检索结果-内蒙古大学图书馆

16th European Dependable Computing Conference (EDCC)

作者： Niebling, Julia Baasch, Benjamin Kruspe, Anna Deutsch Zentrum Luft & Raumfahrt Inst Data Sci Malzerstr 3 D-07745 Jena Germany Deutsch Zentrum Luft & Raumfahrt Inst Transportat Syst Rutherfordstr 2 D-12489 Berlin Germany

ISBN: (纸本)9783030584610;9783030584627

Modern maintenance strategies for railway tracks rely more and more on data acquired with low-cost sensors installed on in-service trains. This quasi-continuous condition monitoring produces huge amounts of data, which require appropriate processing strategies. Deep learning has become a promising tool in analyzing large volumes of sensory data. In this work, we demonstrate the potential of artificial intelligence to analyze railway track defects. We combine traditional signal processing methods with deep convolutional autoencoders and clustering algorithms to find anomalies and their patterns. The methods are applied to real world data gathered with a multi-sensor prototype measurement system on a shunter locomotive operating on the industrial railway network of the inland harbor of Braunschweig (Germany). This work shows that deep learning methods can be applied to find patterns in railway track irregularities and opens a wide area of further improvements and developments.

关键词： Defect detection Deep learning convolutional autoencoder Clustering

来源：评论

学校读者我要写书评

暂无评论

Learnable Image Transformations for Privacy Enhanced Deep Neural Networks 5

Learnable Image Transformations for Privacy Enhanced Deep Ne...

引用

5th IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)

作者： Rodriguez, David Krishnan, Ram Univ Texas San Antonio Dept Elect & Comp Engn San Antonio TX 78249 USA

ISBN: (纸本)9798350323856

A large number of data are uploaded to cloud-based machine learning service providers. A major concern is that such data often contain a lot more sensitive information than the intended purpose for which a model is trained for. To address this problem, we investigate two image transformation schemes using convolutional autoencoder (CAE) latent representation and vision transformer (ViT) embeddings for privacy enhanced image classification. The CAE and ViT image transformation schemes enable us to build deep learning classification models using obfuscated image data while enhancing robustness against reconstruction attacks. In this paper, we demonstrate that CAE and ViT image transformation schemes protect visual feature information of sensitive image data. We evaluate the effectiveness of the image transformation schemes to preserve model utility using classification accuracy and robustness against reconstruction attacks using structural similarity index measure (SSIM). The CAE latent representation classification accuracy for Fashion Mnist, Cifar-10 and Chest X-ray datasets are 91.43%, 89.94% and 92.67%, respectively. The ViT embedding classification accuracy for Fashion Mnist, Cifar-10 and Chest X-ray datasets are 87.32%, 86.01% and 91.98%, respectively. Our SSIM results demonstrate that the CAE and ViT encoding schemes are robust to particular reconstruction attacks while effectively enhance privacy and preserving model utility.

关键词： convolutional autoencoder latent representation vision transformer embeddings robust privacy model utility

来源：评论

学校读者我要写书评

暂无评论

Cluster activation mapping with application to computed tomography scans of the lung

引用

JOURNAL OF MEDICAL IMAGING 2022年第2期9卷 026001页

作者： Ryan, Sarah M. Carlson, Nichole E. Butler, Harris Fingerlin, Tasha E. Maier, Lisa A. Xing, Fuyong Univ Colorado Denver Dept Biostat & Informat Anschutz Med Campus Aurora CO 80204 USA Natl Jewish Hlth Dept Biomed Res Denver CO USA Univ Colorado Denver Dept Epidemiol Anschutz Med Campus Aurora CO USA Natl Jewish Hlth Dept Med Denver CO USA Univ Colorado Denver Dept Med Anschutz Med Campus Aurora CO USA Univ Colorado Denver Dept Environm & Occupat Hlth Anschutz Med Campus Aurora CO USA

Purpose: An open question in deep clustering is how to explain what in the image is driving the cluster assignments. This is especially important for applications in medical imaging when the derived cluster assignments may inform decision-making or create new disease subtypes. We develop cluster activation mapping (CLAM), which is methodology to create localization maps highlighting the image regions important for cluster assignment. Approach: Our approach uses a linear combination of the activation channels from the last layer of the encoder within a pretrained autoencoder. The activation channels are weighted by a channelwise confidence measure, which is a modification of score-CAM. Results: Our approach performs well under medical imaging-based simulation experiments, when the image clusters differ based on size, location, and intensity of abnormalities. Under simulation, the cluster assignments were predicted with 100% accuracy when the number of clusters was set at the true value. In addition, applied to computed tomography scans from a sarcoidosis population, CLAM identified two subtypes of sarcoidosis based purely on CT scan presentation, which were significantly associated with pulmonary function tests and visual assessment scores, such as ground-glass, fibrosis, and honeycombing. Conclusions: CLAM is a transparent methodology for identifying explainable groupings of medical imaging data. As deep learning networks are often criticized and not trusted due to their lack of interpretability, our contribution of CLAM to deep clustering architectures is critical to our understanding of cluster assignments, which can ultimately lead to new subtypes of diseases. (C) 2022 Society of Photo Optical Instrumentation Engineers (SPIE)

关键词： deep clustering explainable machine learning convolutional autoencoder medical imaging sarcoidoisis

来源：评论

学校读者我要写书评

暂无评论

Patch-based Sparse and convolutional autoencoders for Anomaly Detection in Hyperspectral Images 28

Patch-based Sparse and Convolutional Autoencoders for Anomal...

引用

28th Iranian Conference on Electrical Engineering (ICEE)

作者： Rezvanian, Amir Reza Imani, Maryam Ghassemian, Hassan Tarbiat Modares Univ Fac Elect & Comp Engn Image Proc & Informat Anal Lab Tehran Iran

ISBN: (数字)9781728172965

ISBN: (纸本)9781728172965

Anomaly target detection is one of the major aims of Hyperspectral Image (HSI) processing. Since anomalous pixels Compose a small fraction of the hyperspectral data cube, the use of supervised neural networks presents many complications. The reason is that supervised networks need a large training set to fine-tune the model. In this paper we propose two semi-supervised autoencoder based anomaly detection methods using the reconstruction error of each pixel. The reconstruction error is the mean absolute error between each pixel and its reconstruction by the proposed autoencoder networks. The proposed networks are deep fully-connected sparse autoencoders (SAE) and deep one-dimensional convolutional autoencoders (CAE). In addition, a patch-based anomaly detection method is proposed which takes spatial correlation between neighbouring pixels into account. We use the San Diego airport hyperspectral data to carry out the experiments. The results are compared with some state-of-the-art HSI anomaly detection methods. Quantitative results employing ROC and AUC metrics demonstrate the superior performance of the proposed method compared to several anomaly detectors.

关键词： anomaly detection convolutional autoencoder hyperspectral images sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMING SEISMOCARDIOGRAMS INTO ELECTROCARDIOGRAMS BY APPLYING convolutional autoencoderS

TRANSFORMING SEISMOCARDIOGRAMS INTO ELECTROCARDIOGRAMS BY AP...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haescher, Marian Hoepfner, Florian Chodan, Wencke Kraft, Dimitri Aehnelt, Mario Urban, Bodo Univ Rostock Rostock Germany Fraunhofer IGD Rostock Germany

ISBN: (纸本)9781509066315

Electrocardiograms constitute the key diagnostic tool for cardiologists. While their diagnostic value is yet unparalleled, electrode placement is prone to errors, and sticky electrodes pose a risk for skin irritations and may detach in long-term measurements. *** presents a fundamentally new approach, transforming motion-based seismocardiograms into electrocardiograms interpretable by cardiologists. Measurements are conducted simply by placing a sensor on the user's chest. To generate the transformation model, we trained a convolutional autoencoder with the publicly available CEBS dataset. The transformed ECG strongly correlates with the ground truth (r=.94, p<.01), and important features (number of R-peaks, QRS-complex durations) are modeled realistically (Bland-Altman analyses, p>0.12). On a 5-point Likert scale, 15 cardiologists rated the morphological and rhythmological validity as high (4.63/5 and 4.8/5, respectively). Our electrodeless approach solves crucial problems of ECG measurements while being scalable, accessible and inexpensive. It contributes to telemedicine, especially in low-income and rural regions worldwide.

关键词： Electrocardiography cardiology seismocardiography convolutional autoencoder neural networks

来源：评论

学校读者我要写书评

暂无评论

A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 163卷 113788-113788页

作者： Shoeibi, Afshin Ghassemi, Navid Alizadehsani, Roohallah Rouhani, Modjtaba Hosseini-Nejad, Hossein Khosravi, Abbas Panahiazar, Maryam Nahavandi, Saeid KN Toosi Univ Technol Fac Elect & Comp Engn Tehran Iran Ferdowsi Univ Mashhad Comp Engn Dept Mashhad Razavi Khorasan Iran Deakin Univ Inst Intelligent Syst Res & Innovat IISRI Geelong Vic 3217 Australia Univ Calif San Francisco San Francisco CA 94143 USA

Epilepsy, a brain disease generally associated with seizures, has tremendous effects on people's quality of life. Diagnosis of epileptic seizures is commonly performed on electroencephalography (EEG) signals, and by using computer-aided diagnosis systems (CADS), neurologists can diagnose epileptic seizure stages more accurately. In these systems, a mandatory stage is feature extraction, performed by handcrafting features or learning them, ordinarily by a deep neural net. While researches in this field commonly show the value of a group of limited features, yet an accurate comparison between different suggested features is essential. In this article, first, a comparison between the importance of 50 different handcrafted features for seizure detection is presented. Additionally, the computational complexity of features is investigated as well. Then the best features based on Fisher scores are picked to classify signals on a benchmark dataset for evaluation. Additionally, a convolutional autoencoder with five layers is applied to learn features in order to have a complete comparison among feature extraction approaches. Finally, a hybrid method is employed, which combines handcrafted features and encoding of autoencoder to reach high performance in seizure detection in EEG signals.

关键词： Epileptic seizures Electroencephalography (EEG) convolutional autoencoder Feature extraction Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Application of light-weighted CNN for diagnosis of internal concrete defects using hammering sound

引用

NONDESTRUCTIVE TESTING AND EVALUATION 2024年第8期39卷 2426-2449页

作者： Lu, Chi Sonoda, Yoshimi Kyushu Univ Dept Civil Engn Fukuoka Japan

In the past, diagnoses of the internal defects of ageing concrete members by sound tests have relied on the ability and experience of the inspector. However, with the development of deep neural networks, building diagnosis tools without the subjective judgements of humans is feasible. In this study, sound samples are collected from a tapping sound test on concrete slab specimens with internally embedded artificial defects. Spectrograms are generated from the sound samples and used to train a light-weighted convolutional neural network (CNN). Thereafter, the performance of the proposed CNN models at diagnosing the defects of the concrete slabs are examined and compared with convolutional autoencoder (CAE) and support vector regression (SVR). All the models performed well at distinguishing between healthy and defective concrete. Whereas noise can impair the performance of CAE and SVR, CNN is less affected, particularly when classifying sound samples with distinctive features. CNN also has other advantages: the physical area of the artificial defect can be output directly from CNN, and CNN performance is also less affected by the depth of the artificial defect and the rebar embedded in the concrete. At increased depths, the CNN is still able to identify the defect area.

关键词： Hammering sound test concrete flaking anomaly detection convolutional autoencoder convolutional neural network time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Study on classification of attention deficit hyperactivity disorder based on dual-channel autoencoder

引用

JOURNAL OF ELECTRONIC IMAGING 2024年第2期33卷 023032-023032页

作者： Zhu, Saisai Sun, Daoqing Liu, Zifan Zhao, Shanhui Yang, Yang Chen, Fulong Anhui Normal Univ Sch Comp & Informat Wuhu Peoples R China Anhui Engn Res Ctr Med Big Data Intelligent Syst Wuhu Peoples R China

Magnetic resonance imaging (MRI) is extensively utilized in psychiatric disorder diagnosis. However, the high-dimensional nature of the data poses challenges in network training. We propose a classification approach leveraging autoencoder and multilayer perceptron techniques. Initially, a convolutional autoencoder is designed to reduce the dimensionality and extract features from the input feature map using its encoder component. Subsequently, the extracted features are fed into the designed multilayer perceptron for training and testing, enabling joint classification based on dual features. Finally, we apply this method to classify attention deficit hyperactivity disorder (ADHD), and the experimental results demonstrate the effectiveness of our approach in significantly enhancing the accuracy of ADHD classification. (c) 2024 SPIE and IS&T

关键词： magnetic resonance imaging dimensionality reduction convolutional autoencoder multilayer perceptron attention deficit hyperactivity disorder

来源：评论

学校读者我要写书评

暂无评论

Quality inspection of translucent and micro-structured functional surfaces 3

Quality inspection of translucent and micro-structured funct...

引用

Conference on AI and Optical Data Sciences III

作者： Brosch, Nicole Ginner, Laurin Schneider, Sarah Antensteiner, Doris Traxler, Lukas AIT Austrian Inst Technol Giefinggasse 4 A-1210 Vienna Austria Tufts Univ Human Robot Interact Lab Boston Ave 200 Medford MA 02155 USA

ISBN: (数字)9781510649101

ISBN: (纸本)9781510649101;9781510649095

Micro-structured films with surface riblets are used to reduce aerodynamic drag. This is especially relevant on fast and large objects such as on aircraft wings, where they are installed to increase efficiency (e.g., reduce fuel consumption). Their fuel reduction efficiency depends directly on the structural integrity of the films. Therefore, we propose a photometric inspection tool, a hardware setup and tailored analysis algorithms, which detect typical defects of riblet micro-structures occurring during their operational lifetime. We propose two inspection approaches to analyze the micro-structures, (i) a statistical data processing method and (ii) a machine learning algorithm based on convolutional autoencoders. We tested both inspection approaches on rendered and real-world data of riblet films on airplane elements, carbon-fiber parts of race cars, and wind turbine blades.

关键词： Photometric stereo machine learning convolutional autoencoder quality inspection riblets

来源：评论

学校读者我要写书评

暂无评论

Towards an Efficient Facial Image Compression with Neural Networks 21st

Towards an Efficient Facial Image Compression with Neural Ne...

引用

21st International Conference on Image Analysis and Processing (ICIAP)

作者： Spatafora, Maria Ausilia Napoli Ortis, Alessandro Battiato, Sebastiano Univ Catania Dept Math & Comp Sci Catania Italy

ISBN: (纸本)9783031064272;9783031064265

Digital images are more and more part of everyday life. Efficient compression methods are needed to reduce the disk-space usage for their storage and the bandwidth for their transmission while keeping the resolution and the visual quality of the reconstructed images as close to the original images as possible. Not all images have the same importance. The facial images are being extensively used in many applications (e.g., law enforcement, social networks) and require high efficient facial image compression schemes in order to not compromise face recognition and identification (e.g., for surveillance and security scenarios). For this reason, we propose a promising approach that consists of a custom loss that combines the two tasks of image compression and face recognition. The results show that our method compresses efficiently face images guaranteeing high perceptive quality and face verification accuracy.

关键词： convolutional autoencoder Face images compression Custom loss function

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：