检索结果-内蒙古大学图书馆

CESCAL: A joint compression-encryption scheme based on convolutional autoencoder and logistic map

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第11期83卷 32069-32098页

作者： Sabha, Iram Parah, Shabir A. Sarosh, Parsa Ul Islam, Malik Obaid Univ Kashmir Dept Elect & Instrumentat Technol Srinagar 190006 India

In the modern digital world, it is getting harder to share voluminous data with high dimensions, over the internet with adequate security. Images build up a noteworthy section of the data shared online. Sending high-dimensional images over the transmission channel with constrained bandwidth is challenging. Additionally, it takes more time to transmit them furthermore, uses more storage space. In this paper, we present CESCAL, a joint Compression-Encryption Scheme based on convolutional autoencoder and Enhanced Logistic map for image compression. CESCAL effectively reduces the bandwidth/storage requirement for images and ensures secure communication of high-dimensional images over an insecure network. CESCAL makes use of a convolutional autoencoder for compression followed by chaos-based encryption. In the compression phase, the high-dimensional image is applied to a convolutional autoencoder to obtain the compressed output with lower dimensions. The compressed output is then subjected to enhanced logistic map-based encryption. We have achieved the structural similarity index metrics (SSIM) of 0.009, the entropy of 7.9975, and the number of pixels change rate (NPCR) of 99.60 for the plain grayscale image of Lena. The proposed system can successfully resist different statistical attacks while achieving excellent encryption performance compared to the state-of-the-art.

关键词： convolutional autoencoder Image compression Image feature maps Chaotic map Image encryption

来源：评论

学校读者我要写书评

暂无评论

Online quantitative monitoring of milling cutter health condition based on deep convolutional autoencoder

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2023年第9-10期125卷 4739-4752页

作者： Lei, Yuncong Li, Changgen Guo, Liang Gao, Hongli Liang, Junhua Sun, Yi He, Jigang Southwest Jiaotong Univ Sch Mech Engn Chengdu 610031 Sichuan Peoples R China Southwest Jiaotong Univ Engn Res Ctr Adv Drive Energy saving Technol Minist Educ Chengdu 610031 Sichuan Peoples R China

The health condition of milling cutters (HCOMC) could heavily affect workpiece quality. However, it is extremely difficult to be quantified online. To solve this problem, an online quantitative monitoring method (OQM) is proposed based on a deep convolutional autoencoder (CAE). In this method, a health indicator (HI) is constructed for fast HCOMC monitoring. The OQM is composed of two parts, offline training and online monitoring. In the offline stage, the multi-sensor monitoring data that record in the cutter normal wear stage (named normal wear data, NWD) are selected from a subsampled life testing dataset to train a deep CAE. In the online stage, each monitoring data segment (MDS) is directly input into the trained CAE to obtain deep representations. Then, the HI is constructed by the mean square error (MSE) between the MDS and the deep representations to monitor the HCOMC. It is called convolutional-autoencoder-reconstruction-error-based health indicator (CARE-HI). In addition to the above-mentioned method, a new metric named isometric fusion metric (IFM) is also designed to assess HI. IFM is able to address the uneven problem of property contribution when using some widely used HI metrics. In the experiment, 28 milling cutters were subjected to cutting experiments under different working conditions. The experimental result demonstrates that the proposed OQM can efficiently improve feature quality and precisely monitor HCOMC. It also illustrates that the CARE-HI outperformed some existing ones in five metric dimensions. Therefore, the proposed CARE-HI can provide more accurate guidance for tool changing in machining.

关键词： Online quantitative monitoring Health indicator convolutional autoencoder Fusion metric Milling cutters

来源：评论

学校读者我要写书评

暂无评论

Two-Step Electricity Theft Detection Strategy Considering Economic Return Based on convolutional autoencoder and Improved Regression Algorithm

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2022年第3期37卷 2346-2359页

作者： Cui, Xueyuan Liu, Shengyuan Lin, Zhenzhi Ma, Jien Wen, Fushuan Ding, Yi Yang, Li Guo, Wenchong Feng, Xiaofeng Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China Shandong Univ Dept Elect Engn Jinan 250061 Peoples R China Guangdong Power Grid Corp Metrol Ctr Guangzhou 510080 Peoples R China

Electricity theft behaviors have caused great harm to the economic benefits of power companies and the secure operation of power systems, thus electricity theft detection is paid much attention in the actual power supply management. In this work, a two-step electricity theft detection strategy is proposed to identify electricity theft users and predict potentially stolen electricity (PSE) for maximizing economic return. In the first step, a neural network model called convolutional autoencoder (CAE) is proposed for electricity theft identification, and the convolutional layer is adopted in CAE to extract and identify the abnormalities of electricity theft users against the uniformity and periodicity of normal power consumption features. In the second step, the PSE of each identified electricity theft user is predicted by the improved regression algorithm named Tr-XGBoost, which combines the extreme gradient boosting (XGBoost) algorithm and transfer adaptive boosting (TrAdaBoost) training strategy. The propsoed Tr-XGBoost could learn the relationship between the extracted electricity features and the PSE of each electricity theft user, and then the predicted PSE can be used to determine the list of electricity theft users to be inspected for maximizing economic return. Case studies on both the IEEE 33-bus test system and a low-voltage distribution system of a province in China show that the proposed two-step electricity theft detection strategy can improve the accuracy of electricity theft identification, and obtain a larger economic return because of a more accurate result of PSE prediction than other state-of-the-art algorithms.

关键词： Feature extraction Economics Distributed databases Data mining Prediction algorithms Open source software Training convolutional autoencoder economic return electricity theft detection non-technical losses XGBoost

来源：评论

学校读者我要写书评

暂无评论

Field experiment on a PSC-I bridge for convolutional autoencoder-based damage detection

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2021年第4期20卷 1627-1643页

作者： Lee, Kanghyeok Jeong, Seunghoo Sim, Sung-Han Shin, Do Hyoung Inha Univ Dept Civil Engn Incheon 22212 South Korea Sungkyunkwan Univ Sch Civil Architectural Engn & Landscape Architec Suwon South Korea

In this study, a field experiment was performed for damage detection on a PSC-I bridge based on a convolutional autoencoder using the damage detection approach proposed in a previous study by the authors. The field experiment measured the acceleration and strain data of the PSC-I bridge while a single vehicle passed the bridge;subsequently, these data were used to train and test the convolutional autoencoder-based damage detection model. The results of the test showed that the convolutional autoencoder-based model could perform accurate and robust damage detection. Furthermore, these findings indicate that the convolutional autoencoder-based damage detection could also perform satisfactorily in practice. The results of this study can form the basis to facilitate the adoption of the convolutional autoencoder-based damage detection method to monitor bridges in practice.

关键词： Damage detection deep learning convolutional autoencoder field experiment PSC-I bridge autoencoder machine learning field demonstration

来源：评论

学校读者我要写书评

暂无评论

A Deep convolutional autoencoder-Based Approach for Anomaly Detection With Industrial, Non-Images, 2-Dimensional Data: A Semiconductor Manufacturing Case Study

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2022年第3期19卷 1477-1490页

作者： Maggipinto, Marco Beghi, Alessandro Susto, Gian Antonio Univ Padua Dept Informat Engn I-35122 Padua Italy Univ Padua Human Inspired Technol Res Ctr I-35122 Padua Italy

In manufacturing industries, it is of fundamental importance to detect anomalies in production in order to meet the required quality goals and to limit the number of defective products that are accidentally delivered to the customers. Nevertheless, monitoring systems currently employed in production are typically very simple and rely on a set of univariate control charts that fail to capture the multivariate and complex nature of real-world industrial systems. In such context, Machine Learning (ML)-based approaches for Anomaly Detection (AD) have proven to be extremely effective in increasing anomalies detectability and, in general, in enhancing monitoring procedures. However, industrial data are typically very complex and not suitable to be fed directly to classical ML-based AD tools making feature extraction procedures a necessary step that unfortunately may lead to information loss and low scalability. Deep Learning, has proven very effective at learning useful representations of complex data in an automatic way. In this paper, we propose an AD pipeline that makes use of convolutional autoencoders to extract useful features from two-dimensional, non-image, data. We test our approach on real world Optical Emission Spectroscopy data that are typical of semiconductor manufacturing and we achieve improved performance over classical monitoring methods.

关键词： Feature extraction Task analysis Monitoring Anomaly detection Manufacturing Standards Deep learning Anomaly detection convolutional autoencoder deep neural networks Industry 4 0 machine learning semiconductor manufacturing unsupervised feature selection

来源：评论

学校读者我要写书评

暂无评论

A Pansharpening Based on the Non-Subsampled Contourlet Transform and convolutional autoencoder: Application to QuickBird Imagery

引用

IEEE ACCESS 2022年 10卷 44778-44788页

作者： Al Smadi, Ahmad Yang, Shuyuan Abugabah, Ahed Alzubi, Ahmad Ali Sanzogni, Louis Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Zayed Univ Coll Technol Innovat Abu Dhabi U Arab Emirates King Saud Univ Community Coll Comp Sci Dept Riyadh 11437 Saudi Arabia Griffith Univ Dept Business Strategy & Innovat Nathan Campus Nathan Qld 4111 Australia

This paper presents a pansharpening technique based on the non-subsampled contourlet transform (NSCT) and convolutional autoencoder (CAE). NSCT is exceptionally proficient at presenting orientation information and capturing the internal geometry of objects. First, it's used to decompose the multispectral (MS) and panchromatic (PAN) images into high-frequency and low-frequency components using the same number of decomposition levels. Second, a CAE network is trained to generate original low-frequency PAN images from their spatially degraded versions. Low-resolution multispectral images are then fed into the trained convolutional autoencoder network to generate estimated high-resolution multispectral images. Third, another CAE network is trained to generate original high-frequency PAN images from their spatially degraded versions. The result of low-pass CAE is fed to the trained high-pass CAE to generate estimated high-resolution multispectral images. The final pan-sharpened image is accomplished by injecting the detailed map of the spectral bands into the corresponding estimated high-resolution multispectral bands. The proposed method is tested on QuickBird datasets and compared with some existing pan-sharpening techniques. Objective and subjective results demonstrate the efficiency of the proposed method.

关键词： Pansharpening Transforms Spatial resolution Licenses Satellites Image fusion Training Pansharpening multispectral image fusion convolutional autoencoder NSCT remote sensing

来源：评论

学校读者我要写书评

暂无评论

MaskCAE: Masked convolutional autoencoder via Sensor Data Reconstruction for Self-Supervised Human Activity Recognition

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第5期28卷 2687-2698页

作者： Cheng, Dongzhou Zhang, Lei Qin, Lutong Wang, Shuoyuan Wu, Hao Song, Aiguo Nanjing Normal Univ Sch Elect & Automat Engn Nanjing 210023 Peoples R China Univ Macau Dept Comp & Informat Sci Taipa 999078 Peoples R China Yunnan Univ Sch Informat Sci & Engn Kunming 650500 Peoples R China Southeast Univ Sch Instrument Sci & Engn Nanjing 210096 Peoples R China

Self-supervised Human Activity Recognition (HAR) has been gradually gaining a lot of attention in ubiquitous computing community. Its current focus primarily lies in how to overcome the challenge of manually labeling complicated and intricate sensor data from wearable devices, which is often hard to interpret. However, current self-supervised algorithms encounter three main challenges: performance variability caused by data augmentations in contrastive learning paradigm, limitations imposed by traditional self-supervised models, and the computational load deployed on wearable devices by current mainstream transformer encoders. To comprehensively tackle these challenges, this paper proposes a powerful self-supervised approach for HAR from a novel perspective of denoising autoencoder, the first of its kind to explore how to reconstruct masked sensor data built on a commonly employed, well-designed, and computationally efficient fully convolutional network. Extensive experiments demonstrate that our proposed Masked convolutional autoencoder (MaskCAE) outperforms current state-of-the-art algorithms in self-supervised, fully supervised, and semi-supervised situations without relying on any data augmentations, which fills the gap of masked sensor data modeling in HAR area. Visualization analyses show that our MaskCAE could effectively capture temporal semantics in time series sensor data, indicating its great potential in modeling abstracted sensor data. An actual implementation is evaluated on an embedded platform.

关键词： convolutional autoencoder human activity recognition masked reconstruction self-supervised learning sensor

来源：评论

学校读者我要写书评

暂无评论

Indoor tracking trajectory data similarity analysis with a deep convolutional autoencoder

引用

SUSTAINABLE CITIES AND SOCIETY 2019年 45卷 588-595页

作者： Li, Li Li, Xin Yang, Yuan Dong, Jia Southeast Univ Sch Architecture Inst Architecture Algorithm & Applicat Nanjing Jiangsu Peoples R China Wuhan Univ Sch Urban Design Wuhan Hubei Peoples R China Southeast Univ Sch Instrument Sci & Engn Nanjing Jiangsu Peoples R China Southeast Univ Sch Architecture Nanjing Jiangsu Peoples R China

Building energy consumption is influenced not merely by the energy-saving performance of hardware but also by the occupants' indoor behaviours. Advances in indoor positioning technologies can generate large volumes of spatial trajectory data on the occupants, which can reveal the distribution of the occupants or be interpreted to reflect the occupants' behaviours. This calls for systematic research on new computing technologies to identify information from trajectory data rather than from visualizations or statistics. Due to the imperfections and complexities of trajectory data, few robust techniques are available for similarity comparisons, which are critical for further clustering and pattern mining. In this work, we propose a novel means of evaluating similarities in occupant trajectory data based on the use of a convolutional autoencoder (CAE). Trajectory data can be compared and their feature vectors extracted with the CAE in an unsupervised manner. We applied this approach to high-precision tracking data collected from an ultra-wide band (UWB) indoor positioning system (IPS) installed in an exhibition hall. The calculated results show that our approach offers great advantages in terms of its application, robustness, and flexibility.

关键词： Occupant trajectory convolutional autoencoder Indoor positioning system

来源：评论

学校读者我要写书评

暂无评论

Enhancing learning classifier systems through convolutional autoencoder to classify underwater images

引用

SOFT COMPUTING 2021年第15期25卷 10423-10440页

作者： Irfan, Muhammad Jiangbin, Zheng Iqbal, Muhammad Arif, Muhammad Hassan Northwestern Polytech Univ Sch Software Xian Peoples R China Higher Coll Technol Fac Comp & Informat Sci Fujairah U Arab Emirates CESAT Islamabad Pakistan

Underwater image classification is a challenging task because of challenging underwater environment and lighting conditions. We propose a novel learning classifier system (LCS), which can classify large-size underwater images with promising accuracy, and acquire knowledge in interpretable format, by using a novel classification convolution autoencoder (CCAE). In proposed system, CCAE is designed as a hybrid network, which combines benefits of classification and autoencoder, to extract compressed non-trivial features. It is also used to decompress LCS generated rules to original input space. In order to evaluate effectiveness of proposed solution, experiments are conducted on selected underwater synsets of benchmark ImageNet dataset. Results are compared with famous CNN methods based on parameters such as accuracy, precision, recall and F-measure. Experiments show that proposed system can accurately classify large-size underwater images with promising accuracy and outperforms well-known deep CNN methods. It has also been observed that LCS generated rules are well generalized, accurate and interpretable.

关键词： Learning classifier systems Knowledge discovery Underwater images convolutional autoencoder

来源：评论

学校读者我要写书评

暂无评论

Detection and localization of myocardial infarction based on a convolutional autoencoder

引用

KNOWLEDGE-BASED SYSTEMS 2019年第0期178卷 123-131页

作者： Sugimoto, Kaiji Kon, Yudai Lee, Saerom Okada, Yoshifumi Muroran Inst Technol Div Informat & Elect Engn 27-1 Mizumoto Cho Muroran Hokkaido 0508585 Japan Muroran Inst Technol Dept Informat & Elect Engn 27-1 Mizumoto Cho Muroran Hokkaido 0508585 Japan Muroran Inst Technol Coll Informat & Syst 27-1 Mizumoto Cho Muroran Hokkaido 0508585 Japan

Twelve-lead electrocardiograms (ECG) are widely used for the diagnosis of myocardial infarction (MI). For MI detection and localization, 12 ECG signals should be comprehensively checked through visual observation. This process is time-consuming, requires significant effort, and is prone to inducing errors. Hence, computer-aided automatic detection technology is required. Many existing methods perform MI detection and localization using features extracted from normal and abnormal ECG data. However, abnormal ECG signals show various waveforms for the same heart disease;therefore, it is difficult to extract the waveform features common to all the waveforms. In addition, ECG data is extremely imbalanced, and the minority class, including abnormal ECG data, may not be adequately learned. Because of the difficulty of feature extraction in the imbalanced data, in this study, we propose a new method for MI detection and localization that learns only normal ECG data in the public ECG database. This method is based on a convolutional autoencoder (CAE) model for normal ECG waveforms. The CAE model is constructed for each lead and outputs reconstructed input ECG data if normal ECG data is inputted. Otherwise, the waveform is distorted and outputted. MI detection and localization is performed by a k-nearest neighbor (k-NN) classifier using an error vector whose dimension corresponds to each lead and whose element is a degree of deviation between the normal ECG data and the output waveform. In the experiments, the classification performance of the proposed method was evaluated using 353640 beats obtained from the ECG data of MI patients (10 class infarct sites) and healthy subjects. Consequently, the proposed scheme demonstrated a classification performance higher than or comparable to that of existing methods, and the false positive and false negative rates could be reduced compared to existing methods. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Electrocardiogram Myocardial infarction convolutional autoencoder k-nearest neighbor

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：