InRFNet: Involution Receptive Field Network for COVID-19 Diagnosis

COVID-19 is an emerging infectious disease that has been rampant worldwide since its onset causing Lung irregularity and severe respiratory failure due to pneumonia. The Community-Acquired Pneumonia (CAP), Normal, and COVID-19 Computed Tomography (CT) scan images are classified using Involution Receptive Field Network from Large COVID-19 CT scan slice dataset. The proposed lightweight Involution Receptive Field Network (InRFNet) is spatial specific and channel-agnostic with Receptive Field structure to enhance the feature map extraction. The InRFNet model evaluation results show high training (99%) and validation (96%) accuracy. The performance metrics of the InRFNet model are Sensitivity (94.48%), Specificity (97.87%), Recall (96.34%), F1-score (96.33%), kappa score (94.10%), ROC-AUC (99.41%), mean square error (0.04), and the total number of parameters (33100).

Thundercloud Electrostatic Field Measurements during the Inflight EXAEDRE Campaign and during Lightning Strike to the Aircraft

The AMPERA (Atmospheric Measurement of Potential and ElectRic field on Aircraft) electric field network was integrated on the Falcon 20 (F20) of SAFIRE (the French facility for airborne research) in the framework of EXAEDRE (EXploiting new Atmospheric Electricity Data for Research and the Environment) project. From September 2018, an in-flight campaign was performed over Corsica (France) to investigate the electrical activity in thunderstorms. During this campaign, eight scientific flights were done inside or in the vicinity of a thunderstorm. The purpose of this paper is to present the AMPERA system and the atmospheric electrostatic field recorded during the flights, and particularly during the pass inside electrified clouds, in which the aircraft was struck by lightning. The highest value of atmospheric electrostatic field recorded during these flights was around 79 kV·m−1 at 8400 m of altitude. A normalization of these fields is done by computing the reduced atmospheric electrostatic field to take into account the altitude effect (ratio between the atmospheric electrostatic field and the air density). Most of the significant values of reduced atmospheric electrostatic field magnitude retrieved during this campaign occur between around 5.5 and 9.5 km and are included between 50 and 100 kV·m−1. The highest value measured of the reduced atmospheric electrostatic field is 194 kV·m−1 during the lightning strike of the F20. The merging of these results with data from former campaigns suggests that there is a threshold (depending of the aircraft size) for the striking of an aircraft.

Electrocardio Panorama: Synthesizing New ECG views with Self-supervision

Multi-lead electrocardiogram (ECG) provides clinical information of heartbeats from several fixed viewpoints determined by the lead positioning. However, it is often not satisfactory to visualize ECG signals in these fixed and limited views, as some clinically useful information is represented only from a few specific ECG viewpoints. For the first time, we propose a new concept, Electrocardio Panorama, which allows visualizing ECG signals from any queried viewpoints. To build Electrocardio Panorama, we assume that an underlying electrocardio field exists, representing locations, magnitudes, and directions of ECG signals. We present a Neural electrocardio field Network (Nef-Net), which first predicts the electrocardio field representation by using a sparse set of one or few input ECG views and then synthesizes Electrocardio Panorama based on the predicted representations. Specially, to better disentangle electrocardio field information from viewpoint biases, a new Angular Encoding is proposed to process viewpoint angles. Also, we propose a self-supervised learning approach called Standin Learning, which helps model the electrocardio field without direct supervision. Further, with very few modifications, Nef-Net can synthesize ECG signals from scratch. Experiments verify that our Nef-Net performs well on Electrocardio Panorama synthesis, and outperforms the previous work on the auxiliary tasks (ECG view transformation and ECG synthesis from scratch). The codes and the division labels of cardiac cycles and ECG deflections on Tianchi ECG and PTB datasets are available at https://github.com/WhatAShot/Electrocardio-Panorama.

Heterogeneous field network for power distribution grid based on HPLC and RF adaptive communications technology

In order to improve the connection rate and transmission efficiency of field network for power distribution grid, a dual-mode heterogeneous field network with high-speed power line broadband carrier and micro-power radio frequency wireless communication capabilities was designed. First, the topological structure of the field network, the networking process of the central node and the free nodes and the dynamic maintenance mechanism of the network were discussed in detail. Secondly, the routing measurement mechanism for creating a hybrid routing table and the improved layer limit shortest path routing algorithm were presented. On this basis, each node in the network could choose the optimal communication media at any given moment to create communication links with the adaptive data transfer speed according to the real-time hybrid routing table. Finally, the dual-mode heterogeneous field network was applied to the electricity consumption information collection system and tested in the laboratory and jobsite. The test results show that the dual-mode field network was more effective than the single-mode field network in shortening the reading meter time and increasing networking success rate.