Search Results (46)

Ensuring the resilient navigation of unmanned aerial vehicles (UAVs) under conditions of limited or unstable sensor information is one of the key challenges of modern autonomous mobility within smart infrastructure and sustainable development. This article proposes an intelligent autonomous UAV control method based on the integration of geometric trajectory modeling, neural network-based sensor data filtering, and reinforcement learning. The geometric model, constructed using path coordinates, allows the trajectory tracking problem to be formalized as an affine control system, which ensures motion stability even in cases of partial data loss. To process noisy or fragmented GPS and IMU signals, an LSTM-based recurrent neural network filter is implemented. This significantly reduces positioning errors and maintains trajectory stability under environmental disturbances. In addition, the navigation system includes a reinforcement learning module that performs real-time obstacle prediction, path correction, and speed adaptation. The method has been tested in a simulated environment with limited sensor availability, variable velocity profiles, and dynamic obstacles. The results confirm the functionality and effectiveness of the proposed navigation system under sensor-deficient conditions. The approach is applicable to environmental monitoring, autonomous delivery, precision agriculture, and emergency response missions within smart regions. Its implementation contributes to achieving the Sustainable Development Goals (SDG 9, SDG 11, and SDG 13) by enhancing autonomy, energy efficiency, and the safety of flight operations. Full article

Maintaining stable image feature extraction under viewpoint changes is challenging, particularly when the angle between the camera’s reverse direction and the object’s surface normal exceeds 40 degrees. Such conditions can result in unreliable feature detection. Consequently, this hinders the performance of vision-based systems. To address this, we propose a feature point extraction method named Large Viewpoint Feature Extraction (LV-FeatEx). Firstly, the method uses a dual-threshold approach based on image grayscale histograms and Kapur’s maximum entropy to constrain the AGAST (Adaptive and Generic Accelerated Segment Test) feature detector. Combined with the FREAK (Fast Retina Keypoint) descriptor, the method enables more effective estimation of camera motion parameters. Next, we design a longitude sampling strategy to create a sparser affine simulation model. Meanwhile, images undergo perspective transformation based on the camera motion parameters. This improves operational efficiency and aligns perspective distortions between two images, enhancing feature point extraction accuracy under large viewpoints. Finally, we verify the stability of the extracted feature points through feature point matching. Comprehensive experimental results show that, under large viewpoint changes, our method outperforms popular classical and deep learning feature extraction methods. The correct rate of feature point matching improves by an average of 40.1 percent, and speed increases by an average of 6.67 times simultaneously. Full article

Feature point detection in inverse synthetic aperture radar (ISAR) images of space targets is the foundation for tasks such as analyzing space target motion intent and predicting on-orbit status. Traditional feature point detection methods perform poorly when confronted with the low texture and uneven brightness characteristics of ISAR images. Due to the nonlinear mapping capabilities, neural networks can effectively learn features from ISAR images of space targets, providing new ideas for feature point detection. However, the scarcity of labeled ISAR image data for space targets presents a challenge for research. To address the issue, this paper introduces a self-supervised feature point detection method (SFPD), which can accurately detect the positions of feature points in ISAR images of space targets without true feature point positions during the training process. Firstly, this paper simulates an ISAR primitive dataset and uses it to train the proposed basic feature point detection model. Subsequently, the basic feature point detection model and affine transformation are utilized to label pseudo-ground truth for ISAR images of space targets. Eventually, the labeled ISAR image dataset is used to train SFPD. Therefore, SFPD can be trained without requiring ground truth for the ISAR image dataset. The experiments demonstrate that SFPD has better performance in feature point detection and feature point matching than usual algorithms. Full article

Multi-object tracking (MOT) aims to detect objects in video sequences and associate them across frames. Currently, the mainstream research direction regarding MOT is the tracking-by-detection (TBD) framework. Tracking results are highly sensitive to detection outputs, and challenges from object occlusion and complex motion present significant obstacles in the field of MOT. To reduce dependence on detection outputs, we propose a method that integrates predictive information to improve Non-Maximum Suppression (NMS). By applying secondary modulation to the suppression scores and dynamically adjusting the suppression threshold using tracking information, our method better retains candidate boxes for occluded objects. Furthermore, to track occluding and overlapping objects more effectively, we introduce an adaptive measurement noise method that adjusts the measurement noise to mitigate the impact of object occlusion or overlap on tracking accuracy. Additionally, we enhance the affinity matrix in the association algorithm by incorporating height information, thereby improving the stability of complex moving objects. Our method outperforms the baseline model ByteTrack on the DanceTrack dataset, increasing Higher Order Tracking Accuracy (HOTA), Multi-Object Tracking Accuracy (MOTA), and the ID F1 Score (IDF1) by 10.2%, 3.0%, and 4.8%, respectively. Full article

Environmental, Social, and Governance (ESG) finance is a cornerstone of modern finance and investment, as it changes the classical return-risk view of investment by incorporating an additional dimension to investment performance: the ESG score of the investment. We define the ESG price process and include it in an extension of Bachelier’s market model in both discrete and continuous time, enabling option pricing valuation. Full article

Motion-compensated image reconstruction enables new clinical applications of Magnetic Resonance Imaging (MRI), but it relies on computationally intensive algorithms. This study focuses on the Generalized Reconstruction by Inversion of Coupled Systems (GRICS) program, applied to the reconstruction of 3D images in cases of non-rigid or rigid motion. It uses hybrid parallelization with the MPI (Message Passing Interface) and OpenMP (Open Multi-Processing). For clinical integration, the GRICS needs to efficiently harness the computational resources of compute nodes. We aim to improve the GRICS’s performance without any code modification. This work presents a performance study of GRICS on two CPU architectures: Intel Xeon Gold and AMD EPYC. The roofline model is used to study the software–hardware interaction and quantify the code’s performance. For CPU–GPU comparison purposes, we propose a preliminary MATLAB–GPU implementation of the GRICS’s reconstruction kernel. We establish the roofline model of the kernel on two NVIDIA GPU architectures: Quadro RTX 5000 and A100. After the performance study, we propose some optimization patterns for the code’s execution on CPUs, first considering only the OpenMP implementation using thread binding and affinity and appropriate architecture-compilation flags and then looking for the optimal combination of MPI processes and OpenMP threads in the case of the hybrid MPI–OpenMP implementation. The results show that the GRICS performed well on the AMD EPYC CPUs, with an architectural efficiency of 52%. The kernel’s execution was fast on the NVIDIA A100 GPU, but the roofline model reported low architectural efficiency and utilization. Full article

The range–Doppler (R–D) model is extensively employed for the geometric processing of synthetic aperture radar (SAR) images. Refining the sensor motion state and imaging parameters is the most common method for achieving high-precision geometric processing using the R–D model, comprising a process that involves numerous parameters and complex computations. In order to reduce the specialization and complexity of parameter optimization in the classic R–D model, we introduced a novel approach called ICRD (image compensation-based range–Doppler) to improve the positioning accuracy of the R–D model, implementing a low-order polynomial to compensate for the original imaging errors without altering the initial positioning parameters. We also designed low-order polynomial compensation models with different parameters. The models were evaluated on various SAR images from different platforms and bands, including spaceborne TerraSAR-X and Gaofen3-C images, manned airborne SAR-X images, and unmanned aerial vehicle-mounted miniSAR-Ku images. Furthermore, image positioning experiments involving the use of different polynomial compensation models and various numbers and distributions of ground control points (GCPs) were conducted. The experimental results demonstrate that geometric processing accuracy comparable to that of the classical rigorous positioning method can be achieved, even when applying only an affine transformation model to the images. Compared to classical refinement models, however, the proposed image-compensated R–D model is much simpler and easy to implement. Thus, this study provides a convenient, robust, and widely applicable method for the geometric-positioning processing of SAR images, offering a potential approach for the joint-positioning processing of multi-source SAR images. Full article

The substantial data volume within dynamic point clouds representing three-dimensional moving entities necessitates advancements in compression techniques. Motion estimation (ME) is crucial for reducing point cloud temporal redundancy. Standard block-based ME schemes, which typically utilize the previously decoded point clouds as inter-reference frames, often yield inaccurate and translation-only estimates for dynamic point clouds. To overcome this limitation, we propose an advanced patch-based affine ME scheme for dynamic point cloud geometry compression. Our approach employs a forward-backward jointing ME strategy, generating affine motion-compensated frames for improved inter-geometry references. Before the forward ME process, point cloud motion analysis is conducted on previous frames to perceive motion characteristics. Then, a point cloud is segmented into deformable patches based on geometry correlation and motion coherence. During the forward ME process, affine motion models are introduced to depict the deformable patch motions from the reference to the current frame. Later, affine motion-compensated frames are exploited in the backward ME process to obtain refined motions for better coding performance. Experimental results demonstrate the superiority of our proposed scheme, achieving an average 6.28% geometry bitrate gain over the inter codec anchor. Additional results also validate the effectiveness of key modules within the proposed ME scheme. Full article

This paper aims to provide an effective method for pricing forward starting options under the double fractional stochastic volatilities mixed-exponential jump-diffusion model. The value of a forward starting option is expressed in terms of the expectation of the forward characteristic function of log return. To obtain the forward characteristic function, we approximate the pricing model with a semimartingale by introducing two small perturbed parameters. Then, we rewrite the forward characteristic function as a conditional expectation of the proportion characteristic function which is expressed in terms of the solution to a classic PDE. With the affine structure of the approximate model, we obtain the solution to the PDE. Based on the derived forward characteristic function and the Fourier transform technique, we develop a pricing algorithm for forward starting options. For comparison, we also develop a simulation scheme for evaluating forward starting options. The numerical results demonstrate that the proposed pricing algorithm is effective. Exhaustive comparative experiments on eight models show that the effects of fractional Brownian motion, mixed-exponential jump, and the second volatility component on forward starting option prices are significant, and especially, the second fractional volatility is necessary to price accurately forward starting options under the framework of fractional Brownian motion. Full article

Convolutional neural networks (CNNs) have become instrumental in advancing multi-frame image super-resolution (SR), a technique that merges multiple low-resolution images of the same scene into a high-resolution image. In this paper, a novel deep learning multi-frame SR algorithm is introduced. The proposed CNN model, named Exponential Fusion of Interpolated Frames Network (EFIF-Net), seamlessly integrates fusion and restoration within an end-to-end network. Key features of the new EFIF-Net include a custom exponentially weighted fusion (EWF) layer for image fusion and a modification of the Residual Channel Attention Network for restoration to deblur the fused image. Input frames are registered with subpixel accuracy using an affine motion model to capture the camera platform motion. The frames are externally upsampled using single-image interpolation. The interpolated frames are then fused with the custom EWF layer, employing subpixel registration information to give more weight to pixels with less interpolation error. Realistic image acquisition conditions are simulated to generate training and testing datasets with corresponding ground truths. The observation model captures optical degradation from diffraction and detector integration from the sensor. The experimental results demonstrate the efficacy of EFIF-Net using both simulated and real camera data. The real camera results use authentic, unaltered camera data without artificial downsampling or degradation. Full article

Breast cancer (BC) remains the most common cancer among women worldwide, and estrogen receptor-α expression is a critical diagnostic factor for BC. Estrogen receptor (ER-α36) is a dominant-negative effector of ER-α66-mediated estrogen-responsive gene pathways. ER-α36 is a novel target that mediates the non-genomic estrogen signaling pathway. However, the crystallized structure of ER-α36 remains unavailable for molecular studies. ER-positive and triple-negative BC tumors aggressively resist the FDA-approved drugs; therefore, highly potent structure-based inhibitors with preeminent benefits over toxicity will preferably replace the current BC treatment. Broussoflanol B (BFB), a B. papyrifera bark compound, exhibits potent growth inhibitory activity in ER-negative BC cells by inducing cell cycle arrest. For the first time, we unravel the comparative dynamic events of the enzymes’ structures and the binding mechanisms of BFB when bound to the ER-α36 and ER-α66 ligand-binding domain using an all-atom molecular dynamics simulations approach and MM/PBSA-binding-free energy calculations. The dynamic findings have revealed that ER-α36 and ER-α66 LBD undergo timescale “coiling”, opening and closing conformations favoring the high-affinity BFB-bound ER-α36 (ΔG = −52.57 kcal/mol) compared to the BFB-bound ER-α66 (ΔG = −42.41 kcal/mol). Moreover, the unbound (1.260 Å) and bound ER-α36 (1.182 Å) exhibit the highest flexibilities and atomistic motions relative to the ER-α66 systems. The RMSF (Å) of the unbound ER-α36 and ER-α66 exhibit lesser stabilities than the BFB-bound systems, resulting in higher structural flexibilities and atomistic motions than the bound variants. These findings present a model that describes the mechanisms by which the BFB compound induces downregulation-accompanied cell cycle arrest at the Gap₀ and Gap₁ phases. Full article

The floating platform motion of an offshore wind turbine system can exacerbate output power fluctuations and increase fatigue loads. This paper proposes a new scheme based on a fast second-order sliding mode (SOSM) control and an adaptive super-twisting extended state observer to suppress the platform motion and power fluctuation. Firstly, an affine nonlinear model of the floating wind turbine pitch system is constructed. Then, a fast SOSM pitch control law is adopted to adjust the blade pitch angle, and a new adaptive super-twisting extended state observer is constructed to achieve total disturbance observation. Finally, simulations are conducted under two cases of wind and wave conditions based on FAST (fatigue, aerodynamics, structures, and turbulence) and MATLAB/Simulink. Compared with the traditional proportional integral (PI) control scheme and standard super-twisting control scheme, the platform roll under the proposed scheme is reduced by 13% and 4%, and pitch is reduced by 16% and 3% in Case 1. Correspondingly, the roll is reduced by 9% and 15%, and pitch is reduced by 7% and 1% in Case 2. For the tower top pitch and yaw moment, load reductions of 7% and 3% or more are achievable compared with those under the PI control scheme. It is indicated that the proposed scheme is more effective in suppressing floating platform motion, stabilizing output power of the wind turbine system, and reducing tower loads. Full article

Global motion greatly increases the number of false alarms for object detection in video sequences against dynamic backgrounds. Therefore, before detecting the target in the dynamic background, it is necessary to estimate and compensate the global motion to eliminate the influence of the global motion. In this paper, we use the SURF (speeded up robust features) algorithm combined with the MSAC (M-Estimate Sample Consensus) algorithm to process the video. The global motion of a video sequence is estimated according to the feature point matching pairs of adjacent frames of the video sequence and the global motion parameters of the video sequence under the dynamic background. On this basis, we propose an inverse transformation model of affine transformation, which acts on each adjacent frame of the video sequence in turn. The model compensates the global motion, and outputs a video sequence after global motion compensation from a specific view for object detection. Experimental results show that the algorithm proposed in this paper can accurately perform motion compensation on video sequences containing complex global motion, and the compensated video sequences achieve higher peak signal-to-noise ratio and better visual effects. Full article

Multiple object tracking (MOT), as a core technology for environment perception in autonomous driving, has attracted attention from researchers. Combing the advantages of batch global optimization, we present a novel online MOT framework for autonomous driving, consisting of feature extraction and data association on a temporal window. In the feature extraction stage, we design a three-channel appearance feature extraction network based on metric learning by using ResNet50 as the backbone network and the triplet loss function and employ a Kalman Filter with a constant acceleration motion model to optimize and predict the object bounding box information, so as to obtain reliable and discriminative object representation features. For data association, to reduce the ID switches, the min-cost flow of global association is introduced within the temporal window composed of consecutive multi-frame images. The trajectories within the temporal window are divided into two categories, active trajectories and inactive trajectories, and the appearance, motion affinities between each category of trajectories, and detections are calculated, respectively. Based on this, a sparse affinity network is constructed, and the data association is achieved using the min-cost flow problem of the network. Qualitative experimental results on KITTI MOT public benchmark dataset and real-world campus scenario sequences validate the effectiveness and robustness of our method. Compared with the homogeneous, vision-based MOT methods, quantitative experimental results demonstrate that our method has competitive advantages in terms of higher order tracking accuracy, association accuracy, and ID switches. Full article

(1) Background: SARS-CoV-2 RNA-dependent RNA polymerase (RdRp) is a promising therapeutic target to fight COVID-19, and many RdRp inhibitors nucleotide/nucleoside analogs, such as remdesivir, have been identified or are in clinical studies. However, the appearance of resistant mutations could reduce their efficacy. In the present work, we structurally evaluated the impact of RdRp mutations found at baseline in 39 patients treated with remdesivir and associated with a different degree of antiviral response in vivo. (2) Methods: A refined bioinformatics approach was applied to assign SARS-CoV-2 clade and lineage, and to define RdRp mutational profiles. In line with such a method, the same mutations were built and analyzed by combining docking and thermodynamics evaluations with both molecular dynamics and representative pharmacophore models. (3) Results: Clinical studies revealed that patients bearing the most prevalent triple mutant P323L+671S+M899I, which was present in 41% of patients, or the more complex mutational profile P323L+G671S+L838I+D738Y+K91E, which was found with a prevalence of 2.6%, showed a delayed reduced response to remdesivir, as confirmed by the increase in SARS-CoV-2 viral load and by a reduced theoretical binding affinity versus RdRp (ΔGbind_WT = −122.70 kcal/mol; ΔGbind_{P323L+671S+M899I} = −84.78 kcal/mol; ΔGbind_{P323L+G671S+L838I+D738Y+K91E} = −96.74 kcal/mol). Combined computational approaches helped to rationalize such clinical observations, offering a mechanistic understanding of the allosteric effects of mutants on the global motions of the viral RNA synthesis machine and in the changes of the interactions patterns of remdesivir during its binding. Full article