Search Results (308)

The paper presents an approach to solving the problem of unknown motion parameters Bayesian identification for the stochastic dynamic system model with randomly delayed observations. The system identification and the object tracking tasks obtain solutions in the form of recurrent Bayesian relations for a posteriori probability density. These relations are not practically applicable due to the computational challenges they present. For practical implementation, we propose a conditionally minimax nonlinear filter that implements the concept of conditionally optimal estimation. The random delays model source is the area of autonomous underwater vehicle control. The paper discusses in detail a computational experiment based on a model that is closely aligned with this practical need. The discussion includes both a description of the filter synthesis features based on the geometric interpretation of the simulated measurements and an impact analysis of the effectiveness of model special factors, such as time delays and model unknown parameters. Furthermore, the paper puts forth a novel approach to the identification problem statement, positing a random jumping change in the motion parameters values. Full article

Machine learning-based source range estimation is a promising method for enhancing the performance of tracking both the dynamic and static positions of targets in the underwater acoustic environment using extensive training data. This study constructed a machine learning model for source range estimation using ship-radiated noise recorded by two vertical line arrays (VLAs) during the Shallow-water Acoustic Variability Experiment (SAVEX-15), employing the Sample Covariance Matrix (SCM) and the Generalized Cross Correlation (GCC) as input features. A feed-forward neural network (FNN) was used to train the model on the acoustic characteristics of the source at various distances, and the range estimation results indicated that the SCM outperformed the GCC with lower error rates. Additionally, array tilt correction using the array invariant-based method improved range estimation accuracy. The impact of the training data composition corresponding to the bottom depth variation between the source and receivers on range estimation performance was also discussed. Furthermore, the estimated ranges from the two VLA locations were applied to localization using trilateration. Our results confirm that the SCM is the more appropriate feature for the FNN-based source range estimation model compared with the GCC and imply that ocean environment variability should be considered in developing a general-purpose machine learning model for underwater acoustics. Full article

The potential of RNA-based liquid biopsy is increasingly being recognized in diffuse large B-cell lymphoma (DLBCL), the most common subtype of non-Hodgkin’s lymphoma. This study explores the cell-free transcriptome in a humanized DLBCL patient-derived tumor xenograft (PDTX) model. Blood plasma samples (n = 171) derived from a DLBCL PDTX model, including 27 humanized (HIS) PDTX, 8 HIS non-PDTX, and 21 non-HIS PDTX non-obese diabetic (NOD)-scid IL2Rgnull (NSG) mice were collected during humanization, xenografting, treatment, and sacrifice. The mice were treated with either rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP), CD20-targeted human IFNα2-based AcTaferon combined with CHOP (huCD20-Fc-AFN-CHOP), or phosphate-buffered saline (PBS). RNA was extracted using the miRNeasy serum/plasma kit and sequenced on the NovaSeq 6000 platform. RNA sequencing data of the formalin-fixed paraffin-embedded (FFPE) tissue and blood plasma samples of the original patient were included. Flow cytometry was performed on immune cells isolated from whole blood, spleen, and bone marrow. Bulk deconvolution was performed using the Tabula Sapiens v1 basis matrix. Both R-CHOP and huCD20-Fc-AFN-CHOP were able to control tumor growth in most mice. Xenograft tumor volume was strongly associated with circulating tumor RNA (ctRNA) concentration (p < 0.001, R = 0.89), as well as with the number of detected human genes (p < 0.001, R = 0.79). Abundance analysis identified tumor-specific biomarkers that were dynamically tracked during tumor growth or treatment. An 8-gene signature demonstrated high accuracy for assessing therapy response (AUC 0.92). The tumoral gene detectability in the ctRNA of the PDTX-derived plasma was associated with RNA abundance levels in the patient’s tumor tissue and blood plasma (p < 0.001), confirming that tumoral gene abundance contributes to the cell-free RNA (cfRNA) profile. Decomposing the transcriptome, however, revealed high inter- and intra-mouse variability, which was lower in the HIS PDTX mice, indicating an impact of human engraftment on the stability and profile of cfRNA. Immunochemotherapy resulted in B cell depletion, and tumor clearance was reflected by a decrease in the fraction of human CD45+ cells. Lastly, bulk deconvolution provided complementary biological insights into the composition of the tumor and circulating immune system. In conclusion, the blood plasma-derived transcriptome serves as a biomarker source in a preclinical PDTX model, enables the assessment of biological pathways, and enhances the understanding of cfRNA dynamics. Full article

Interrupted and multi-source track segment association (TSA) are two key challenges in target trajectory research within radar data processing. Traditional methods often rely on simplistic assumptions about target motion and statistical techniques for track association, leading to problems such as unrealistic assumptions, susceptibility to noise, and suboptimal performance limits. This study proposes a unified framework to address the challenges of associating interrupted and multi-source track segments by measuring trajectory similarity. We present TSA-cTFER, a novel network utilizing contrastive learning and TransFormer Encoder to accurately assess trajectory similarity through learned Representations by computing distances between high-dimensional feature vectors. Additionally, we tackle dynamic association scenarios with a two-stage online algorithm designed to manage tracks that appear or disappear at any time. This algorithm categorizes track pairs into easy and hard groups, employing tailored association strategies to achieve precise and robust associations in dynamic environments. Experimental results on real-world datasets demonstrate that our proposed TSA-cTFER network with the two-stage online algorithm outperforms existing methods, achieving 94.59% accuracy in interrupted track segment association tasks and 94.83% in multi-source track segment association tasks. Full article

This study utilized the WRF model to investigate the track evolution and rapid intensification (RI) of Typhoon Doksuri (2023) as it moved across the Luzon Strait and through the South China Sea (SCS). The simulation results indicate that Doksuri has a smaller track sensitivity to the use of different physics schemes, while having a greater intensity sensitivity. Sensitivity numerical experiments with different physics schemes can well capture its northwestward movement in the first two days, but they predict less westward track deflection as the typhoon moves across the Luzon Strait and through the SCS. Moreover, all the experiments successfully simulated Doksuri’s RI, albeit with quite different rates and a time lag of 12 h. Among different combinations of physics schemes, there exists an optimal set of cumulus parameterization and cloud microphysics schemes for track and intensity predictions. Doksuri’s track changes as the typhoon moved across the Luzon Strait and through the SCS were influenced by the topographic effects of the terrain of the Philippines and Taiwan, to different extents. The track changes of Doksuri are explained by the wavenumber-one potential vorticity (PV) tendency budget from different physical processes, highlighting that the horizontal PV advection dominates the PV tendency throughout most of the simulation time due to the offset of vertical PV advection and differential diabatic heating. In addition, this study applies the extended Sawyer–Eliassen (SE) equation to compare the transverse circulations of the typhoon induced by various forcing sources. The SE solution indicates that radial inflow was largely driven in the lower-tropospheric vortex by strong diabatic heating, while being significantly enhanced in the lower boundary layer due to turbulent friction. All other physical forcing terms were relatively insignificant for the induced transverse circulation. The coordinated radial inflow at low levels may have led to the eyewall development in unbalanced dynamics. Intense diabatic heating thus was vital to the severe RI of Doksuri under a weak vertical wind shear. Full article

Cross-domain dialogue state tracking (DST) focuses on using labeled data from source domains to train a DST model for target domains. It is of great significance for transferring a dialogue system into new domains. Most of the existing cross-domain DST models track each slot independently, which leads to poor performances caused by not considering the correlation among different slots, as well as low efficiency of training and inference. This paper, therefore, proposes a prompt-based end-to-end cross-domain DST method for efficiently tracking all slots simultaneously. A dynamic prompt template shuffle method is proposed to alleviate the bias of the slot order, and a dynamic prompt template sampling method is proposed to alleviate the bias of the slot number, respectively. The experimental results on the MultiWOZ 2.0 and MultiWOZ 2.1 datasets show that our approach consistently outperforms the state-of-the-art baselines in all target domains and improves both training and inference efficiency by at least 5 times. Full article

As electricity demand increases, especially in transportation, renewable sources such as solar energy become more important. The direct integration of solar energy in rail transportation mostly involves utilizing station roofs and track side spaces. This paper proposes a novel approach by proposing the integration of photovoltaic systems directly on the roofs of trains to generate clean electricity and reduce dependence on the main grid. Installing solar photovoltaic (PV) systems on train rooftops can reduce energy costs and emissions and develop a more sustainable and ecological rail transport system. This research focuses on the Milan Cadorna-Saronno railway line, examining the feasibility of installing PV panels onto train rooftops to generate power for the train’s internal consumption, including lighting and air conditioning. In addition, it is a solution to reduce the power absorbed by the train from the main supply. Simulations conducted using PVSOL software 2023 (R7) indicate that equipping a train roof with PV panels could supply up to almost 10% of the train’s auxiliary power needs, equating to over 600 MWh annually. Implementing the suggested system may also result in a decrease of more than 27 tons of CO₂ emissions per year for one train. To optimize the performance of PV systems and maximize power output, the gravitational search algorithm (GSA) as an evolutionary-based method is proposed alongside a DC/DC boost converter and its performance is compared with two other main maximum power point tracking (MPPT) methods of perturb and observe (PO), and incremental conductance (INC). The accuracy of the suggested algorithm was confirmed utilizing MATLAB SIMULINK R2023b, and the results were compared with those of the PO and INC algorithms. The findings indicate that the GSA performs better in terms of accuracy, while the PO and INC algorithms demonstrate greater robustness and dynamic response. Full article

The integration of vehicle-to-grid (V2G) technology into smart energy management systems represents a significant advancement in the field of energy suppliers for Industry 4.0. V2G systems enable a bidirectional flow of energy between electric vehicles and the power grid and can provide ancillary services to the grid, such as peak shaving, load balancing, and emergency power supply during power outages, grid faults, or periods of high demand. In this context, reliable prediction of the availability of V2G as an energy source in the grid is fundamental in order to optimize both grid stability and economic returns. This requires both an accurate modeling framework that includes the integration and pre-processing of readily accessible data and a prediction phase over different time horizons for the provision of different time-scale ancillary services. In this research, we propose and compare two data-driven predictive modeling approaches to demonstrate their suitability for dealing with quasi-periodic time series, including those dealing with mobility data, meteorological and calendrical information, and renewable energy generation. These approaches utilize publicly available vehicle tracking data within the floating car data paradigm, information about meteorological conditions, and fuzzy weekend and holiday information to predict the available aggregate capacity with high precision over different time horizons. Two data-driven predictive modeling approaches are then applied to the selected data, and the performance is compared. The first approach is Hankel dynamic mode decomposition with control (HDMDc), a linear state-space representation technique, and the second is long short-term memory (LSTM), a deep learning method based on recurrent nonlinear neural networks. In particular, HDMDc performs well on predictions up to a time horizon of 4 h, demonstrating its effectiveness in capturing global dynamics over an entire year of data, including weekends, holidays, and different meteorological conditions. This capability, along with its state-space representation, enables the extraction of relationships among exogenous inputs and target variables. Consequently, HDMDc is applicable to V2G integration in complex environments such as smart grids, which include various energy suppliers, renewable energy sources, buildings, and mobility data. Full article

In recent years, many studies have used Siamese networks (SNs) for UAV tracking. However, there are two problems with SNs for UAV tracking. Firstly, the information sources of the SNs are the invariable template patch and the current search frame. The static template information lacks the perception of dynamic feature information flow, and the shallow feature extraction and linear sequential mapping severely limit the mining of feature expressiveness. This makes it difficult for many existing SNs to cope with the challenges of UAV tracking, such as scale variation and viewpoint change caused by the change in height and angle of the UAV, and the challenges of background clutter and occlusion caused by complex aviation backgrounds. Secondly, the SNs trackers for UAV tracking still struggle with extracting lightweight and effective features. A tracker with a heavy-weighted backbone is not welcome due to the limited computing power of the UAV platform. Therefore, we propose a lightweight spatial-temporal contextual Siamese tracking system for UAV tracking (SiamST). The proposed SiamST improves the UAV tracking performance by augmenting the horizontal spatial information and introducing vertical temporal information to the Siamese network. Specifically, a high-order multiscale spatial module is designed to extract multiscale remote high-order spatial information, and a temporal template transformer introduces temporal contextual information for dynamic template updating. The evaluation and contrast results of the proposed SiamST with many state-of-the-art trackers on three UAV benchmarks show that the proposed SiamST is efficient and lightweight. Full article

Considering the characteristics of the power system, where “the source moves with the load”, the load side is primarily responsible for the carbon emissions of the regional power grid. Consequently, users’ electricity consumption behavior has a significant impact on system carbon emissions. Therefore, this paper proposes a multi-objective bi-level optimization strategy for source-load coordination, considering dual demand responses for both electricity and carbon. The upper layer establishes a multi-objective low-carbon economic dispatch model for power grid operators, aiming to minimize the system’s total operating cost, the total direct carbon emissions of the power grid, and the disparity in regional carbon emissions. In the lower layer, a low-carbon economic dispatch model for load aggregators is established to minimize the total cost for load aggregators. To obtain the dynamic carbon emission factor signal, a complex power flow tracking method that considers the power supply path is proposed, and a carbon flow tracking model is established. NSGA-II is used to obtain the Pareto optimal frontier set for the upper model, and the ‘optimal’ scheme is determined based on the fuzzy satisfaction decision. The example analysis demonstrates that the interactive carbon reduction effect under the guidance of dual signals is the most effective. This approach fully exploits the carbon reduction potential of the flexible load, enhancing both the economic efficiency and low-carbon operation of the system. Full article

Ocean plastic pollution is one of the global environmental problems of our time. “Rubbish islands” formed in the ocean are increasing every year, damaging the marine ecosystem. In order to effectively address this type of pollution, it is necessary to accurately and quickly identify the sources of plastic entering the ocean, identify where it is accumulating, and track the dynamics of waste movement. To this end, remote sensing methods using satellite imagery and aerial photographs from unmanned aerial vehicles are a reliable source of data. Modern machine learning technologies make it possible to automate the detection of floating plastics. This review presents the main projects and research aimed at solving the “plastic” problem. The main data acquisition techniques and the most effective deep learning algorithms are described, various limitations of working with space images are analyzed, and ways to eliminate such shortcomings are proposed. Full article

Static and mobile radiation detectors can be deployed in urban environments for a range of nuclear security applications, including radiological source search-and-tracking scenarios. Modeling detector performance for such applications is challenging, as it does not depend solely on the detector capabilities themselves. Many factors must be taken into consideration, including specific source and background signatures, the topology and constraints of the deployment environment, the presence of nuisance sources, and whether detectors are mobile or static. When considering the simultaneous deployment of multiple, heterogeneous detectors, assessment of the system-wide performance requires the simulation of the individual detectors, and a system-level analysis of the detection performance. In radiological source search-and-tracking scenarios, performance is mostly dominated by the probability of encounter, which depends on the specifics of a given deployment, e.g., static vs. mobile detectors or a combination of both modalities, the number of detectors deployed, the dynamic vs. static setting of false alarm rates, and individual vs. networked operation. The Urban Deployment Model (UDM) toolset was specifically developed to cover the gap in the available generic frameworks for the simulation of radiation detector deployments at city scales. UDM provides a unified and modular framework to support the simulation and performance characterization of heterogeneous detector deployments in urban environments. This paper presents the key components along the UDM workflow. Full article

When analyzing microscopic time-lapse observations, frame alignment is an essential task to visually understand the morphological and translation dynamics of cells and tissue. While in traditional single-sample microscopy, the region of interest (RoI) is fixed, multi-sample microscopy often uses a single microscope that scans multiple samples over a long period of time by laterally relocating the sample stage. Hence, the relocation of the optics induces a statistical RoI offset and can introduce jitter as well as drift, which results in a misaligned RoI for each sample’s time-lapse observation (stage drift). We introduce a robust approach to automatically align all frames within a time-lapse observation and compensate for frame drift. In this study, we present a sub-pixel precise alignment approach based on recurrent all-pairs field transforms (RAFT); a deep network architecture for optical flow. We show that the RAFT model pre-trained on the Sintel dataset performed with near perfect precision for registration tasks on a set of ten contextually unrelated time-lapse observations containing 250 frames each. Our approach is robust for elastically undistorted and translation displaced (x,y) microscopic time-lapse observations and was tested on multiple samples with varying cell density, obtained using different devices. The approach only performed well for registration and not for tracking of the individual image components like cells and contaminants. We provide an open-source command-line application that corrects for stage drift and jitter. Full article

Accurate identification of crop phenology timing is crucial for agriculture. While remote sensing tracks vegetation changes, linking these to ground-measured crop growth stages remains challenging. Existing methods offer broad overviews but fail to capture detailed phenological changes, which can be partially related to the temporal resolution of the remote sensing datasets used. The availability of higher-frequency observations, obtained by combining sensors and gap-filling, offers the possibility to capture more subtle changes in crop development, some of which can be relevant for management decisions. One such dataset is Planet Fusion, daily analysis-ready data obtained by integrating PlanetScope imagery with public satellite sensor sources such as Sentinel-2 and Landsat. This study introduces a novel method utilizing Dynamic Time Warping applied to Planet Fusion imagery for maize phenology detection, to evaluate its effectiveness across 70 micro-stages. Unlike singular template approaches, this method preserves critical data patterns, enhancing prediction accuracy and mitigating labeling issues. During the experiments, eight commonly employed spectral indices were investigated as inputs. The method achieves high prediction accuracy, with 90% of predictions falling within a 10-day error margin, evaluated based on over 3200 observations from 208 fields. To understand the potential advantage of Planet Fusion, a comparative analysis was performed using Harmonized Landsat Sentinel-2 data. Planet Fusion outperforms Harmonized Landsat Sentinel-2, with significant improvements observed in key phenological stages such as V4, R1, and late R5. Finally, this study showcases the method’s transferability across continents and years, although additional field data are required for further validation. Full article

This study explored the impact of various label information (extrinsic attributes) and sociodemographic and attitudinal factors (intrinsic attributes) on Brazilian consumer choices, using simulated traditional and plant-based muçarela cheese as the model product. The research was conducted in two phases: the first involved a structured questionnaire assessing attitudinal dimensions such as Health Consciousness, Climate Change, Plant-based Diets, and Food Neophobia, along with sociodemographic data collection. The second phase comprised a discrete choice experiment with (n = 52) and without (n = 509) eye tracking. The term “Cheese” on labels increased choice probability by 7.6% in a general survey and 15.1% in an eye tracking study. A prolonged gaze at “Cheese” did not affect choice, while more views of “Plant-based product” slightly raised choice likelihood by 2.5%. Repeatedly revisiting these terms reduced the choice probability by 3.7% for “Cheese” and 1% for “Plant-based product”. Nutritional claims like “Source of Vitamins B6 and B12” and “Source of Proteins and Calcium” boosted choice probabilities by 4.97% and 5.69% in the general and 8.4% and 6.9% in the eye-tracking experiment, respectively. Conversely, front-of-package labeling indicating high undesirable nutrient content decreased choice by 13% for magnifying presentations and 15.6% for text. In a plant-based subsample, higher environmental concerns and openness to plant-based diets increased choice probabilities by 5.31% and 5.1%, respectively. These results highlight the complex dynamics between label information, consumer understanding, and decision-making. Full article