Search Results (1,252)

In computer vision tasks, the ability to remove rain from a single image is a crucial element to enhance the effectiveness of subsequent high-level tasks in rainy conditions. Recently, numerous data-driven single-image deraining techniques have emerged, primarily relying on paired images (i.e., in a supervised manner). However, when dealing with real deraining tasks, it is common to encounter unpaired images. In such scenarios, removing rain streaks in an unsupervised manner becomes a challenging task, as there are no constraints between images, resulting in suboptimal restoration results. In this paper, we introduce a new unsupervised single-image deraining method called SE-RRACycleGAN, which does not require a paired dataset for training and can effectively leverage the constrained transfer learning capability and cyclic structures inherent in CycleGAN. Since rain removal is closely associated with the analysis of texture features in an input image, we proposed a novel recurrent rain attentive module (RRAM) to enhance rain-related information detection by simultaneously considering both rainy and rain-free images. We also utilize the squeeze-and-excitation enhancement technique to the generator network to effectively capture spatial contextual information among channels. Finally, content loss is introduced to enhance the visual similarity between the input and generated images. Our method excels at removing numerous rain streaks, preserving a smooth background, and closely resembling the ground truth compared to other approaches, based on both quantitative and qualitative results, without the need for paired training images. Extensive experiments on synthetic and real-world datasets demonstrate that our approach shows superiority over most unsupervised state-of-the-art techniques, particularly on the Rain12 dataset (achieving a PSNR of 34.60 and an SSIM of 0.954) and real rainy images (achieving a PSNR of 34.17 and an SSIM of 0.953), and is highly competitive when compared to supervised methods. Moreover, the performance of our model is evaluated using RMSE, FSIM, MAE, and the correlation coefficient, achieving remarkable results that indicate a high degree of accuracy in rain removal and strong preservation of the original image’s structural details. Full article

Standard endovascular aortic repair (EVAR) has become the standard of care for treating infrarenal abdominal aortic aneurysms (AAAs) in patients with favorable anatomies, while patients with challenging AAA anatomies, and those with suprarenal or thoraco-abdominal aneurysms, still need alternative, more complex, solutions, including custom-made branched or fenestrated grafts, which are constrained by production delay and costs. To address urgent needs and complex cases, physicians have proposed modifying standard endografts by manually creating graft fenestrations. This allows for effective aneurysm exclusion and satisfactory patency of visceral vessels. Although physician-modified grafts (PMEGs) have demonstrated high technical success, standardized creation processes and long-term safety data are still lacking, necessitating further study to validate their clinical and legal standing. The aim of this article is to illustrate the state of the art with regard to this surgical technique, summarizing its origin, evolution, and the main clinical evidence supporting its effectiveness. The paper also aims to discuss the main medico-legal issues related to the use of PMEGs, with particular reference to the issue of safety related to the standardization of the surgical technique, medical liability profiles, and informed consent. Full article

This study considers the problem of controlling multi-unmanned aerial vehicles (UAVs) to consistently track a non-cooperative ground target with uncertain motion in a hostile environment with obstacles. An active information acquisition (AIA) problem is formulated to minimize the uncertainty of the target tracking task. The uncertain motion of the target is represented as a Wiener process. First, we optimize the configuration of the UAV swarm considering the collision avoidance, horizontal field of view (HFOV), and communication radius to calculate the reference trajectories of the UAVs. Next, a novel algorithm called Constrained Iterative Linear Quadratic Gaussian (CILQG) is introduced to track the reference trajectory. The target’s state with uncertainty and the UAV state are described as beliefs. The CILQG algorithm utilizes the Unscented Transform to propagate the belief regarding the UAVs’ motions, while also accounting for the impact of navigation errors on the target tracking process. The estimation error of the target position of the proposed method is under 4 m, and the error of tracking the reference trajectories is under 3 m. The estimation error remains unchanged even in the presence of obstacles. Therefore, this approach effectively deals with the uncertainties involved and ensures accurate tracking of the target. Full article

Underwater vehicles heavily depend on the integration of inertial navigation with Doppler Velocity Log (DVL) for fusion-based localization. Given the constraints imposed by sensor costs, ensuring the optimization ability and robustness of fusion algorithms is of paramount importance. While filtering-based techniques such as Extended Kalman Filter (EKF) offer mature solutions to nonlinear problems, their reliance on linearization approximation may compromise final accuracy. Recently, Invariant EKF (IEKF) methods based on the concept of smooth manifolds have emerged to address this limitation. However, the optimization by matrix Lie groups must satisfy the “group affine” property to ensure state independence, which constrains the applicability of IEKF to high-precision positioning of underwater multi-sensor fusion. In this study, an alternative state-independent underwater fusion invariant filtering approach based on a two-frame group utilizing DVL, Inertial Measurement Unit (IMU), and Earth-Centered Earth-Fixed (ECEF) configuration is proposed. This methodology circumvents the necessity for group affine in the presence of biases. We account for inertial biases and DVL pole-arm effects, achieving convergence in an imperfect IEKF by either fixed observation or body observation information. Through simulations and real datasets that are time-synchronized, we demonstrate the effectiveness and robustness of the proposed algorithm. Full article

Conventional chiral metasurfaces are constrained by predetermined functionalities and have limited versatility. To address these constraints, we propose a novel chirality-switchable terahertz (THz) metasurface with integrated heating control circuits tailored for spin-selective anomalous reflection, leveraging the phase-change material vanadium dioxide (VO₂). The reversible and abrupt insulator-to-metal phase transition feature of VO₂ is exploited to facilitate a chiral meta-atom with spin-selectivity capabilities. By employing the Pancharatnam–Berry phase principle, complete 2$\pi$ reflection phase coverage is achieved by adjusting the orientation of the chiral structure. At the resonant frequency of 0.137 THz, the designed metasurface achieves selective absorption of a circularly polarized wave corresponding to the state of the VO₂ patches. Concurrently, it reflects the circularly polarized wave of the opposite chirality anomalously at an angle of 28.4° while maintaining its handedness. This chirality-switchable THz metasurface exhibits promising potential across various applications, including wireless communication data capacity enlargement, polarization modulation, and chirality detection. Full article

Addressing the limitation of traditional deep learning models in capturing the spatio-temporal characteristics of flight data and the constrained prediction accuracy due to sequence length in aero-engine life prediction, this study proposes an aero-engine remaining life prediction approach integrating a kernel slow feature analysis, a Gaussian mixture model, and an improved Autoformer model. Initially, the slow degradation features of gas path performance parameters over time are extracted through kernel slow feature analysis, followed by the establishment of a Gaussian mixture model to create a health state representation using Bayesian inferred distances for quantifying the aero-engine’s health status. Moreover, a spatial attention mechanism is introduced alongside the autocorrelation mechanism of the Autoformer model to augment the global feature extraction capacity. Additionally, a multilayer perceptron is employed to further elucidate the degradation trends, which enhances the model’s learning and predictive capabilities for extended sequences. Subsequently, experiments are conducted using authentic aero-engine operational data, comparing the proposed method with the standard Autoformer and Transformer models. The results demonstrate that the proposed method outperforms both models in swiftly and accurately predicting the remaining life of aero-engines with robustness and high prediction accuracy. Full article

To protect forest land from loss and mitigate the global climate crisis, China has proposed a stringent natural forest protection plan, known as China’s natural forest logging ban (NFLB). This policy aims to halt the over-exploitation of natural forests, restore forest ecosystem functions, and promote regional green economic development. This study uses a regression discontinuity design (RDD) model to quantitatively and comprehensively assess the effectiveness of this policy in the key state-owned forest regions in Northeast China. Additionally, it analyzes the heterogeneity and structural characteristics of the policy’s effects on the internal composition of ecological and economic systems. The empirical results are as follows: (1) Ecological and economic impacts: The policy has successfully achieved its ecological objectives by significantly enhancing the quality and value of ecosystem services. However, it has also had a notable adverse impact on economic development, particularly in the timber supply sector, reducing the conversion efficiency of ecosystem service values into economic benefits. (2) Structural analysis: The logging ban effectively promoted the value of various ecosystem services, particularly enhancing regulatory and support functions, with a LATE estimate of approximately 8.47 units. The implementation of the policy caused a negative growth in the output value of supply-oriented ecological products, and the significance level was lower than 0.1. Conversely, the LATE estimates for different types of GDP indicate a negative growth in supply-type GDP due to the policy, with p < 0.1. (3) Heterogeneity: On the one hand, a simplistic and singular approach to logging prohibition may constrain the efficiency of enhancing ecosystem service values. On the other hand, although the policy disrupted the majority of traditional forest enterprise operations, business models focusing on quality and technology improvements were able to mitigate this impact. Full article

Synthetic Aperture Radar (SAR) is renowned for its all-weather and all-time imaging capabilities, making it invaluable for ship target recognition. Despite the advancements in deep learning models, the efficiency of Convolutional Neural Networks (CNNs) in the frequency domain is often constrained by memory limitations and the stringent real-time requirements of embedded systems. To surmount these obstacles, we introduce the Split_ Composite method, an innovative convolution acceleration technique grounded in Fast Fourier Transform (FFT). This method employs input block decomposition and a composite zero-padding approach to streamline memory bandwidth and computational complexity via optimized frequency-domain convolution and image reconstruction. By capitalizing on FFT’s inherent periodicity to augment frequency resolution, Split_ Composite facilitates weight sharing, curtailing both memory access and computational demands. Our experiments, conducted using the OpenSARShip-4 dataset, confirm that the Split_ Composite method upholds high recognition precision while markedly enhancing inference velocity, especially in the realm of large-scale data processing, thereby exhibiting exceptional scalability and efficiency. When juxtaposed with state-of-the-art convolution optimization technologies such as Winograd and TensorRT, Split_ Composite has demonstrated a significant lead in inference speed without compromising the precision of recognition. Full article

Integrated geochemical, U-Pb zircon, and Pb isotopic data from granitoids of the Wulandele porphyry molybdenum deposit, northeastern Inner Mongolia, are reported to disclose the possible magmatic process and Mo ore-forming process. LA-ICP-MS zircon U-Pb dating constrains the timing of the quartz diorite and monzonitic granite to 282 ± 2.4 Ma and 135.4 ± 2.1 Ma, respectively. The ages are accordant with geological facts which state that the shallow Permian granitoids are only the ore-hosting rock while the concealed Cretaceous fine-grained granite is the causative intrusion. Whole-rock geochemical data show that the granitoids belong to the high-K calc-alkaline series, and are enriched in LILEs, but depleted in HSFEs. Permian granitoids exhibit I-type characteristics, while Cretaceous granite is akin to A-type granite. Pb isotopic ratios are consistent between Permian granitoids and Cretaceous granite with ratios of ²⁰⁶Pb/²⁰⁴Pb = 18.048–18.892, ²⁰⁷Pb/²⁰⁴Pb = 15.488–15.571, and ²⁰⁸Pb/²⁰⁴Pb = 37.066–38.441. Considering geological and geochemical features together, Permian granitoids are interpreted as subduction-related continental margin high-K calc-alkaline rocks, while Cretaceous granite may be the result of the remelting of the relic Permian arc in an extensional environment induced by the rollback of the Paleo-Pacific plate. Different from classical porphyry-type deposits, the Wulandele Mo deposit, which formed in an intraplate tectonic setting, indicates that the intraplate porphyry Mo deposit should be one of the important exploration targets in the Central Asian Orogenic Belt, especially its eastern segment. Full article

Disturbances in the aviation environment can compromise the stability of the aviation optoelectronic stabilization platform. Traditional methods, such as the proportional integral adaptive robust (PI + ARC) control algorithm, face a challenge: once high-frequency disturbances are introduced, their effectiveness is constrained by the control system’s bandwidth, preventing further stability enhancement. A state equalizer speed closed-loop control algorithm is proposed, which combines proportional integral adaptive robustness with state equalizer (PI + ARC + State equalizer) control algorithm. This new control structure can suppress high-frequency disturbances caused by mechanical resonance, improve the bandwidth of the control system, and further achieve fast convergence and stability of the PI + ARC algorithm. Experimental results indicate that, in comparison to the control algorithm of PI + ARC, the inclusion of a state equalizer speed closed-loop compensation in the model significantly increases the closed-loop bandwidth by 47.6%, significantly enhances the control system’s resistance to disturbances, and exhibits robustness in the face of variations in the model parameters and feedback sensors of the control object. In summary, integrating a state equalizer speed closed-loop with PI + ARC significantly enhances the suppression of high-frequency disturbances and the performance of control systems. Full article

Organic room temperature afterglow (ORTA) can be categorized into two key mechanisms: continuous thermally activated delayed fluorescence (TADF) and room-temperature phosphorescence (RTP), both of which involve a triplet excited state. However, triplet excited states are easily quenched by non-radiative transitions due to oxygen and molecular vibrations. Solid-phase systems provide a conducive environment for triplet excitons due to constrained molecular motion and limited oxygen permeation within closely packed molecules. The stimulated triplet state tends to release energy through radiative transitions. Despite numerous reports on RTP in solid-phase systems in recent years, the complexity of these systems precludes the formulation of a universal theory to elucidate the underlying principles. Several strategies for achieving ORTA luminescence in the solid phase have been developed, encompassing crystallization, polymer host-guest doping, and small molecule host-guest doping. Many of these systems exhibit luminescent responses to various physical stimuli, including light stimulation, mechanical stimuli, and solvent vapor exposure. The appearance of these intriguing luminescent phenomena in solid-phase systems underscores their significant potential applications in areas such as light sensing, biological imaging, and information security. Full article

This evaluation of deep learning and traditional machine learning methods for tool state recognition in milling processes aims to automate furniture manufacturing. It compares the performance of long short-term memory (LSTM) networks, support vector machines (SVMs), and boosting ensemble decision trees, utilizing sensor data from a CNC machining center. These methods focus on the challenges and importance of feature selection, data preprocessing, and the application of tailored machine learning models to specific industrial tasks. Results show that SVM, with an accuracy of 96%, excels in handling high-dimensional data and robust feature extraction. In contrast, LSTM, which is appropriate for sequential data, is constrained by limited training data and the absence of pre-trained networks. Boosting ensemble decision trees also demonstrate efficacy in reducing model bias and variance. Conclusively, selecting an optimal machine learning strategy is crucial, depending on task complexity and data characteristics, highlighting the need for further research into domain-specific models to improve performance in industrial settings. Full article

The energy-absorbing capacity and friction phenomena of different closed-cell aluminium foam-filled Al tube types are investigated through experimental compression tests. Concerning the kind of investigation, free, radial-constrained and friction tests occurred. The radial-constrained compression test results confirm that the process requires significantly more compression energy than without the constrain. Pushing away different pre-compressed foams inside the aluminium tube, the static and kinematic frictional resistances can be determined and the energy required to move them can be calculated. Knowing the value of the energy required for the frictional resistance, we can obtain how much of the energy surplus in radially inhibited compression is caused by the friction phenomena. The main goal present study is to reveal the magnitude of friction between the foam and the wall of the tube during the radially constrained test. The investigation used 0.4 and 0.7 g/cm³ density closed-cell aluminium foam whilst a compressive test was applied where the force–displacement data were recorded to calculate the absorbed energy due to friction. Considering the results of the test, it can be stated that 18% of the invested energy was used to overcome friction in the case of lighter foam and almost 23% with 0.7 g/cm³ foam during the radial-constrained test. Full article

Throughout the evolution of machine learning, the size of models has steadily increased as researchers strive for higher accuracy by adding more layers. This escalation in model complexity necessitates enhanced hardware capabilities. Today, state-of-the-art machine learning models have become so large that effectively training them requires substantial hardware resources, which may be readily available to large companies but not to students or independent researchers. To make the research on machine learning models more accessible, this study introduces a size reduction technique that leverages stages in pyramid training and similarity comparison. We conducted experiments on classification, segmentation, and object detection tasks using various network configurations. Our results demonstrate that pyramid training can reduce model complexity by up to 70% while maintaining accuracy comparable to conventional full-sized models. These findings offer a scalable and resource-efficient solution for researchers and practitioners in hardware-constrained environments. Full article

Monitoring and classifying cognitive workload in real time is vital for optimizing human–machine interactions and enhancing performance while ensuring safety, particularly in industrial scenarios. Considering this significance, the authors aim to formulate a cognitive workload monitoring system (CWMS) by leveraging the deep gated neural network (DGNN), a hybrid model integrating bi-directional long short-term memory (Bi-LSTM) and gated recurrent unit (GRU) networks. In our experimental setup, each of the four virtual users is equipped with a Raspberry Pi Zero W module to ensure efficient data transmission, thereby enhancing the reliability and efficacy of the monitoring process. This seamless monitoring framework utilizes the constrained application protocol (CoAP) and the Things Board platform to evaluate cognitive workload in real time. The most popular EEG benchmark dataset, the STEW is utilized for workload classification in this study. We employ the short-time Fourier transformation (STFT) to extract frequency bands corresponding to users in both high and low cognitive workload modes. The proposed DGNN models achieve a perfect accuracy of 99.45%, outperforming every previous state-of-the-art model. We meticulously monitored critical parameters, including latency, classification processing time, and cognitive workload levels. This research demonstrates the importance of continuous monitoring for increasing productivity and safety in industries by introducing a novel method of real-time cognitive workload monitoring. The implementation codes for each experiment are documented and made available for reproducibility. Full article