检索结果-内蒙古大学图书馆

Stochastic Variational Inference-Based Parallel and Online Supervised Topic Model for Large-Scale Text Processing

Journal of Computer Science & Technology 2018年第5期33卷 1007-1022页

作者： Yang Li Wen-Zhuo Song Bo Yang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun 130012 China Aviation University of Air Force Changchun 130062 China

Topic modeling is a mainstream and effective technology to deal with text data, with wide applications in text analysis, natural language, personalized recommendation, computer vision, etc. Among all the known topic models, supervised Latent Dirichlet Allocation （sLDA） is acknowledged as a popular and competitive supervised topic model. How- ever, the gradual increase of the scale of datasets makes sLDA more and more inefficient and time-consuming, and limits its applications in a very narrow range. To solve it, a parallel online sLDA, named PO-sLDA （Parallel and Online sLDA）, is proposed in this study. It uses the stochastic variational inference as the learning method to make the training procedure more rapid and efficient, and a parallel computing mechanism implemented via the MapReduce framework is proposed to promote the capacity of cloud computing and big data processing. The online training capacity supported by PO-sLDA expands the application scope of this approach, making it instrumental for real-life applications with high real-time demand. The validation using two datasets with different sizes shows that the proposed approach has the comparative accuracy as the sLDA and can efficiently accelerate the training procedure. Moreover, its good convergence and online training capacity make it lucrative for the large-scale text data analyzing and processing.

关键词： topic modeling, large-scale text classification, stochastic variational inference, cloud computing online learning

来源：评论

学校读者我要写书评

暂无评论

Application of Hybrid Monocular SLAM Method in Augmented Reality

引用

Journal of Physics: Conference Series 2021年第4期1748卷

作者： Zuoming Zhang Hanwen Wang Man Shu Xin Wang College of Software Engineering Jilin University Changchun Jilin 130000 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun Jilin 130000 China

In this paper, we design a hybrid (semi-direct) approach to simultaneous localization and mapping (SLAM) for monocular cameras and apply it to augmented reality (AR) for monocular cameras. We combine the advantagesof the direct method and the feature point method. We use both photometric bundle adjustment which is robust to camera exposure time and motion bundle adjustment which is geometrically robust based on feature points to do tracking process. This approach can maintain an intuitive direct local map as well as a reusable global sparse feature point map. Through the processing of point clouds, such as PCA plane detection and grid reconstruction, we greatly improve the effect of the augmented reality system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IInfoGAN: Improved Information Maximizing Generative Adversarial Networks

IInfoGAN: Improved Information Maximizing Generative Adversa...

引用

International Conference on Mechanical, Control and Computer engineering (ICMCCE)

作者： Yan Wang Pujia Wang Boyang Sun Kai He Lan Huang School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Ministry of Education Changchun China

Generative Adversarial Networks (GANs) have achieved huge success in some unsupervised learning fields. There is no doubt that clustering takes a lot of weight in unsupervised algorithm. And in this paper, we raise the Improved Information Maximizing Generative Adversarial Networks (IInfoGAN) algorithm for learning discriminative classifiers from unlabeled data. The basis of our method is an math function that contains the Mutual Information (MI) and Cross Entropy of the observed examples and their predicted classification category distribution, thus enhancing the robustness of the classifier to adversarial generative models. Experiments show that the interpretable representation learned by IInfoGAN is competitive with the representation learned by existing unsupervised methods.

关键词： Training Time series analysis Clustering algorithms Predictive models Generative adversarial networks Prediction algorithms Entropy

来源：评论

学校读者我要写书评

暂无评论

Curvature regularization to prevent distortion in graph embedding 20

Curvature regularization to prevent distortion in graph embe...

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Hongbin Pei Bingzhe Wei Kevin Chen-Chuan Chang Chunxu Zhang Bo Yang College of Computer Science and Technology Jilin University China and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign and Department of Computer Science University of Illinois at Urbana-Champaign

ISBN: (纸本)9781713829546

Recent research on graph embedding has achieved success in various applications. Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space. We argue an important but neglected problem about this proximity-preserving strategy: Graph topology patterns, while preserved well into an embedding manifold by preserving proximity, may distort in the ambient embedding Euclidean space, and hence to detect them becomes difficult for machine learning models. To address the problem, we propose curvature regularization, to enforce flatness for embedding manifolds, thereby preventing the distortion. We present a novel angle-based sectional curvature, termed ABS curvature, and accordingly three kinds of curvature regularization to induce flat embedding manifolds during graph embedding. We integrate curvature regularization into five popular proximity-preserving embedding methods, and empirical results in two applications show significant improvements on a wide range of open graph datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pyramid Pooling Dense Convolutional Neural Network for Multi-focus Image Fusion

Pyramid Pooling Dense Convolutional Neural Network for Multi...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yi Li Xuanjing Shen Haipeng Chen College of Software Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (数字)9781728138633

ISBN: (纸本)9781728138640

In recent years, image fusion becomes one of the important technique in information fusion fields. In this paper, we proposed a Deep Learning-based pyramid pooling dense convolutional neural network for multi-focus image fusion problem. The PDenseCNN we proposed can accurately detect the clear regions and generate a fused decision feature map, afterward, morphological operation and guided filter are used to optimize the initial map. Finally, it can obtain a clear fusion image based on weighted-sum strategy. The experimental results proved that the proposed method can obtain accurate decision maps and state-of-art fusion results on both visual effect and objective evaluation assessment.

关键词： Economic indicators

来源：评论

学校读者我要写书评

暂无评论

Multiple Auxiliary Information Based Deep Model for Collaborative Filtering

引用

Journal of Computer Science & Technology 2018年第4期33卷 668-681页

作者： Lin Yue Xiao-Xin Sun Wen-Zhu Gao Guo-Zhong Feng Bang-Zuo Zhang School of Information Science and Technology Northeast Normal University Changchun 130117 China Key Laboratory of Applied Statistics of Ministry of Education Northeast Normal University Changchun 130024 China School of Environment Northeast Normal University Changchun 130117 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 China

With the ever-growing dynamicity, complexity, technique is proposed and becomes one of the most effective and volume of information resources, the recommendation techniques for solving the so-called problem of information overload. Traditional recommendation algorithms, such as collaborative filtering based on the user or item, only measure the degree of similarity between users or items with single criterion, i.e., ratings. According to the experience of previous studies, single criterion cannot accurately measure the similarity between user preferences or items. In recent years, the application of deep learning techniques has gained significant momentum in recommender systems for better understanding of user preferences, item characteristics, and historical interactions. In this work, we integrate plot information as auxiliary information into the denoising autoencoder （DAE）, called SemRe-DCF, which aims at learning semantic representations of item descriptions and succeeds in capturing fine-grained semantic regularities by using vector arithmetic to get better rating prediction. The results manifest that the proposed method can effectively improve the accuracy of prediction and solve the cold start problem.

关键词： semantic representation plot information denoising autoencoder collaborative filtering auxiliary information

来源：评论

学校读者我要写书评

暂无评论

Parking Space Prediction Algorithm Based on Recurrent Neural Network and Ensemble Learning Algorithm

Parking Space Prediction Algorithm Based on Recurrent Neural...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Kedi Lv Haipeng Chen Yingda Lv Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Center for Computer Fundamental Education Jilin University Changchun China

ISBN: (数字)9781728138633

ISBN: (纸本)9781728138640

The essence of parking space prediction is a practical application of time series prediction problem. It provides effective auxiliary information for traffic management and personal travel. As a new demand, they face challenges in data acquisition, accuracy and robustness. The parking space prediction algorithm based on recurrent neural network (RNN) and ensemble learning algorithm is proposed in this paper. However, because the neural network needs large data training, the lack of parking space data in specific areas is a common challenge for researchers. In this paper, a new network model structure based on ensemble learning algorithm is proposed, which is called E-RNN. The ensemble learning algorithm model is used as the primary learner and the neural network as the secondary learner for the ensemble learning. By using the adaptability of the algorithm in ensemble learning to the collective data, the neural network can get better prediction effect under the training of small data sets. Finally, the parameters of the new model are optimized by using particle swarm optimization (PSO) algorithm, and a better model is obtained. The experimental results show that the algorithm has high accuracy and robustness for parking space prediction with a small data sets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Motion Deblur of QR Code Based on Generative Adversative Network

Motion Deblur of QR Code Based on Generative Adversative Net...

引用

2019第二届算法、计算和人工智能国际会议

作者： Benzhi Wang Jingben Xu Junke Zhang Guancheng Li Xin Wang College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University

Aiming at the problem that the QR codes cannot be recognized due to factors such as motion blur caused by the hand tremor and environmental noise in the QR codes of the packaged product, this paper proposes an algorithm based on the Generative Adversative Network to remove QR codes motion blur. Compared with the traditional deblurring algorithm, this method eliminates the process of blur kernel estimation, directly restores the motion blurred image. Gradient L1 regularization is added on the basis of the traditional GAN, which enhances the edge features of the restored image and adds the perceptual loss term, so that the image generated by the generator is closer to the global structure of the target clear image. The results show that the generator can remove the blur and generate a QR code with high recognition rate.

关键词： Generative Adversative Network Motion Blur, QR Code, Perceived Loss Function

来源：评论

学校读者我要写书评

暂无评论

AR Marketing Application Based on iOS Platform

AR Marketing Application Based on iOS Platform

引用

作者： Zheng Zhang Xin Wang Hongchen Jiang Yuemeng Hu Jiayu Du Qiang Zhang College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University

Due to the development of computer vision, in recent years, augmented reality grows rapidly. A lot of augmented technologies have been applied in actual problems. At present, the industry of traditional marketing requires a lot of manpower, and the application of AR technology in marketing industry can greatly reduce industrial costs. In this paper, an Augmented Reality Marketing Application based on iOS platform is designed. Users can use this APP to scan physical stores signboards, which are saved previously, to trigger a 3D stereo model combined with the real world. At the same time, through the interaction with the model, users can get the business information and its sales activities, thus enhancing the consumer interest in the physical *** experiment results show this application work feasible and reliable. It is an attempt to integrate online and offline economy.

关键词： Augmented Reality Entity marketing Image Identification Online and offline technique

来源：评论

学校读者我要写书评

暂无评论

An Unmanned Aerial Vehicle Pose Estimation System Guided by Desired Shot

An Unmanned Aerial Vehicle Pose Estimation System Guided by ...

引用

IEEE International Conference on Automation, Electronics and Electrical engineering (AUTEEE)

作者： Xinglei Dou Qijian Ding Qiao Du Min Yang Yuzhou Huo Xin Wang College of Software Engineering Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun China

ISBN: (数字)9781728150307

ISBN: (纸本)9781728150314

Unmanned aerial vehicles (UAVs) are widely used in aerial photography nowadays for their strong maneuverability, good image quality and high cost performance, while they have limited battery capacity and difficulty in operation. It is difficult to reach the ideal pose and get the desired shot by manual manipulation in a short time. To solve these problems, an UAV pose estimation system guided by desired shot is constructed. Either a sequence of images or a video is taken as input. The user interacts with the system to express the desired shot. The 3D-reconstruction is done by Structure from Motion (SfM). Then the Perspective-n-Point (PnP) problem is solved to estimate the ideal pose of the UAV. The experimental results proves that the system is effective and valid.

关键词： Three-dimensional displays Feature extraction Unmanned aerial vehicles Cameras Pose estimation Software engineering Data mining

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：