检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Yamada, Kodai Mori, Hiroyuki Tepco Power Grid Inc. Tokyo General Branch Tokyo Japan Meiji University Dept. of Network Design Tokyo Japan

ISBN: (纸本)9781665471640

This paper proposes a method for electricity price forecasting (EPF) with Deep Modified autoencoder (DMAE). It is based on a deep model of the modified autoencoder (MAE) that improves the learning process by adding noise to the original data. EPF is hard to handle due to higher volatility in comparison with other time series in power systems. autoencoder (AE) plays a key role in reducing the dimensionality of input variables in Deep Neural Network (DNN), which is useful for constructing reasonable models with fewer parameters. In this paper, DMAE is proposed as a pretraining technique in Deep Neural Network (DNN). It may be regarded as an integration model that combines MAE with Stacked AE. The proposed method integrates DMAE with Multi-layer perceptron (MLP) to construct DNN. The effectiveness of the proposed method is tested for real data in Boston, MA, USA. © 2023 IEEE.

关键词： autoencoder deep neural network electricity price forecasting power markets

来源：评论

学校读者我要写书评

暂无评论

An Experimental Analysis of Lung Cancer Classification Based on autoencoder on CT Scan Images

An Experimental Analysis of Lung Cancer Classification Based...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Sivakumar, Shreya Govindaraj, Ramkumar Saveetha Institute of Medical and Technical Sciences Saveetha Medical College Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of ECE Chennai India

ISBN: (纸本)9798350319200

When it comes to medical picture recognition, convolutional neural networks are now the gold standard. The mistake in recreating the CT picture is responsible for the low overall accuracy in lung tumor prediction and the lengthy processing time. The use of multispace images in the pooling layer of a convolutional neural network is proposed here in an effort to boost overall prediction accuracy while simultaneously decreasing processing time. Using multispace images in the pooling layer of a convolutional neural network and an Adam Procedure for optimization, the suggested technique is able to detect lung cancer with high precision. The autoencoder system contributes to this success. The CT images were first fed into a convolution filter and down sampled using max pooling as a first step in the processing pipeline. autoencoder models based on convolutional neural networks are utilized to extract features, and multispace image reconstruction techniques are employed to minimize reconstruction errors, resulting in greater precision for predicting lung cancer. Python Tensor Flow was used to analyze the state-of-the-art and recommended remedies, and the results show a considerable improvement (from 91 to 87) in accuracy when classifying lung cancer. The suggested approach boasts the lowest error rate alongside the best accuracy, sensitivity, and *** suggested technique reduces processing time while maintaining superior categorization accuracy, as contrasted to the state of the art. Low-pixel images may be analyzed for categorization evaluation now that the huge dataset is operational. © 2023 IEEE.

关键词： autoencoder Classification Deep Learning LungCancer Machine Learning Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Stacked autoencoder based Soft Sensor Modeling for the Dow Data Challenge Problem 9

Spatiotemporal Stacked Autoencoder based Soft Sensor Modelin...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Zhu, Xiuli Damarla, Seshu Kumar Huang, Biao University of Shanghai for Science and Technology Department of Optical-Electrical and Computer Engineering Shanghai China University of Alberta Department of Chemical and Materials Engineering AB Canada

ISBN: (纸本)9798350319804

Process data with characteristics such as strong nonlinearity, high dimensionality, cross-correlations and auto correlations pose a great challenge for data-driven soft sensor modeling. Albeit the conventional stacked autoencoder (SAE) is able to learn low dimensional nonlinear features from the process data, it fails to extract spatial and temporal features. To overcome this shortcoming, in the present work, spatiotemporal SAE (STSAE) is proposed based on convolutional and LSTM layers. Lower dimensional nonlinear features (spatial and temporal) extracted from STSAE are used to build the soft sensor. The effectiveness of the STSAE-based soft sensor is demonstrated in an industrial case study, the Dow data challenge problem. For the purpose of comparison, soft sensor models based on popular machine learning algorithms are developed and applied to the industrial case study. The obtained results demonstrate that the proposed STSAE based soft sensor yields more accurate estimations for impurity level at the primary column outlet of Dow process refining system. © 2023 IEEE.

关键词： autoencoder CNN Dow data challenge problem LSTM stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Enhancing Drift Detection and Model Uncertainty Handling in Imbalanced Streaming Data using autoencoder-based Approach 2

Enhancing Drift Detection and Model Uncertainty Handling in ...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Suryawanshi, Shubhangi Goswami, Anurag Patil, Pramod Bennett University Greater Noida India Dr. D. Y. Patil Institute of Technology Pune India

ISBN: (纸本)9798350305418

In today’s digital era, numerous applications are generating data in the form of data stream. The data streams are a continuous massive amount of data generated in real-time. Handling the data streams in real-time environments is a critical challenge. The data stream classification becomes more challenging when the statistical properties of the features (changes in the underlying data distribution) or their relationship with the target label are changing and the phenomenon is known as concept drift. When concept drift occurs, a machine learning model trained on previous data may no longer predict or generalise to new incoming data accurately. This can lead to a decrease in performance, poor accuracy, and unreliable predictions. In this paper, we propose an approach for drift detection using an Auto-encoder-based model that incorporates KL divergence and reconstruction loss, along with class imbalance handling and integrating the Monte Carlo Dropout. The autoencoder learns to capture the inherent patterns and regularities, facilitating drift detection by computing the reconstruction loss. KL divergence is an additional loss term, which encourages the Auto-encoder to learn a latent space that is sensitive to changes in the data distribution. Borderline-Synthetic Minority Oversampling Technique (Borderline-SMOTE) is used to address the challenge of class imbalance in drift detection, which generates synthetic minority samples. Integrated the Monte Carlo Dropout, a probabilistic regularization technique, to enhance the model’s uncertainty estimation. The proposed model was evaluated on real-world datasets. The results showed that the proposed model outperformed the other state-of-the-art methods. © 2023 IEEE.

关键词： autoencoder Class Imbalance Concept Drift Data Stream Ensemble Learning

来源：评论

学校读者我要写书评

暂无评论

An autoencoder-based Spiking Representation for Images 2

An Autoencoder-based Spiking Representation for Images

引用

2nd International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023

作者： Zhan, Qiugang Tao, Ran Wei, Ru Jiang, Anning University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China Southwestern University of Finance and Economics School of Computing and Artificial Intelligence Chengdu China

ISBN: (纸本)9798350331417

autoencoders effectively extract low-dimensional features in artificial neural networks (ANNs) but remain scarcely explored for spiking neural networks (SNNs) which enable low-power hardware implementation. This paper presents a spiking autoencoder (SAE) trained by surrogate gradient backpropagation. We implement an encoder-decoder architecture and optimize it to reconstruct images from a compressed spiking representation. Experiments on MNIST and Fashion-MNIST show the SAE accurately reconstructs inputs and compresses them into binary spike codes. Our work demonstrates successful SAE training using surrogate gradients and shows potential for exploiting autoencoders for efficient neural coding with SNNs. © 2023 IEEE.

关键词： autoencoder spiking neural network surrogate gradient

来源：评论

学校读者我要写书评

暂无评论

Automobile Theft Detection by Driving Behavior Identification Using Deep autoencoder

Automobile Theft Detection by Driving Behavior Identificatio...

引用

1st International Conference on Security and Information Technologies with AI, Internet Computing, and Big data Applications (SITAIBA)

作者： Kristianto, Edy Lin, Po-Ching Natl Chung Cheng Univ Dept Comp Sci & Informat Engn Chiayi Minhsiung Taiwan

ISBN: (纸本)9783031054914;9783031054907

Modern vehicles consist of an on-board detection unit that can record a driver's driving behavior. Detecting anomaly in the driving behavior can be used for theft detection. There are many supervised learning models to detect driving behavior. However, it is impractical to collect the behavior of possible thieves beforehand for training. In this work, we design an unsupervised deep autoencoder model, which can learn the driving behavior only from one or few vehicle owners and it can recognize non-owner driving behavior as the vehicle theft. The model is lightweight and it can achieve high accuracy up to around 98% like a supervised model. The analysis results also show that each driver has different important features for the detection when compared with the other drivers.

关键词： Unsupervised learning Anomaly detection Vehicle theft autoencoder

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based anomaly root cause analysis for wind turbines

引用

Energy and AI 2021年第2期4卷 57-65页

作者： Cyriana M.A.Roelofs Marc-Alexander Lutz Stefan Faulstich Stephan Vogt Fraunhofer IEE Konigstor 59Kassel 34119Germany Intelligent Embedded Systems Universitat KasselWilhelmshoher Allee 67Kassel 34121Germany

A popular method to detect anomalous behaviour or specific failures in wind turbine sensor data uses a specific type of neural network called an *** models have proven to be very successful in detecting such deviations,yet cannot show the underlying cause or failure *** information is necessary for the implementation of these models in the planning of maintenance *** this paper we introduce a novel method:*** use ARCANA to identify the possible root causes of anomalies detected by an *** describes the process of reconstruction as an optimisation problem that aims to remove anomalous properties from an anomaly *** reconstruction must be similar to the anomaly and thus identify only a few,but highly explanatory anomalous features,in the sense of Ockham’s *** proposed method is applied on an open data set of wind turbine sensor data,where an artificial error was added onto the wind speed sensor measurements to acquire a controlled test *** results are compared with the reconstruction errors of the autoencoder *** ARCANA method points out the wind speed sensor correctly with a significantly higher feature importance than the other features,whereas using the non-optimised reconstruction error does *** though the deviation in one specific input feature is very large,the reconstruction error of many other features is large as well,complicating the interpretation of the detected ***,we apply ARCANA to a set of offshore wind turbine *** case studies are discussed,demonstrating the technical relevance of ARCANA.

关键词： Anomaly detection autoencoder Root cause analysis Predictive maintenance Wind turbine Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

autoencoder and CNN for Content-based Retrieval of Multimodal Medical Images

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第4期15卷 281-290页

作者： Suresh, Kumar J. S. Maria, Celestin Vigila S. Noorul Islam Ctr Higher Educ Dept Comp Sci & Engn Kanyakumari Tamil Nadu India Noorul Islam Ctr Higher Educ Dept Informat Technol Kanyakumari Tamil Nadu India

Content-Based Medical Image Retrieval (CBMIR) is a widely adopted approach for retrieving related images by the comparison inherent features present in the input image to those stored in the database. However, the domain of CBMIR specific to multiclass medical images faces formidable challenges, primarily stemming from a lack of comprehensive research in this area. Existing methodologies in this field have demonstrated suboptimal performance and propagated misinformation, particularly during the crucial feature extraction process. In response, this investigation seeks to leverage deep learning, a subset of artificial intelligence for the extraction of features and elevate overall performance outcomes. The research focuses on multiclass medical images employing the ImageNet dataset, aiming to rectify the deficiencies observed in previous studies. The utilization of the CNN-based autoencoder method manifests as a strategic choice to enhance the accuracy of feature extraction, thereby fostering improved retrieval results. In the ImageNet dataset, the results obtained from the proposed CBMIR model demonstrate notable average values for accuracy (95.87%), precision (96.03%) and recall (95.54%). This underscores the efficacy of the CNN-based autoencoder model in achieving good accuracy and underscores its potential as a transformative tool in advancing medical image retrieval.

关键词： Medical image retrieval multiclass medical images artificial intelligence deep learning convolutional neural network autoencoder

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based 3D representation learning for industrial seedling abnormality detection

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2023年第1期206卷

作者： de Villiers, Hendrik A. C. Otten, Gerwoud Chauhan, Aneesh Meesters, Lydia Wageningen Univ & Res Food & Biobased Res Bornse Weilanden 9 NL-6708 WG Wageningen Netherlands

Industrial seedling quality assessment, such as attempting to find abnormal seedlings, is a challenging task where assessment methods must contend with the natural variability of seedlings, as well as the subjective nature of expert judgements. Furthermore, obtaining expert judgements is expensive and time-consuming, so machine learning approaches which rely on fewer judgements would be useful in practice. We investigate autoencoders, operating on 3D point clouds obtained from 6732 seedlings to address this challenge, exploiting such systems' ability to work with partially labelled data. Point clouds from tomato seedlings are recorded using a 3D data capture platform, MARVIN'', and the quality of each seedling is determined by expert judgement. An existing system is used to establish baseline performance scores using a rule-based expert system and machine learning with handcrafted features. autoencoders are trained on the point clouds to learn representations for subsequent use in classification. We examine scenarios where large amounts of partially labelled data are available, and compare with the case where fully labelled data is available. To improve performance, we compare the architectural subcomponents based on PointNet and PointNet++, as well as the effect of different training strategies. We fad, with 13.6% of training data labelled, our model has correct classification rates of 97.7% and 82.7% for normals and abnormals respectively. With further improvements and fully labelled data, we find that correct classification rates of 97.6% and 96.1% can be reached. The results demonstrate that semi-supervised learning supported by partially labelled data has the potential to greatly reduce the cost of data curation, with minimal impact on overall accuracy.

关键词： Deep learning autoencoder Seedling 3D PointNet Usable transplant test

来源：评论

学校读者我要写书评

暂无评论

End-to-End Learning Based Symbol-to-Symbol autoencoder for G-band Fiber-Terahertz integrated Communication System

End-to-End Learning Based Symbol-to-Symbol Autoencoder for G...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Huang, Changle Li, Zhongya Jia, Junlian Xing, Size Wang, Chengxi Dong, Boyu Shi, Jianyang Chi, Nan Zhang, Junwen Shanghai China Shanghai China

ISBN: (纸本)9798350312614

Fiber-terahertz integrated communication system has emerged as a promising technology for 6G. In this paper, an end-to-end learning-based quadrature amplitude modulation (QAM) symbol-to-symbol autoencoder frame work is proposed and demonstrated to solve problems in fiber-terahertz integrated communication system. The bit error rate (BER) performance is studied at different peak-to-peak voltage (Vpp) and received optical power (ROP). We compare this method with a baseline using sub-carrier modulation (SCM) signal based on Volterra nonlinear compensation and Least Mean Square (LMS) linear equalization. Through appropriate channel modeling and end-to-end optimization, a sensitivity gain of 1.3 dB is achieved at a data rate of 40 Gbps and a forward error correction (FEC) BER threshold of 1\times 10^-2 after 10-km fiber and 1-m wireless transmission. © 2023 IEEE.

关键词： autoencoder end-to-end deep learning fiber-wireless teraherz

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：