The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In order to improve the accuracy of SOC estimation for vehicle battery pack and optimize the management of the battery system, a new method based on deep belief network for remote correction of SOC accuracy is proposed in this paper. The monitoring data obtained by the remote monitoring center of the electric vehicle should be pre-processed before the establishment of deep belief network, which is...
Faster R-CNN (R corresponds to “Region”) which combined the RPN network and the Fast R-CNN network is one of the best ways to object detection of R-CNN series based on deep learning. The proposal obtained by RPN is directly connected to the ROI Pooling layer, which is a framework for CNN to achieve end-to-end object detection. The feasibility of Faster R-CNN implementation of ResNet101 network and...
For face recognition systems, impostors can obtain legal identity authentication by presenting the printed images, the downloaded images or candid videos to the sensor. In this paper, an enhanced face local binary feature (ELBP) of a face map is extracted as a classification feature to identify whether the face map is a real face or a fake face. Compared with the dynamic or static methods proposed...
K-Nearest Neighbor (KNN) is a commonly used fault diagnosis method, which is based on Euclidean distance between samples to carry out fault diagnosis. The differences between the variables have a direct effect on the Euclidean distance, which affects the KNN fault diagnosis effect. After the dimensional normalization, there are also some problems such as the decrease of variable diversity, and the...
Object detection in Very High Resolution (VHR) optical remote sensing images is a challenged work for objects are usually dense and tiny. With random orientation, various backgrounds as well as unpredictable noise make traditional image processing methods perform badly. In this paper, we propose using state-of-art Region-based fully convolutional networks to solve object detection tasks in aerial...
As the deep learning exhibits strong advantages in the feature extraction, it has been widely used in the field of computer vision and among others, and gradually replaced traditional machine learning algorithms. This paper first reviews the main ideas of deep learning, and displays several related frequently-used algorithms for computer vision. Afterwards, the current research status of computer...
Recently, deep learning has been proposed and verified to possess the strong ability to learn and express complex features, which has brought significant research achievements in signal processing. As a challenging task in speech signal processing, monaural speech separation has always been the research focus of researchers. From the usage of traditional signal processing methods and shallow models...
Many face recognition tasks encounter the problem of having only one sample for each subject, which is known as the single sample per person (SSPP) problem. To tackle the problem, we propose a strategy of sparse representation with dense matching method. First, an external training set is used to form an intra-class variation dictionary. Then, noting that captured facial features will vary with facial...
For remote sensing image understanding, target detection is one of the most important tasks. In this paper, we propose one object detection method based on region proposal detection via active contour model and detection based on one-class classification method. The large scale remote sensing image is split into several connected components. And then, the proposed algorithm detects the object from...
Generating a realistic image from a novel viewpoint has always been a key problem in image-based rendering and other related domains. In this paper we utilize the state-of-the-art generative adversarial networks(GAN) to synthesize novel views of a structured scene. Based on our proposed representations for traffic scene, a realistic image of a certain viewpoint can be generated via conditional GANs,...
Training and testing unmanned vehicles need various real data. However, data of some special or dangerous testing environment may not be accessible, or may only be accessible at certain times. So, using generative adversarial networks to learn the real traffic scene and generate a new scene is an effective way of solving the problem. In this paper, a framework of deep convolutional generative adversarial...
At present, shallow characteristics are usually utilized to represent the distributed features of text for Chinese spam classification, causing the problem of inexact text vector representation and low classification performance. A novel Chinese spam classification method based on weighted distributed feature is proposed by combining the features of TF-IDF weighted algorithm with the distributed text-based...
This paper proposes an object detection strategy with a deep reinforcement learning method Double DQN in which, given an image window, a deep reinforcement learning agent is trained to determine which predefined region candidates to focus the attention on. In the Double DQN framework, the first DQN is used to select an action to search the target region and the second is to evaluate the selected action...
A power transformer fault diagnosis method based on Improved Particle Swarm Optimization and BP neural network is proposed. The particle swarm algorithm that used to optimize the parameters of the BP neural network is prone to “premature”. By optimizing the inertia weight, in the process of increasing the number of iterations, the inertia weight can be gradually reduced, and the algorithm can avoid...
Traditional pairwise learning to rank algorithms pay little attention to top ranked documents in the query list, and do not work well when they are used on a data set with multiple rating grades. In this paper, a novel pairwise learning to rank algorithm is proposed to solve this problem. This algorithm defines a bounded loss function and introduces the preference weights between document pairs into...
In order to make the robot obtain the optimal action directly from the original visual perception without any hand-crafted features and features matching, a novel end-to-end path planning method-mobile robot path planning using deep reinforcement learning is proposed. Firstly, a deep Q-network (DQN) is designed and trained to approximate the mobile robot state-action value function. Then, the Q value...
Most techniques for dealing with imbalanced data classification in SVM-related methods are sampling, weighting and ensemble strategies, which aim at balancing the importance of different classes when computing the decision boundary. But how to choose and design an appropriate balance strategy is still a difficult problem. In this paper, we propose a between-class discriminant twin support vector machine...
The accuracy of object recognition has been greatly improved due to the rapid development of deep learning, but the deep learning generally requires a lot of training data and the training process is very slow and complex. We propose an incremental object recognition system based on deep learning techniques and speech recognition technology with high learning speed and wide applicability. The system...
Inspired by recent work in Optical Character Recognition (OCR) and image captioning, an end-to-end system is utilized which implements the recognition of image formulas. An attention based two-way encoder-decoder structure has been proposed to normal image captioning systems, and it achieves good performance on the recognition of image formulas task. This structure together with a new training method...
In complex industrial environment, there are many interference objects when detect the objects on the production line. The interference objects are very similar with the objects to be sorted in terms of color, shape and size. The existing detection method like edge detection and object segmentation is difficult to recognize the objects when it comes to complex industrial environment. In the complex...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.