检索结果-内蒙古大学图书馆

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Patel, Jignesh R. Joshi, Manjunath, V Bhatt, Jignesh S. Dhirubhai Ambani Inst Informat & Commun Technol Gandhinagar India Indian Inst Informat Technol Vadodara India

ISBN: (纸本)9781665403696

In this paper, we propose a novel approach for spectral unmixing based on unsupervised learning using autoencoder with Inhomogeneous Gaussian Markov random field (IGMRF) as prior for regularization. The decoder part of our autoencoder has linear weights making it a linear mixture model (LMM). The weights represent the endmember matrix that makes the hidden unit of autoencoder as abundances. IGMRF is used to apply spatial regularization on abundances that also preserves the discontinuities. To incorporate the spectral regularization, we use IGMRF priors on endmembers. In addition, we also apply the spatial and spectral regularizations on the given hyperspectral images (HSI). IGMRF parameters at every pixel locations are calculated using initial estimates of endmembers and abundances. We obtain both endmembers and their abundances by optimizing the loss function that consists of a data term and IGMRF prior terms. Experiments are performed on different noise level synthetic data and two real data (Jasper ridge and Urban). The results of the proposed approach are better when compared to existing state-of-the-art approaches.

关键词： autoencoder IGMRF Spectral unmixing

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Reconstruction of Color Images in Different Lighting Conditions Based on autoencoder Technique

A Deep Learning Approach for Reconstruction of Color Images ...

引用

20th International Conference on Electronics, Information, and Communication (ICEIC)

作者： Gomes, Paul Richie Sabuj, Hasibul Hasan Uddin, Muhammad Arman Reza, Md Tanzim Ibn Faiz, Raian Alam, Md. Ashraful BRAC Univ Dept Comp Sci & Engn 66 Mohakhali Dhaka Bangladesh

ISBN: (纸本)9781728191614

Object detection problem in terms of different lighting conditions has been a challenging issue. Existing algorithms can only detect the objects with their shapes. However, when the color of an object changes in different times of a day for its various lighting conditions, these models fail to detect the shape of those color changing objects. As a result, the reliability of those models decreases. This model proposes an autoencoder technique which can transfer an image of an object to its exact color. A new dataset is created where the image of an object is taken in two different lighting conditions to represent change in color of the same object. Then an autoencoder technique is applied on this dataset. The main function of an autoencoder is to reconstruct its input image which is given in output through a neural network. Once the object is reconstructed to its exact color, understanding the object for any model becomes much more efficient in comparison with existing object detection models.

关键词： Image Reconstruction autoencoder Deep Neural Network Computer Vision

来源：评论

学校读者我要写书评

暂无评论

Weak Anomaly-reinforced autoencoder for Unsupervised Anomaly Detection 13

Weak Anomaly-reinforced Autoencoder for Unsupervised Anomaly...

引用

13th International Conference on Machine Vision

作者： Chen, Xinqiang Su, Lumei Deng, Guansen Huang, Mingyong Wu, Jiajun Peng, Yanqing Xiamen Univ Technol Sch Elect Engn & Automat Xiamen Peoples R China

ISBN: (纸本)9781510640412

At present, most unsupervised abnormal behavior detection method only relies on powerful behavior detection classifiers, does not make full use of prior knowledge. This method often has the problem of a huge amount of calculation and affecting the detection speed. In view of the above problems, this paper proposes a weak anomaly-reinforced autoencoder for unsupervised anomaly detection method, using U-Net to reconstruct video frames and generative adversarial network to learn the correlation between image entropy and abnormal behavior. Comprehensive experiments on the avenue data set and UCSD data sets verify the effectiveness of our method to detect abnormal events.

关键词： Video anomaly detection frame reconstruction autoencoder

来源：评论

学校读者我要写书评

暂无评论

Age Progression/Regression by Dual Discriminator Adversarial autoencoder

Age Progression/Regression by Dual Discriminator Adversarial...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Lan, Li-Chi Liu, Tsung-Jung Liu, Kuan-Hsien Natl Chung Hsing Univ Grad Inst Commun Engn Taichung 40227 Taiwan Natl Chung Hsing Univ Dept Elect Engn Taichung 40227 Taiwan Natl Taichung Univ Sci & Technol Dept Comp Sci & Informat Engn Taichung 40401 Taiwan

ISBN: (纸本)9781728197661

The progression/regression of facial age can be applied to cross-age recognition or entertainment-related applications. It is challenging due to lack of facial expressions of the same person in a longer age range. Conditional Adversarial autoencoder (CAAE) can learn facial manifolds and achieve smooth age development and regression at the same time. Since the generated face is different from the real face, we develop a novel model based on CAAE, which used two discriminators instead of one to solve this problem. The proposed model can produce better results and improve the similarity degree of age progression for different races of people.

关键词： Face aging age progression generative adversarial networks discriminator autoencoder

来源：评论

学校读者我要写书评

暂无评论

AutoFuse: A Semi-supervised autoencoder based Multi-Sensor Fusion Framework

AutoFuse: A Semi-supervised Autoencoder based Multi-Sensor F...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Kumar, Kriti Sahu, Saurabh Majumdar, Angshul Chandra, M. Girish TCS Res & Innovat Bangalore Karnataka India IIIT Delhi New Delhi India

ISBN: (纸本)9780738133669

The performance of existing methods for multi-sensor fusion are severely affected by the lack of significant amount of labeled data. In most practical scenarios, the amount of unlabeled data is huge in comparison to labeled data. To address this problem, a novel autoencoder based multi-sensor fusion framework for semi-supervised learning is proposed in this work. Here, both labeled and unlabeled data are used for learning the latent representation from each sensor. Subsequently, the latent representation of all the sensors are combined to perform classification. A joint optimization formulation is presented for learning the sensor-specific latent representation, their encoder and decoder weights and the classification weights together. This ensures discriminative features to be learnt from individual sensors that aids in classification. The requisite solution steps and the closed form updates for the joint learning of all the parameters are given. Experiment results presented on two datasets from different domains demonstrate the generalizability and superior performance of the proposed AutoFuse compared to state-of-the-art methods with relatively less complexity and the ability to work with partially annotated data.

关键词： Multi-sensor fusion autoencoder Semi-supervised learning Representation learning Classification

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of autoencoder-LSTM Accelerator for Edge Outlier Detection

Design and Implementation of Autoencoder-LSTM Accelerator fo...

引用

35th IEEE Workshop on Signal Processing Systems (IEEE SiPS)

作者： Mohamed, Nadya A. Cavallaro, Joseph R. Rice Univ Dept Elect & Comp Engn POB 1892 Houston TX 77251 USA

ISBN: (纸本)9781665401449

Sensors are used to monitor various parameters in many real-world applications. Sudden changes in the underlying patterns of the sensors readings may represent events of interest. Therefore, event detection, an important temporal version of outlier detection, is one of the primary motivating applications in sensor networks. This work describes the implementation of a real-time outlier detection that uses an autoencoder-LSTM neural-network accelerator implemented on the Xilinx PYNQ-Z1 development board. The implemented accelerator consists of a fine-tuned autoencoder to extract the latent features in sensor data followed by a Long short-term memory (LSTM) network to predict the next step and detect outliers in real-time. The implemented design achieves 2.06 ms minimum latency and 85.9 GOp/s maximum throughput. The low latency and 0.25 W power consumption of the autoencoder-LSTM outlier detector makes it suitable for resource-constrained computing platforms.

关键词： Accelerator FPGA embedded systems autoencoder LSTM outliers CORDIC

来源：评论

学校读者我要写书评

暂无评论

Reducing the Training Overhead of the HPC Compression autoencoder via Dataset Proportioning 15

Reducing the Training Overhead of the HPC Compression Autoen...

引用

15th IEEE International Conference on Networking, Architecture and Storage (NAS)

作者： Liu, Tong Alibhai, Shakeel Wang, Jinzhen Liu, Qing He, Xubin Temple Univ Dept Comp & Informat Sci Philadelphia PA 19122 USA New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA

ISBN: (纸本)9781728177441

As the storage overhead of high-performance computing (HPC) data reaches into the petabyte or even exabyte scale, it could be useful to find new methods of compressing such data. The compression autoencoder (CAE) has recently been proposed to compress HPC data with a very high compression ratio. However, this machine learning-based method suffers from the major drawback of lengthy training time. In this paper, we attempt to mitigate this problem by proposing a proportioning scheme to reduce the amount of data that is used for training relative to the amount of data to be compressed. We show that this method drastically reduces the training time without, in most cases, significantly increasing the error. We further explain how this scheme can even improve the accuracy of the CAE on certain datasets. Finally, we provide some guidance on how to determine a suitable proportion of the training dataset to use in order to train the CAE for a given dataset.

关键词： Data compression HPC machine learning autoencoder training time

来源：评论

学校读者我要写书评

暂无评论

Reference-Relation Guided autoencoder with Deep CCA Restriction for Awake-to-Sleep Brain Functional Connectome Prediction 24th

Reference-Relation Guided Autoencoder with Deep CCA Restrict...

引用

International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

作者： Hu, Dan Yin, Weiyan Wu, Zhengwang Chen, Liangjun Wang, Li Lin, Weili Li, Gang Univ N Carolina Dept Radiol & BRIC Chapel Hill NC 27599 USA

ISBN: (纸本)9783030871994;9783030871987

The difficulty of acquiring resting-state fMRI of early developing children under the same condition leads to a dedicated protocol, i.e., scanning younger infants during sleep and older children during being awake, respectively. However, the obviously different brain activities of sleep and awake states arouse a new challenge of awake-to-sleep connectome prediction/translation, which remains unexplored despite its importance in the longitudinally-consistent delineation of brain functional development. Due to the data scarcity and huge differences between natural images and geometric data (e.g., brain connectome), existing methods tailored for image translation generally fail in predicting functional connectome from awake to sleep. To fill this critical gap, we unprecedentedly propose a novel reference-relation guided autoencoder with deep CCA restriction (R(2)AE-dCCA) for awake-to-sleep connectome prediction. Specifically, 1) A reference-autoencoder (RAE) is proposed to realize a guided generation from the source domain to the target domain. The limited paired data are thus greatly augmented by including the combinations of all the age-restricted neighboring subjects as the references, while the target-specific pattern is fully learned;2) A relation network is then designed and embedded into RAE, which utilizes the similarity in the source domain to determine the belief-strength of the reference during prediction;3) To ensure that the learned relation in the source domain can effectively guide the generation in the target domain, a deep CCA restriction is further employed to maintain the neighboring relation during translation;4) New validation metrics dedicated for connectome prediction are also proposed. Experimental results showed that our proposed R(2)AE-dCCA produces better prediction accuracy and well maintains the modular structure of brain functional connectome in comparison with state-of-the-art methods.

关键词： Functional connectome prediction rs-fMRI autoencoder

来源：评论

学校读者我要写书评

暂无评论

autoencoder as a New Method for Maintaining Data Privacy While Analyzing Videos of Patients With Motor Dysfunction: Proof-of-Concept Study

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2020年第5期22卷 e16669页

作者： D'Souza, Marcus Van Munster, Caspar E. P. Dorn, Jonas F. Dorier, Alexis Kamm, Christian P. Steinheimer, Saskia Dahlke, Frank Uitdehaag, Bernard M. J. Kappos, Ludwig Johnson, Matthew Univ Hosp Basel Dept Med Neurol Clin & Policlin Petersgraben 4 Basel 4031 Switzerland Univ Hosp Basel Dept Biomed Neurol Clin & Policlin Petersgraben 4 Basel 4031 Switzerland Univ Hosp Basel Dept Clin Res Neurol Clin & Policlin Petersgraben 4 Basel 4031 Switzerland Univ Basel Petersgraben 4 Basel 4031 Switzerland Univ Amsterdam Multiple Sclerosis Ctr Amsterdam Dept Neurol Med Ctr Amsterdam Netherlands Novartis Pharma AG Basel Switzerland Luzerner Kantonsspital Neuroctr Luzern Switzerland Univ Bern Dept Neurol Inselspital Bern Switzerland Microsoft Res Cambridge England

Background: In chronic neurological diseases, especially in multiple sclerosis (MS), clinical assessment of motor dysfunction is crucial to monitor the disease in patients. Traditional scales are not sensitive enough to detect slight changes. Video recordings of patient performance are more accurate and increase the reliability of severity ratings. When these recordings are automated, quantitative disability assessments by machine learning algorithms can be created. Creation of these algorithms involves non-health care professionals, which is a challenge for maintaining data privacy. However, autoencoders can address this issue. Objective: The aim of this proof-of-concept study was to test whether coded frame vectors of autoencoders contain relevant information for analyzing videos of the motor performance of patients with MS. Methods: In this study, 20 pre-rated videos of patients performing the finger-to-nose test were recorded. An autoencoder created encoded frame vectors from the original videos and decoded the videos again. The original and decoded videos were shown to 10 neurologists at an academic MS center in Basel, Switzerland. The neurologists tested whether the 200 videos were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-Expanded Disability Status Scale definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between the original and decoded videos. Results: In total, 172 of 200 (86.0%) videos were of sufficient quality to be ratable. The intrarater agreement between the original and decoded videos was 0.317 (Cohen weighted kappa). The average difference in the ratings between the original and decoded videos was 0.26, in which the original videos were rated as more severe. The interrater agreement between the original videos was 0.459 and that between the decoded videos was 0.302. The agreement was higher when no deficits or very severe de

关键词： autoencoder video-rating machine learning algorithms deep neuronal network Neurostatus-EDSS

来源：评论

学校读者我要写书评

暂无评论

Fault Detection and Isolation for Chiller System based on Deep autoencoder 16

Fault Detection and Isolation for Chiller System based on De...

引用

16th IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Cheng, Fanyong Cai, Wenjian Liao, Huanyue Wu, Bingjie Dubey, Swapnil Nanyang Technol Univ SJ NTU Corp Lab 50 Nanyang Ave Singapore 639798 Singapore

ISBN: (纸本)9781665422482

In practical chiller systems, applying efficient fault diagnosis and Isolation (FDI) techniques can significantly reduce the energy consumption and keep the environment comfortable. The success of the existing methods for fault detection and diagnosis of chillers relies on the condition that sufficient labeled data are available for training. Generally, the number of labeled data is limited while abundant unlabeled normal data are available. To make effective use of the large number of unlabeled data to improve the fault detection (FD) performance and realize fault isolation (FI), a novel data driven FDI method based on the deep autoencoder (DAEFDI) is proposed. Specifically, DAEFDI method consists of two parts: fault detection (DAEFD) and fault isolation (DAEFI). For the DAEFD part, the unlabeled normal data is used to learn a DAE model to describe the chiller system. When the reconstruction error is higher than the threshold, it is considered that the system deviates from the normal state. For the DAEFI part, when it is detected that the system is in a fault state, the source variable caused the fault is found according to their proportion in the reconstruction error. Experimental results demonstrate the effectiveness of the DAEFDI method.

关键词： Fault detection Isolation Deep learning autoencoder Chiller system

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：