In current power grids, a massive amount of power equipment raises various emerging requirements, e.g., data perception, information transmission, and real-time control. The existing cloud computing paradigm is stubborn to address issues and challenges such as rapid response and local autonomy. Microgrids contain diverse and adjustable power components, making the power system complex and difficult to optimize. The existing traditional adjusting methods are manual and centralized, which requires many human resources with expert experience. The adjustment method based on edge intelligence can effectively leverage ubiquitous computing capacities to provide distributed intelligent solutions with lots of research issues to be reckoned with. To address this challenge, we consider a power control framework combining edge computing and reinforcement learning, which makes full use of edge nodes to sense network state and control power equipment to achieve the goal of fast response and local autonomy. Additionally, we focus on the non-convergence problem of power flow calculation, and combine deep reinforcement learning and multi-agent methods to realize intelligent decisions, with designing the model such as state, action, and reward. Our method improves the efficiency and scalability compared with baseline methods. The simulation results demonstrate the effectiveness of our method with intelligent adjusting and stable operation under various conditions.

Ultrasonography (US) is frequently applied in clinical imaging because of its inherent merits compared with those of other imaging methods. Nanoparticle (NP)‐based imaging and therapeutic modalities have been widely used because of their unique functionalities and high performance. The report is mainly about the classifications and applications of NPs for US‐based theranostic biomedicine. The US‐based applications include single‐modality US imaging, multimodality US imaging, high‐intensity focused US, US‐triggered drug release, US‐enhanced gene transfection, and US‐irradiated sonodynamic therapy. In addition, current challenges, including the biological effects and biosafety, are discussed in this interview. NPs have tremendous potential as a US‐based theranostic tool and have revealed a new direction in cancer therapy.

Graph Neural Networks~(GNNs) have emerged as a powerful category of learning architecture for handling graph-structured data. However, existing GNNs typically ignore crucial structural characteristics in node-induced subgraphs, which thus limits their expressiveness for various downstream tasks. In this paper, we strive to strengthen the representative capabilities of GNNs by devising a dedicated plug-and-play normalization scheme, termed as SUbgraph-sPEcific FactoR Embedded Normalization (SuperNorm), that explicitly considers the intra-connection information within each node-induced subgraph. To this end, we embed the subgraph-specific factor at the beginning and the end of the standard BatchNorm, as well as incorporate graph instance-specific statistics for improved distinguishable capabilities. In the meantime, we provide theoretical analysis to support that, with the elaborated SuperNorm, an arbitrary GNN is at least as powerful as the 1-WL test in distinguishing non-isomorphism graphs. Furthermore, the proposed SuperNorm scheme is also demonstrated to alleviate the over-smoothing phenomenon. Experimental results related to predictions of graph, node, and link properties on the eight popular datasets demonstrate the effectiveness of the proposed method. The code is available at https://github.com/chenchkx/SuperNorm.

This letter has developed an electrical circuit analogy-based maximum latency calculation (MLC) method of the internet data center (IDC) in power-communication network. Firstly, by analogy with the circuit model, the basic concepts to describe information flow are defined, including information current, information resistance, information conductivity, and information voltage. Based on these concepts, the information processing model considering both channel blocking and user priority is established. By analogy with the electrical circuit, the information flow calculation laws are introduced to calculate the maximum latency of IDCs. Verification results show that the maximum latency of IDCs in power-communication network can be accurately calculated by the proposed MLC method.

Background: To study the correlation of neurological function in degenerative cervical myelopathy (DCM) patients with quantitative assessment of spinal cord compression and impairment by intraoperative ultrasound imaging (IOUSI). Methods: Twenty-three patients who underwent French-Door laminoplasty for multilevel DCM were followed for 6 months. Modified Japanese Orthopaedic Association (mJOA) score and cervical MRI were assessed before surgery and at postoperative 6 months. IOUS, used to guide decompression, were recorded. The anteroposterior diameter (APD) and the gray values of the IOUSI hyperechogenicity of the midsagittal IOUSI at the narrowest level and at the lesion-free level, and the APD and traverse diameter at the traverse maximum compression level of IOUSI were measured. Maximum spinal cord compression (MSCC), compression rate (CR), and IOUSI gray value ratio (R_gray) were calculated. The appearance of preoperative T2W MRI increased signal intensity (ISI), and the signal change rate (SCR) on postoperative T2W MRI of 9 patients were also measured and calculated, and compared with that of IOUSI hyperechogenicity. Results: Average mJOA score increased significantly from 11.57 ± 2.67 before surgery to 15.39 ± 1.50 at 6 months after surgery, with an average recovery rate (RR) of 71.11 ± 22.81%. The difference between the appearance of preoperative T2W MRI ISI and IOUSI hyperechogenicity was not significant. Spearman correlation analysis found that the IOUSI R_gray were negatively correlated with the RR of mJOA score with a coefficient of − 0.77, and the IOUSI R_gray was not correlated with the postoperative MRI SCR. Conclusions: In DCM patients, the gray values of IOUSI can be measured accurately. The IOUSI R_gray correlated with postoperative neurological recovery significantly.