检索结果-内蒙古大学图书馆

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Wang, Qinghao Yang, Geying Wang, Lina Fu, Jie Liu, Xiaowen Wuhan Univ Sch Cyber Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9783031442124;9783031442131

As a proactive network security protection scheme, network intrusion detection system (NIDS) has become a powerful tool for early warning of computer and communication systems attacks. However, traditional machine learning methods struggle to pay attention to both spatial and temporal features of network traffic simultaneously, resulting in poor detection performance. In this paper, we propose SR-IDS, an Intrusion Detection System based on Self-taught learning and Representation learning, which consists of one-dimensional stacked convolutional autoencoders (1D-SCAE) and bidirectional gated recurrent units (BiGRU). SR-IDS can extract spatial features through 1D-SCAE and abstract temporal features via BiGRU. It uses self-taught learning and representation learning to simultaneously focus on the spatial and temporal characteristics of network traffic, overcoming the challenges of traditional methods in feature extraction. Experiments show that our SR-IDS model can distinguish the network traffic with 98.90% accuracy on the UNSW-NB15 dataset.

关键词： convolutional autoencoders Feature extraction Recurrent neural networks Traffic intrusion detection

来源：评论

学校读者我要写书评

暂无评论

CHISEL: Compression-Aware High-Accuracy Embedded Indoor Localization With Deep Learning

引用

IEEE EMBEDDED SYSTEMS LETTERS 2022年第1期14卷 23-26页

作者： Wang, Liping Tiku, Saideep Pasricha, Sudeep Colorado State Univ Dept Elect & Comp Engn Ft Collins CO 80523 USA

GPS technology has revolutionized the way we localize and navigate outdoors. However, the poor reception of GPS signals in buildings makes it unsuitable for indoor localization. WiFi fingerprinting-based indoor localization is one of the most promising ways to meet this demand. Unfortunately, most work in the domain fails to resolve challenges associated with deployability on resource-limited embedded devices. In this work, we propose a compression-aware and high-accuracy deep learning framework called CHISEL that outperforms the best-known works in the area while maintaining localization robustness on embedded devices.

关键词： Location awareness Fingerprint recognition Buildings Deep learning Floors Quantization (signal) Computational modeling convolutional autoencoders deep learning indoor localization model compression WiFi fingerprinting

来源：评论

学校读者我要写书评

暂无评论

Cannula Localization Using Separate Plane Wave Ultrasound Measurements and a Deep Neural Network

Cannula Localization Using Separate Plane Wave Ultrasound Me...

引用

IEEE International Ultrasonics Symposium (IUS)

作者： Fouad, Mariam Dencks, Stefanie Schmitz, Georg Ruhr Univ Bochum Chair Med Engn Bochum Germany

ISBN: (数字)9781665466578

ISBN: (纸本)9781665466578

Sonography is commonly used to monitor the insertion of a cannula into human tissue. However, good visibility in B-mode images is rarely guaranteed, especially with deep punctures and steep insertion angles. In previous work, we showed that resonance effects in the cannula can be observed in the received signals [1] . However, these nonlinear effects are not exploited in conventional ultrasound imaging. We hypothesize that the utilization of deep neural networks is particularly suitable to process this nonlinear cannula-related information. Moreover, we presume that the exploitation of different information found in different plane waves could enhance the localization of the cannula compared to the direct utilization of compounded B-mode images. Therefore, a deep learning-based framework capable of extracting the information provided by the separate plane waves is employed to enhance the localization of the shaft and tip of the cannula. The implemented architecture is based on a modified U-Net architecture. It predicts the position of the cannula from three different input scenarios: compounded B-mode images, separate plane wave B-mode images (3 angles), and separate plane wave B-mode images combined with their difference images. The model was first trained on data acquired in a water bath and then fine-tuned on a porcine dataset. This way, even with a comparatively small dataset, it was possible to achieve faster convergence and better localization results. Using separate plane wave B-mode images and their difference images substantially improved the visualization of the cannula by achieving 4.5-times lower tip localization error (measured by calculating the mean absolute difference between the true and the predicted tip location) and improving the estimation of the puncture angle by 30.6% (measured by calculating the mean absolute difference between the true and the predicted puncture angles) compared to the direct utilization of compounded B-mode images.

关键词： cannula visibility cannula visibility convolutional autoencoders DNN localization monitoring nonlinear resonance effects punctures separate plane waves

来源：评论

学校读者我要写书评

暂无评论

Deep learning pipeline for quality filtering of MRSI spectra

引用

NMR IN BIOMEDICINE 2024年第7期37卷 e5012-e5012页

作者： Rakic, Mladen Turco, Federico Weng, Guodong Maes, Frederik Sima, Diana M. Slotboom, Johannes Icometrix Res & Dev Leuven Belgium Katholieke Univ Leuven Proc Speech & Images PSI & Med Imaging Res Ctr Dept Elect Engn ESAT Leuven Belgium Univ Bern Inst Diagnost & Intervent Radiol Support Ctr Adv Neuroimaging SCAN Bern Switzerland Icometrix Kolonel Begaultlaan 1b-12 B-3012 Leuven Belgium

With the rise of novel 3D magnetic resonance spectroscopy imaging (MRSI) acquisition protocols in clinical practice, which are capable of capturing a large number of spectra from a subject's brain, there is a need for an automated preprocessing pipeline that filters out bad-quality spectra and identifies contaminated but salvageable spectra prior to the metabolite quantification step. This work introduces such a pipeline based on an ensemble of deep-learning classifiers. The dataset consists of 36,338 spectra from one healthy subject and five brain tumor patients, acquired with an EPSI variant, which implemented a novel type of spectral editing named SLOtboom-Weng (SLOW) editing on a 7T MR scanner. The spectra were labeled manually by an expert into four classes of spectral quality as follows: (i) noise, (ii) spectra greatly influenced by lipid-related artifacts (deemed not to contain clinical information), (iii) spectra containing metabolic information slightly contaminated by lipid signals, and (iv) good-quality *** AI model consists of three pairs of networks, each comprising a convolutional autoencoder and a multilayer perceptron network. In the classification step, the encoding half of the autoencoder is kept as a dimensionality reduction tool, while the fully connected layers are added to its output. Each of the three pairs of networks is trained on different representations of spectra (real, imaginary, or both), aiming at robust decision-making. The final class is assigned via a majority voting *** F1 scores obtained on the test dataset for the four previously defined classes are 0.96, 0.93, 0.82, and 0.90, respectively. The arguably lower value of 0.82 was reached for the least represented class of spectra mildly influenced by *** only does the proposed model minimise the required user interaction, but it also greatly reduces the computation time at the metabolite quantification step (by selecting a subset of spectra worth quantifying)

关键词： convolutional autoencoders MRSI quality filtering spectral quality

来源：评论

学校读者我要写书评

暂无评论

Inverted Pulse Estimation in Pulse Inversion Harmonic Imaging using Deep Learning

Inverted Pulse Estimation in Pulse Inversion Harmonic Imagin...

引用

IEEE International Ultrasonics Symposium (IUS)

作者： Fouad, Mariam Schmitz, Georg Ruhr Univ Bochum Chair Med Engn Bochum Germany

ISBN: (数字)9781665466578

ISBN: (纸本)9781665466578

Conventional methods such as filtering and multi-pulse acquisition techniques play an important role in ultrasonic nonlinear imaging, specifically harmonic imaging. However, the former suffers from spectral leakage, while the latter is hindered by the low frame rate and increased susceptibility to motion artifacts caused by the need to transmit two or more pulses. In this work, deep learning concepts are exploited to achieve a single-shot harmonic imaging application. This is accomplished by implementing an asymmetric convolutional autoencoder, capable of learning the nonlinear relationship between the echo resulting from the first transmitted pulse (network input) and the echo resulting from the second transmitted (inverted) pulse (network output) used in the conventional pulse inversion technique. The proposed approach yielded harmonic images with comparable contrast to noise and contrast ratios to the conventional pulse inversion technique, yet at approximately double the frame rate. These findings pave the way for harmonic imaging to be used with quality that is on par with the quality achieved by current harmonic imaging methods but with a higher framerate and fewer motion artifacts.

关键词： deep learning convolutional autoencoders harmonic imaging pulse inversion nonlinear propagation

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-based image processing framework for object appearance modifications

引用

NEURAL COMPUTING & APPLICATIONS 2021年第4期33卷 1079-1090页

作者： Slot, Krzysztof Kapusta, Pawel Kucharski, Jacek Lodz Univ Technol Inst Appl Comp Sci Lodz Poland

The presented paper introduces a novel method for enabling appearance modifications for complex image objects. Qualitative visual object properties, quantified using appropriately derived visual attribute descriptors, are subject to alterations. We adopt a basic convolutional autoencoder as a framework for the proposed attribute modification algorithm, which is composed of the following three steps. The algorithm begins with the extraction of attribute-related information from autoencoder's latent representation of an input image, by means of supervised principal component analysis. Next, appearance alteration is performed in the derived feature space (referred to as 'attribute-space'), based on appropriately identified mappings between quantitative descriptors of image attributes and attribute-space features. Finally, modified attribute vectors are transformed back to latent representation, and output image is reconstructed in the decoding part of an autoencoder. The method has been evaluated using two datasets: images of simple objects-digits from MNIST handwritten-digit dataset and images of complex objects-faces from CelebA dataset. In the former case, two qualitative visual attributes of digit images have been selected for modifications: slant and aspect ratio, whereas in the latter case, aspect ratio of face oval was subject to alterations. Evaluation results prove, both in qualitative and quantitative terms, that the proposed framework offers a promising tool for visual object editing.

关键词： Visual object editing convolutional autoencoders Supervised principal component analysis Machine learning

来源：评论

学校读者我要写书评

暂无评论

Image retrieval based on texture using latent space representation of discrete Fourier transformed maps

引用

NEURAL COMPUTING & APPLICATIONS 2021年第20期33卷 13301-13316页

作者： Saikia, Surajit Fernandez-Robles, Laura Alegre, Enrique Fidalgo, Eduardo Univ Leon Dept Elect Syst & Automat Engn Leon Spain INCIBE Spanish Natl Cybersecur Inst Leon Spain Univ Leon Dept Mech Informat & Aerosp Engn Leon Spain

Texture-based instance retrieval is typically performed on images that present a single texture pattern and is mainly applied to the retrieval of fabrics or textiles. In this work, we apply it to indoor scene images that typically present many different texture patterns, which constitutes a more challenging problem. Such retrieval systems, together with the retrieval of faces and objects, can be used as a valuable tool for evidence matching in crime scene investigation. Even though recent deep learning-based approaches have made significant improvement in many computer vision tasks, texture retrieval remains an open problem. In this work, we introduce a Fourier-based approach, in which spatial images and their discrete Fourier transform maps are combined to derive a novel texture representation. We further present a new and efficient texture-based image retrieval framework based on region proposal networks, convolutional autoencoders and transfer learning, in which we extract the features from the latent space layer of the encoder as texture descriptors. The experimental results on four datasets: TextileTube, Outex, USPtex and Stex, validated the effectiveness of our proposed method, yielding better results than the current state of the art.

关键词： Texture retrieval convolutional autoencoders Texture classification Discrete Fourier transform

来源：评论

学校读者我要写书评

暂无评论

Vibration Fault Detection in Wind Turbines Based on Normal Behaviour Models without Feature Engineering

引用

ENERGIES 2023年第4期16卷 1760页

作者： Jonas, Stefan Anagnostos, Dimitrios Brodbeck, Bernhard Meyer, Angela Bern Univ Appl Sci Sch Engn & Comp Sci Quellgasse 21 CH-2501 Biel Switzerland WinJi AG Badenerstr 808 CH-8048 Zurich Switzerland

Most wind turbines are remotely monitored 24/7 to allow for early detection of operation problems and developing damage. We present a new fault detection approach for vibration-monitored drivetrains that does not require any feature engineering. Our method relies on a simple model architecture to enable a straightforward implementation in practice. We propose to apply convolutional autoencoders for identifying and extracting the most relevant features from a broad continuous range of the spectrum in an automated manner, saving time and effort. We focus on the range of [0, 1000] Hz for demonstration purposes. A spectral model of the normal vibration response is learnt for the monitored component from past measurements. We demonstrate that the trained model can successfully distinguish damaged from healthy components and detect a damaged generator bearing and damaged gearbox parts from their vibration responses. Using measurements from commercial wind turbines and a test rig, we show that vibration-based fault detection in wind turbine drivetrains can be performed without the usual upfront definition of spectral features. Another advantage of the presented method is that a broad continuous range of the spectrum can be monitored instead of the usual focus on monitoring individual frequencies and harmonics. Future research should investigate the proposed method on more comprehensive datasets and fault types.

关键词： condition monitoring wind turbines fault detection vibrations autoencoders convolutional autoencoders neural networks renewable energy

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Students' Flow State in an E-learning Environment Through Activity and Performance Using Deep Learning Techniques

引用

JOURNAL OF EDUCATIONAL COMPUTING RESEARCH 2021年第5期59卷 960-987页

作者： Semerci, Yusuf Can Goularas, Dionysis Yeditepe Univ Dept Comp Engn Istanbul Turkey

Estimating the flow state of students in a course allows evaluating their sentimental state and the challenges they are facing. In e-learning platforms, the evaluation of flow state is a complex task because it depends on the ability to extract the parameters that better reflect the activity and effort of students. In this scope, the current study proposes a method based on flow theory aiming to provide information about the students' flow state in a course that is taught in an e-learning environment. First, the interaction of students with an e-learning platform that comprises classical e-learning pages and a timeline tool is analyzed, using activity heatmaps and deep neural networks. Then, by taking also in account their grades, the flow state of students is calculated. The resulted data are validated with a statistical analysis that also utilizes student surveys. In order to guarantee that this method is applicable to various profiles, students from different faculties participated in this study. In a period where education is rapidly adapting to online lectures and e-learning platforms, the estimation of student's flow state in e-learning environments can provide useful feedback and data to students and educators.

关键词： e-learning environment flow theory deep learning convolutional autoencoders interaction

来源：评论

学校读者我要写书评

暂无评论

3D autoencoders FOR FEATURE EXTRACTION IN X-RAY TOMOGRAPHY

3D AUTOENCODERS FOR FEATURE EXTRACTION IN X-RAY TOMOGRAPHY

引用

IEEE International Conference on Image Processing (ICIP)

作者： Tekawade, Aniket Liu, Zhengchun Kenesei, Peter Bicer, Tekin De Carlo, Francesco Kettimuthu, Rajkumar Foster, Ian Argonne Natl Lab Data Sci & Learning Div Lemont IL 60439 USA Argonne Natl Lab Xray Sci Div Lemont IL USA

ISBN: (纸本)9781665441155

Real-time steering of time-resolved or in-situ X-ray tomography requires capturing changes in morphological descriptors in a sample (e.g., porosity, particle size, and crack width) during continuous data acquisition. Segmentation of 2D or 3D images followed by quantitative measurement is the conventional method for tracking changes in these descriptors with respect to a previous time-step or a 3D search in a volume. However, image segmentation is expensive. As a faster and unsupervised alternative, we propose a feature-extraction approach using a convolutional autoencoder, where the latent space of the encoder responds to relative changes in morphology without prior knowledge of the morphological descriptors. To test this approach in parametric experiments, we used a digital twin for micro-CT to generate realistic datasets of porous materials. We show that for some configurations of the autoencoder, its n-dimensional latent space encodes a sample's local porosity metrics while disregarding contrast information (relative proportion of absorption and phase contrast) determined by the imaging modality and not the sample. Through dimensionality reduction, the vector's response is visualized in 2D space to find clusters of data with similar porosity metrics. Our approach can extract features from grayscale tomographic data more than 4x faster than a segmentation + pore analysis workflow.

关键词： convolutional autoencoders U-net insitu tomography porosity

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：