Forecasting traffic flow is a typical time series problem, which has attracted increasing attention due to the urgent need in intelligent transportation systems. Although numerous time series forecasting methods have been investigated in past decades, from statistics based models to deep neural networks models, the main disadvantages of aforementioned work could be summarized as follows: 1) incapable to handle the complexity and uncertainty of series; 2) incapable to consider external features such as spatial information and importance of points during the learning process; 3) unstable performance on forecasting task given various data patterns. In this study, a novel strategy was proposed to extract context-awareness information and then integrated with Temporal Convolution Network(TCN) model, namely Context-Aware Temporal Convolution Network(CATCN), which utilized local sub-segments to portrait the potential patterns of a series based on series decomposition. The experiments were conducted using three sets of field-captured traffic datasets. The results were presented and compared to state-of-the-art methodologies. The results showed that the performance of proposed method is significantly improved, especially, on the auto-correlation series corpora.

Background: Psoriasis is a chronic inflammatory skin disease due to genetic susceptibility and multiple environmental factors. Transient receptor potential vanilloid 4 (TRPV4) is a calcium channel extensively expressed throughout the body with multiple functions. However, the role of TRPV4 in imiquimod (IMQ)-induced -psoriasis progression remains unclear although it is ubiquitously expressed in skin tissues and participates in cutaneous mechano- and thermo-sensation. Methods: Both in vivo and in vitro studies were performed in murine skin tissue and isolated cells. TRPV4 expression, autophagy, and Akt/mTOR phosphorylation were assessed by Western blot and reactive oxygen species (ROS) generation was examined by MitoSOX staining. Cytokine levels were measured by ELISA and cell proliferation was determined by CCK staining. The severity of psoriasis was also checked by psoriasis severity index (PSI), scale and thickness scoring and microscopic observations. Results: IMQ-induced psoriasis was remarkably attenuated in TRPV4 knockout mice compared with their wild-type counterparts, accompanied by reduced expression of several inflammatory cytokines. Deletion of TRPV4 diminished ROS production and Akt/mTOR phosphorylation. In vitro experiments showed that IMQ caused a concentration-dependent increase in autophagy, characterized by an initial increasing phase followed by a declining phase in primary keratinocytes. IMQ-induced autophagic activity was enhanced via Calmodulin/Akt pathway suppression while weakened by CaMKKβ/AMPK pathway inhibition. Moreover, blockade of the Calmodulin/Akt pathway significantly reduced IMQ-induced ROS production and psoriasis severity, whereas inhibition of the CaMKKβ/AMPK pathway exacerbated IMQ-induced psoriasis progression through ROS accumulation. Conclusions: Both CaMKKβ/AMPK and Calmodulin/Akt signaling pathways, as downstream components of TRPV4, are involved in IMQ-induced psoriasis: lower IMQ dosage activates AMPK, thereby preventing psoriasis by ROS clearance, whereas higher IMQ dosage activates Calmodulin and exacerbates psoriasis. Our findings reveal the potential values of targeting TRP-related channels in IMQ-induced psoriasis.