Multi-View Linear Discriminant Analysis Network

This paper presents the exponential synchronization for a class of memristive Cohen-Grossberg neural networks (MCGNNs) with mixed delays via a new hybrid control strategy. This new hybrid control strategy combines pinning control and periodic intermittent control. According to the feature of memristor, the memristive terms of the MCGNNs with mixed delays are normalized by a simple linear transformation. Then the designed periodic intermittent control is added to selected partial network nodes. Based on the stability theory of memristive neural networks and the exponential synchronization rule, the new synchronization conditions are given. Finally, numerical simulations are provided to show the effectiveness of the theoretical method. INDEX TERMS Memristive Cohen-Grossberg neural networks, exponential synchronization, pinning control, periodic intermittent control.

Section: Preliminarymentioning

confidence: 99%

Pinning Synchronization via Intermittent Control for Memristive Cohen-Grossberg Neural Networks With Mixed Delays

Hui

Luo

et al. 2020

“…Recently, with the improvement of transportation infrastructure, different data collection technologies such as monitoring points, detectors, have provide a mass of available data for traffic flow prediction. Data-driven approaches can be separated into two subclasses: machine learning and deep learning [2]- [4]. Common machine learning methods are inadequate when processing high-dimensional data and also rely on detailed feature engineering.…”

Section: Introductionmentioning

confidence: 99%

A General Traffic Flow Prediction Approach Based on Spatial-Temporal Graph Attention

Tang

Sun

et al. 2020

Accurate and reliable traffic flow prediction is critical to the safe and stable deployment of intelligent transportation systems. However, it is very challenging since the complex spatial and temporal dependence of traffic flows. Most existing works require the information of the traffic network structure and human intervention to model the spatial-temporal association of traffic data, resulting in low generality of the model and unsatisfactory prediction performance. In this paper, we propose a general spatial-temporal graph attention based dynamic graph convolutional network (GAGCN) model to predict traffic flow. GAGCN uses the graph attention networks to extract the spatial associations among nodes hidden in the traffic feature data automatically which can be dynamically adjusted over time. And then the graph convolution network is adjusted based on the spatial associations to extract the spatial features of the road network. Notably, the information of rode network structure and human intervention are not required in GAGCN. The forecasting accuracy and the generality are evaluated with two real-world traffic datasets. Experimental results indicate that our GAGCN surpasses the state-of-the-art baselines on one of two datasets.

“…The experimental results and their discussion are shown in Section IV. Finally, general conclusions and suggestions for future research directions are presented in Section V. DL methods have been utilized to address many problems in the surveillance environment, including person reidentification [24], face recognition [9], anomaly detection [25], multi-view analysis [26], and traffic monitoring [27].…”

Section: Introductionmentioning

confidence: 99%

EPYNET: Efficient Pyramidal Network for Clothing Segmentation

Inácio

Lopes

2020

Soft biometrics traits extracted from a human body, including the type of clothes, hair color, and accessories, are useful information used for people tracking and identification. Semantic segmentation of these traits from images is still a challenge for researchers because of the huge variety of clothing styles, layering, shapes, and colors. To tackle these issues, we proposed EPYNET, a framework for clothing segmentation. EPYNET is based on the Single Shot MultiBox Detector (SSD) and the Feature Pyramid Network (FPN) with the EfficientNet model as the backbone. The framework also integrates data augmentation methods and noise reduction techniques to increase the accuracy of the segmentation. We also propose a new dataset named UTFPR-SBD3, consisting of 4,500 manually annotated images into 18 classes of objects, plus the background. Unlike available public datasets with imbalanced class distributions, the UTFPR-SBD3 has, at least, 100 instances per class to minimize the training difficulty of deep learning models. We introduced a new measure of dataset imbalance, motivated by the difficulty in comparing different datasets for clothing segmentation. With such a measure, it is possible to detect the influence of the background, classes with small items, or classes with a too high or too low number of instances. Experimental results on UTFPR-SBD3 show the effectiveness of EPYNET, outperforming the state-of-art methods for clothing segmentation on public datasets. Based on these results, we believe that the proposed approach can be potentially useful for many real-world applications related to soft biometrics, people surveillance, image description, clothes recommendation, and others.