Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting

Graph convolutional neural networks (GCNN) have become an increasingly active field of research. It models the spatial dependencies of nodes in a graph with a pre-defined Laplacian matrix based on node distances. However, in many application scenarios, spatial dependencies change over time, and the use of fixed Laplacian matrix cannot capture the change. To track the spatial dependencies among traffic data, we propose a dynamic spatio-temporal GCNN for accurate traffic forecasting. The core of our deep learning framework is the finding of the change of Laplacian matrix with a dynamic Laplacian matrix estimator. To enable timely learning with a low complexity, we creatively incorporate tensor decomposition into the deep learning framework, where real-time traffic data are decomposed into a global component that is stable and depends on long-term temporal-spatial traffic relationship and a local component that captures the traffic fluctuations. We propose a novel design to estimate the dynamic Laplacian matrix of the graph with above two components based on our theoretical derivation, and introduce our design basis. The forecasting performance is evaluated with two realtime traffic datasets. Experiment results demonstrate that our network can achieve up to 25% accuracy improvement.

Download Full-text

Multi-Task Learning for Metaphor Detection with Graph Convolutional Neural Networks and Word Sense Disambiguation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6326 ◽

2020 ◽

Vol 34 (05) ◽

pp. 8139-8146

Author(s):

Duong Le ◽

My Thai ◽

Thien Nguyen

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Word Sense Disambiguation ◽

Word Sense ◽

Knowledge Resources ◽

Useful Knowledge ◽

Learning Framework ◽

Task Learning ◽

Sense Disambiguation

The current deep learning works on metaphor detection have only considered this task independently, ignoring the useful knowledge from the related tasks and knowledge resources. In this work, we introduce two novel mechanisms to improve the performance of the deep learning models for metaphor detection. The first mechanism employs graph convolutional neural networks (GCN) with dependency parse trees to directly connect the words of interest with their important context words for metaphor detection. The GCN networks in this work also present a novel control mechanism to filter the learned representation vectors to retain the most important information for metaphor detection. The second mechanism, on the other hand, features a multi-task learning framework that exploits the similarity between word sense disambiguation and metaphor detection to transfer the knowledge between the two tasks. The extensive experiments demonstrate the effectiveness of the proposed techniques, yielding the state-of-the-art performance over several datasets.

Download Full-text

DeepGly: A Deep Learning Framework With Recurrent and Convolutional Neural Networks to Identify Protein Glycation Sites From Imbalanced Data

IEEE Access ◽

10.1109/access.2019.2944411 ◽

2019 ◽

Vol 7 ◽

pp. 142368-142378

Author(s):

Jingui Chen ◽

Runtao Yang ◽

Chengjin Zhang ◽

Lina Zhang ◽

Qian Zhang

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Imbalanced Data ◽

Protein Glycation ◽

Learning Framework

Download Full-text

Identification of Protein Lysine Crotonylation Sites by a Deep Learning Framework With Convolutional Neural Networks

IEEE Access ◽

10.1109/access.2020.2966592 ◽

2020 ◽

Vol 8 ◽

pp. 14244-14252 ◽

Cited By ~ 8

Author(s):

Yiming Zhao ◽

Ningning He ◽

Zhen Chen ◽

Lei Li

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Learning Framework

Download Full-text

Skin Diseases Prediction using Deep Learning Framework

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.f9038.038620 ◽

2020 ◽

Vol 8 (6) ◽

pp. 4781-4784

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Real Time ◽

Convolutional Neural Networks ◽

Skin Diseases ◽

Dermatological Diseases ◽

Learning Framework ◽

Computer Aided ◽

High Level ◽

Almost All

Dermatological diseases are found to induce a serious impact on the health of millions of people as everyone is affected by almost all types of skin disorders every year. Since the human analysis of such diseases takes some time and effort, and current methods are only used to analyse singular types of skin diseases, there is a need for a more high-level computer-aided expertise in the analysis and diagnosis of multi-type skin diseases. This paper proposes an approach to use computer-aided techniques in deep learning neural networks such as Convolutional neural networks (CNN) and Residual Neural Networks (ResNet) to predict skin diseases real-time and thus provides more accuracy than other neural networks.

Download Full-text

DeepEP: a deep learning framework for identifying essential proteins

BMC Bioinformatics ◽

10.1186/s12859-019-3076-y ◽

2019 ◽

Vol 20 (S16) ◽

Cited By ~ 9

Author(s):

Min Zeng ◽

Min Li ◽

Fang-Xiang Wu ◽

Yaohang Li ◽

Yi Pan

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Sampling Method ◽

Ppi Network ◽

Essential Proteins ◽

Learning Framework ◽

Multi Scale ◽

Topological Features

Abstract Background Essential proteins are crucial for cellular life and thus, identification of essential proteins is an important topic and a challenging problem for researchers. Recently lots of computational approaches have been proposed to handle this problem. However, traditional centrality methods cannot fully represent the topological features of biological networks. In addition, identifying essential proteins is an imbalanced learning problem; but few current shallow machine learning-based methods are designed to handle the imbalanced characteristics. Results We develop DeepEP based on a deep learning framework that uses the node2vec technique, multi-scale convolutional neural networks and a sampling technique to identify essential proteins. In DeepEP, the node2vec technique is applied to automatically learn topological and semantic features for each protein in protein-protein interaction (PPI) network. Gene expression profiles are treated as images and multi-scale convolutional neural networks are applied to extract their patterns. In addition, DeepEP uses a sampling method to alleviate the imbalanced characteristics. The sampling method samples the same number of the majority and minority samples in a training epoch, which is not biased to any class in training process. The experimental results show that DeepEP outperforms traditional centrality methods. Moreover, DeepEP is better than shallow machine learning-based methods. Detailed analyses show that the dense vectors which are generated by node2vec technique contribute a lot to the improved performance. It is clear that the node2vec technique effectively captures the topological and semantic properties of PPI network. The sampling method also improves the performance of identifying essential proteins. Conclusion We demonstrate that DeepEP improves the prediction performance by integrating multiple deep learning techniques and a sampling method. DeepEP is more effective than existing methods.

Download Full-text

Deep Learning Using Isotroping, Laplacing, Eigenvalues Interpolative Binding, and Convolved Determinants with Normed Mapping for Large-Scale Image Retrieval

Sensors ◽

10.3390/s21041139 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1139

Author(s):

Khadija Kanwal ◽

Khawaja Tehseen Ahmad ◽

Rashid Khan ◽

Naji Alhusaini ◽

Li Jing

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Image Retrieval ◽

Convolutional Neural Networks ◽

Large Scale ◽

Spatial Dependencies ◽

Hidden Patterns ◽

Large Scale Image Retrieval ◽

High Level ◽

Object Features

Convolutional neural networks (CNN) are relational with grid-structures and spatial dependencies for two-dimensional images to exploit location adjacencies, color values, and hidden patterns. Convolutional neural networks use sparse connections at high-level sensitivity with layered connection complying indiscriminative disciplines with local spatial mapping footprints. This fact varies with architectural dependencies, insight inputs, number and types of layers and its fusion with derived signatures. This research focuses this gap by incorporating GoogLeNet, VGG-19, and ResNet-50 architectures with maximum response based Eigenvalues textured and convolutional Laplacian scaled object features with mapped colored channels to obtain the highest image retrieval rates over millions of images from versatile semantic groups and benchmarks. Time and computation efficient formulation of the presented model is a step forward in deep learning fusion and smart signature capsulation for innovative descriptor creation. Remarkable results on challenging benchmarks are presented with a thorough contextualization to provide insight CNN effects with anchor bindings. The presented method is tested on well-known datasets including ALOT (250), Corel-1000, Cifar-10, Corel-10000, Cifar-100, Oxford Buildings, FTVL Tropical Fruits, 17-Flowers, Fashion (15), Caltech-256, and reported outstanding performance. The presented work is compared with state-of-the-art methods and experimented over tiny, large, complex, overlay, texture, color, object, shape, mimicked, plain and occupied background, multiple objected foreground images, and marked significant accuracies.

Download Full-text