RESUMO
The precise forecasting of air quality is of great significance as an integral component of early warning systems. This remains a formidable challenge owing to the limited information of emission source and the considerable uncertainties inherent in dynamic processes. To improve the accuracy of air quality forecasting, this work proposes a new spatiotemporal hybrid deep learning model based on variational mode decomposition (VMD), graph attention networks (GAT) and bi-directional long short-term memory (BiLSTM), referred to as VMD-GAT-BiLSTM, for air quality forecasting. The proposed model initially employ a VMD to decompose original PM2.5 data into a series of relatively stable sub-sequences, thus reducing the influence of unknown factors on model prediction capabilities. For each sub-sequence, a GAT is then designed to explore deep spatial relationships among different monitoring stations. Next, a BiLSTM is utilized to learn the temporal features of each decomposed sub-sequence. Finally, the forecasting results of each decomposed sub-sequence are aggregated and summed as the final air quality prediction results. Experiment results on the collected Beijing air quality dataset show that the proposed model presents superior performance to other used methods on both short-term and long-term air quality forecasting tasks.
RESUMO
Ship images are easily affected by light, weather, sea state, and other factors, making maritime ship recognition a highly challenging task. To address the low accuracy of ship recognition in visible images, we propose a maritime ship recognition method based on the convolutional neural network (CNN) and linear weighted decision fusion for multimodal images. First, a dual CNN is proposed to learn the effective classification features of multimodal images (i.e., visible and infrared images) of the ship target. Then, the probability value of the input multimodal images is obtained using the softmax function at the output layer. Finally, the probability value is processed by linear weighted decision fusion method to perform maritime ship recognition. Experimental results on publicly available visible and infrared spectrum dataset and RGB-NIR dataset show that the recognition accuracy of the proposed method reaches 0.936 and 0.818, respectively, and it achieves a promising recognition effect compared with the single-source sensor image recognition method and other existing recognition methods.
RESUMO
Automatic electroencephalogram (EEG) emotion recognition is a challenging component of human-computer interaction (HCI). Inspired by the powerful feature learning ability of recently-emerged deep learning techniques, various advanced deep learning models have been employed increasingly to learn high-level feature representations for EEG emotion recognition. This paper aims to provide an up-to-date and comprehensive survey of EEG emotion recognition, especially for various deep learning techniques in this area. We provide the preliminaries and basic knowledge in the literature. We review EEG emotion recognition benchmark data sets briefly. We review deep learning techniques in details, including deep belief networks, convolutional neural networks, and recurrent neural networks. We describe the state-of-the-art applications of deep learning techniques for EEG emotion recognition in detail. We analyze the challenges and opportunities in this field and point out its future directions.
RESUMO
Interleukin-1ß (IL-1ß), a key pro-inflammatory cytokine, is majorly produced by macrophages through NOD-, LRR-, and pyrin domain-containing protein 3 (NLRP3) inflammasome, which has been identified as the culprit to deteriorate the inflammatory crosstalk between macrophages and adipocytes. Ainsliadimer C (AC) is a disesquiterpenoid isolated from Ainsliaea macrocephala. In the current study, we investigated the effects of AC on adipose tissue inflammation in co-culture of macrophages and adipocytes in vitro as well as in LPS-treated mice in vivo. We showed that AC (20-80 µM) dose-dependently inhibited the secretion of IL-1ß from LPS plus ATP-stimulated THP-1 macrophages by inhibiting the activation of NLRP3 inflammasome. Furthermore, we found that AC treatment activated NAD+-dependent deacetylase Sirtuin 1 (SIRT1), resulting in reduced acetylation level of NLRP3. Molecular modeling analysis revealed that binding of AC to sirtuin-activating compound-binding domain increased the affinity of the substrate to the catalytic domain of SIRT1. Moreover, AC (80 µM) significantly attenuated macrophage-conditioned medium-induced inflammatory responses in 3T3-L1 adipocytes. In LPS-induced acute inflammatory mice, administration of AC (20, 60 mg·kg-1·d-1, ip) for 5 days significantly suppressed the pro-inflammatory cytokine levels in serum and epididymal white adipose tissue (eWAT), attenuated macrophage infiltration into eWAT, and mitigated adipose tissue inflammation. The beneficial effects of AC were blocked by co-administration of a selective SIRT1 inhibitor EX-527 (10 mg·kg-1·d-1). Taken together, AC suppresses NLRP3-mediated IL-1ß secretion through activating SIRT1, leading to attenuated inflammation in macrophages and adipose tissue, which might be a candidate to treat obesity-associated metabolic diseases.
Assuntos
Inflamassomos , Proteína 3 que Contém Domínio de Pirina da Família NLR , Tecido Adiposo/metabolismo , Animais , Citocinas/metabolismo , Inflamassomos/metabolismo , Inflamação/tratamento farmacológico , Inflamação/metabolismo , Interleucina-1beta/metabolismo , Lipopolissacarídeos/farmacologia , Camundongos , Camundongos Endogâmicos NOD , Proteína 3 que Contém Domínio de Pirina da Família NLR/metabolismo , Sirtuína 1/metabolismoRESUMO
Macrocephatriolides A and B (1 and 2), two novel guaiane-type sesquiterpene lactone trimers possessing unique linkage patterns, were identified from the whole plant of Ainsliaea macrocephala. The trimeric architecture of 1 features a cyclohexene linkage and a methylene bridge, which were presumably constructed from three constitutive monomers via a Diels-Alder cycloaddition and a Michael addition, respectively. The three monomers of 2 were tethered by a 1,2-ethanediyl and a methylene linkage at the same time. Their complex structures were established by extensive analysis of spectroscopic data inclusive of band-selective CT-HSQC and CT-HMBC and time-dependent density functional theory (TDDFT) ECD calculations. Compound 2 showed potent inhibition against protein tyrosine phosphatase 1B (PTP1B) with an IC50 value of 26.26 ± 0.88 µM but not compound 1. In the kinetic study, compound 2 was disclosed as a competitive inhibitor of PTP1B with a Ki value of 16.34 ± 4.72 µM. In insulin-stimulated C2C12 myotubes, compound 2 dose-dependently enhanced glucose uptake by activating the insulin signaling pathway. Compound 2 might represent a new scaffold of insulin sensitizers.
Assuntos
Asteraceae , Insulina , Inibidores Enzimáticos , Proteína Tirosina Fosfatase não Receptora Tipo 1RESUMO
Two guaianolide sesquiterpenoid tetramers named ainsliatetramers A and B were separated from Ainsliaea fragrans. Through spectroscopic analyses, especially the band-selective CT-HSQC and CT-HMBC techniques, the complex skeleton was constructed from four sesquiterpene units via three different linkages. A biosynthetic pathway was proposed featuring a Michael addition and a regular and a hetero-Diels-Alder cycloaddition. Both exhibited potent cytotoxicity against human cancer cell lines with IC50 values ranging from 2 to 15 µM.
Assuntos
Antineoplásicos Fitogênicos/farmacologia , Asteraceae/química , Sesquiterpenos/farmacologia , Antineoplásicos Fitogênicos/química , Antineoplásicos Fitogênicos/isolamento & purificação , Linhagem Celular Tumoral , Proliferação de Células/efeitos dos fármacos , Sobrevivência Celular/efeitos dos fármacos , Relação Dose-Resposta a Droga , Ensaios de Seleção de Medicamentos Antitumorais , Humanos , Conformação Molecular , Sesquiterpenos/química , Sesquiterpenos/isolamento & purificação , Estereoisomerismo , Relação Estrutura-AtividadeRESUMO
Ainsliatriolides A (1) and B (2), two guaianolide sesquiterpenoid trimers possessing an unprecedented skeleton, were isolated from Ainsliaea fragrans. Their structures were elucidated through extensive analysis of spectroscopic data and confirmed by single-crystal X-ray diffraction experiment. Ainsliatriolides A and B are first examples of compound trimerized from guaianolide sesquiterpenoids through two different C-C linkages (type A, 4-2'/15-14'; type B, 15'-15â³). Ainsliatriolide A displayed potent cytotoxicity with an averaged IC50 value of 1.17 µM against four cancer cells.