Accurate object detection in unmanned aerial vehicle (UAV) images plays a crucial role in fields such as aviation, transportation, and agriculture. However, UAV images often contain a high proportion of small objects, and the limited resources of UAV platforms make it challenging for existing small object detection algorithms to balance detection performance and resource consumption. To address these issues, a lightweight small object detection algorithm called SRP-YOLO is proposed. Compared to the YOLOv8 network, the following improvements are made: first, a high-resolution detection head is designed; second, a receptive field attention convolution module tailored for small UAV objects is introduced to replace the standard convolution module, enhancing the detection capability for small objects and significantly improving their feature representation; Third, partial convolution is combined with C2f to replace some of the standard convolutions, fully leveraging the high-resolution information from shallow features. Finally, a normalized Gaussian Wasserstein distance (NWD) metric is introduced to reduce the sensitivity of intersection over union (IoU) to minor positional deviations of small objects. On VisDrone-DET2019, SRP-YOLO reduces parameters while improving [Formula: see text] by 7.9%. Generalization tests on TinypersonV2 and RAIVD confirm significant gains in small object detection.

Frequency security assessment (FSA) is critical for the safe operation of modern power systems, particularly under increasing uncertainty and renewable integration. In online prefault scenarios, a large set of anticipated disturbances, such as generator tripping, load shedding, and HVdc blocking, must be evaluated rapidly and accurately. However, existing data-driven methods struggle to capture disturbance mechanisms and neglect the spatial influence of disturbance locations, resulting in reduced generalization and reliability. To address these limitations, this article proposes a trustworthy disturbance-informed learning (DIL) framework that incorporates location-sensitive disturbance features into data-driven FSA. By integrating steady-state power flow with power disturbance data into graph-structured representations, DIL leverages graph convolutional networks (GCN) to extract topology-aware features. To reflect disturbance location differences, DIL modifies the dropout process in GCN training by replacing random sampling with location-based sampling. This helps the model focus on critical nodes, improving accuracy and robustness. In addition, disturbance location information enhances trustworthiness by comparing model attention with actual disturbance positions. Case studies on the IEEE 39-bus system and a provincial power grid in China (3748 buses) demonstrate that DIL outperforms existing models in accuracy and robustness, while enabling more trustworthy predictions.

This article develops a fully decentralized approximate dynamic programming (FD-ADP) algorithm for stochastic energy management (SEM) of a networked microgrid (NMG) system. First, considering the ac power flow constraints, an alternating direction method of multipliers (ADMM)-based decentralized SEM framework is proposed for NMG coordination. Then, a transactive energy scheme is introduced to further decouple each microgrid (MG) optimization for privacy enhancement and computation reduction. Next, a FD-ADP algorithm is proposed to cope with the real-time uncertainties. The piecewise linear function (PLF) is employed for value function approximation, and a fully decentralized PLF slope update method based on ADMM framework is designed for decentralized property preservation, which trains the value function just through each MG local information and neighboring communication, thus the well-trained decentralized PLF slopes can help achieve the global optimal SEM strategy for NMG coordination under stochastic environments. Finally, case studies demonstrate the effectiveness of the proposed ADMM-based FD-ADP algorithm in terms of decentralized optimization, decentralized training, and global optimality.

Accurate and high-quality tooth mesh generation from cone-beam computerized tomography (CBCT) is an essential computer-aided technology for digital dentistry. However, existing segmentation-based methods require complicated post-processing and significant manual correction to generate regular tooth meshes. In this paper, we propose a method of continuous bijection supervised pyramid diffeomorphic deformation (PDD) for learning tooth meshes, which could be used to directly generate high-quality tooth meshes from CBCT Images. Overall, we adopt a classic two-stage framework. In the first stage, we devise an enhanced detector to accurately locate and crop every tooth. In the second stage, a PDD network is designed to deform a sphere mesh from low resolution to high one according to pyramid flows based on diffeomorphic mesh deformations, so that the generated mesh approximates the ground truth infinitely and efficiently. To achieve that, a novel continuous bijection distance loss on the diffeomorphic sphere is also designed to supervise the deformation learning, which overcomes the shortcoming of loss based on nearest-neighbour mapping and improves the fitting precision. Experiments show that our method outperforms the state-of-the-art methods in terms of both different evaluation metrics and the geometry quality of reconstructed tooth surfaces.

The fusion of magnetic resonance imaging and positron emission tomography can combine biological anatomical information and physiological metabolic information, which is of great significance for the clinical diagnosis and localization of lesions. In this paper, we propose a novel adaptive linear fusion method for multi-dimensional features of brain magnetic resonance and positron emission tomography images based on a convolutional neural network, termed as MdAFuse. First, in the feature extraction stage, three-dimensional feature extraction modules are constructed to extract coarse, fine, and multi-scale information features from the source image. Second, at the fusion stage, the affine mapping function of multi-dimensional features is established to maintain a constant geometric relationship between the features, which can effectively utilize structural information from a feature map to achieve a better reconstruction effect. Furthermore, our MdAFuse comprises a key feature visualization enhancement algorithm designed to observe the dynamic growth of brain lesions, which can facilitate the early diagnosis and treatment of brain tumors. Extensive experimental results demonstrate that our method is superior to existing fusion methods in terms of visual perception and nine kinds of objective image fusion metrics. Specifically, in the results of MR-PET fusion, the SSIM (Structural Similarity) and VIF (Visual Information Fidelity) metrics show improvements of 5.61% and 13.76%, respectively, compared to the current state-of-the-art algorithm. Our project is publicly available at: https://github.com/22385wjy/MdAFuse.

Multimodal image fusion plays an essential role in medical image analysis and application, where computed tomography (CT), magnetic resonance (MR), single-photon emission computed tomography (SPECT), and positron emission tomography (PET) are commonly-used modalities, especially for brain disease diagnoses. Most existing fusion methods do not consider the characteristics of medical images, and they adopt similar strategies and assessment standards to natural image fusion. While distinctive medical semantic information (MS-Info) is hidden in different modalities, the ultimate clinical assessment of the fusion results is ignored. Our MsgFusion first builds a relationship between the key MS-Info of the MR/CT/PET/SPECT images and image features to guide the CNN feature extractions using two branches and the design of the image fusion framework. For MR images, we combine the spatial domain feature and frequency domain feature (SF) to develop one branch. For PET/SPECT/CT images, we integrate the gray color space feature and adapt the HSV color space feature (GV) to develop another branch. A classification-based hierarchical fusion strategy is also proposed to reconstruct the fusion images to persist and enhance the salient MS-Info reflecting anatomical structure and functional metabolism. Fusion experiments are carried out on many pairs of MR-PET/SPECT and MR-CT images. According to seven classical objective quality assessments and one new subjective clinical quality assessment from 30 clinical doctors, the fusion results of the proposed MsgFusion are superior to those of the existing representative methods.

Simulation analysis is critical for identifying possible hazards and ensuring secure operation of power systems. In practice, large-disturbance rotor angle stability and voltage stability are two frequently intertwined stability problems. Accurately identifying the dominant instability mode (DIM) between them is important for directing power system emergency control action formulation. However, DIM identification has always relied on human expertise. This article proposes an intelligent DIM identification framework that can discriminate among stable status, rotor angle instability, and voltage instability based on active deep learning (ADL). To reduce human expert efforts required to label the DIM dataset when building DL models, a two-stage batch-mode integrated ADL query strategy (preselection and clustering) is designed for the framework. It samples only the most helpful samples to label in each iteration and considers both information contents and diversity in them to improve query efficiency, significantly reducing the required number of labeled samples. Case studies conducted on a benchmark power system (China Electric Power Research Institute (CEPRI) 36-bus system) and a practical large-area power system (Northeast China Power System) reveal that the proposed approach outperforms conventional methods in terms of accuracy, label efficiency, scalability, and adaptability to operational variability.

Cross-modal retrieval has attracted great attention due to the increasing demand for tremendous amounts of multimodal data in recent years. These retrievals could either be text-to-image or image-to-text. To address the problem of inappropriate information included between images and texts, we propose two cross-modal recovery techniques established on a dual-branch neural network defined on a common subspace and the hashing learning method. First, a cross-modal recovery technique established on a multilabel information deep ranking model (MIDRM) is provided. In this method, we introduce a triplet-loss function into the dual-branch neural network model. This function takes advantage of the semantic information of the bimodal components, focusing on not only the similarities between similar images and text features but also the distances between dissimilar images and texts. Second, we establish a new cross-modal hashing technique said to be the deep regularized hashing constraint (DRHC). In this method, the regularized function is used to replace the binary constraint, and the discrete value is constrained to a certain numerical range so that the network can achieve end-to-end training. Overall, the time complexity is greatly improved, and the occupied storage space is also greatly reduced. Different experiments on our proposed MIDRM and DRHC models demonstrate their superior performance to those of the state-of-the-art methods on two widely used data sets. The experimental results show that our approach also increases the mean average precision of cross-modal recovery.

The growth of electric vehicles (EVs) significantly increases the residential electricity demand and potentially leads to the overload of the transformer in the distribution grid. Aiming to coordinate the charging control of EVs, this article formulates the EVs charging problem as a Markov game with an unknown transition function and proposes a cooperative charging control strategy based on the multiagent deep reinforcement learning. The uncertainties from the dynamic electricity price, non-EV residential load consumption and drivers’ individual behaviors are considered to construct the dynamic charging environment. Each agent contains a collective-policy model and an independent learner. The collective-policy model is introduced to model other agent's behaviors by approximating their power consumption. The independent learner is used to learn the optimal charging strategy by interacting with the environment. The soft-actor-critic framework is adopted to train the independent learner, enabling the proposed method to address the continuous state and action. Agents are trained with only the local observation and approximation, indicating that the proposed approach is fully decentralized and scalable to the problem with multiple agents. Finally, several numerical studies constructed based on the real-world data demonstrate the effectiveness and scalability of the proposed approach.

To improve the boundary processing ability and anti‐noise performance of image segmentation algorithm，a neutrosophic fuzzy clustering algorithm based on non‐local information is proposed here. Initially, the proposed approach uses the data distribution of deterministic subset to determine the clustering centre of the fuzzy subset. Besides, the fuzzy non‐local pixel correlation is introduced into the neutrosophic fuzzy mean clustering algorithm. The experimental results on synthetic images, medical images and natural images show that the proposed method is more robust and more accurate than the existing clustering segmentation methods.

The active power transfer capability (APTC) of a converter integrated with a weak AC grid is limited by the small-signal stability. This paper analyzes the APTC for the hybrid MMC interfacing a weak AC grid. Firstly, the time-domain small-signal model for the hybrid MMC is derived. Then, the impact of the active power on the small-signal stability is analyzed through root loci calculation for the hybrid MMC with DC voltage/reactive power and active/reactive power control modes under the rectifier and inverter operation status respectively. The instability phenomenon is verified in PSCAD/EMTDC regarding the critical active power and the oscillation frequency. Sensitivity analysis is conducted to distinguish the effective parameters to enhance APTC. The proper parameter adjustment methods are given by double-checking their effect on the enhancement of APTC and the dynamics performance of the controllers.

This paper develops a novel distributed iterative event-triggered control scheme for a master-slave-organized dc microgrid network with limited communication bandwidth. The proposed scheme can synchronize the voltage of multiple distributed energy resources (DER) to their desired value. Moreover, the optimal load sharing for their economic operation (e.g., minimize the total generation cost) can be achieved through a low bandwidth communication network. The designed controllers are fully distributed and only triggered at their own event time, which effectively reduces the frequency of controller updates compared with continuous-time feedback control. Eventually, each DER only requires the local voltage and current measurement from its own and some nearest (but not all) neighbors at given event-triggered time through limited-bandwidth communication links. The Lyapunov technique is employed to derive the event-triggered conditions that guarantee the stability. Furthermore, the lower bound of the interevent intervals is captured by the proposed iterative algorithm to exclude Zeno behaviors. Different cases in MATLAB/SimPowerSystems are investigated and results demonstrate the effectiveness and the performance of the proposed approach.

This paper develops a distributed cooperative control scheme for DC microgrids with time-varying coupling delays in noisy environments. The proposed distributed cooperative control, consisting of distributed primary control and secondary control, will regulate the voltage of microgrids to the desired values and through a sparse communication network with asymmetric communication delays and noise disturbances. Distributed cooperative controllers are designed into the secondary control stage for DC microgrids, in which manner the criteria for the stability analysis and delays boundedness to maintain the system stable are derived. With the proposed algorithms, control derivation of voltage produced during the primary control stage can be well remedied even if the communication delays and noise disturbances may exist. The effectiveness of the proposed control methodology is verified by the simulation of a DC microgrid system in MATLAB/SimPowerSystems.

This paper develops an adaptive modulation approach for power system control based on the approximate/adaptive dynamic programming method, namely, the goal representation heuristic dynamic programming (GrHDP). In particular, we focus on the fault recovery problem of a doubly fed induction generator (DFIG)-based wind farm and a static synchronous compensator (STATCOM) with high-voltage direct current (HVDC) transmission. In this design, the online GrHDP-based controller provides three adaptive supplementary control signals to the DFIG controller, STATCOM controller, and HVDC rectifier controller, respectively. The mechanism is to observe the system states and their derivatives and then provides supplementary control to the plant according to the utility function. With the GrHDP design, the controller can adaptively develop an internal goal representation signal according to the observed power system states, therefore, to achieve more effective learning and modulating. Our control approach is validated on a wind power integrated benchmark system with two areas connected by HVDC transmission lines. Compared with the classical direct HDP and proportional integral control, our GrHDP approach demonstrates the improved transient stability under system faults. Moreover, experiments under different system operating conditions with signal transmission delays are also carried out to further verify the effectiveness and robustness of the proposed approach.

In this paper, we present a new adaptive dynamic programming approach by integrating a reference network that provides an internal goal representation to help the systems learning and optimization. Specifically, we build the reference network on top of the critic network to form a dual critic network design that contains the detailed internal goal representation to help approximate the value function. This internal goal signal, working as the reinforcement signal for the critic network in our design, is adaptively generated by the reference network and can also be adjusted automatically. In this way, we provide an alternative choice rather than crafting the reinforcement signal manually from prior knowledge. In this paper, we adopt the online action-dependent heuristic dynamic programming (ADHDP) design and provide the detailed design of the dual critic network structure. Detailed Lyapunov stability analysis for our proposed approach is presented to support the proposed structure from a theoretical point of view. Furthermore, we also develop a virtual reality platform to demonstrate the real-time simulation of our approach under different disturbance situations. The overall adaptive learning performance has been tested on two tracking control benchmarks with a tracking filter. For comparative studies, we also present the tracking performance with the typical ADHDP, and the simulation results justify the improved performance with our approach.

Goal representation heuristic dynamic programming (GrHDP) is proposed in this paper to demonstrate online learning in the Markov decision process. In addition to the (external) reinforcement signal in literature, we develop an adaptively internal goal/reward representation for the agent with the proposed goal network. Specifically, we keep the actor-critic design in heuristic dynamic programming (HDP) and include a goal network to represent the internal goal signal, to further help the value function approximation. We evaluate our proposed GrHDP algorithm on two 2-D maze navigation problems, and later on one 3-D maze navigation problem. Compared to the traditional HDP approach, the learning performance of the agent is improved with our proposed GrHDP approach. In addition, we also include the learning performance with two other reinforcement learning algorithms, namely Sarsa(λ) and Q-learning, on the same benchmarks for comparison. Furthermore, in order to demonstrate the theoretical guarantee of our proposed method, we provide the characteristics analysis toward the convergence of weights in neural networks in our GrHDP approach.