RESUMO
A High Altitude Platform Station (HAPS) can facilitate high-speed data communication over wide areas using high-power line-of-sight communication; however, it can significantly interfere with existing systems. Given spectrum sharing with existing systems, the HAPS transmission power must be adjusted to satisfy the interference requirement for incumbent protection. However, excessive transmission power reduction can lead to severe degradation of the HAPS coverage. To solve this problem, we propose a multi-agent Deep Q-learning (DQL)-based transmission power control algorithm to minimize the outage probability of the HAPS downlink while satisfying the interference requirement of an interfered system. In addition, a double DQL (DDQL) is developed to prevent the potential risk of action-value overestimation from the DQL. With a proper state, reward, and training process, all agents cooperatively learn a power control policy for achieving a near-optimal solution. The proposed DQL power control algorithm performs equal or close to the optimal exhaustive search algorithm for varying positions of the interfered system. The proposed DQL and DDQL power control yields the same performance, which indicates that the actional value overestimation does not adversely affect the quality of the learned policy.
RESUMO
Although various linear log-distance path loss models have been developed for wireless sensor networks, advanced models are required to more accurately and flexibly represent the path loss for complex environments. This paper proposes a machine learning framework for modeling path loss using a combination of three key techniques: artificial neural network (ANN)-based multi-dimensional regression, Gaussian process-based variance analysis, and principle component analysis (PCA)-aided feature selection. In general, the measured path loss dataset comprises multiple features such as distance, antenna height, etc. First, PCA is adopted to reduce the number of features of the dataset and simplify the learning model accordingly. ANN then learns the path loss structure from the dataset with reduced dimension, and Gaussian process learns the shadowing effect. Path loss data measured in a suburban area in Korea are employed. We observe that the proposed combined path loss and shadowing model is more accurate and flexible compared to the conventional linear path loss plus log-normal shadowing model.
RESUMO
Treatment of multiple sclerosis is effective when anti-inflammatory, neuroprotective and regenerative strategies are combined. Dendropanax morbiferus (DM) has anti-inflammatory, anti-oxidative properties, which may be beneficial for multiple sclerosis. However, there have been no reports on the effects of DM on myelination, which is critical for regenerative processes. To know whether DM benefits myelination, we checked differentiation and myelination of oligodendrocytes (OLs) in various primary culture systems treated with DM leaf EtOH extracts or control. DM extracts increased the OL membrane size in the mixed glial and pure OL precursor cell (OPC) cultures and changed OL-lineage gene expression patterns in the OPC cultures. Western blot analysis of DM-treated OPC cultures showed upregulation of MBP and phosphorylation of ERK1/2. In myelinating cocultures, DM extracts enhanced OL differentiation, followed by increased axonal contacts and myelin gene upregulations such as Myrf, CNP and PLP. Phytochemical analysis by LC-MS/MS identified multiple components from DM extracts, containing bioactive molecules such as quercetin, cannabidiol, etc. Our results suggest DM extracts enhance OL differentiation, followed by an increase in membrane size and axonal contacts, thereby indicating enhanced myelination. In addition, we found that DM extracts contain multiple bioactive components, warranting further studies in relation to finding effective components for enhancing myelination.