Purpose To ensure the safety of electric power supply, it is necessary to inspect substation equipment. With the dramatic increase in the number of substations, especially indoor substations, intelligent robot inspection has become an important development direction. This paper aims to describe the design of a trackless robot with a robotic arm, which is capable of navigating autonomously and inspecting the equipment in a narrow and complex indoor substation. Design/methodology/approach A robust four-wheel platform powered by electric motors is used to carry the robot. By fusing multiple-sensor data and visual markers, the robot achieves autonomous movement based on simultaneous localization and mapping. In addition, to accurately obtain the reading of meters located at height or in a narrow space, the robot is equipped with a newly designed visual servo robotic arm. Findings In practical application, the robot satisfies the requirements of substation inspection, improves work efficiency, saves costs and achieves good results. The robot is also approved by the relevant departments of the State Grid Corporation of China. Practical implications After stable operation in a substation for a period of one year, the robot shows high efficiency and stability, meeting the requirements of indoor substation inspection. Meanwhile, the robot greatly promoted the realization of indoor and outdoor integrated substation automatic inspection, and is expected to be further applied in other industrial inspection sites, including mine, tunnel and nuclear power plant. Originality/value Due to the complex indoor environment, most of the existing inspection robots are only used outdoors, and there are no good trackless inspection robots for use indoors. The proposed robot is a trackless intelligent inspection robot for use in indoor substations. The robot features a number of important modules, including an autonomous localization and navigation module and a visual servo manipulator module, which can be used in narrow spaces or at height.
Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy. This paper introduces an end-to-end deep learning model, named RKGCN, which dynamically analyses each user's preferences and makes a recommendation of suitable items. It combines knowledge graphs on both the item side and user side to enrich their representations to maximize the utilization of the abundant information in knowledge graphs. RKGCN is able to offer more personalized and relevant recommendations in three different scenarios. The experimental results show the superior effectiveness of our model over 5 baseline models on three real-world datasets including movies, books, and music.
Abstract Background: The progression of coagulation in COVID-19 patients with confirmed discharge status and the combination of autopsy with complete hemostasis parameters have not been well studied. Objective : To clarify the thrombotic phenomena and hemostasis state in COVID-19 patients based on epidemiological statistics combining autopsy and statistical analysis. Methods: Using autopsy results from 9 patients with COVID-19 pneumonia and the medical records of 407 patients, including 39 deceased patients whose discharge status was certain, time-sequential changes in 11 relevant indices within mild, severe and critical infection throughout hospitalization according to the Chinese National Health Commission (NHC) guidelines were evaluated. Statistical tools were applied to calculate the importance of 11 indices and the correlation between those indices and the severity of COVID-19. Results: At the beginning of hospitalization, platelet (PLT) counts were significantly reduced in critically ill patients compared with severely or mildly ill patients. Blood glucose (GLU), prothrombin time (PT), activated partial thromboplastin time (APTT), and D-dimer levels in critical patients were increased compared with mild and severe patients during the entire admission period. The International Society on Thrombosis and Haemostasis (ISTH) disseminated intravascular coagulation (DIC) score was also high in critical patients. In the relatively late stage of nonsurvivors, the temporal changes in PLT count, PT, and D-dimer levels were significantly different from those in survivors. A random forest model indicated that the most important feature was PT followed by D-dimer, indicating their positive associations with disease severity. Autopsy data from 9 deceased patients also revealed DIC phenomena with prolonged PT, APTT, lower PLT count and thrombosis in multiple organs. Conclusions: Combining autopsy data, time-sequential changes and statistical methods to explore hemostasis-relevant indices among the different severities of the disease helps guide therapy and detect prognosis in COVID-19 infection.
With the increasing use of high-precision system analysis programs in nuclear engineering, the number of high-fidelity computational data for accident simulation is exploding. Therefore, an algorithm that can achieve both automatic extraction of low-dimensional features from the data and guarantee the validity of the features is needed to improve the performance and confidence of the accident diagnosis system. This study proposes an autoencoder-based autonomous learning framework, namely Padded Auto-Encoder (PAE), which is able to automatically encode accident monitoring data that has been noise-added and with partially missing data into low-dimensional feature vectors via a Vision Transformer-based encoder, and to decode the feature vectors into noise-free and complete reconstructed monitoring data. Thus, the encoder part of the framework is able to automatically infer valid representations from partially missing and noisy monitoring data that reflect the complete and noise-free original data, and the representation vectors can be used for downstream tasks for accident diagnosis or else. In this paper, LOCA of HPR1000 was used as the study object, and the PAE was trained by an unsupervised method using cases with different break locations and sizes as the dataset. The encoder part of the pre-trained PAE was subsequently used as the feature extractor for the monitoring data, and several basic statistical learning algorithms for predicting the break locations and sizes. The results of the study show that the pre-trained diagnostic model with two stages has a better performance in break location and size diagnostic capability with an improvement of 41.62% and 80.86% in the metrics respectively, compared to the diagnostic model with end-to-end model structure.
Abstract Background: The progress of coagulation in COVID-19 patients with confirmed discharge status (decease or discharge) and the combination of the autopsy with the complete coagulation parameters were not well studied. Objective : To clarify the thrombotic phenomena with coagulation progress in COVID-19 patients based on epidemiological statistics combining the autopsy and informatics analysis. Methods: Using 9 autopsy results with COVID-19 pneumonia and the medical records of 407 patients including 39 deceased ones whose discharge status was certain, time-sequential changes of 11 relevant indices within mild, severe and critical infection throughout hospitalization according to the Chinese National Health Commission (NHC) guidelines were evaluated. Informatics tools were applied to calculate the importance of 11 indices and the correlation between those indices and the severities of COVID-19. Results: At the beginning of the hospitalization, platelet (PLT) had a significant decrease in critically ill patients. Blood glucose (GLU), prothrombin time (PT), activated partial thromboplastin time (APTT), and D-dimer in critical patients were higher than those in mild and severe during the whole admission period. The International Society on Thrombosis and Haemostasis (ISTH) disseminated intravascular coagulation (DIC) score also showed the high DIC level in critical patients. At the relatively late stage of non-survivors, the temporal changes of PLT count, PT, and D-dimer were significantly different from survivors. A random forest model indicated that the most important feature was PT, followed by D-dimer, indicating their positive associations for the severities of disease. Autopsy data from 9 deceased patients also showed the DIC phenomena with prolonged PT, APTT, less PLT count and thrombosis in multiple organs. Conclusions : Combining autopsy data, time-sequential changes and informatics methods to explore the coagulation relevant indices among the different severities of the disease, helps guide the therapy and detect the prognosis in COVID-19 infection.
Different from object detection in natural image, optical remote sensing object detection is a challenging task, due to the diverse meteorological conditions, complex background, varied orientations, scale variations, etc. In this paper, to address this issue, we propose a novel object detection network (the global-local saliency constraint network, GLS-Net) that can make full use of the global semantic information and achieve more accurate oriented bounding boxes. More precisely, to improve the quality of the region proposals and bounding boxes, we first propose a saliency pyramid which combines a saliency algorithm with a feature pyramid network, to reduce the impact of complex background. Based on the saliency pyramid, we then propose a global attention module branch to enhance the semantic connection between the target and the global scenario. A fast feature fusion strategy is also used to combine the local object information based on the saliency pyramid with the global semantic information optimized by the attention mechanism. Finally, we use an angle-sensitive intersection over union (IoU) method to obtain a more accurate five-parameter representation of the oriented bounding boxes. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed GLS-Net achieves a state-of-the-art detection performance.
In this paper, we researched the status of the Visitor Locations Register (VLR) in the third generation communication system (3G). Basing on automata theory, we offer the statues modeling of the VLR, is called Visitor Locations Register Automata (VLRA), which formally describes the states, the behavior, and the variation of the VLR in the authentication protocol. Finally, we formally analyzed the VLRA in the authentication process.
We propose a compact visible light indoor positioning system fashioned with a single transmitter and a single tilted receiver. The tilted optical receiver is mounted on a rotatable platform and thus, various azimuth angles can be obtained by rotating the platform, which offers a feasible way to perform multiple measurements with different azimuth angles to achieve the angle gain. An indoor positioning algorithm is provided in comparison with the angle gain difference. Experimental results show that the average distance error between the estimated position and the real position is less than 25 mm in an indoor environment of 600mm×600mm×1135mm, which is in good agreement with the simulations. This work indicates that the proposed compact system is promising for visible light indoor positioning.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cpath fill='%23fff' d='m8.751-17.959 10.11 11.373L3.997-9.844l13.94-6.1-7.692 13.129z'/%3e%3c/svg%3e)