检索结果-内蒙古大学图书馆

A DNA Based Colour Image Encryption Scheme Using A Convolutional autoencoder

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2023年第3期19卷 128-128页

作者： Ahmed, Fawad Rehman, Muneeb Ur Ahmad, Jawad Khan, Muhammad Shahbaz Boulila, Wadii Srivastava, Gautam Lin, Jerry Chun-Wei Buchanan, William J. NUST Pakistan Navy Engn Coll Dept Cyber Secur HABIB IR Rd Karachi 75350 Sindh Pakistan HITEC Univ Dept Elect Engn Museum Rd Taxila 47080 Punjab Pakistan Edinburgh Napier Univ Sch Comp Merchiston Campus10 Colinton Rd Edinburgh EH10 5DT Scotland Prince Sultan Univ Robot & Internet of Things Lab Rafha St Riyadh 11586 Saudi Arabia Univ Manouba Natl Sch Comp Sci RIADI Lab Manouba Campus Manouba 2010 Tunisia Brandon Univ Dept Math & Comp Sci 270 18th St Brandon MB R7A 6A9 Canada China Med Univ Res Ctr Interneural Comp 91 Xueshi Rd Taichung 40402 Taiwan Lebanese Amer Univ Dept Comp Sci & Math POB 13-5053 Chouran Beirut 11022 Lebanon Western Norway Univ Appl Sci Dept Comp Sci Elect Engn & Math Sci Inndalsveien 28 N-5063 Bergen Norway

With the advancement in technology, digital images can easily be transmitted and stored over the Internet. Encryption is used to avoid illegal interception of digital images. Encrypting large-sized colour images in their original dimension generally results in low encryption/decryption speed along with exerting a burden on the limited bandwidth of the transmission channel. To address the aforementioned issues, a new encryption scheme for colour images employing convolutional autoencoder, DNA and chaos is presented in this paper. The proposed scheme has two main modules, the dimensionality conversion module using the proposed convolutional autoencoder, and the encryption/decryption module using DNA and chaos. The dimension of the input colour image is first reduced from NxMx3 to PxQ gray-scale image using the encoder. Encryption and decryption are then performed in the reduced dimension space. The decrypted gray-scale image is upsampled to obtain the original colour image having dimension N xM x 3. The training and validation accuracy of the proposed autoencoder is 97% and 95%, respectively. Once the autoencoder is trained, it can be used to reduce and subsequently increase the dimension of any arbitrary input colour image. The efficacy of the designed autoencoder has been demonstrated by the successful reconstruction of the compressed image into the original colour image with negligible perceptual distortion. The second major contribution presented in this paper is an image encryption scheme using DNA along with multiple chaotic sequences and substitution boxes. The security of the proposed image encryption algorithm has been gauged using several evaluation parameters, such as histogram of the cipher image, entropy, NPCR, UACI, key sensitivity, contrast, and so on. The experimental results of the proposed scheme demonstrate its effectiveness to perform colour image encryption.

关键词： autoencoder chaos DNA coding deep learning colour image encryption dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

autoencoder-guided GAN for minority-class cloth-changing gait data generation

引用

DIGITAL SIGNAL PROCESSING 2022年第0期128卷

作者： Xu, Jian Li, Hai Hou, Shujuan Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China

In the gait recognition task, cloth-changing data (e.g., CL-class data in the CASIA-B dataset) account for a very low proportion of the gait dataset, which brings serious recognition accuracy degradation to gait recognition algorithm in clothes changing scenarios. One way to solve this problem is to use data generation algorithms to expand the cloth-changing data. When facing the generation of minority-class data, the existing GAN-based image data expansion algorithms require a large amount of data to ensure the convergence, while mode collapse can occur due to the conflict between the true-false discriminant loss and the classification loss. In order to solve the above problems, we propose an autoencoder-guided GAN for cloth-changing gait data generation, which uses the autoencoder with embedding layer to extract the data features of the entire data set, rather than only extracting the features of the required CL data. Then the labeled latent vector (representing the extracted data features) in the autoencoder is taken as the input of the GAN, solving the problem that GAN convergence requires a lot of training data. The GAN has the same topology as the autoencoder and uses the parameter matrix of the autoencoder as the initial weights. Secondly, the true classification in GAN is canceled, and only the false classification is retained, which solves the problem of the collision of the loss function between the true-false discrimination and the classification discrimination. In the cloth-changing data generation experiments, compared with other GAN data expansion algorithms, our method generates clothes changing data with high quality, and ensures the diversity of the generated data. When using the CASIA-B dataset expanded by our algorithm, several gait recognition algorithms all show significant improvement, especially in the clothes changing scenario.

关键词： Gait recognition Minority-class data generation autoencoder GAN

来源：评论

学校读者我要写书评

暂无评论

Simulating clinical features on chest radiographs for medical image exploration and CNN explainability using a style-based generative adversarial autoencoder

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-12页

作者： Hasenstab, Kyle A. Hahn, Lewis Chao, Nick Hsiao, Albert San Diego State Univ Dept Math & Stat 5500 Campanile Dr San Diego CA 92182 USA Univ Calif San Diego Dept Radiol 9500 Gilman Dr La Jolla CA 92093 USA

Explainability of convolutional neural networks (CNNs) is integral for their adoption into radiological practice. Commonly used attribution methods localize image areas important for CNN prediction but do not characterize relevant imaging features underlying these areas, acting as a barrier to the adoption of CNNs for clinical use. We therefore propose Semantic Exploration and Explainability using a Style-based Generative Adversarial autoencoder Network (SEE-GAAN), an explainability framework that uses latent space manipulation to generate a sequence of synthetic images that semantically visualizes how clinical and CNN features manifest within medical images. Visual analysis of changes in these sequences then facilitates the interpretation of features, thereby improving explainability. SEE-GAAN was first developed on a cohort of 26,664 chest radiographs across 15,409 patients from our institution. SEE-GAAN sequences were then generated across several clinical features and CNN predictions of NT-pro B-type natriuretic peptide (BNPP) as a proxy for acute heart failure. Radiological interpretations indicated SEE-GAAN sequences captured relevant changes in anatomical and pathological morphology associated with clinical and CNN predictions and clarified ambiguous areas highlighted by commonly used attribution methods. Our study demonstrates SEE-GAAN can facilitate our understanding of clinical features for imaging biomarker exploration and improve CNN transparency over commonly used explainability methods.

关键词： Convolutional neural network Generative adversarial network autoencoder Explainable artificial intelligence Chest radiographs

来源：评论

学校读者我要写书评

暂无评论

Model Order Reduction of Cardiac Monodomain Model using Deep autoencoder Based Neural Networks

引用

APPLIED COMPUTATIONAL ELECTROMAGNETICS SOCIETY JOURNAL 2021年第8期36卷 1120-1124页

作者： Khan, Riasat Ng, T. Kwong North South Univ Dept Elect & Comp Engn Dhaka Bangladesh New Mexico State Univ Dept Elect & Comp Engn Las Cruces NM 88003 USA

-The numerical study of electrocardiology involves prohibitive computational costs because of its complex and nonlinear dynamics. In this paper, a low -dimensional model of the cardiac monodomain formulation has been developed by using the deep learning method. The restricted Boltzmann machine and deep autoencoder machine learning techniques have been used to approximate the cardiac tissue's full order dynamics. The proposed reduced order modeling begins with the development of the low-dimensional representations of the original system by implementing the neural networks from the numerical simulations of the full order monodomain system. Consequently, the reduced order representations have been utilized to construct the lower-dimensional model, and finally, it has been reconstructed back to the original system. Numerical results show that, the proposed deep learning MOR framework gained computational efficiency by a factor of 85 with acceptable accuracy. This paper compares the accuracy of the deep learning based model order reduction method with the two different techniques of model reduction: proper orthogonal decomposition (POD) and dynamic mode decomposition (DMD). The model order reduction deploying the deep learning method outperforms the POD and DMD concerning the modeling accuracy.

关键词： autoencoder Cardiac monodomain model deep learning technique dynamic mode decomposition proper orthogonal decomposition reduced order modeling semi-implicit scheme

来源：评论

学校读者我要写书评

暂无评论

Data-driven bearing fault detection using hybrid autoencoder-LSTM deep learning approach

引用

INTERNATIONAL JOURNAL OF MODELLING IDENTIFICATION AND CONTROL 2021年第1期38卷 88-103页

作者： Kamat, Pooja Sugandhi, Rekha Kumar, Satish Symbiosis Int Deemed Univ Symbiosis Inst Technol Pune Maharashtra India MIT ADT Univ MIT Sch Engn Pune Maharashtra India

Artificial intelligence (AI) and its sub-domains of machine learning and deep learning have kindled the interests of both industry practitioners and academicians. Its contribution to the manufacturing industry in making intelligent predictions about a machinery's health and its working has seen a huge surge in the research carried in recent years. Nowadays, AI in manufacturing is popularly applied for the efficient fault detection of machinery using data analytics. Traditional fault predictive classification and further diagnosis have pitfalls such as low prediction accuracy, poor feature extraction and susceptibility to noise. To overcome these disadvantages, this paper proposes the deep-learning-based hybrid autoencoders (AE) - long-short-term memory (LSTM) framework for fault detection. The dimensionality reduction with automatic latent feature extraction by autoencoders and temporal feature consideration by LSTM help to achieve high fault diagnosis accuracy. The empirical results show that fault detection of roll bearings based on the proposed hybrid AE-LSTM deep learning technique achieved superior results in comparison to the traditional K-means clustering technique.

关键词： bearings fault detection deep learning autoencoder long-short-term memory LSTM K-means

来源：评论

学校读者我要写书评

暂无评论

A novel GPU based intrusion detection system using deep autoencoder with Fruitfly optimization

引用

SN APPLIED SCIENCES 2021年第6期3卷 1-16页

作者： Sekhar, R. Sasirekha, K. Raja, P. S. Thangavel, K. Minist Home Affairs Disaster Recovery Ctr Natl Intelligence Grid Bengaluru India Periyar Univ Dept Comp Sci Salem Tamil Nadu India

Intrusion Detection Systems (IDSs) have received more attention to safeguarding the vital information in a network system of an organization. Generally, the hackers are easily entering into a secured network through loopholes and smart attacks. In such situation, predicting attacks from normal packets is tedious, much challenging, time consuming and highly technical. As a result, different algorithms with varying learning and training capacity have been explored in the literature. However, the existing Intrusion Detection methods could not meet the desired performance requirements. Hence, this work proposes a new Intrusion Detection technique using Deep autoencoder with Fruitfly Optimization. Initially, missing values in the dataset have been imputed with the Fuzzy C-Means Rough Parameter (FCMRP) algorithm which handles the imprecision in datasets with the exploit of fuzzy and rough sets while preserving crucial information. Then, robust features are extracted from autoencoder with multiple hidden layers. Finally, the obtained features are fed to Back Propagation Neural Network (BPN) to classify the attacks. Furthermore, the neurons in the hidden layers of Deep autoencoder are optimized with population based Fruitfly Optimization algorithm. Experiments have been conducted on NSL_KDD and UNSW-NB15 dataset. The computational results of the proposed intrusion detection system using deep autoencoder with BPN are compared with Naive Bayes, Support Vector Machine (SVM), Radial Basis Function Network (RBFN), BPN, and autoencoder with *** HighlightsA hybridized model using Deep autoencoder with Fruitfly Optimization is introduced to classify the *** values have been imputed with the Fuzzy C-Means Rough Parameter *** discriminate features are extracted using Deep autoencoder with more hidden layers.

关键词： autoencoder Deep learning Intrusion detection Fruitfly Back propagation neural network

来源：评论

学校读者我要写书评

暂无评论

Data-driven fault detection for chemical processes using autoencoder with data augmentation

引用

KOREAN JOURNAL OF CHEMICAL ENGINEERING 2021年第12期38卷 2406-2422页

作者： Lee, Hodong Kim, Changsoo Jeong, Dong Hwi Lee, Jong Min Seoul Natl Univ Sch Chem & Biol Engn Inst Chem Proc 1 Gwanak Ro Seoul 08826 South Korea Korea Inst Sci & Technol Clean Energy Res Ctr Seoul 02792 South Korea Univ Ulsan Sch Chem Engn 93 Daehak Ro Ulsan 44610 South Korea

Process monitoring plays an essential role in safe and profitable operations. Various data-driven fault detection models have been suggested, but they cannot perform properly when the training data are insufficient or the information to construct the manifold is confined to a specific region. In this study, a process monitoring framework integrated with data augmentation is proposed to supplement rare but informative samples for the boundary regions of the normal state. To generate data for augmentation, a variational autoencoder was employed to exploit its advantage of stable convergence. For the construction of the process monitoring system, an autoencoder that can extract useful features in an unsupervised manner was used. To illustrate the efficacy of the proposed method, a case study for the Tennessee Eastman process was applied. The results show that the proposed method can improve the monitoring performance compared to the autoencoder without data augmentation in terms of fault detection accuracy and delay, particularly within the feature space.

关键词： Process Monitoring Fault Detection and Isolation (FDI) autoencoder Variational autoencoder Data Augmentation

来源：评论

学校读者我要写书评

暂无评论

Calibration method for sensor drifting bias in data center cooling system using Bayesian Inference coupling with autoencoder

引用

JOURNAL OF BUILDING ENGINEERING 2023年 67卷

作者： Tian, Yaoyue Wang, Jiaqiang Qi, Zhaohui Yue, Chang Wang, Peng Yoon, Sungmin Cent South Univ Sch Energy Sci & Engn Changsha 410083 Hunan Peoples R China Xian Univ Architecture & Technol State Key Lab Green Bldg Western China Xian 710055 Shanxi Peoples R China Dalian Univ Technol Sch Civil Engn Dalian 116024 Liaoning Peoples R China Sungkyunkwan Univ Sch Civil Architectural Eng & Landscape Architectu Suwon 16419 South Korea

The optimal control strategy is considered a promising solution to reduce the energy consumption of cooling supply systems in data centers. The strategy is mainly based on sensor measurement data to adjust and control, thereby achieving energy-saving effects. However, the high thermal density characteristics of data centers can cause drifting bias of the sensor, resulting in failure to achieve the desired optimal control strategy. This study proposed a novel method based on Bayesian inference (BI) coupled with autoencoder to model the drifting bias correlation functions and calibrate the sensor drifting bias. Therein, Markov Chain Monte Carlo (MCMC) algorithm was used to generate the equivalent samples without complex integral solution process. Case studies of eight individual/multiple sensors drifting bias scenarios in the computer room air handler (CRAH), were conducted to comprehensively evaluate the calibration performance of the pro-posed method. Moreover, the effect of prior distribution parameters setting on the calibration performance was also discussed. The simulation results show that the proposed method performs well in terms of correction accuracy exceeding 92.60% and 96.34% for individual sensor and multiple sensors drifting bias scenarios, respectively. In addition, the updated strategy of the prior distribution parameter settings plays a crucial role in improving the correction accuracy, espe-cially for multiple sensors drifting bias scenarios. This study filled the knowledge gap of sensor drifting bias correction for data center cooling supply systems and facilitates the application of advanced technologies in data centers.

关键词： Data center Computer room air handler Drifting bias correction Bayesian Inference autoencoder

来源：评论

学校读者我要写书评

暂无评论

Transformer-based autoencoder with ID constraint for unsupervised anomalous sound detection

引用

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2023年第1期2023卷 42页

作者： Guan, Jian Liu, Youde Kong, Qiuqiang Xiao, Feiyang Zhu, Qiaoxi Tian, Jiantong Wang, Wenwu Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Heilongjiang Peoples R China ByteDance Shanghai Peoples R China Univ Technol Sydney Ctr Audio Acoust & Vibrat Ultimo NSW 2007 Australia Univ Surrey Ctr Vis Speech Signal Proc Guildford GU2 7XH England

Unsupervised anomalous sound detection (ASD) aims to detect unknown anomalous sounds of devices when only normal sound data is available. The autoencoder (AE) and self-supervised learning based methods are two mainstream methods. However, the AE-based methods could be limited as the feature learned from normal sounds can also fit with anomalous sounds, reducing the ability of the model in detecting anomalies from sound. The self-supervised methods are not always stable and perform differently, even for machines of the same type. In addition, the anomalous sound may be short-lived, making it even harder to distinguish from normal sound. This paper proposes an ID-constrained Transformer-based autoencoder (IDC-TransAE) architecture with weighted anomaly score computation for unsupervised ASD. Machine ID is employed to constrain the latent space of the Transformer-based autoencoder (TransAE) by introducing a simple ID classifier to learn the difference in the distribution for the same machine type and enhance the ability of the model in distinguishing anomalous sound. Moreover, weighted anomaly score computation is introduced to highlight the anomaly scores of anomalous events that only appear for a short time. Experiments performed on DCASE 2020 Challenge Task2 development dataset demonstrate the effectiveness and superiority of our proposed method.

关键词： Anomalous sound detection autoencoder ID classifier Weighted anomaly score computation

来源：评论

学校读者我要写书评

暂无评论

autoencoder-Based Characterisation of Passive IEEE 802.11 Link Level Measurements 30

Autoencoder-Based Characterisation of Passive IEEE 802.11 Li...

引用

Joint 30th European Conference on Networks and Communications / 3rd 6G Summit (EuCNC/6G Summit)

作者： Neuhau, Priyanka Henninger, Marcus Frotzscher, Andreas Wetzker, Ulf Fraunhofer Inst Integrated Circuits Div EAS D-01069 Dresden Germany Nokia Bell Labs D-70435 Stuttgart Germany

ISBN: (纸本)9781665415262

Wireless networks are indispensable in today's industrial manufacturing and automation. Due to harsh signal propagation conditions as well as co-existing wireless networks, transmission failures resulting in severe application malfunctions are often difficult to diagnose. Remote wireless monitoring systems are extremely useful tools for troubleshooting such failures. However, the completeness of data captured by a remote wireless monitor is highly dependent on the temporal, e.g., short-term interference, and spatial characteristics of its environment. It is necessary to first ensure that the data was completely captured at the remote monitor in order to maintain the integrity of the failure analysis, i.e., to avoid false positives. In this paper, we propose an autoencoder-based framework to evaluate the quality of wireless data captured at a remote wireless monitor. The algorithm is trained using data generated under controlled laboratory conditions and validated on testbed as well as real-world measurement data.

关键词： Wireless Network Analysis Industrial Wireless Communications Passive Monitoring Anomaly Detection Machine Learning autoencoder

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：