Search Results (5,206)

Occluded person re-identification (Re-ID) faces significant challenges, mainly due to the interference of occlusion noise and the scarcity of realistic occluded training data. Although data augmentation is a commonly used solution, the current occlusion augmentation methods suffer from the problem of dual inconsistencies: intra-sample inconsistency is caused by misaligned synthetic occluders (an augmentation operation for simulating real occlusion situations); i.e., randomly pasted occluders ignore spatial prior information and style differences, resulting in unrealistic artifacts that mislead feature learning; inter-sample inconsistency stems from information loss during random cropping (an augmentation operation for simulating occlusion-induced information loss); i.e., single-scale cropping strategies discard discriminative regions, weakening the robustness of the model. To address the aforementioned dual inconsistencies, this study proposes the unified Multi-Aligned and Multi-Scale Augmentation (MA–MSA) framework based on the core principle of ”synthetic data should resemble real-world data”. First, the Frequency–Style–Position Data Augmentation (FSPDA) module is designed: it ensures consistency in three aspects (frequency, style, and position) by constructing an occluder library that conforms to real-world distribution, achieving style alignment via adaptive instance normalization and optimizing the placement of occluders using hierarchical position rules. Second, the Multi-Scale Crop Data Augmentation (MSCDA) strategy is proposed. It eliminates the problem of information loss through multi-scale cropping with non-overlapping ratios and dynamic view fusion. In addition, different from the traditional serial augmentation method, MA–MSA integrates FSPDA and MSCDA in a parallel manner to achieve the collaborative resolution of dual inconsistencies. Extensive experiments on Occluded-Duke and Occluded-REID show that MA–MSA achieves state-leading performance of 73.3% Rank-1 (+1.5%) and 62.9% mAP on Occluded-Duke, and 87.3% Rank-1 (+2.0%) and 82.1% mAP on Occluded-REID, demonstrating superior robustness without auxiliary models. Full article

We address surrogate-assisted multi-objective optimization for computationally expensive structural designs. The testbed is an axisymmetric laminated composite shell whose geometry, ply angles, and plywise materials are optimized to simultaneously (i) maximize separation of selected natural frequencies from a known excitation and (ii) minimize material cost. To reduce high-fidelity (HF) finite element evaluations, we develop a deep neural network surrogate framework with three variants: an HF-only baseline; a multi-fidelity (MF) pipeline using an auxiliary refinement network to convert abundant low-fidelity (LF) data into pseudo-HF labels for a single-fidelity evaluator; and a cascaded ensemble that emulates HF responses and then maps them to pseudo-experimental targets. During optimization, only surrogates are queried—no FEM calls—while final designs are verified by FEM. Pareto-front quality is quantified primarily by a normalized relative hypervolume indicator computed against an envelope approximation of the True Pareto Front, complemented where appropriate by standard indicators. A controlled training protocol and common validation regime isolate the effect of fidelity strategy from architectural choices. Results show that MF variants markedly reduce HF data requirements and improve Pareto-front quality over the HF-only baseline, offering a practical route to scalable, accurate design under strict computational budgets. Full article

Bacteriophages have been widely investigated as a promising treatment of food, medical equipment, and humans colonized by antibiotic-resistant bacteria. Phages pose particular interest in combating those bacteria which form biofilms, such as the medically important human pathogen Pseudomonas aeruginosa and several plant pathogens, including P. syringae. In an undergraduate lab course, P. putida was used as the host to isolate novel anti-pseudomonal bacteriophages. Environmental samples of soil and water were collected, and purified phage isolates were obtained. After Illumina sequencing, genomes of these phages were assembled de novo and annotated. Assembled genomes were compared with known genomes in the literature and GenBank to identify taxonomic relations and to refine their functional annotations. The thirteen phages described are sipho-, myo-, and podoviruses in several families of Caudoviricetes, spanning several novel genera, with genomes ranging from 40,000 to 96,000 bp. One phage (DDSR119) is unique and is the first reported P. putida siphovirus. The remaining 12 can be clustered into four distinct groups. Six are highly related to each other and to previously described Autotranscriptaviridae phages: Waldo5, PlaquesPlease, and Laces98 all belong to the Waldovirus genus, whereas Stalingrad, Bosely, and Stamos belong to the Troedvirus genus. Zuri was previously classified as the founding member of a new genus Zurivirus within the family Schitoviridae. Ebordelon and Holyagarpour each represent different species within Zurivirus, whereas Meara is a more distantly related member of the Schitoviridae. Dolphis and Jeremy are similar enough to form a genus but have only a few distant relatives among sequenced phages and are notable for being temperate. We identified the lysis cassettes in all 13 phages, compared tail spike structures, and found auxiliary metabolic genes in several. Studies like these, which isolate and characterize infectious virions, enable the identification of novel proteins and molecular systems and also provide the raw materials for further study, evaluation, and manipulation of phage proteins and their hosts. Full article

In recent years, numerous constrained multi-objective evolutionary algorithms (CMOEAs) have been proposed to tackle constrained multi-objective optimization problems (CMOPs). However, most of them still struggle to achieve a good balance among convergence, diversity, and feasibility. To address this issue, we develop an adaptive constraint-boundary learning-based two-stage dual-population evolutionary algorithm for CMOPs, referred to as CL-TDEA. The evolutionary process of CL-TDEA is divided into two stages. In the first stage, two populations cooperate weakly through environmental selection to enhance the exploration ability of CL-TDEA under constraints. In particular, the auxiliary population employs an adaptive constraint-boundary learning mechanism to learn the constraint boundary, which in turn enables the main population to more effectively explore the constrained search space and cross infeasible regions. In the second stage, the cooperation between the two populations drives the search toward the complete constrained Pareto front (CPF) through mating selection. Here, the auxiliary population provides additional guidance to the main population, helping it escape locally feasible but suboptimal regions by means of the proposed cascaded multi-criteria hierarchical ranking strategy. Extensive experiments on 54 test problems from four benchmark suites and three real-world applications demonstrate that the proposed CL-TDEA exhibits superior performance and stronger competitiveness compared with several state-of-the-art methods. Full article

This paper focuses on the design of a three-dimensional trajectory tracking controller for underactuated quadrotor-like autonomous underwater vehicles (QAUVs) subject to actuator saturation. A hand position method with a signum function is proposed to handle the under-actuation of QAUVs, while avoiding trajectory tracking in the opposite direction. The dynamic surface control (DSC) technique is integrated to eliminates the complexity explosion problem of standard backstepping. An auxiliary dynamic system is employed to handle input saturation. By using Lyapunov stability theory and phase plane analysis, it is proved that the proposed control law ensures that the QAUVs converge to the desired position with arbitrarily small errors, while guaranteeing the uniform ultimate boundedness of the whole closed-loop system. Comparative simulation results verify the effectiveness of the proposed control law. Full article

Predefined-time control has been extensively implemented in marine control systems due to its capability to enhance transient performance and achieve superior control specifications. However, inaccurate control execution resulting from faulty actuators can compromise this control strategy and critically undermine system performance. To address this challenge, this paper propose a predefined-time model predictive fault-tolerant control strategy for unmanned surface vessels (USVs) while considering actuator failures and ocean disturbances. Firstly, a novel predefined-time model predictive control (PTMPC) strategy is designed by incorporating contraction constraints derived from an auxiliary predefined-time control system into the proposed optimization framework. This ensures that the resulting control variables guarantee predefined-time convergence of tracking errors when applied to the USV system. Furthermore, a long short-term memory-based neural network for disturbance prediction is integrated into the control strategy, leveraging its exceptional capability in modeling temporal sequences to achieve accurate forecasting of ocean disturbances. Thirdly, the proposed control scheme utilizes its integrated fault observation mechanism to actively compensate for actuator failures through real-time fault estimation, ensuring predefined-time convergence performance while providing rigorous guarantees of closed-loop stability and feasibility. Finally, simulation results demonstrate the efficacy and superiority of the proposed algorithm. Full article

With the widespread adoption of virtual fitting technology in e-commerce and fashion, optimizing user experience through interface design has become increasingly critical. However, research on the usability of virtual fitting interaction interfaces remains limited. Current interfaces frequently suffer from disorganized information layouts and ambiguous auxiliary instructions, reducing efficiency and immersion. This study systematically investigates the effects of information layout (matrix layout, list layout, horizontal layout) and auxiliary instruction display mode (positive polarity: dark content on light background; negative polarity: light content on dark background) on user task performance and subjective experience. A between-subjects experiment was conducted with 60 participants across six conditions. Participants performed a series of tasks, and data were collected on task completion time, subjective ratings, and Technology Acceptance Model responses. Analyses were conducted using two-way ANOVA. The main findings were as follows: (1) The matrix layout demonstrated higher efficiency in multi-target search and complex decision-making tasks, and also received higher subjective ratings for perceived ease of use. (2) The positive polarity display mode demonstrated better performance in single-information search and cognitively intensive tasks, coupled with higher subjective ratings for interface rationality and information clarity. (3) A significant interaction effect was identified between information layout and display mode. The matrix layout combined with positive polarity improved efficiency, whereas the list layout with negative polarity impaired task performance. The horizontal layout was also rated lower for operational fluency. These findings provide practical guidance for designing virtual fitting interfaces that enhance both performance and subjective user experience. Full article

Land cover mapping is essential for territorial management due to its links with ecological, hydrological, climatic, and socioeconomic processes. Traditional methods use discrete classes per pixel, but this study proposes estimating cover fractions with Sentinel-2 imagery (20 m) and AI. We employed the French Land cover from Aerospace ImageRy (FLAIR) dataset (810 km² in France, 19 classes), with labels co-registered with Sentinel-2 to derive precise fractional proportions per pixel. From these references, we generated training sets combining spectral bands, derived indices, and auxiliary data (climatic and temporal variables). Various machine learning models—including XGBoost three deep neural network (DNN) architectures with different depths, and convolutional neural networks (CNNs)—were trained and evaluated to identify the optimal configuration for fractional cover estimation. Model validation on the test set employed RMSE, MAE, and R² metrics at both pixel level (20 m Sentinel-2) and scene level (100 m FLAIR). The training set integrating spectral bands, vegetation indices, and auxiliary variables yielded the best MAE and RMSE results. Among all models, DNN2 achieved the highest performance, with a pixel-level RMSE of 13.83 and MAE of 5.42, and a scene-level RMSE of 4.94 and MAE of 2.36. This fractional approach paves the way for advanced remote sensing applications, including continuous cover-change monitoring, carbon footprint estimation, and sustainability-oriented territorial planning. Full article

Drone-based target detection using visible and thermal (RGB-T) images is critical in disaster rescue, intelligent transportation, and wildlife monitoring. However, persons typically occupy fewer pixels and exhibit more varied postures than vehicles or large animals, making them difficult to detect in unmanned aerial vehicle (UAV) remote sensing images with complex backgrounds. We propose a novel progressive target-aware network (PTANet) for person detection using RGB-T images. A global adaptive feature fusion module (GAFFM) is designed to fuse the texture and thermal features of persons. A progressive focusing strategy is used. Specifically, we incorporate a person segmentation auxiliary branch (PSAB) during training to enhance target discrimination, while a cross-modality background mask (CMBM) is applied in the inference phase to suppress irrelevant background regions. Extensive experiments demonstrate that the proposed PTANet achieves high accuracy and generalization performance, reaching 79.5%, 47.8%, and 97.3% mean average precision (mAP)@50 on three drone-based person detection benchmarks (VTUAV-det, RGBTDronePerson, and VTSaR), with only 4.72 M parameters. PTANet deployed on an embedded edge device with TensorRT acceleration and quantization achieves an inference speed of 11.177 ms (640 × 640 pixels), indicating its promising potential for real-time onboard person detection. The source code is publicly available on GitHub. Full article

This paper develops an explicit positivity-preserving method for the nonlinear Aït-Sahalia interest rate model driven by fractional Brownian motion. To overcome the difficulties in obtaining the convergence rate of this positivity-preserving method, the Lamperti transformation is utilized, which gives an auxiliary equation. And the convergence rate of the numerical method for this auxiliary equation is obtained by virtue of Malliavin calculus. Naturally, the target follows from the inverse of the Lamperti transformation. As a byproduct, the convergence rate of the explicit positivity-preserving method for stochastic differential equations driven by fractional Brownian motion with symmetric coefficients is obtained. Finally, several numerical experiments are performed to verify the theoretical results and demonstrate the advantage of the explicit method. Full article

In this study, the decarburization behavior in basic oxygen furnace (BOF) steelmaking was investigated based on the multi-zone reaction mechanism. The contributions of the main reaction zones to decarburization were clarified, and the effects of key factors—including the effective reaction amount in the main reaction zones, the post combustion ratio (PCR) in auxiliary reaction zones, and the carbon content of scrap steel—on decarburization behavior were quantitatively analyzed. The results indicate that decarburization predominantly occurs in the jet impact reaction zone (approximately 76% of the total decarburization), followed by the emulsion and metal droplet reaction zone (approximately 14%) and the bulk metal and slag reaction zone (approximately 10%). Variations in the effective reaction amount for the main reaction zones significantly affect both the decarburization rate and the endpoint carbon content, with the direct oxidation decarburization reaction in the jet impact reaction zone being the dominant factor. In addition, the PCR in the gas homogenization zone of the auxiliary reaction zones determines the distribution ratio of effective reaction oxygen, while the melting behavior of scrap steel in the metal homogenization zone plays a critical role in the precise control of the endpoint carbon content. This study provides a quantitative elucidation of the effects of different reaction zones on decarburization behavior, offering a foundation for the precise control of endpoint carbon content in BOF steelmaking. Full article

An overview of the Common Rail (CR) diesel engine challenges and of the promising state-of-the-art solutions for addressing them is provided. The different CR injector driving technologies have been compared, based on hydraulic, spray and engine performance for conventional diesel combustion. Various injection patterns, high injection pressures and nozzle design features are analyzed with reference to their advantages and disadvantages in addressing engine issues. The benefits of the statistically optimized engine calibrations have also been examined. With regard to the combustion strategy, the role of a CR engine in the implementation of low-temperature combustion (LTC) is reviewed, and the effect of the ECU calibration parameters of the injection on LTC steady-state and transition modes, as well as on an LTC domain, is illustrated. Moreover, the exploitation of LTC in the last generation of CR engines is discussed. The CR apparatus offers flexibility to optimize the engine calibration even for biofuels and e-fuels, which has gained interest in the last decade. The impact of the injection strategy on spray, ignition and combustion is discussed with reference to fuel consumption and emissions for both biodiesel and green diesel. Finally, the electrification of CR diesel engines is reviewed: the effects of electrically heated catalysts, electric supercharging, start and stop functionality and electrical auxiliaries on NO_x, CO₂, consumption and torque are analyzed. The feasibility of mild hybrid, strong hybrid and plug-in CR diesel powertrains is discussed. For the future, based on life cycle and manufacturing cost analyses, a roadmap for the automotive sector is outlined, highlighting the perspectives of the CR diesel engine for different applications. Full article

Fuel cell trucks are a promising solution to reduce the disproportionately high greenhouse gas emissions of heavy-duty long-haul transportation. However, unlike conventional diesel vehicles, they lack combustion engine waste heat for cabin heating. As a result, electric heaters are often employed, which increase auxiliary energy consumption and reduce driving range. To address this challenge, advanced control strategies are needed to improve heating efficiency while maintaining passenger comfort. This study proposes and validates a methodology for implementing Model Predictive Control (MPC) in the cabin heating system of a fuel cell truck. Vehicle experiments were conducted to characterize dynamic heating behavior, passenger comfort indices, and to provide validation data for the mathematical models. Based on these models, an MPC strategy was developed in a Model-in-the-Loop simulation environment. The proposed approach achieves energy savings of up to 8.1% compared with conventional control using purely electric heating, and up to 21.7% when cabin heating is coupled with the medium-temperature cooling circuit. At the same time, passenger comfort is maintained within the desired range (PMV within ±0.5 under typical winter conditions). The results demonstrate the potential of MPC to enhance the energy efficiency of fuel cell trucks. The methodology presented provides a validated foundation for the further development of predictive thermal management strategies in heavy-duty zero-emission vehicles. Full article

Marine animal segmentation aims at segmenting marine animals in complex ocean scenes, which plays an important role in underwater intelligence research. Due to the complexity of underwater scenes, relying solely on a single RGB image or learning from a specific combination of multi-model information may not be very effective. Therefore, we propose a uniform multi-modal feature extraction and adaptive local–global feature fusion structure for RGB-X marine animal segmentation. It can be applicable to various situations such as RGB-D (RGB+depth) and RGB-O (RGB+optical flow) marine animal segmentation. Specifically, we first fine-tune the SAM encoder using parallel LoRA and adapters to separately extract RGB information and auxiliary information. Then, the Adaptive Local–Global Feature Fusion (ALGFF) module is proposed to progressively fuse multi-modal and multi-scale features in a simple and dynamical way. Experimental results on both RGB-D and RGB-O datasets demonstrate that our model achieves superior performance in underwater scene segmentation tasks. Full article

After the original support system in the auxiliary transportation roadway of the northern wing of the Zhaoxian Mine failed, the extent of damage and deformation varied significantly across different sections of the drift. A single support method could not meet the engineering requirements. Therefore, this paper conducted research on the classification of roadway damage and zoning repair. The overall damage characteristics of the roadway are described by three indicators: roadway deformation, development of rock mass fractures, and water seepage conditions. These are further refined into nine secondary indicators. In summary, a rock mass damage combination weighting evaluation model based on the FAHP–entropy weight TOPSIS method is proposed. According to this model, the degree of damage to the roadway is divided into five grades. After analyzing the damage conditions and support requirements at each grade, corresponding zoning repair plans are formulated by adjusting the parameters of bolts, cables, channel steel beams, and grouting materials. At the same time, the reliability of partition repair is verified using FLAC3D 6.0 numerical simulation software. Field monitoring results demonstrated that this approach not only met the support requirements for the roadway but also improved the utilization rate of support materials. This provides valuable guidance for the design of support systems for roadways with similar heterogeneous damage. Full article