Air quality forecasting has been regarded as the key problem of air pollution early warning and control management. In this paper, we propose a novel deep learning model for air quality (mainly PM2.5) forecasting, which learns the spatial-temporal correlation features and interdependence of multivariate air quality related time series data by hybrid deep learning architecture. Due to the nonlinear and dynamic characteristics of multivariate air quality time series data, the base modules of our model include one-dimensional Convolutional Neural Networks (1D-CNNs) and Bi-directional Long Short-term Memory networks (Bi-LSTM). The former is to extract the local trend features and spatial correlation features, and the latter is to learn spatial-temporal dependencies. Then we design a jointly hybrid deep learning framework based on one-dimensional CNNs and Bi-LSTM for shared representation features learning of multivariate air quality related time series data. We conduct extensive experimental evaluations using two real-world datasets, and the results show that our model is capable of dealing with PM2.5 air pollution forecasting with satisfied accuracy.Index Terms-Air quality forecasting, deep learning, convolutional neural networks, long short-term memory networks ---------- ----------
Traffic flow forecasting has been regarded as a key problem of intelligent transport systems. In this work, we propose a hybrid multimodal deep learning method for short-term traffic flow forecasting, which can jointly and adaptively learn the spatialtemporal correlation features and long temporal interdependence of multi-modality traffic data by an attention auxiliary multimodal deep learning architecture. According to the highly nonlinear characteristics of multi-modality traffic data, the base module of our method consists of one-dimensional Convolutional Neural Networks (1D CNN) and Gated Recurrent Units (GRU) with the attention mechanism. The former is to capture the local trend features and the latter is to capture the long temporal dependencies. Then, we design a hybrid multimodal deep learning framework for fusing share representation features of different modality traffic data by multiple CNN-GRU-Attention modules. The experimental results indicate that the proposed multimodal deep learning model is capable of dealing with complex nonlinear urban traffic flow forecasting with satisfying accuracy and effectiveness.
By introducing a flux-controlled memristor model with absolute value function, a 5D multistable four-wing memristive hyperchaotic system (FWMHS) with linear equilibrium points is proposed in this paper. The dynamic characteristics of the system are studied in terms of equilibrium point, perpetual point, bifurcation diagram, Lyapunov exponential spectrum, phase portraits, and spectral entropy. This system is of the group of systems that have coexisting attractors. In addition, the circuit implementation scheme is also proposed. Then, a secure communication scheme based on the proposed 5D multistable FWMHS with disturbance inputs is designed. Based on parametric modulation theory and Lyapunov stability theory, synchronization and secure communication between the transmitter and receiver are realized and two message signals are recovered by a convenient robust high-order sliding mode adaptive controller. Through the proposed adaptive controller, the unknown parameters can be identified accurately, the gain of the receiver system can be adjusted continuously, and the disturbance inputs of the transmitter and receiver can be suppressed effectively. Thereafter, the convergence of the proposed scheme is proven by means of an appropriate Lyapunov functional and the effectiveness of the theoretical results is testified via numerical simulations.
By introducing a flux-controlled memristor with quadratic nonlinearity into a 4D hyperchaotic system as a feedback term, a novel 5D hyperchaotic four-wing memristive system (HFWMS) is derived in this paper. The HFWMS with multiline equilibrium and three positive Lyapunov exponents presented very complex dynamic characteristics, such as the existence of chaos, hyperchaos, limit cycles, and periods. The dynamic characteristics of the HFWMS are analyzed by using equilibria, phase portraits, poincare map, Lyapunov exponential spectrum, bifurcation diagram, and spectral entropy. Of particular interest is that this novel system can generate two-wing hyperchaotic attractor under appropriate parameters and initial conditions. Moreover, the FPGA realization of the novel 5D HFWMS is reported, which prove that the system has complex dynamic behavior. Finally, synchronization of the 5D hyperchaotic system with different structures by active control and a secure signal masking application of the HFWMS are implemented based on numerical simulations and FPGA. This research demonstrates that the hardware-based design of the 5D HFWMS can be applied to various chaos-based embedded system applications including random number generation, cryptography, and secure communication.
A uniformly strategic total synthesis of Aspidosperma alkaloids (+)-vincadifformine, (-)-quebrachamine, (+)-aspidospermidine, (-)-aspidospermine, (-)-pyrifolidine, and nine others from efficiently constructed tricyclic ketone 13 is reported. Highlights of these divergent and practical syntheses include (i) stereoselective intermolecular [4 + 2] cycloaddition to establish a C-E ring with one all-carbon quaternary stereocenter (C-5) and two bridged contiguous cis-stereocenters (C-12 and C-19), (ii) a Pd/C-catalyzed hydrogenation/deprotection/amidation cascade process to assemble the D ring, and (iii) Fischer indolization to forge the A-B ring.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.