-sight communication performance is shown to depend heavily on the design of the constellation and how frequently the satellites can communicate with one another. To explore how higher-level coordination can impact performance, a centralized mixed-integer programming optimization approach to global target distribution is explored and compared to a decentralized approach. A genetic algorithm is also implemented for comparison purposes, and the proposed method is shown to achieve higher reward on average at a fraction of the computational cost.

Prefrontal Cortex Codes Representations of Target Identity and Feature Uncertainty.

Many objects in the real world have features that vary over time, creating uncertainty in how they will look in the future. This uncertainty makes statistical knowledge about the likelihood of features critical to attention demanding processes such as visual search. However, little is known about how the uncertainty of visual features is integrated into predictions about search targets in the brain. In the current study, we test the idea that regions prefrontal cortex code statistical knowledge about search targets before the onset of search. Across 20 human participants (13 female; 7 male), we observe target identity in the multivariate pattern and uncertainty in the overall activation of dorsolateral prefrontal cortex (DLPFC) and inferior frontal junction (IFJ) in advance of the search display. This indicates that the target identity (mean) and uncertainty (variance) of the target distribution are coded independently within the same regions. Furthermore, once the search display appears the univariate IFJ signal scaled with the distance of the actual target from the expected mean, but more so when expected variability was low. These results inform neural theories of attention by showing how the prefrontal cortex represents both the identity and expected variability of features in service of top-down attentional control.SIGNIFICANCE STATEMENT Theories of attention and working memory posit that when we engage in complex cognitive tasks our performance is determined by how precisely we remember task-relevant information. However, in the real world the properties of objects change over time, creating uncertainty about many aspects of the task. There is currently a gap in our understanding of how neural systems represent this uncertainty and combine it with target identity information in anticipation of attention demanding cognitive tasks. In this study, we show that the prefrontal cortex represents identity and uncertainty as unique codes before task onset. These results advance theories of attention by showing that the prefrontal cortex codes both target identity and uncertainty to implement top-down attentional control.

Variable-Length Resolvability for General Sources and Channels.

We introduce the problem of variable-length (VL) source resolvability, in which a given target probability distribution is approximated by encoding a VL uniform random number, and the asymptotically minimum average length rate of the uniform random number, called the VL resolvability, is investigated. We first analyze the VL resolvability with the variational distance as an approximation measure. Next, we investigate the case under the divergence as an approximation measure. When the asymptotically exact approximation is required, it is shown that the resolvability under two kinds of approximation measures coincides. We then extend the analysis to the case of channel resolvability, where the target distribution is the output distribution via a general channel due to a fixed general source as an input. The obtained characterization of channel resolvability is fully general in the sense that, when the channel is just an identity mapping, it reduces to general formulas for source resolvability. We also analyze the second-order VL resolvability.

Quantum image denoising: a framework via Boltzmann machines, QUBO, and quantum annealing

We investigate a framework for binary image denoising via restricted Boltzmann machines (RBMs) that introduces a denoising objective in quadratic unconstrained binary optimization (QUBO) form well-suited for quantum annealing. The denoising objective is attained by balancing the distribution learned by a trained RBM with a penalty term for derivations from the noisy image. We derive the statistically optimal choice of the penalty parameter assuming the target distribution has been well-approximated, and further suggest an empirically supported modification to make the method robust to that idealistic assumption. We also show under additional assumptions that the denoised images attained by our method are, in expectation, strictly closer to the noise-free images than the noisy images are. While we frame the model as an image denoising model, it can be applied to any binary data. As the QUBO formulation is well-suited for implementation on quantum annealers, we test the model on a D-Wave Advantage machine, and also test on data too large for current quantum annealers by approximating QUBO solutions through classical heuristics.

Faster and Lightweight: An Improved YOLOv5 Object Detector for Remote Sensing Images

In recent years, the realm of deep learning has witnessed significant advancements, particularly in object detection algorithms. However, the unique challenges posed by remote sensing images, such as complex backgrounds, diverse target sizes, dense target distribution, and overlapping or obscuring targets, demand specialized solutions. Addressing these challenges, we introduce a novel lightweight object detection algorithm based on Yolov5s to enhance detection performance while ensuring rapid processing and broad applicability. Our primary contributions include: firstly, we implemented a new Lightweight Asymmetric Detection Head (LADH-Head), replacing the original detection head in the Yolov5s model. Secondly, we introduce a new C3CA module, incorporating the Coordinate Attention mechanism, strengthening the network’s capability to extract precise location information. Thirdly, we proposed a new backbone network, replacing the C3 module in the Yolov5s backbone with a FasterConv module, enhancing the network’s feature extraction capabilities. Additionally, we introduced a Content-aware Feature Reassembly (content-aware reassembly of features) (CARAFE) module to reassemble semantic similar feature points effectively, enhancing the network’s detection capabilities and reducing the model parameters. Finally, we introduced a novel XIoU loss function, aiming to improve the model’s convergence speed and robustness during training. Experimental results on widely used remote sensing image datasets such as DIOR, DOTA, and SIMD demonstrate the effectiveness of our proposed model. Compared to the original Yolov5s algorithm, we achieved a mean average precision (mAP) increase of 3.3%, 6.7%, and 3.2%, respectively. These findings underscore the superior performance of our proposed model in remote sensing image object detection, offering an efficient, lightweight solution for remote sensing applications.

REIN: Reliability Estimation via Importance sampling with Normalizing flows

We introduce a novel framework called REIN: Reliability Estimation by learning an Importance sampling (IS) distribution with Normalizing flows (NFs). The NFs learn probability space maps that transform the probability distribution of the input random variables into a quasi-optimal IS distribution. NFs stack together invertible neural networks to construct differentiable bijections with efficiently computed Jacobian determinants. The NF ‘pushes forward’ a realization from the input probability distribution into a realization from the IS distribution, with importance weights calculated using the change of variables formula. We also propose a loss function to learn a NF map that minimizes the reverse Kullback–Leibler divergence between the ‘pushforward’ distribution and a sequentially updated target distribution obtained by modifying the optimal IS distribution. We demonstrate REIN’s efficacy on a set of benchmark problems that feature very low failure rates, multiple failure modes and high dimensionality, while comparing against other variance reduction methods. We also consider two simple applications, the reliability analyses of a thirty-four story building and a cantilever tube, to demonstrate the applicability of REIN to practical problems of interest. As compared to other methods, REIN is shown to be useful for high-dimensional reliability estimation problems with very small failure probabilities.