CLR-based deep convolutional spiking neural network with validation based stopping for time series classification

A Reinforced, Event-Driven, and Attention-Based Convolution Spiking Neural Network for Multivariate Time Series Prediction

Despite spiking neural networks (SNNs) inherently exceling at processing time series due to their rich spatio-temporal information and efficient event-driven computing, the challenge of extracting complex correlations between variables in multivariate time series (MTS) remains to be addressed. This paper proposes a reinforced, event-driven, and attention-based convolution SNN model (REAT-CSNN) with three novel features. First, a joint Gramian Angular Field and Rate (GAFR) coding scheme is proposed to convert MTS into spike images, preserving the inherent features in MTS, such as the temporal patterns and spatio-temporal correlations between time series. Second, an advanced LIF-pooling strategy is developed, which is then theoretically and empirically proved to be effective in preserving more features from the regions of interest in spike images than average-pooling strategies. Third, a convolutional block attention mechanism (CBAM) is redesigned to support spike-based input, enhancing event-driven characteristics in weighting operations while maintaining outstanding capability to capture the information encoded in spike images. Experiments on multiple MTS data sets, such as stocks and PM2.5 data sets, demonstrate that our model rivals, and even surpasses, some CNN- and RNN-based techniques, with up to 3% better performance, while consuming significantly less energy.

Reservoir based spiking models for univariate Time Series Classification

A variety of advanced machine learning and deep learning algorithms achieve state-of-the-art performance on various temporal processing tasks. However, these methods are heavily energy inefficient-they run mainly on the power hungry CPUs and GPUs. Computing with Spiking Networks, on the other hand, has shown to be energy efficient on specialized neuromorphic hardware, e.g., Loihi, TrueNorth, SpiNNaker, etc. In this work, we present two architectures of spiking models, inspired from the theory of Reservoir Computing and Legendre Memory Units, for the Time Series Classification (TSC) task. Our first spiking architecture is closer to the general Reservoir Computing architecture and we successfully deploy it on Loihi; the second spiking architecture differs from the first by the inclusion of non-linearity in the readout layer. Our second model (trained with Surrogate Gradient Descent method) shows that non-linear decoding of the linearly extracted temporal features through spiking neurons not only achieves promising results, but also offers low computation-overhead by significantly reducing the number of neurons compared to the popular LSM based models-more than 40x reduction with respect to the recent spiking model we compare with. We experiment on five TSC datasets and achieve new SoTA spiking results (-as much as 28.607% accuracy improvement on one of the datasets), thereby showing the potential of our models to address the TSC tasks in a green energy-efficient manner. In addition, we also do energy profiling and comparison on Loihi and CPU to support our claims.

Application Model of Public Health Visual Art Creation Concept Based on Artificial Intelligence Technology in Venice Biennale

There are some problems in the creation process of public health visual art works, such as low accuracy and poor content quality. In order to further improve the accuracy and quality of artistic creation, based on artificial intelligence technology, a neural network model and an error backpropagation algorithm are used to analyze artistic creation, so as to obtain the corresponding optimization model. This model can analyze the application of public health visual art creation concepts in the Venice Biennale, so as to obtain the corresponding model calculation results under different indicators. Finally, data comparison is used to verify the accuracy of the model. Relevant studies show that activation values have different trends in connection weights under the action of different factors. The fluctuation of the curve is obvious in the initial state, but when the factor is high, the corresponding connection weight tends to be stable gradually. The range of learning rate in the initial state is relatively small, and the connection weights show a V-shaped change at higher factors. It can be seen from the curve corresponding to the ω learning method that the increase in learning speed will lead to further compression of calculation time, and the curve shows a trend of fluctuation. The corresponding learning error decreases gradually with the increase in factors, which indicates that higher factors will promote the accuracy of connection weights. Artificial intelligence-based visual models of art can calculate public health. It can be seen from the calculation results that the curve corresponding to artistic connotation has the largest range of variation and the highest influence on the model. The theme, form, and style of art all show a linear trend of improvement with the increase in time, while the content of art shows a downward trend. This research can provide support for the application of artificial intelligence theory in the field of public health.

Time Series Classification by Shapelet Dictionary Learning with SVM-Based Ensemble Classifier

Time series classification is a basic and important approach for time series data mining. Nowadays, more researchers pay attention to the shape similarity method including Shapelet-based algorithms because it can extract discriminative subsequences from time series. However, most Shapelet-based algorithms discover Shapelets by searching candidate subsequences in training datasets, which brings two drawbacks: high computational burden and poor generalization ability. To overcome these drawbacks, this paper proposes a novel algorithm named Shapelet Dictionary Learning with SVM-based Ensemble Classifier (SDL-SEC). SDL-SEC modifies the Shapelet algorithm from two aspects: Shapelet discovery method and classifier. Firstly, a Shapelet Dictionary Learning (SDL) is proposed as a novel Shapelet discovery method to generate Shapelets instead of searching them. In this way, SDL owns the advantages of lower computational cost and higher generalization ability. Then, an SVM-based Ensemble Classifier (SEC) is developed as a novel ensemble classifier and adapted to the SDL algorithm. Different from the classic SVM that needs precise parameters tuning and appropriate features selection, SEC can avoid overfitting caused by a large number of features and parameters. Compared with the baselines on 45 datasets, the proposed SDL-SEC algorithm achieves a competitive classification accuracy with lower computational cost.