RESUMO
In order to realize the optimization of autonomous navigation of mobile robot under the condition of partial environmental knowledge known. An improved Q-learning reinforcement learning algorithm based on prior knowledge is proposed to solve the problem of slow convergence and low learning efficiency in mobile robot path planning. Prior knowledge is used to initialize the Q-value, so as to guide the agent to move toward the target direction with a greater probability from the early stage of the algorithm, eliminating a large number of invalid iterations. The greedy factor ε is dynamically adjusted based on the number of times the agent successfully reaches the target position, so as to better balance exploration and exploitation and accelerate convergence. Simulation results show that the improved Q-learning algorithm has a faster convergence rate and higher learning efficiency than the traditional algorithm. The improved algorithm has practical significance for improving the efficiency of autonomous navigation of mobile robots.
Assuntos
Algoritmos , Conhecimento , Simulação por Computador , Probabilidade , RegistrosRESUMO
Purpose: ARFIP2, a canonical BAR domain-containing protein, is closely associated with regulating cargo exit from the Golgi. However, the potential biological functions of ARFIP2 in hepatocellular carcinoma (HCC) have not been well investigated. This study aimed to explore the critical role of ARFIP2 in HCC cells. Methods: The expression of proteins related to epithelial to mesenchymal transition (EMT) and cell autophagy in HCC cells and tissues was assayed by quantitative real-time PCR, Western blotting, immunohistochemistry and immunofluorescence staining. The ability of cells to proliferate, migrate and invade was detected by Cell Counting Kit-8, Transwell migration and invasion assays. In addition, the function of ARFIP2 in vivo was assessed using a tumour xenograft model. Results: ARFIP2 expression is significantly upregulated in early recurrent and metastatic HCC patients and was positively correlated with a poor prognosis. ARFIP2 overexpression promoted cell proliferation, migration, and invasion by inducing EMT and inhibiting autophagy in vitro. Furthermore, the regulatory effects of ARFIP2 on autophagy and EMT were partially attributed to its regulation of the PI3K/AKT signalling pathway. The in vivo results also showed that ARFIP2 modulates HCC progression. Conclusion: Our results substantiate a novel mechanism by which ARFIP2 can regulate the activity/phosphorylation of Akt to promote EMT and inhibit autophagy in part via the PI3K/Akt signalling pathway. The ARFIP2/PI3K/Akt axis may be a potential diagnostic biomarker and therapeutic target for HCC.
RESUMO
BACKGROUND: No data is available about in-flight transmission of SARS-CoV-2. Here, we report an in-flight transmission cluster of COVID-19 and describe the clinical characteristics of these patients. METHODS: After a flight, laboratory-confirmed COVID-19 was reported in 12 patients. Ten patients were admitted to the designated hospital. Data was collected from 25th January to 28th February 2020. Clinical information was retrospectively collected. RESULTS: All patients were passengers, and none were flight attendants. The median age was 33 years, and 70% were females. None was admitted to intensive care unit, and no patients died up to 28th February. The median incubation period was 3.0 days and time from onset of illness to hospital admission was 2 days. The most common symptom was fever. Two patients were asymptomatic and had normal chest CT scan during hospital stay. On admission, initial RT-PCR was positive in 9 patients, and initial chest CT was positive in half of the patients. The median lung 'total severity score' of chest CT was 6. 'Crazy-paving' pattern, pleural effusion, and ground-glass nodules were seen. CONCLUSION: There is potential for COVID-19 transmission in aeroplanes, but the symptoms were mild in our patients. Passengers and attendants must be protected during flights.
