检索结果-内蒙古大学图书馆

sparse Feature Learning for Correlation Filter Tracking Toward 5G-Enabled Tactile Internet

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2020年第3期16卷 1904-1913页

作者： Jia, Min Gao, Zheng Guo, Qing Lin, Yun Gu, Xuemai Harbin Inst Technol Sch Elect & Informat Engn Commun Res Ctr Harbin 150006 Peoples R China Harbin Engn Univ Coll Informat & Commun Engn Harbin 150001 Peoples R China

Fifth generation with high dimensions and capabilities is expected to fulfil the requirements of the Tactile Internet. Tracking provides strong support for intuitive interaction with interfaces by hands, eyes, bodies, etc. Such interfaces can be used in the Tactile Internet for interaction with real and virtual objects. The trackers based on tracking-by-detection framework rely on manual feature detectors for robust tracking, which is particularly useful for specific objects like humans but cannot handle generic tracking problems. Therefore, a sparse feature learning method beyond manual design is proposed to learn features from the samples sampled during tracking. The basic idea is to learn a dictionary from the samples in the previous frames and construct feature representations to represent the object for detection of the location in the current frame. The samples are patches centered at the keypoints based on an adaptive features from accelerated segment test (FAST) detector with local threshold. The dictionary is learned with sparse coding for sparse representations and atoms of the dictionary are grouped to describe the local orientation of these samples. The integrated features are built after rectification of the sparse representations. The correlation filter is used to infer the object location from the sparse features. The qualitative and quantitative experimental results on OTB100 show the advantage of the proposed tracker against current state-of-the-art trackers in terms of accuracy.

关键词： Feature extraction Correlation Detectors Dictionaries Training Internet Informatics Feature learning fifth generation (5G) object tracking sparse coding Tactile Internet

来源：评论

学校读者我要写书评

暂无评论

A New Transfer Learning Fault Diagnosis Method Using TSC and JGSA Under Variable Condition

引用

IEEE ACCESS 2020年 8卷 177287-177295页

作者： Yu, Yujie Zhang, Chunguang Li, Yingjie Li, Yuangang Dalian Jiaotong Univ Sch Elect & Informat Engn Dalian 116028 Peoples R China Spic Hubei New Energy Co Ltd Wuhan 430077 Peoples R China Dalian Univ Foreign Languages Business Sch Dalian 116044 Peoples R China Southwest Jiaotong Univ Tract Power State Key Lab Chengdu 610031 Peoples R China

It is very difficult to obtain the label data of rolling bearings under the complicated and variable working conditions, which results in low diagnosis accuracy. Transfer sparse coding(TSC) is a new feature representation method, which can effectively extract features from data matrix. Joint geometric and statistical alignment (JGSA) is a domain adaptation method, which can reduce the distribution shift and geometric shift between domains. In order to make full use of the feature extraction ability of the TSC and the transfer classification ability of the JGSA, a new transfer learing fault diagnosis(TSC-JGSA) method based on combining the characteristics of the TSC and JGSA is proposed to realize the fault diagnosis of rolling bearings under variable working conditions in this paper. In the TSC-JGSA, the fast Fourier transform technology is used to transform the time-domain signals into frequency-domain amplitudes. Then the TSC is used to effectively extract the deep features from the obtained frequency-domain amplitudes in order to construct a sparse feature matrix, which is input into the JGSA in order to realize the fault diagnosis of rolling bearings. Finally, the vibration data of rolling bearings under variable working conditions is used to prove the effectiveness of the TSC-JGSA. The experiment results show that the TSC-JGSA can effecrively solve the problem of lacking label data in actual engineering by using label data in the laboratory, and obtan higher diagnosis accuracy than other compared methods. It provides a new diagnosis idea for rotating machinery.

关键词： Fault diagosis transfer learning domain adaptation sparse coding variable working conditions

来源：评论

学校读者我要写书评

暂无评论

Image restoration based on sparse representation using feature classification learning

引用

EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING 2020年第1期2020卷 1-18页

作者： Chang, Minhui Zhang, Lei Yuncheng Univ Sch Math & Informat Technol Yuncheng 044000 Peoples R China

In the image inpainting method based on sparse representation, the adaptability of over-complete dictionary has a great influence on the result of image restoration. If the over-complete dictionary cannot effectively reflect the differences between different local features, it may result in the loss of texture details, resulting in blurred or over-smooth phenomenon in restored images. In view of these problems, we propose an image restoration method based on sparse representation using feature classification learning. Firstly, we perform singular value decomposition on the local gradient vector. According to the relationship between the main orientation and the secondary orientation, we classify all the local patches into three categories: smooth patch, edge patch and texture patch. Secondly, we use K-Singular Value Decomposition method to learn over-complete dictionaries that adapt to different features. Finally, we use Orthogonal Matching Pursuit method to calculate the sparse coding of target patches with different local features on their corresponding over-complete dictionaries, and use the over-complete dictionary and corresponding sparse coding to restore the damaged pixels. A series of experiments on various restoration tasks show the superior performance of the proposed method.

关键词： Image restoration sparse representation Feature classification learning sparse coding

来源：评论

学校读者我要写书评

暂无评论

Image Compression Based on Compressive Sensing: End-to-End Comparison With JPEG

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2020年第11期22卷 2889-2904页

作者： Yuan, Xin Haimi-Cohen, Raziel Bell Labs 600 Mt Ave Murray Hill NJ 07974 USA Verizon Labs Bedminster NJ 07921 USA

We present an end-to-end image compression system based on compressive sensing. The presented system integrates the conventional scheme of compressive sampling (on the entire image) and reconstruction with quantization and entropy coding. The compression performance, in terms of decoded image quality versus data rate, is shown to be comparable with JPEG and significantly better at the low rate range. We study the parameters that influence the system performance, including (i) the choice of sensing matrix, (ii) the trade-off between quantization and compression ratio, and (iii) the reconstruction algorithms. We propose an effective method to select, among all possible combinations of quantization step and compression ratio, the ones that yield the near-best quality at any given bit rate. Furthermore, our proposed image compression system can be directly used in the compressive sensing camera, e.g., the single pixel camera, to construct a hardware compressive sampling system.

关键词： Image coding Transform coding Quantization (signal) Sensors Image reconstruction Reconstruction algorithms Bit rate Compressive sensing image compression quantization entropy coding sparse coding reconstruction JPEG JPEG2000

来源：评论

学校读者我要写书评

暂无评论

Adversarial Noise Attacks of Deep Learning Architectures: Stability Analysis via sparse-Modeled Signals

引用

JOURNAL OF MATHEMATICAL IMAGING AND VISION 2020年第3期62卷 313-327页

作者： Romano, Yaniv Aberdam, Aviad Sulam, Jeremias Elad, Michael Stanford Univ Dept Stat Stanford CA 94305 USA Technion Israel Inst Technol Elect Engn Haifa Israel Johns Hopkins Univ Biomed Engn Baltimore MD USA Technion Israel Inst Technol Comp Sci Haifa Israel

Despite their impressive performance, deep convolutional neural networks (CNN) have been shown to be sensitive to small adversarial perturbations. These nuisances, which one can barely notice, are powerful enough to fool sophisticated and well performing classifiers, leading to ridiculous misclassification results. In this paper, we analyze the stability of state-of-the-art deep learning classification machines to adversarial perturbations, where we assume that the signals belong to the (possibly multilayer) sparse representation model. We start with convolutional sparsity and then proceed to its multilayered version, which is tightly connected to CNN. Our analysis links between the stability of the classification to noise and the underlying structure of the signal, quantified by the sparsity of its representation under a fixed dictionary. In addition, we offer similar stability theorems for two practical pursuit algorithms, which are posed as two different deep learning architectures-the layered thresholding and the layered basis pursuit. Our analysis establishes the better robustness of the later to adversarial attacks. We corroborate these theoretical results by numerical experiments on three datasets: MNIST, CIFAR-10 and CIFAR-100.

关键词： Theory for deep learning Adversarial noise sparse coding

来源：评论

学校读者我要写书评

暂无评论

Transfer Dictionary Learning Method for Cross-Domain Multimode Process Monitoring and Fault Isolation

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2020年第11期69卷 8713-8724页

作者： Huang, Keke Wen, Haofei Zhou, Can Yang, Chunhua Gui, Weihua Cent South Univ Sch Automat Changsha 410083 Peoples R China

Data-driven methods have shown its great latent capacity in the field of industrial process monitoring. However, the existing methods usually achieve good results under the assumption that the offline learning data and the online monitoring data are drawn from the same distribution. Unfortunately, in the industrial system, the assumption is often violated due to the harsh operating environment. Especially, with the increasing complexity and scale of industrial production, the supervisory control and data acquisition (SCADA) data of the industrial production process often collected from different machines, seasons, or operating modes. In addition, due to the cost of manual data labeling and real-time requirement of process monitoring, the offline learning data, which was used to build the model, often have abundant source-domain data and insufficient target-domain data. Consequently, these methods have bad performance on the online monitoring data collected from the target domain. In order to make full use of the knowledge from the abundant source-domain data, a transfer dictionary learning method is proposed to address the cross-domain problem in this article. The proposed method can learn an initial dictionary from the abundant source-domain data, and then, the final dictionary is updated by incorporating the feature of insufficient target-domain data in a smooth subspace interpolation way. The effectiveness of the proposed method is evaluated through a numerical simulation case, a continuous stirred tank heater (CSTH) case, and a wind turbine system case, from which we can see the proposed method has a better performance compared with some state-of-the-art methods.

关键词： Machine learning Data models Dictionaries Hidden Markov models Interpolation Cross domain process monitoring sparse coding subspace interpolation transfer learning

来源：评论

学校读者我要写书评

暂无评论

Pooling spike neural network for fast rendering in global illumination

引用

NEURAL COMPUTING & APPLICATIONS 2020年第2期32卷 427-446页

作者： Constantin, Joseph Bigand, Andre Constantin, Ibtissam Univ Libanaise Lab Phys Appl Fac Sci 2 Campus FanarBP 90656 Jdeidet Lebanon ULCO LISIC 50 Rue F BuissonBP 719 F-62228 Calais France

The generation of photo-realistic images is a major topic in computer graphics. By using the principles of physical light propagation, images that are indistinguishable from real photographs can be generated. However, this computation is a very time-consuming task. When simulating the real behavior of light, images can take hours to be of sufficient quality. This paper proposes a bio-inspired architecture with spiking neurons for fast rendering in global illumination. The objective is to find the number of paths that are required for each image in order to be perceived identical to the visually converged one computed by the path tracing algorithm. The challenge is that the visually converged image is unknown so that we start from a very noisy image to converge toward the less noisy image. This architecture with functional parts of sparse encoding, dynamic learning, and decoding consists of a robust convergence measure on blocks. Different pooling strategies are performed in order to separate noise from signal in a deep learning process. The learning algorithm selects the most pertinent images using clustering dynamic learning. The system dynamic computes a learning parameter for each image based on its level of noise. The experiments are conducted on a global illumination set which contains a large number of images with different resolutions and noise levels computed using diffuse and specular rendering. With respect to the scenes with 512x512resolution, 3232 different images are used for learning and 9696 images are used for testing. For the scenes with 800x800resolution, the training and the testing data contain, respectively, 3760 and 6320 images. The result is a system composed from only two spike pattern association neurons that accurately predict the quality of images with respect to human psycho-visual scores. The pooling spike neural network has been compared with the support vector and fast relevance vector machines. The obtained results show that the propo

关键词： Clustering-based dynamic learning Global illumination sparse coding Pooling spike neural network

来源：评论

学校读者我要写书评

暂无评论

Weighted Huber constrained sparse face recognition

引用

NEURAL COMPUTING & APPLICATIONS 2020年第9期32卷 5235-5253页

作者： Lei, Dajiang Jiang, Zhijie Wu, Yu Chongqing Univ Posts & Telecommun Coll Comp Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Inst Web Intelligence Chongqing 400065 Peoples R China

Recently sparse coding based on regression analysis has been widely used in face recognition research. Most existing regression methods add an extra constraint factor to the coding residual to make the fidelity term in the l2 loss approach the Gaussian or Laplace distribution. But the essence of these methods is that only the fidelity term of l1 loss or l2 loss is used. In this paper, weighted Huber constrained sparse coding (WHCSC) is used to study the robustness of face recognition in occluded environments, and alternating direction method of multipliers is used to solve the problem of model minimization. In WHCSC, we propose a sparse coding with weight learning and use Huber loss to determine whether the fidelity is a l2 loss or l1loss. For the WHCSC model, the two kinds of classification modes and the two kinds of weight coefficients are further studied for the intra-class difference and the inter-class difference in the face image classification. Through a large number of experiments on a public face database, WHCSC shows strong robustness in face occlusion, corrosion and illumination changes comparing to the state-of-the-art methods.

关键词： sparse coding Face recognition Robustness ADMM

来源：评论

学校读者我要写书评

暂无评论

KSR-BOF: a new and exemplified method (as KSRs method) for image classification

引用

IET IMAGE PROCESSING 2020年第5期14卷 853-861页

作者： Maleki, Mohammad Hassan Hodtani, Ghosheh Abed Hashemi, Seyed Hesam Odin Sadjad Univ Technol Dept Elect Engn Mashhad Razavi Khorasan Iran Ferdowsi Univ Mashhad Dept Elect Engn Mashhad Razavi Khorasan Iran

Image classification is very important in pattern recognition and computer vision, where, for integrating final representation, feature pooling methods of the max-pooling, sum-pooling and average-pooling have been widely used. In this study, the authors propose a new method called K-strongest responses (KSRs) on the dictionary atoms for integrating the coding coefficients to generate the final representation that is compared with the previous pooling methods, produces better performance for the image classification task. On the basis of the KSR method, to improve classification accuracy and generate more compact and discriminative final representation, a new framework consisting of two-part KSR and bag-of-features is proposed. To evaluate the performance of the proposed method and framework, they apply it to locality-constrained linear coding, linear distance coding and sparse coding by using two datasets from benchmarks of scene classification: 19-class satellite scene and UC Merced Land. The results show that the coding coefficients integrated by their method and framework are more discriminative than other methods.

关键词： computer vision feature extraction image classification linear codes image representation image coding pattern recognition computer vision max-pooling sum-pooling average-pooling dictionary atoms coding coefficients pooling methods image classification task KSR method classification accuracy compact representation discriminative final representation two-part KSR bag-of-features locality-constrained linear coding linear distance coding sparse coding scene classification KSR-BOF method K-strongest responses UC Merced land 19-class satellite scene

来源：评论

学校读者我要写书评

暂无评论

Feature Learning from Spectrograms for Assessment of Personality Traits

引用

IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 2020年第1期11卷 25-31页

作者： Carbonneau, Marc-Andre Granger, Eric Attabi, Yazid Gagnon, Ghyslain Ecole Technol Super Montreal PQ H3C 1K3 Canada

Several methods have recently been proposed to analyze speech and automatically infer the personality of the speaker. These methods often rely on prosodic and other hand crafted speech processing features extracted with off-the-shelf toolboxes. To achieve high accuracy, numerous features are typically extracted using complex and highly parameterized algorithms. In this paper, a new method based on feature learning and spectrogram analysis is proposed to simplify the feature extraction process while maintaining a high level of accuracy. The proposed method learns a dictionary of discriminant features from patches extracted in the spectrogram representations of training speech segments. Each speech segment is then encoded using the dictionary, and the resulting feature set is used to perform classification of personality traits. Experiments indicate that the proposed method achieves state-of-the-art results with an important reduction in complexity when compared to the most recent reference methods. The number of features, and difficulties linked to the feature extraction process are greatly reduced as only one type of descriptors is used, for which the 7 parameters can be tuned automatically. In contrast, the simplest reference method uses 4 types of descriptors to which 6 functionals are applied, resulting in over 20 parameters to be tuned.

关键词： Automatic personality perception spectrograms analysis sparse coding dictionary learning feature learning speaker trait classification acoustic and prosodic modeling

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：