Deep Lossless Compression Algorithm Based on Arithmetic Coding for Power Data.

Classical lossless compression algorithm highly relies on artificially designed encoding and quantification strategies for general purposes. With the rapid development of deep learning, data-driven methods based on the neural network can learn features and show better performance on specific data domains. We propose an efficient deep lossless compression algorithm, which uses arithmetic coding to quantify the network output. This scheme compares the training effects of Bi-directional Long Short-Term Memory (Bi-LSTM) and Transformers on minute-level power data that are not sparse in the time-frequency domain. The model can automatically extract features and adapt to the quantification of the probability distribution. The results of minute-level power data show that the average compression ratio (CR) is 4.06, which has a higher compression ratio than the classical entropy coding method.

Characteristics and Effectiveness of the Coronavirus Disease 2019 (COVID-19) Prevention and Control in a Representative City in China.

BACKGROUND SARS-CoV-2 has caused a pandemic. Control measures differ among countries. It is necessary to assess the effectiveness of these control measures. MATERIAL AND METHODS We collected the data of COVID-19 patients and control measures between January 18, 2020 and September 18, 2020 from the Changshou District and analyzed the clinical characteristics, epidemiological data, and the adjustment of policies to assess the effectiveness of control measures. The control of COVID-19 was divided into 2 stages, with the lifting of lockdown in Hubei province (March 25, 2020) as a dividing line. RESULTS We identified 32 patients through different means in the first stage. All the imported patients entered this area before the lockdown. In 93.1% of patients, the last exposure occurred before the implementation of the stay-at-home order and centralized isolation. Tracing of high-risk people and RT-PCR screening identified 56.3% of cases. In the second stage, all the high-risk people were under centralized isolation. Nine asymptomatic patients were identified. City lockdown and stay-at-home orders were not issued again, and no second-generation patients were found. CONCLUSIONS We have provided a successful model to control the transmission of COVID-19 in a short period.

Definition and retrospective application of a clinical scoring system for COVID-19 triage at presentation.

BACKGROUND: A simple scoring system for triage of suspected patients with COVID-19 is lacking. METHODS: A multi-disciplinary team developed a screening score taking into account epidemiology history, clinical feature, radiographic feature, and routine blood test. At fever clinics, the screening score was used to identify the patients with moderate to high probability of COVID-19 among all the suspected patients. The patients with moderate to high probability of COVID-19 were allocated to a single room in an isolation ward with level-3 protection. And those with low probability were allocated to a single room in a general ward with level-2 protection. At the isolation ward, the screening score was used to identify the confirmed and probable cases after two consecutive real-time reverse transcription polymerase chain reaction (RT-PCR) tests. The data in the People's Hospital of Changshou District were used for internal validation and those in the People's Hospital of Yubei District for external validation. RESULTS: We enrolled 76 and 40 patients for internal and external validation, respectively. In the internal validation cohort, the area under the curve of receiver operating characteristics (AUC) was 0.96 [95% confidence interval (CI): 0.89-0.99] for the diagnosis of moderate to high probability of cases among all the suspected patients. Using 60 as cut-off value, the sensitivity and specificity were 88% and 93%, respectively. In the isolation ward, the AUC was 0.94 (95% CI: 0.83-0.99) for the diagnosis of confirmed and probable cases. Using 90 as cut-off value, the sensitivity and specificity were 78% and 100%, respectively. These results were confirmed in the validation cohort. CONCLUSION: The scoring system provides a reference on COVID-19 triage in fever clinics to reduce misdiagnosis and consumption of protective supplies.The reviews of this paper are available via the supplemental material section.