The rapid growth in satellite and aerial remote sensing platforms has created a growing need for distributed remote sensing scene classification. Conventional centralized scene classification methods, which involve transmitting remote sensing data to a ground station for processing, encounter limitations in both transmission efficiency and data privacy. Federated learning (FL) has emerged as a promising approach by enabling terminals to collaboratively train models without exchanging raw data. However, the non-independent and identically distributed (Non-IID) nature of remote sensing data significantly impedes FL performance. To address these challenges, a federated framework with feature distillation (FD) (FedFD) is proposed for FL-based remote sensing scene classification. Specifically, FedFD facilitates collaborative training by aggregating model parameters from multiple terminals to the cloud, thereby optimizing a global model. To further alleviate the impact of Non-IID data, an innovative partial feature-sharing strategy based on FD is designed, which divides features into globally shared essential features and locally maintained supplementary features. Moreover, to cope with object and scene scale variation, the squeeze and excitation module and the pyramid pooling module are incorporated into the scene classification network to enhance multiscale feature extraction. Extensive experiments on the Northwestern Polytechical University Remote Sensing Image Scene Classification 45 (NWPU-RESISC45) dataset and University of California, Merced Land Use (UC-Merced) dataset, under varying numbers of terminals and Non-IID levels, validate the effectiveness and scalability of FedFD, and demonstrate its superior performance in FL-based remote sensing scene classification.

Azimuth ambiguity significantly degrades the quality of synthetic aperture radar images. Sub-look spectral analysis (SSA) is a common ambiguity-detection method, but its performance is limited by threshold sensitivity and the high correlation of specific ambiguities across sub-looks. To overcome these specific limitations, this paper proposes an improved detection method. It first increases the number of sub-looks and constructs a high-dimensional multi-look matrix to enrich the coherence differences between targets and ambiguities. Non-negative matrix factorization is then employed to decompose this matrix, effectively separating the coherent target components from the variably coherent ambiguity components without relying on predefined thresholds. Experimental results on real data demonstrate that the proposed improvements achieve superior azimuth-ambiguity-detection performance compared with conventional SSA methods.

Cross-domain feature fusion offers an approach to weak target recognition in complex sea environments. This paper proposes a distance metric learning-based method for weak target classification. The method first extracts three time-domain features and three frequency-domain features from radar echo signals. Then, the features are partitioned and mapped to low-dimensional subspaces using linear projection matrices. The squared Euclidean distance is used as a metric function to measure the similarity between samples, and supervised optimization is performed by introducing information from similar and dissimilar sample pairs. Next, the projection matrices of each group are jointly updated iteratively using the gradient descent method to achieve supervised feature fusion. Finally, the fused feature is input into an ensemble one-class support vector machine (EOCSVM) for classification. Verified by IPIX measured data, the proposed method can effectively improve the separability of targets and sea clutter and improve the classification ability of sea clutter and weak targets under short-time observation. The proposed method enhances the features correlation from different domains through metric learning and EOCSVM, which can effectively alleviate the sample imbalance problem between sea clutter and targets.

The rapid proliferation of unmanned aerial vehicles (UAVs) has increasingly posed significant challenges for airspace security, particularly under long-range and visually degraded conditions. Effective UAV recognition is thus critical, yet current methodologies typically depend on single-sensor inputs, such as infrared (IR) imaging and radio frequency (RF) analysis, which suffer inherent limitations in complex environments. Although multimodal sensing has been explored in UAV detection, the joint exploitation of IR imagery and RF signals for UAV type recognition remains largely underexplored. The structural heterogeneity between IR and RF features presents challenges for joint representation and decision-making, which remains underexplored in previous work. To address this gap, this paper proposes RF-IRSynNet, a multimodal UAV classification framework that integrates IR imagery and in-flight RF emissions to enhance recognition performance. In RF-IRSynNet, IR images are processed using YOLOv11 to detect UAV candidates and extract structured semantic features. Meanwhile, RF signals are modeled using reservoir computing, which efficiently encodes temporal and spectral dynamics via feature sequences. These modalities are fused through an adaptive confidence-weighted soft-voting strategy, dynamically balancing their contributions based on specific tasks. Experimental results demonstrate that RF-IRSynNet outperforms both unimodal baselines and existing multimodal approaches, achieving robust classification at long ranges. The framework maintains high accuracy even with reduced training data, indicating high efficiency for real-world UAV monitoring.

Extracting infrared small targets from heterogeneous backgrounds remains a challenging task, as these targets lack salient texture and morphological features while the backgrounds are cluttered with noise. Therefore, effectively extracting discriminative features is essential for achieving complete and accurate detection. To address this issue, this paper proposes an algorithmic framework based on robust principal component analysis (RPCA), specifically designed for infrared small target detection in complex backgrounds. First, infrared small target detection is formulated as a generalized RPCA problem. A discriminative and reconstructive dictionary is constructed using supervised learning. Next, by introducing an ideal regularization term, the infrared image is reconstructed without losing structural information, yielding a discriminative principal component representation with respect to the learned dictionary. Finally, the structural features of infrared small targets are reconstructed via sparse coding, thereby enabling the extraction of infrared small targets. Extensive experimental results demonstrate the effectiveness of the proposed method.

Accurately sensing the channel state of heterogeneous networks is key to matching users’ diverse service communication demands with the channel state, and is an effective way to improve the utilization efficiency of network resource. However, existing channel state perception methods are not suitable for heterogeneous network, and their perception performance is easily affected by interference uncertainty. In order to achieve channel state perception of heterogeneous networks, this paper adopts a centralized collaborative perception model, where each node obtains local channel state perception results based on statistical pulse parameters at the physical layer. In order to reduce the impact of interference on perception performance, this paper uses the Jousselme distance to quantify the degree of difference among nodes caused by interference. Using the average credibility as a threshold, nodes in the sensing area are classified. On this basis, the local perception results of each node are performed classification-based correction to improve the accuracy and reliability of channel state perception. Simulation results indicate that the proposed method has good adaptability for channel state perception in complex electromagnetic environments. The perception results can accurately reflect the actual channel state, which is conducive to improving the network throughput.

Aiming at the issues where traditional direction-of-arrival (DOA) estimation algorithms experience substantial performance degradation in low signal-to-noise ratio environments, and deep learning-based DOA estimation methods rely on massive training data with prolonged model training cycles, this paper proposes two efficient and high-precision DOA estimation methods based on ensemble learning. By formulating DOA estimation as a multi-label classification problem and leveraging the classification chain paradigm, data-driven models, classification chain-random forest (CC-RF) and classification chain-eXtreme gradient boosting (CC-XGBoost), are constructed, which are capable of handling multi-label classification tasks. To verify the effectiveness of the proposed methods, a multi-dimensional comparative experiment is designed to benchmark their performance against the traditional multiple signal classification (MUSIC) algorithm and a convolutional neural network (CNN) model. Experimental results indicate that in both single-source and multi-source scenarios, the proposed CC-RF algorithm exhibits excellent performance, achieving DOA estimation accuracy comparable to the MUSIC algorithm; in multi-source estimation scenarios, both proposed models demonstrate strong noise adaptability. Compared with the traditional MUSIC and CNN algorithms, the estimation error of the CC-XGBoost and CC-RF models is reduced by up to nearly 30 times while maintaining low time complexity, with the single estimation time reduced by approximately 90% compared to traditional methods. This study provides a technical pathway for DOA estimation in complex environments and holds significant application value in fields such as radar detection and wireless communication.

The physical architecture of optical convolution restricts its capacity to capture multi-scale features from targets, thus impeding the precision of network recognition. In this work, we propose a multi-scale optical convolutional neural network (MS-OCNN), which uses convolution kernels with different resolutions in the convolution layer to extract different scale features, along with attention mechanism and residual structure to analyze features. By separating the training and inference platforms of the network, we facilitate the electronic training of model parameters on a computer and the optical deployment on a system equipped with a spatial light modulator, enabling efficient target classification. The proposed MS-OCNN exhibits 1% to 3% improvement in classification performance on the modified national institute of standards and technology (MNIST) and Fashion-MNIST datasets compared to single-scale optical inference models. Online experimental systems in real-world scenarios have validated the target recognition capabilities of this method, which yielded classification accuracies of 97% and 87% on the MNIST and Fashion-MNIST datasets, respectively. This work enhances the feature acquisition capabilities of optical convolutional networks, elevates network recognition accuracy, and significantly propels the application of optical computing in domains such as guidance systems, autonomous driving, and robotics.

As is well known, mutual coupling between array elements has a significant negative impact on direction of arrival (DOA) estimation. To achieve DOA estimation under unknown mutual coupling, this paper proposes a low computational complexity Newton-like method. Firstly, a block sparse model based on the signal subspace is established, and the Lagrangian function is established according to the block sparse model. Secondly, since the Hessian matrix of the Lagrangian function cannot always ensure positive definiteness and the computational complexity of the inverse matrix of the Hessian matrix is enormous, the Newton method is no longer applicable. Therefore, this paper proposes a Newton-like method to achieve DOA estimation under mutual coupling and reduce the computational complexity by matrix inversion lemma. Finally, compared with existing methods of DOA estimation under array mutual coupling, the simulation results validate the effectiveness of the proposed method.

A millimeter-wave (mm-Wave) dual circularly polarized (CP) antenna in gap waveguide (GWG) technology with high port isolation is proposed in this paper. It is consisted of a simplified orthomode transducer (OMT) and an improved multi-section hexagonal waveguide CP horn antenna. The OMT is composed of two metal layers without the traditional septum or iris, which makes the structure simpler. The CP horn antenna can be easily integrated with the OMT without mode conversion. The principle analysis as well as the simulated and measured results of the proposed antenna are given in this paper. The simulated and measured results agree very well with each other. The port isolation of more than 27 dB over bandwidth of 26.5?31 GHz (|S₁₁|< ?15 dB) is achieved with relative bandwidth of 15.7%. The axial ratio (AR) lower than 2.5 dB for both left-hand and right-hand CP (LHCP and RHCP) are achieved over the bandwidth. The proposed antenna is a candidate for mm-Wave satellite communications or beyond fifth-generation (5G) communications applications.

The calibration of parameters for onboard stereo cameras is crucial for achieving efficient visual-assisted driving. However, in practical scenarios, low-resolution images often result in inaccuracies in feature point extraction, thereby affecting the accuracy of camera parameter calibration. To address this issue, this paper proposes a self-calibration method for stereo cameras based on joint de-noising, de-mosaic, de-ringing, and super-resolution network (JDDDSN) super-resolution reconstruction. By reconstructing images into higher-resolution images with richer details, feature points are extracted for extrinsic calibration of stereo cameras. For real-world driving scenarios, the reconstructed images achieve noise and ringing artifact reduction while obtaining clearer high-resolution images. This study further investigates the impact of the super-resolution reconstruction network on target area calibration at various distances. Additionally, it highlights the significant role of super-resolution in enhancing stereo camera calibration accuracy by removing dynamic points and focusing on static regions. Through a series of experiments, this paper validates the effectiveness and practicality of the JDDDSN super-resolution reconstruction network in improving stereo camera calibration accuracy, demonstrating its application value in the field of stereoscopic vision.

A dual-frequency aperiodic planar scanning array with diversified radiation elements is proposed. The proposed element consists of an elliptic patch and two parasitic rectangular patches, which can work both at 5.28?5.33 GHz with difference radiation beam and 5.78?5.83 GHz with sum radiation beam. A four equivalent magnetic currents model has been established to explain the radiation principle of the proposed element. Compared to the beamwidth of the sum beam, the 3 dB beamwidth of the difference beam is broadened about 30% and the radiation gain of the sum beam is obviously improved about 48%. A 64-element aperiodic array with diversified radiation elements is constructed. The array can scan at a wide angle of ±70° with no grating lobes at difference radiation mode and can scan in the range of ±60° with high gain at sum radiation mode.

Validation for simulation models often confronts challenges with small samples due to the costs of time and money. To address this issue, this paper presents a validation method for small-sample dynamic outputs based on Gaussian process regression (GPR) models. Firstly, a validation framework based on Bayes statistics is proposed, shifting the focus from merely analyzing validation data to a more comprehensive analysis of posterior distributions. Subsequently, the posterior distributions of both the simulation outputs and the reference data are separately captured through segmented GPR. Then, the consistency of these posterior distributions is evaluated in terms of the central tendency and the distribution range. This consistency serves as a quantitative measure of the simulation model’s credibility, expressed as a value ranging from 0 to 1, where a value closer to 1 indicates higher credibility. Finally, the effectiveness of this validation method is demonstrated through a numerical example and an application example, highlighting its capability in uncertainty description and adaptability to small samples.

This research proposes an odd-even dimension RUNge Kutta algorithm (ODRUN) to solve global optimization and a well-known NP-hard problem in inventory management. The rpoposed algorithm integrates odd-even dimensional, fourth-order Runge-Kutta method, and neighbor search strategies. This hybrid approach significantly improves population diversity, avoids local optima, and enhances convergence accuracy. To validate the performance of the proposed algorithm, a widely recognized benchmark function suit from CEC2022 is first employed. Results confirm that ODRUN achieves an overall effectiveness ratio of 66.67% across three statistical indicators (best, mean, and standard deviation) for 12 benchmark functions. The test shows this algorithm is ranked first compared to seven state-of-the-art metaheuristic algorithms. Furthermore, ODRUN is applied to the joint replenishment problem with imperfect items and trade credit. Numerical examples from 600 randomly generated large-scale instances highlight that the algorithm’s performance remains unaffected by an increase in problem scale. The significant cost savings brought by the ODRUN algorithm, with the maximum improvement ratio in average cost and best-found total cost ranging from 14.81% to 19.5%, are achieved in comparison to other algorithms. In conclusion, ODRUN is an effective and robust tool for complex optimization problems.

To address the energy consumption issues caused by task lengths in task scheduling on heterogeneous multi-core systems, this paper proposes an adaptive parameterized improved simulated annealing algorithm based on the directed acyclic graph task model. The algorithm employs feedback from acceptance rates to dynamically adjust the temperature and neighborhood size of the simulated annealing process. Additionally, it introduces a security mechanism to enhance convergence speed and global search capabilities. Compared against classical simulated annealing and standard heuristic algorithms, the proposed algorithm achieves reductions exceeding 54% in convergence generations, 50% in task slots, and 10% in scheduling time, providing a direction for low-power task scheduling.

Integrating prognostics and health management (PHM) with the existing maintenance support system of systems plays an important role in implementing reliability-centered maintenance (RCM). However, the increasing complexity and integration of civil aircraft systems pose challenges for conventional document-based systems engineering (DBSE) practice. Aiming at the specific problems of poor modeling degree, weak traceability between problem and solution domains, and insufficient integration in civil aircraft PHM development, a model-based systems engineering (MBSE) approach is adopted to overcome the limitations of DBSE method. This paper proposes a structured integrated modeling method to facilitate PHM functional integration with other aircraft systems. An MBSE modeling method based on traceable requirements, functional, logical, and physical models, is applied in the integration process. Additionally, a multi-viewpoint analysis method within the Department of Defense Architecture Framework (DoDAF) is introduced to illustrate the modeling elements and processes from a multi-dimensional perspective. The modeling logic and architecture are subsequently presented, followed by examples of requirements, functional flows, and resource flows models using the systems modeling language (SysML). Finally, a preliminary logic simulation verification is conducted as a case study of typical PHM functional integration with maintenance support. The case study results demonstrate that the proposed method enhances information traceability and consistency, which can offer theoretical support and technical reference for the development of maintenance support system.

Existing weapon portfolio selection methods do not sufficiently support specific combat tasks, with uncertainty in the decision information. Therefore, a combat task–oriented weapon portfolio selection method that adapts weapon capabilities to combat tasks is proposed. The approach is based on specific combat tasks and weapon background, using fuzzy interval values to describe indicators and the applicability of a weapon portfolio. In addition, an interval entropy weighting method is applied to obtain weight information of indicators. Meanwhile, we define the similarity measure of fuzzy interval values and use the interval fuzzy collaborative filtering algorithm to calculate the fitness of the residual weapons. Furthermore, the interval fuzzy set clustering algorithm clusters the tasks to inform the decision of weapon portfolio. Finally, we verify the method’s feasibility and advancement by comparing actual combat tasks as examples with the traditional methods. The contributions of this paper include improvements to the accuracy and reliability of decision-making from the perspective of adapting weapon capability to combat tasks. At the same time, this paper accounts for the method’s shortcomings by considering the hesitancy and ambiguity of the indicator data.

Remote sensing satellites (RSS) are highly complex and customized from a common product family. It makes the traditional model-based system engineering (MBSE) method, which lacks architecture-level reusability, difficult to apply to their architecture design. Considering RSS has a relatively fixed common architecture from which the various design solutions are customized specific to different missions, the model-based product line engineering (MBPLE) methodology can be leveraged. In this paper, based on the analysis of the current RSS development process in practice and the main issues of current MBPLE methods, an RSS-specific MBPLE approach is proposed. Firstly, the RSS domain terminology is consolidated into the RSS-MBPLE SysML profile to support the construction of models in the design process. Then, the two key steps, i.e., architecture configuration and standalone product selection are efficiently conducted following the MBPLE principles supported by plugins of the mainstream SysML platform. Finally, a typical RSS control subsystem is illustrated as the case study to demonstrate the effectiveness of the proposed method. The results show that the proposed approach improves architecture-level reusability and design automation compared with traditional methodology, thereby reducing manual clone-and-modify efforts and enhancing the efficiency of RSS architecture design.

The implementation of timely monitoring and preventive maintenance plays a fundamental role to ensure the reliable operation of complex systems. Condition-based maintenance strategy offers an effective means to leverage system remaining life information, enabling the application of targeted measures to reduce maintenance costs and elevate overall operational efficiency. This study delves into a performance degradation system affected by external random shocks, utilizing the Wiener process model to characterize the continuous degradation process. Within this framework, two distinct condition-based monitoring schemes are proposed: one is the real-time condition monitoring and the other is the dynamic periodic monitoring. Through the optimization of maintenance strategies for each scheme based on the long-term average cost, the study aims to optimize the preventive maintenance threshold for system failure. The Monte Carlo simulation algorithm is adopted to solve the optimization problem. Finally, a comprehensive numerical example is provided to validate the efficiency of both the models and the proposed maintenance strategies.

Forest fires are characterized by their abrupt onset and highly destructive nature, resulting in significant annual property losses. Hence, regular surveillance is imperative for forest fire prevention and mitigation. The fundamental challenge in patrolling is akin to the problem of helicopter route planning. Conventional unmanned aerial vehicle (UAV) path planning commonly entails single-trip missions. Considering the extensive and complex forest environments, we advocate a multi-stage UAV reconnaissance strategy to address the daily inspection route planning conundrum. This approach facilitates UAVs to conduct round-trip flights between designated surveillance points and the base station at diverse time intervals, effectively satisfying the requirements for multi-tiered, hierarchical reconnaissance. Furthermore, we develop an advanced multi-strategy genetic algorithm (MSGA) to optimize the multi-stage reconnaissance model. Experimental outcomes underscore the superior performance of the enhanced MSGA, achieving a reduction of nearly 20% in total flight path length relative to the traditional genetic algorithm. This methodology significantly enhances the efficacy of daily forest patrols.

The evaluation of the equipment contribution rate to system-of-systems (CRSoS) is crucial for optimizing the armament system-of-systems structure and enhancing combat effectiveness. The traditional relative contribution rate method poses limitations by focusing on individual equipment evaluation without considering the interrelations between equipment. In response to the issue, this study proposes a framework based on operation loop and improved Shapley value (OLISV) for analysis to ananlyze the equipment CRSoS. Specifically, a multi-layer network model is first constructed based on complex heterogeneous network and operation loop theory. Next, information entropy and evidence theory are used for the edges of the functional node layer, while improving the parallel node structure within the network. Subsequently, an improved Shapley value contribution rate method based on non-efficiency influencing factors is proposed. Finally, the rationality and effectiveness of the OLISV are illustrated through a case study.

In this paper, the system we consider has multiple inventory warehouses and multiple pieces of equipment with multiple repairable components, where the joint planning of spare components and maintenance workers with lateral and cross-echelon transshipment is studied. Firstly, the characteristics of inventory system is analyzed, and the scheduled relationship of maintenance resources is carded. Based on this, a total system cost model is proposed, incorporating holding, ordering, and maintenance costs under an average waiting time constraint. A hyper-heuristic algorithm is then introduced to efficiently solve larger-scale problems with improved computational speed, and is applied to derive an optimized inventory allocation plan for maintenance resources. Finally, a maintenance system is analyzed, comprising four local warehouses, three central warehouses, and one plant that serves five machine groups. Each group contains four machines, each warehouse supports one or two machines, and every machine includes five independently failing key components. By analyzing the effect on reducing total cost, improving maintenance demand satisfaction rate, the effectiveness of the proposed optimization approach is verified.

To enhance the real-time performance and accuracy of guidance command generation, we propose an online reentry guidance algorithm based on analytical solutions of the hypersonic glide trajectory (HGT). Initially, an altitude-velocity profile is designed in the longitudinal plane to satisfy both path and terminal constraints. Based on this profile, we derive analytical solutions for the flight path angle (FPA) and bank angle. Subsequently, by employing the Newton-Raphson method to linearize the reentry motion equations, analytical solutions for the latitude and heading angle are obtained. Furthermore, we introduce an improved particle swarm optimization (IPSO) algorithm to optimize the profile parameters. This approach significantly enhances the algorithm’s global convergence by narrowing the parameter optimization range and adaptively adjusting the inertia weight and cognitive factors. Finally, we present an online guidance algorithm that combines the HGT analytical solutions with the IPSO algorithm. This algorithm effectively achieves longitudinal and lateral guidance by continuously updating the altitude-velocity profile and bank angle symbol in real time. Simulation results demonstrate that the proposed algorithm is fast, efficient, accurate, and holds significant potential for broader application.

To address the attitude control problem under the uncertainty, external disturbance, and actuator failure, a predefined-time fault-tolerant control method based on a predefined time disturbance observer is proposed. First, the dynamics model of hypersonic morphing vehicle (HMV) is established, and the control system is designed as an outer-loop attitude angle control loop and an inner-loop angular rate control loop considering the actuator failure problem. Secondly, a predefined-time disturbance observer is designed to estimate the comprehensive disturbances, and compensate in the control law. By integrating back-stepping control with predefined-time theory, a predefined-time attitude tracking control method is proposed, enabling the convergence time of the attitude tracking error to be designed through a simple parameter. Rigorous Lyapunov function analysis has demonstrated that the attitude tracking error can converge to an arbitrarily small neighborhood around the origin within a predefined time, and all signals in the closed-loop system are bounded. Finally, comparative simulations validate the effectiveness of the proposed method.

We propose a deep-learning-assisted strapdown inertial navigation system (SINS)/refraction celestial navigation system (RCNS) integrated navigation method to control the adverse effects of atmospheric density errors on the accuracy of stellar refraction navigation and enhance the reliability of SINS/RCNS integrated navigation for aerospace vehicles. This method utilizes satellite navigation data and a long short-term memory network to establish a mapping relationship between the navigation moments, refraction angles, and the apparent height errors. Using deep learning algorithm to address complex time-series prediction problems, thereby compensates the impact of atmospheric density deviations on star sensor measurements. Simulation experiments of vehicle navigation in scenarios with atmospheric density errors are conducted using this method. The results show that the deep learning scheme can effectively resist the adverse effects of atmospheric density errors on navigation, demonstrating strong reliability.

In this paper, a three-dimension envelope-based path planning algorithm (3DE-PP) is proposed to automatically generate a collision-free trajectory for unmanned aerial vehicle (UAV). Firstly, focusing on the defects of low efficiency of obstacle modelling representation and large search space, an elliptical envelope-based obstacle modelling method is proposed to facilitate the generation of obstacle avoidance waypoints and improve the search efficiency. Then, considering safety and aiming at minimum energy consumption, waypoint generation strategies based on tangent guidance and minimum deviation are designed. Meanwhile, aiming at the UAV motion constraint, a three-dimension (3D) path construction method based on improved Dubins is proposed. Finally, combined with the main path generation algorithm based on saving algorithm, a safe and feasible 3D flight path is constructed by considering the power constraint of UAV and the access of charging stations comprehensively. The proposed 3DE-PP is compared with four algorithms (SAS, Dubins-RRT*, APF, 3D-TG) by 15 examples generated from five typical environments, and the computational results confirm its advantages. Furthermore, a real-world case is introduced, and the key factors influencing path planning are analyzed.

Global Navigation Satellite Systems (GNSSs) are the specific term utilized with satellite constellation to acquire regional or global services. GNSS sensors use pseudo-distance measurement to estimate the position, velocity, and time (PVT). Several GNSS devices are exposed to detect spoofing attacks due to the use of unsafe locations. In addition, misleading signals are intentionally used to generate timing and position, and GNSS signal spoofing provides a constant risk to consumers. In past works, the implementation of the Global Positioning System (GPS) in autonomous vehicle navigation might be endangered by spoofing. To mitigate these issues, this task develops a hybrid machine-learning method for mitigating and detecting GNSS spoofing attacks. The developed model is processed with three phases: data collection, feature extraction, and detection. Initially, the required data is taken from the standard resource. Then, the data is given to the feature extraction phase. The features of the data are retrieved using the principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) model. The features obtained from the collected data are transferred to the detection phase. In the final phase, the GNSS spoofing detection and mitigation is executed using a machine learning method called as hybridized adaptive Bayesian learning and multi-layer perceptron (HABMLP). Enhanced osprey optimization algorithm (EOOA) is utilized for optimizing the variables to enhance the efficacy of models and achieves greater performance than other standard models.