检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition and image analysis (IPRIA)

作者： Seyed Amir Latifi Hassan Ghassemian Maryam Imani Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

Bacteria, viruses, and fungi can cause respiratory infections. It is usually possible to detect respiratory diseases early by listening to the lung sounds with a stethoscope. In reality, lung sound analysis is a time-consuming and difficult task that depends on medical skills and recognition experience. Recent advances in automatic respiratory sound recognition and classification have attracted more attention. The outbreak of COVID-19 throughout the world and the high patient numbers have placed a great deal of pressure on medical professionals. A smart algorithm is therefore a necessity to provide a faster and more accurate detection of lung infections by automatically processing the sounds of the lungs. This paper proposes two new lung sound feature extraction, maximum entropy Gabor filter bank (MAGFB), and maximum entropy Mel filter bank (MAMFB). The classification is performed by a deep neural convolution network (DCNN) by using 50% of data for training the classifier. The filter banks have been substituted, instead of the convolutional layers. Experiments were conducted on the ICBHI 2017 Challenge dataset (with eight classes). The proposed method has a better performance compared to famous methods such as MFCC and Wavelet transform. Particularly, the performance of the second method is significant. For ICBHI 2017 challenge dataset, the overall accuracy of MFCC, Wavelet, MAGFB and MAMFB were 87%, 86%,90% and 93%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion of Multi-Level CNN With LBP Features For Facial Emotion Recognition

Fusion of Multi-Level CNN With LBP Features For Facial Emoti...

引用

Iranian Conference on Electrical Engineering (ICEE)

作者： Ehsan Bahmanabady Maryam Imani Hassan Ghassemian Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

A facial emotion recognition framework is proposed in this work. The convolutional neural network (CNN) has high ability in extraction of hierarchical spatial features from low level texture characteristics to high level contextual features. A simple CNN model with three layers is suggested in this paper where the features extracted in all layers containing multi-level features are activated and used for classification. In addition, the local binary pattern (LBP) descriptor is used to extract discriminative features from the spatial structure of the input image. Therefore, four feature sources are provided by multi levels of CNN and the LBP descriptor. Each feature source is used for facial emotion recognition by applying to the support vector machine (SVM) classier. Finally, the majority voting rule is used for decision fusion to provide the final emotional label of each given face image. The proposed method with 84% overall accuracy, 83% weighted F1-score and 81% kappa coefficient provides the best performance compared to LBP, multi-level CNN and two-dimensional principal component analysis (2DPCA) methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Spectral-Spatial Network for Feature Fusion and Classification of Hyperspectral images 7

A New Spectral-Spatial Network for Feature Fusion and Classi...

引用

7th International Conference on Signal processing and Intelligent Systems, ICSPIS 2021

作者： Aghili, Mohamad Ebrahim Ghassemian, Hassan Imani, Maryam Tarbiat Modares University Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9781665409384

Hyperspectral image (HSI) classification is one of the most important applications among all types of classification fields. Proper classification of spectral data leads to discovery of important land covers. In recent years, many methods have been introduced to increase the HSI classification accuracy. Methods based on neural networks show superior results compared to other methods. Among them, the two-dimensional convolutional neural networks (2D-CNNs) inspired by the human eye retina have achieved higher accuracy in classification. In most cases, HSI classifiers use only spectral features. In this paper, the spectral-spatial feature fusion and HSI classification using 2D-CNN are focused. For this purpose, the first 2D-convolutional layer of CNN is substituted by two combined 2D-Gabor-Shapelet filter banks. This layer extracts contextual information and provides valuable joint spectral-spatial features. The experimental results on real HSI (including the urban and agricultural areas and their mixture) show that the proposed method improves the overall classification performance. Compared to several famous HSI classification based on neural networks, the proposed method has higher speed and classification accuracy. © 2021 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Knowledge-guided EEG Representation Learning

Knowledge-guided EEG Representation Learning

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Aditya Kommineni Kleanthis Avramidis Richard Leahy Shrikanth Narayanan Signal Analysis and Interpretation Lab University of Southern California Los Angeles CA Signal and Image Processing Institute University of Southern California Los Angeles CA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Self-supervised learning has produced impressive results in multimedia domains of audio, vision and speech. This paradigm is equally, if not more, relevant for the domain of biosignals, owing to the scarcity of labelled data in such scenarios. The ability to leverage large-scale unlabelled data to learn robust representations could help improve the performance of numerous inference tasks on biosignals. Given the inherent domain differences between multimedia modalities and biosignals, the established objectives for self-supervised learning may not translate well to this domain. Hence, there is an unmet need to adapt these methods to biosignal analysis. In this work we propose a self-supervised model for EEG, which provides robust performance and remarkable parameter efficiency by using state space-based deep learning architecture. We also propose a novel knowledge-guided pre-training objective that accounts for the idiosyncrasies of the EEG signal. The results indicate improved embedding representation learning and downstream performance compared to prior works on exemplary tasks. Also, the proposed objective significantly reduces the amount of pre-training data required to obtain performance equivalent to prior works.

关键词： Representation learning Adaptation models Biological system modeling Deep architecture Self-supervised learning Motors Brain modeling Electroencephalography Engineering in medicine and biology image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Riemannian SOS-Polynomial Normalizing Flows 1

引用

42nd German Conference on Pattern Recognition, DAGM GCPR 2020 held in parallel with 25th International Symposium on Vision, Modeling, and Visualization, VMV 2020 and 10th Eurographics Workshop on Visual Computing for Biology and Medicine, VCBM 2020

作者： Schwarz, Jonathan Draxler, Felix Köthe, Ullrich Schnörr, Christoph Heidelberg Collaboratory for Image Processing Heidelberg University Heidelberg Germany Image and Pattern Analysis Group Heidelberg University Heidelberg Germany Visual Learning Lab Heidelberg University Heidelberg Germany

ISBN: (数字)9783030712785

ISBN: (纸本)9783030712778

Sum-of-Squares polynomial normalizing flows have been proposed recently, without taking into account the convexity property and the geometry of the corresponding parameter space. We develop two gradient flows based on the geometry of the parameter space of the cone of SOS-polynomials. Few proof-of-concept experiments using non-Gaussian target distributions validate the computational approach and illustrate the expressiveness of SOS-polynomial normalizing flows. © 2021, Springer Nature Switzerland AG.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Characterizing the Role of a Single Coupling Layer in Affine Normalizing Flows 1

引用

作者： Draxler, Felix Schwarz, Jonathan Schnörr, Christoph Köthe, Ullrich Heidelberg Collaboratory for Image Processing Heidelberg University Heidelberg Germany Visual Learning Lab Heidelberg University Heidelberg Germany Image and Pattern Analysis Group Heidelberg University Heidelberg Germany

ISBN: (数字)9783030712785

ISBN: (纸本)9783030712778

Deep Affine Normalizing Flows are efficient and powerful models for high-dimensional density estimation and sample generation. Yet little is known about how they succeed in approximating complex distributions, given the seemingly limited expressiveness of individual affine layers. In this work, we take a first step towards theoretical understanding by analyzing the behaviour of a single affine coupling layer under maximum likelihood loss. We show that such a layer estimates and normalizes conditional moments of the data distribution, and derive a tight lower bound on the loss depending on the orthogonal transformation of the data before the affine coupling. This bound can be used to identify the optimal orthogonal transform, yielding a layer-wise training algorithm for deep affine flows. Toy examples confirm our findings and stimulate further research by highlighting the remaining gap between layer-wise and end-to-end training of deep affine flows. © 2021, Springer Nature Switzerland AG.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Knowledge-guided EEG Representation Learning

arXiv

引用

arXiv 2024年

作者： Kommineni, Aditya Avramidis, Kleanthis Leahy, Richard Narayanan, Shrikanth Signal Analysis and Interpretation Lab University of Southern California Los AngelesCA90089 United States Signal and Image Processing Institute University of Southern California Los AngelesCA90089 United States

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A New Composite Multimodality image Fusion Method Based on Shearlet Transform and Retina Inspired Model 1

A New Composite Multimodality Image Fusion Method Based on S...

引用

1st International Conference on Machine Vision and image processing, MVIP 2020

作者： Sayadi, Mohammadmahdi Ghassemian, Hassan Naimi, Reza Imani, Maryam Tarbiat Modares University Image Processing and Information Analysis Lab. Tehran Iran

ISBN: (纸本)9781728168326

Medical imaging is a very important element in disease diagnosis. MRI image has structural information, while PET image has functional information. However, there is no medical imagery device that has both structural and functional information simultaneously. Thus, the image fusion technique is used. This work concentrates on PET and MRI fusion. It is based on the combination of retina-inspired model and Non-Subsampled shearlet transform. In the first step, the high-frequency component is obtained by applying the shearlet transform to the MRI image, which produces sub-images in several scales and directions, and by adding up these images together a single edge image is reconstructed. In the second step, the PET image is transferred from RGB color space into IHS color space. Then the low-frequency component is produced by applying a Gaussian low pass filter to the luminance channel of the PET image. By adding up low frequency component and high-frequency component together and transferring the result from IHS color space to RGB color space the fused image is obtained. © 2020 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Estimation of Free Parameters of Morphological Profiles for Building Extraction Using SAR images

Estimation of Free Parameters of Morphological Profiles for ...

引用

International Conference of Signal processing and Intelligent Systems (ICSPIS)

作者： Fateme Amjadipour Hassan Ghassemian Maryam Imani Image Processing and Information Analysis Lab Tarbiat Modares University Tehran Iran

ISBN: (纸本)9781665409391

Nowadays, one of the most challenging issues in the field of remote sensing and satellite imagery is production of cadastral maps. Synthetic aperture radar (SAR) images are among the most widely used satellite images in the last decade. Due to radar nature of these images, the buildings in SAR images face with two problems: shadow and layover. Morphological mathematics are efficient tools for detection of buildings with providing a contextual profile containing shape and geometrical characteristics of the objects in radar images. By using the suggested method, two characteristics of shadow and brightness are detected separately. Then, the construction areas are extracted by using a fuzzy fusion approach. In this method, various parameters such as size and direction of the structural element and the weighting factor of the shadow, bright area, and the recursive parameter have to be determined independently. To this end, an iterative method using MSE is suggested. The experimental results show a detection rate of 94.3% achieved by the proposed method.

关键词： Satellites Shape Spaceborne radar Roads Buildings Radar imaging Signal processing

来源：评论

学校读者我要写书评

暂无评论

Deep Curriculum Learning for PolSAR image Classification

arXiv

引用

arXiv 2021年

作者： Mousavi, Hamidreza Imani, Maryam Ghassemian, Hassan Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tehran Iran

Following the great success of curriculum learning in the area of machine learning, a novel deep curriculum learning method proposed in this paper, entitled DCL, particularly for the classification of fully polarimetric synthetic aperture radar (PolSAR) data. This method utilizes the entropy-alpha target decomposition method to estimate the degree of complexity of each PolSAR image patch before applying it to the convolutional neural network (CNN). Also, an accumulative mini-batch pacing function is used to introduce more difficult patches to CNN. Experiments on the widely used data set of AIRSAR Flevoland reveal that the proposed curriculum learning method can not only increase classification accuracy but also lead to faster training convergence. © 2021, CC BY.

关键词： Curricula

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：