In recent years skeleton-based action recognition has gained widespread attention in applications such as intelligent medical monitoring and rehabilitation assessment due to its compact representation and robustness to appearance variations. However, accurately distinguishing fine-grained motion differences among semantically similar actions remains a challenging problem. To address this, this paper approaches the issue from two perspectives: structural modeling and semantic modeling, and proposes a Channel-Aware Prototype Reconstruction Network (CAPR-Net). In structural modeling, the network introduces a channel-aware mechanism that fuses channel-specific and channel-shared feature modeling strategies to fully capture spatial dependencies across mixed channels. In semantic modeling, a prototype reconstruction module is designed to project action features into a prototype space, combined with class-aware prototype contrastive learning to enhance category discrimination and improve fine-grained semantic representation. Experiments conducted on the NTU RGB+D datasets under two settings, cross-subject (X-Sub) and cross-view (X-View), demonstrate that CAPR-Net achieves top-1 accuracies of 92.4 % and 97.4 %, respectively, Experimental results demonstrate that the proposed model exhibits strong performance and outperforms current state-of-the-art methods across multiple evaluation metrics.

With the widespread proliferation of electric vehicles (EVs), optimizing the operation of EV charging stations (EVCSs) has become increasingly important. Strategic charging prices can influence both revenue and service efficiency, while differentiated pricing for different EVs can further help mitigate overstay issues. Moreover, under the concept of the peer-to-peer (P2P) sharing economy, energy and carbon allowance trading among EVCSs presents a significant opportunity to reduce both operational costs and carbon emissions. However, limited research has examined such interactions and the specific economic and environmental impacts of joint energy and carbon (E&C) trading in multi-EVCS systems. In this paper, we investigate a joint differentiated pricing and E&C trading problem for multiple EVCSs, aiming to maximize both economic and environmental benefits. Specifically, we first formulate a total revenue-maximization problem that incorporates anxiety-differentiated pricing and P2P E&C trading among multiple interconnected EVCSs. We then propose an operational algorithm to solve the problem based on Nash bargaining and the alternating direction method of multipliers, which can protect privacy and mitigate communication barriers among EVCSs. Simulation results demonstrate that the proposed algorithm can simultaneously improve revenue and achieve low-carbon goals.

Gesture recognition based on surface electromyography has become increasingly important in human-machine interaction. Existing deep learning architectures primarily rely on convolutional neural networks (CNNs) to capture spatial in-formation from sEMG signals. Given the multi-channel nature of temporal sEMG signals, we propose a neural network architecture that combines the power of multi-stream convolution and bidirectional gated units to better capture the temporal properties of multi-channel sEMG signals for gesture recognition. Moreover, individual differences in surface electromyography datasets can lead to overfitting and other issues in classification models. Data augmentation proves effective in mitigating overfitting problems by increasing dataset diversity, enabling the model to learn more comprehensive features, enhancing its generalization capability, and reducing the risk of overfitting. Experimental results on the NinaProDB2 dataset demonstrate that the proposed method achieves an average recognition accuracy of 89.21% on sparse multi-channel sEMG databases, surpassing the recognition level of traditional machine learning models. Additionally, the conducted ablation experiments validate the correctness of the proposed model.

This study proposes an automatic fracture image recognition method based on an improved Multi-Stream Residual Convolutional Neural Network (MSR-CNN). Fractures, typically caused by external forces or diseases, are often accompanied by severe pain, swelling, and functional impairment. This is particularly concerning for the elderly, as fractures can lead to prolonged bed rest and multiple complications, significantly affecting their quality of life. Imaging techniques such as Xray, CT, MRI, and ultrasound play a crucial role in fracture diagnosis. However, traditional diagnostic methods heavily rely on the subjective judgment of radiologists, which has inherent limitations. The application of computer-aided diagnosis (CAD) and artificial intelligence technologies has brought about new breakthroughs in medical image recognition. The proposed MSRCNN model combines multi-stream network structures with residual network modules, effectively enhancing the accuracy and efficiency of fracture image recognition. Experimental results demonstrate that the model achieves excellent performance in terms of accuracy, precision, recall, and F1 scores in fracture detection tasks, highlighting its potential for broader applications in medical image analysis.

Digitalization is one of the key drivers for energy system transformation. The advances in communication technologies and measurement devices render available a large amount of operational data and enable the centralization of such data storage and processing. The greater access to data opens up new opportunities for a more efficient and decentralized management of the energy system. At the distribution level of the energy system, local electricity markets (LEMs) provide new degrees of flexibility by trading and balancing the energy locally and offering ancillary services to the wider transmission and distribution system operators. Maximizing the grid impact from this flexibility calls for novel data analytics and artificial intelligence techniques to enhance the system’s security and reduce the energy costs of local prosumers. At the same time, however, relying on data-based approaches increases the risk of cyberattacks, and robust countermeasures are, therefore, needed as an integral aspect of digitalization efforts. This article discusses the key role of centralized data analytics to fully benefit from the advantages of LEMs in terms of system’s security enhancement and energy costs’ reduction. Data-driven paradigms are investigated that allow for flexibility from decentralized markets, mitigate the physical security risks, and devise defensive strategies shielding the system from cyber threats.

Multienergy microgrids (MEMGs) have significant potential to offer high energy utilization efficiency and system flexibility. The coordination of these MEMGs poses challenges due to the various system dynamics and uncertainties and the need to preserve privacy. This article proposes a double auction (DA)-market-based coordination framework. As such, MEMGs can not only schedule their own energy components but also trade energy with others in the DA market. After that, we formulate this problem as Markov games and propose a multiagent reinforcement learning method by making use of the DA market public information to enhance the stability with privacy perseverance. Case studies involving a real-world scenario validate the superior performance of the proposed method in reducing both the energy costs and the carbon emissions.

The deployment of renewable energy in power systems may raise serious voltage instabilities. Electric vehicles (EVs), owing to their mobility and flexibility characteristics, can provide various ancillary services including active and reactive power. However, the distributed control of EVs under such scenarios is a complex decision-making problem with enormous dynamics and uncertainties. Most existing literature employs model-based approaches to formulate active and reactive power control problems, which require full models and are time-consuming. This article proposes a multiagent reinforcement learning algorithm featuring a deep deterministic policy gradient (DDPG) method and a parameter sharing framework to solve the EVs’ coordinated active and reactive power control problem toward both demand-side response and voltage regulations. The proposed algorithm can further enhance the learning stability and scalability with privacy perseverance via the location marginal prices. Simulation results based on a modified IEEE 15-bus network are developed to validate its effectiveness in providing system charging and voltage regulation services. The proposed location marginal price (LMP) PSDDPG algorithm is evaluated to achieve 38%, 16%, and 25% speedup, and 1.58, 0.69, and 0.27 times higher reward over the benchmarks DDPG, TD3, and LMP-DDPG, respectively.

In responseto low-carbon requirements, a large amount of renewable energy resources (RESs) have been deployed in power systems; nevertheless, the intermittency of RESs raises the system vulnerability and even causes severe damage under extreme events. Electric vehicles (EVs), owing to their mobility and flexibility characteristics, can provide various ancillary services meanwhile enhancing system resilience. The distributed control of EVs under such scenarios in power-transportation network becomes a complex decision-making problem with enormous dynamics and uncertainties. To this end, a multiagent reinforcement learning method is proposed to compute both discrete and continuous actions simultaneously that aligns with the nature of EV routing and scheduling problems. Furthermore, the proposed method can enhance the learning stability and scalability with privacy perseverance in the multiagent setting. Simulation results based on IEEE 6- and 33-bus power networks integrated with transportation systems validate its effectiveness in providing system resilience and carbon intensity service.

Coronavirus disease2019 (COVID-19)has become a global pandemic. Many recognition approaches based on convolutional neural networks have been proposed for COVID-19 chest X-ray images. However, only a few of them make good use of the potential inter- and intra-relationships of feature maps. Considering the limitation mentioned above, this paper proposes an attention-based convolutional neural network, called PCXRNet, for diagnosis of pneumonia using chest X-ray images. To utilize the information from the channels of the feature maps, we added a novel condense attention module (CDSE) that comprised of two steps: condensation step and squeeze-excitation step. Unlike traditional channel attention modules, CDSE first downsamples the feature map channel by channel to condense the information, followed by the squeeze-excitation step, in which the channel weights are calculated. To make the model pay more attention to informative spatial parts in every feature map, we proposed a multi-convolution spatial attention module (MCSA). It reduces the number of parameters and introduces more nonlinearity. The CDSE and MCSA complement each other in series to tackle the problem of redundancy in feature maps and provide useful information from and between feature maps. We used the ChestXRay2017 dataset to explore the internal structure of PCXRNet, and the proposed network was applied to COVID-19 diagnosis. As a result, the network achieves an accuracy of 94.619%, recall of 94.753%, precision of 95.286%, and F1-score of 94.996% on the COVID-19 dataset.

Knee osteoarthritis (OA) is a common skeletal muscle disease with a high incidence in the elderly. Common symptoms of knee OA include popping, swelling, and fluid accumulation. Certain serious cases may experience joint deformities. The accuracy of clinical diagnosis often depends on the subjective experience of radiologists. Computer-aided diagnosis can effectively reduce the workload of radiologists and improve the diagnostic efficiency. In this paper, a channel attention module and spatial attention module are introduced to enhance the utilization of effective information and the suppression of unwanted information. The merged results of the double branches in the attention modules were compressed and transformed. The Mish activation function was introduced to enhance the stability of the network and enable the network to converge quickly. Training and testing were performed on a knee OA dataset, and the proposed method achieved an overall accuracy, recall, precision and F1 scores of 70.23, 68.23, 70.25, and 67.55% respectively, demonstrating that the network could achieve state-of-the-art results on the knee OA dataset. A gradient-weighted class activation-mapping algorithm was applied to visualize the output results.

With increasing prosumers employed with distributed energy resources (DER), advanced energy management has become increasingly important. To this end, integrating demand-side DER into electricity market is a trend for future smart grids. The double-side auction (DA) market is viewed as a promising peer-to-peer (P2P) energy trading mechanism that enables interactions among prosumers in a distributed manner. To achieve the maximum profit in a dynamic electricity market, prosumers act as price makers to simultaneously optimize their operations and trading strategies. However, the traditional DA market is difficult to be explicitly modelled due to its complex clearing algorithm and the stochastic bidding behaviors of the participants. For this reason, in this paper we model this task as a multi-agent reinforcement learning (MARL) problem and propose an algorithm called DA-MADDPG that is modified based on MADDPG by abstracting the other agents’ observations and actions through the DA market public information for each agent’s critic. The experiments show that 1) prosumers obtain more economic benefits in P2P energy trading w.r.t. the conventional electricity market independently trading with the utility company; and 2) DA-MADDPG performs better than the traditional Zero Intelligence (ZI) strategy and the other MARL algorithms, e.g., IQL, IDDPG, IPPO and MADDPG.

The problem of real-time autonomous energy management is an application area that is receiving unprecedented attention from consumers, governments, academia, and industry. This paper showcases the first application of deep reinforcement learning (DRL) to real-time autonomous energy management for a multi-carrier energy system. The proposed approach is tailored to align with the nature of the energy management problem by posing it in multi-dimensional continuous state and action spaces, in order to coordinate power flows between different energy devices, and to adequately capture the synergistic effect of couplings between different energy carriers. This fundamental contribution is a significant step forward from earlier approaches that only sought to control the power output of a single device and neglected the demand-supply coupling of different energy carriers. Case studies on a real-world scenario demonstrate that the proposed method significantly outperforms existing DRL methods as well as model-based control approaches in achieving the lowest energy cost and yielding a representation of energy management policies that adapt to system uncertainties.

In traditional Chinese medicine processing domain, the ‘firepower’ and ‘proper roasting’ are vital for medicinal efficacy of Chinese herbs. We take phellodendron microscopic images to determine if the roasting is appropriate according to some features of crystal fiber and stone cell, these features include color, geometrical appearance, and so on. The first step of feature analysis is to segment objects accurately. In the paper, we propose an efficient unsupervised algorithm to segment stone cell and crystal fiber in phellodendron microscopic images automatically without any human's intervene. Firstly, the superpixels is adopted, then the method extracts features such as RGB, Sobel, Harris and so on, clustering superpixels patches according to the characteristic of phellodendron, lastly morphological operations are implemented to produce segmented stone cell and crystal fiber. The experimental evaluation shows that the proposed algorithm can segment objects automatically with about 87% precision and 93% recall.

The rolling bearing fault diagnosis with vibration data is critical to the reliability and the safety of rotating machinery. According to the non-stationary characteristics and the simple logical structure characteristics of rolling bearing vibration data, a rolling bearing fault diagnosis method based on modified bidirectional long short-term memory (Bi-LSTM) neural network is put forward in this paper. Firstly, original vibration data are decomposed into time-frequency feature with the combination of Daubechies 10 wavelet packet transform and Symlets 8 wavelet packet transform. Then, we design bidirectional long-term memory (Bi-LTM) neural network, the Bi-LTM neural network only uses long-term memory to process rolling bearing feature data and get the result of fault diagnosis. In order to enhance functionality of the Bi-LTM internal activation function, the Bi-LTM internal function uses softsign. We evaluate our models on a standard dataset. Moreover, given the analytical results, compared to Bi-LSTM, the proposed Bi-LTM method further reduces the rolling bearing fault diagnosis error rate by 6 times. Numerical and simulation results verify that the rolling bearing fault diagnosis method based on the proposed method is justified.