检索结果-内蒙古大学图书馆

CSiamese: a novel semi-supervised anomaly detection framework for gas turbines via reconstruction similarity

NEURAL COMPUTING & APPLICATIONS 2023年第22期35卷 16403-16427页

作者： Liu, Dan Zhong, Shisheng Lin, Lin Zhao, Minghang Fu, Xuyun Liu, Xueyun Harbin Inst Technol Sch Mechatron Engn Harbin 150006 Peoples R China Harbin Inst Technol Sch Ocean Engn Weihai 264209 Peoples R China Harbin Inst Technol Weihai Key Lab Intelligent Operat & Maintenance Weihai 264209 Peoples R China

The main problem in data-driven anomaly detection of gas turbines is that the monitoring data consists of only a very small number of abnormal samples with the overwhelming majority of normal samples. To address this problem, this paper develops a novel semi-supervised anomaly detection framework, namely CSiamese, and the parameters of the framework are optimized only using normal samples, with the ultimate purpose of improving the anomaly detection performance on imbalanced data sets. First, the convolutional auto-encoder is used to learn the reconstructed representation of the input sample. Second, the Siamese network is selected to learn to measure the similarity between the input and its reconstructed representation under noise conditions. Besides, a new loss function is developed by improving the contrastive loss, namely triangle loss, and can reduce the risk of collapsing solutions of the Siamese network when only using positive sample pairs. Third, maximum likelihood estimation is used to set the proper detection threshold to separate abnormal samples from normal samples. Finally, the effectiveness of the developed CSiamese has been evaluated using the real monitoring data of gas turbines and a public CIFAR-10 data set.

关键词： Anomaly detection convolutional auto-encoder The Siamese network Threshold selection

来源：评论

学校读者我要写书评

暂无评论

Deep convolutional neural network based secure wireless voice communication for underground mines

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2021年第10期12卷 9591-9610页

作者： Dey, Prasanjit Kumar, Chandan Mitra, Mitrabarun Mishra, Richa Chaulya, S. K. Prasad, G. M. Mandal, S. K. Banerjee, G. CSIR Cent Inst Min & Fuel Res Barwa Rd Dhanbad 826001 Bihar India

A secure wireless voice communication system for underground miners is an essential gadget for efficient and safe mining. Voice over internet protocol is a proven solution for wireless communication in underground mines where other cellular and satellite networks cannot be deployed. However, the wireless network's security is the major issue for the reliable operation of the system. A secure voice communication system has been developed by integrating voice over internet protocol system and deep convolutional neural network (DCNN) based trained model. Experimental results indicated that voice recognition accuracy of the DCNN based developed model was 93.7% for the noiseless environment. In contrast, it was 82.1 and 79% for the existing K-nearest-neighbour (KNN) and support vector machine (SVM) algorithms, respectively. Voice recognition response time of the DCNN, KNN, and SVM algorithms was 178, 220, and 228 ms, respectively. Thus, deployment of the developed secure and robust voice communication system would improve safety and productivity in underground mines.

关键词： convolutional auto-encoder Deep convolutional neural network Underground mine VoIP Wireless communication

来源：评论

学校读者我要写书评

暂无评论

Sky Imager Data Reduction Using autoencoder and Internet of Things Computing

引用

IEEE ACCESS 2022年 10卷 111232-111240页

作者： Alotaibi, Ziyad N. Khouli, Saeed A. Ibrahim, Ahmed B. Alrabeiah, Muhammad Ragheb, Amr M. Almaiman, Ahmed S. Alshebeili, Saleh A. King Saud Univ Elect Engn Dept Riyadh 11421 Saudi Arabia

Forecasting the output power of renewable energy sources is of an utmost importance for maintaining the stability of the electricity grid and ensuring uninterrupted service. Internet-of-Things (IoT) devices equipped with sky imagers are often used to estimate solar irradiance whose value is essential for forecasting solar energy. This paper considers distributed sky imagers whose data are transmitted through the Internet to a cloud for possible storage, forecasting, and/or performing other signal processing operations. The data comprise a collection of images, and this makes their streaming to the cloud a burden, i.e., they require a large bandwidth. In an attempt to deal with that, an IoT system is proposed in this paper such that it collects, compresses, transmits, and reconstructs those images with as little bandwidth as possible. More specifically, an IoT device multiplexes the collected images and compresses them using a deep learning algorithm, the encoder of a convolutional autoencoder (CAE) in particular. It, then, transmits the compressed images to a cloud server where they could be decompressed with high-fidelity using the decoder of the CAE. As the core to the proposed system, the performance of the CAE algorithm is evaluated using a publicly available dataset of sky images. Results indicate that the images can be compressed to 2% of their original size (i.e., compression ratio of 98%) and reconstructed again with high fidelity, i.e., average structural similarity index measure (SSIM) of 99%. Hardware implementation of the CAE algorithm has also been attempted using a Raspberry Pi platform representing the IoT device with an average processing speed of 6.6681 seconds per frame. This speed well meets practical requirements given the low frame-rate of sky imagers.

关键词： Image coding Forecasting Internet of Things Cloud computing Signal processing algorithms Codecs Image reconstruction convolutional neural networks convolutional auto-encoder image compression sky imager raspberry pi Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A denoising-classification neural network for power transformer protection

引用

Protection and Control of Modern Power Systems 2022年第1期7卷 801-814页

作者： Zongbo Li Zaibin Jiao Anyang He Nuo Xu School of Electrical Engineering Northeast Electric Power UniversityJilinJilinChina School of Electrical Engineering Xi’an Jiaotong UniversityXi’anShaanxiChina

Artificial intelligence(AI)can potentially improve the reliability of transformer protection by fusing multiple ***,owing to the data scarcity of inrush current and internal fault,the existing methods face the problem of poor *** this paper,a denoising-classification neural network(DCNN)is proposed,one which inte-grates a convolutional auto-encoder(CAE)and a convolutional neural network(CNN),and is used to develop a reli-able transformer protection scheme by identifying the exciting voltage-differential current curve(VICur).In the DCNN,CAE shares its encoder part with the CNN,where the CNN combines the encoder and a *** on the inter-action of the CAE reconstruction process and the CNN classification process,the CAE regards the saturated features of the VICur as noise and removes them ***,it guides CNN to focus on the unsaturated features of the *** unsaturated part of the VICur approximates an ellipse,and this significantly differentiates between a healthy and faulty ***,the unsaturated features extracted by the CNN help to decrease the data ergodicity requirement of AI and improve the ***,a CNN which is trained well by the DCNN is used to develop a protection *** simulations and dynamic model experiments verify its superior performance.

关键词： Transformer protection Exciting voltage-differential current curve convolutional auto-encoder convolutional neural network Denoising-classification neural network

来源：评论

学校读者我要写书评

暂无评论

Handwritten numeral recognition through superimposition onto printed form

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第9期34卷 7751-7764页

作者： Shuvo, M. I. R. Akhand, M. A. H. Siddique, Nazmul Khulna Univ Engn & Technol Dept Comp Sci & Engn Khulna 9203 Bangladesh Ulster Univ Sch Comp Engn Intelligent Syst Belfast North Ireland

Handwriting is, eventually, a variation of the printed forms where the characters are little larger, smaller, angled and deformed than the printed forms. The small changes in handwriting define the parameters of the character to be recognized. Handwritten numeral recognition (HNR) poses significant challenges due to the deformations and other variations. This study proposes a new notion of HNR on the hypothesis that the handwritten numerals are distinct deformations of the printed forms, which leads to easier recogni-tion task with higher accuracy when superimposing handwritten numeral images onto the corresponding printed numeral images. In the proposed HNR, auto-encoder and convolutional auto-encoder have been adapted for the superimposing task that transform HNIs into PNIs, while neural network and convolu-tional neural network are employed for classification of PNIs. The superimposition method reduces the computational overhead. Moreover, this method employs simple pre-processing without feature extrac-tion whereas the traditional methods employ pre-processing, feature extraction, and recognition with machine learning tools, which add to the computational overhead. The performance of HNRSP has been evaluated for recognizing handwritten numerals of Bengali, Devanagari, and English on benchmark data -sets and the proposed system achieves 99.68%, 99.73%, and 99.62% recognition accuracy for Bengali, Devanagari, and English handwritten numerals, respectively.(c) 2022 Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Handwritten numeral recognition Printed numeral Artificial neural network convolutional neural network auto-encoder convolutional auto-encoder

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Convolution auto-encoder Based on Spiking Neurons 29th

An Adaptive Convolution Auto-encoder Based on Spiking Neuron...

引用

29th International Conference on Neural Information Processing

作者： Zhu, Chuanmeng Jiang, Jiaqiang Jiang, Runhao Yan, Rui Zhejiang Univ Technol Coll Comp Sci Hangzhou Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou Peoples R China

ISBN: (纸本)9783031301070;9783031301087

Neural coding is one of the central questions in neuroscience for converting visual information into spike patterns. However, the existing encoding techniques require a preset time window and lack effective learning. In order to overcome these two problems, we design an adaptive convolutional auto-encoder based on spiking neurons in this paper. We first exploit the spike pixel mapping decoding approach to find the optimal value of the time window automatically. Next, we design a deep convolutional neural network to adapt the learning parameters by reconstruction errors to realize the spike encoding process. Then we can naturally get coding pre-training parameters for unifying the convolutional spike coding layer with back-end deep spiking neural networks (SNNs) for recognition tasks. Simulation results demonstrate that the proposed method can achieve better performance compared with other encoding methods.

关键词： Neural coding convolutional auto-encoder Encoding time window Spike decoding Reconstruction error SNNs

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Fault Diagnosis Method Based on Less Tag Data 6th

Reinforcement Learning Fault Diagnosis Method Based on Less ...

引用

Conference of The-Efficiency-and-Performance-Engineering-Network (TEPEN) / 6th International conference on Maintenance Engineering (IncoME)

作者： Xin, Kuo Wang, Jianguo Zhang, Wenxing Inner Mongolia Univ Sci & Technol Coll Mech Engn Baotou 014010 Inner Mongolia Peoples R China

ISBN: (纸本)9783030990756;9783030990749

Vibration signals are often used in the fault diagnosis of rotating machinery. However, due to the influence of complex environment, environmental noise is often doped, and the diagnostic accuracy is reduced. The traditional deep self-encoder is used in the noise reduction process of rotating machinery fault diagnosis. The pooling model is poor and easy to lead to over-fitting problems, and deep learning training needs a large number of labeled data. Therefore, this paper proposes a reinforcement learning fault diagnosis method based on less label data. The random pooling is used to replace the pooling layer of the original convolutional self-encoder, and the exponential linear unit (ELU) is used to replace the original activation function to enhance the convolutional self-encoder. A large number of unlabeled samples are used for training, and then the deep reinforcement learning is used for network fine tuning. The experimental results of the sensor data collected by the fault diagnosis test bench show that the method used has a good improvement in denoising ability and feature extraction ability, and the recognition accuracy and stability are better than traditional convolutional autoencoder and traditional machine learning methods.

关键词： Reinforcement learning Stochastic pooling convolutional auto-encoder Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

RECONSTRUCTION OF MISSING DATA IN SATELLITE IMAGES OF THE SOUTHERN NORTH SEA USING A convolutional NEURAL NETWORK (DINCAE)

RECONSTRUCTION OF MISSING DATA IN SATELLITE IMAGES OF THE SO...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Barth, A. Alvera-Azcarate, A. Troupin, C. Beckers, J-M Van der Zande, D. Univ Liege GHER Liege Belgium RBINS Direct Nat Environm Brussels Belgium

ISBN: (纸本)9781665403696

A neural network with the architecture of a convolutional autoencoder is used to reconstruct missing data in satellite images of the Southern North Sea. The technique is applied to a multi-satellite data product of chlorophyll-a and total suspended particulate matter (SPM) concentration (representing 20 years of data). The presence of clouds significantly reduces the extent of the ocean that can be measured by satellite sensors using the visible or infrared spectrum. The accuracy of the reconstruction is assessed using cross-validation (i.e. increasing the actual extent of the cloud coverage). The results of the neural network compare favourably the data withheld for cross-validation.

关键词： Satellite data reconstruction convolutional auto-encoder neural network machine learning DINCAE

来源：评论

学校读者我要写书评

暂无评论

Remaining useful life prediction techniques for electric valves based on convolution auto encoder and long short term memory

引用

ISA TRANSACTIONS 2021年 108卷 333-342页

作者： Wang, Hang Peng, Min-jun Miao, Zhuang Liu, Yong-kuo Ayodeji, Abiodun Hao, Chengming Harbin Engn Univ Key Subject Lab Nucl Safety & Simulat Technol Harbin 150001 Peoples R China China Nucl Power Engn Co LTD Beijing 100840 Peoples R China Nucl Power Inst China Chengdu 610213 Peoples R China

To optimize the operation and maintenance of nuclear power systems, this study presents a remaining useful life (RUL) prediction method for electric valves by combining convolutional auto-encoder (CAE) and long short term memory (LSTM). CAE can extract deeper features and LSTM is efficient in dealing with time-series data. Moreover, by designing a parallel structure between the outputs of CAE and the original data, features fed into the LSTM are enriched. Also, network structure and corresponding hyper-parameters are compared to obtain a more suitable model. Moreover, the accuracy of the proposed method is tested and compared with other machine learning algorithms. This work also serves as a critical innovation to enhance the safety and economic operation of nuclear plants and other complex systems. (c) 2020 ISA. Published by Elsevier Ltd. All rights reserved.

关键词： Electric valve convolutional auto-encoder Long short term memory Remaining useful life prediction

来源：评论

学校读者我要写书评

暂无评论

Learning image by-parts using early and late fusion of auto-encoder features

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第19期80卷 29601-29615页

作者： Susan, Seba Malhotra, Jatin Delhi Technol Univ Dept Informat Technol Delhi 110042 India

A novel sub-part learning scheme is introduced in our work for the purpose of recognizing handwritten numeral images. The idea is borrowed from the concept of visual perception and part-wise integration of visual information by the cortical regions of the brain. In this context, each numeral image is divided into four half-parts: top-half, bottom-half, left-half and right-half;the other half of the image being kept masked. An efficient data representation is derived in an unsupervised manner, from each image part, using convolutional auto-encoders (CAE), for our learning scheme that involves both early and late fusion of features. The chief advantage of the features derived from convolutional auto-encoders is the preservation of 2D spatial locality while the features are being filtered layer-by-layer through the convolutional architecture. The features derived from each individual CAE are fused by concatenation in our early fusion scheme, and learnt using an appropriate classifier. The late fusion strategy involves learning the probability density pertaining to the predicted values emanating from the four base classifiers using a meta-learner classifier. The early-cum-late fusion is proposed in the later stage of our work to combine the goodness of both schemes and enhance the performance. The support vector machine is used in all the classification stages. Experiments on the benchmark MNIST dataset of handwritten English numerals prove that our method competes favorably to the state of the art, as inferred from the high classification scores achieved. Our method thus provides a computationally simple and effective methodology for sub-part learning and part-wise integration of information from different parts of the image. The method also contributes to saving in computational expense since, at a time, only a small part of the image is processed, speeding up the inferencing process.

关键词： Handwritten numeral recognition Sub-part learning convolutional auto-encoder Early fusion Late fusion Early-cum-late fusion

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：