Search

Deep learning based on deep neural networks has been very successful in many practical applications, but it lacks enough theoretical understanding due to the network architectures and structures. In this paper, we establish some analysis for linear feature extraction by a deep multi-channel convolutional neural networks (CNNs), which demonstrates the power of deep learning over traditional linear transformations, like Fourier, wavelets, redundant dictionary coding methods. Moreover, we give an exact construction presenting how linear features extraction can be conducted efficiently with multi-channel CNNs. It can be applied to lower the essential dimension for approximating a high-dimensional function. Rates of function approximation by such deep networks implemented with channels and followed by fully connected layers are investigated as well. Harmonic analysis for factorizing linear features into multi-resolution convolutions plays an essential role in our work. Nevertheless, a dedicate vectorization of matrices is constructed, which bridges 1D CNN and 2D CNN and allows us to have corresponding 2D analysis. [ABSTRACT FROM AUTHOR]

Mathematical morphology intends to extract object features such as geometric and topological structures in digital images. Given a set of target images and original images, it is cumbersome and time-consuming to determine the suitable morphological operations and structuring elements. In this paper, we propose deep morphological neural networks, which include a nonlinear feature extraction layer to learn the structuring element correctly and an adaptive layer to select appropriate morphological operations automatically. We demonstrate the applications of object recognition, including hand-written digits, geometric shapes, traffic signs, and brain tumor. Experimental results show the higher computational efficiency and higher accuracy of our developed model as compared against existing convolutional neural network models. [ABSTRACT FROM AUTHOR]

Accurate short-term price forecasting is crucial for the power system and electricity market. This paper proposes a hybrid short-term electricity price forecasting model based on empirical mode decomposition (EMD) and deep neural network (DNN). Firstly, EMD is used to denoise the data set. Next, the reconstructed data are input into the DNN composed of a convolutional neural network (CNN) and long-short-term memory (LSTM) neural network to analyze the characteristics and output the prediction results. Finally, the superiority of this model is verified by comparing the electricity price data of the Australian electricity market with a single LSTM network, EMD-CNN model, and CNN-LSTM model. [ABSTRACT FROM AUTHOR]

Real-time detection of possible deforestation of urban landscapes is an essential task for many urban forest monitoring services. Computational methods emerge as a rapid and efficient solution to evaluate bird's-eye-view images taken by satellites, drones, or even street-view photos captured at the ground level of the urban scenery. Identifying unhealthy trees requires detecting the tree itself and its constituent parts to evaluate certain aspects that may indicate unhealthiness, being street-level images a cost-effective and feasible resource to support the fieldwork survey. This paper proposes detecting trees and their specific parts on street-view images through a Convolutional Neural Network model based on the well-known You Only Look Once network with a MobileNet as the backbone for feature extraction. Essentially, from a photo taken from the ground, the proposed method identifies trees, isolates them through their bounding boxes, identifies the crown and stem, and then estimates the height of the trees by using a specific handheld object as a reference in the images. Experiment results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The optimization of the problems significantly improves the solution of the complex problems. The reduction in the feature dimensionality is enormously salient to reduce the redundant features and improve the system accuracy. In this paper, an amalgamation of different concepts is proposed to optimize the features and improve the system classification. The experiment is performed on the facial expression detection application by proposing the amalgamation of deep neural network models with the variants of the gravitational search algorithm. Facial expressions are the movement of the facial components such as lips, nose, eyes that are considered as the features to classify human emotions into different classes. The initial feature extraction is performed with the local binary pattern. The extracted feature set is optimized with the variants of gravitational search algorithm (GSA) as standard gravitational search algorithm (SGSA), binary gravitational search algorithm (BGSA) and fast discrete gravitational search algorithm (FDGSA). The deep neural network models of deep convolutional neural network (DCNN) and extended deep convolutional neural network (EDCNN) are employed for the classification of emotions from imagery datasets of JAFFE and KDEF. The fixed pose images of both the datasets are acquired and comparison based on average recognition accuracy is performed. The comparative analysis of the mentioned techniques and state-of-the-art techniques illustrates the superior recognition accuracy of the FDGSA with the EDCNN technique. [ABSTRACT FROM AUTHOR]

Pedestrian detection provides manager of a smart city with a great opportunity to manage their city effectively and automatically. Specifically, pedestrian detection technology can improve our secure environment and make our traffic more efficient. In this paper, all of our work both modification and improvement are made based on YOLO, which is a real-time Convolutional Neural Network detector. In our work, we extend YOLO’s original network structure, and also give a new definition of loss function to boost the performance for pedestrian detection, especially when the targets are small, and that is exactly what YOLO is not good at. In our experiment, the proposed model is tested on INRIA, UCF YouTube Action Data Set and Caltech Pedestrian Detection Benchmark. Experimental results indicate that after our modification and improvement, the revised YOLO network outperforms the original version and also is better than other solutions. [ABSTRACT FROM AUTHOR]