检索结果-内蒙古大学图书馆

Traffic classification using distributions of latent space in software-defined networks: An experimental evaluation

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年 119卷

作者： Jang, Yehoon Kim, Namgi Lee, Byoung-Dai Kyonggi Univ Div AI & Comp Engn Suwon South Korea

With the emergence of new Internet services and the drastic increase in Internet traffic, traffic classification has become increasingly important to effectively satisfy the quality of service to users. The traffic classification system should be resilient and operate smoothly regardless of network conditions or performance and should be capable of handling various classes of Internet services. This paper proposes a traffic classification method in a software-defined network environment that employs a variational autoencoder (VAE) to accomplish this. The proposed method trains the VAE using six statistical features and extracts the distributions of latent features for the flows in each service class. Furthermore, it classifies the query traffic by comparing the distributions of latent features for the query traffic with the learned distributions of the service classes. For the experiment, the statistical features of network flows were collected from real-world domestic and overseas Internet services for training and testing. According to the experimental results, the proposed method has an average accuracy of 89%. This accuracy was 52%, 47%, 39%, 59%, and 26% higher than conventional statistics-based classification methods, MLP, AE+MLP, VAE+MLP, and SVM, respectively. This result clearly suggests that probability distributions of latent features, rather than specific values for latent features, can be used as more stable features.

关键词： Flow classification Jensen-Shannon divergence Latent features Software-defined network variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep variational magnetic resonance image denoising via network conditioning

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年第PartA期95卷

作者： Aetesam, Hazique Maji, Suman Kumar Birla Inst Technol Mesra Dept Comp Sci & Engn Patna 800014 India Indian Inst Technol Patna Dept Comp Sci & Engn Patna 801106 India

In this paper, we propose a variational approach towards denoising magnetic resonance images (MRI) corrupted by spatially variant and signal-dependent Rician noise in a deep learning framework. To obtain a mathematically sound inference network, approximate variational posteriors are designed keeping in mind the Rician nature of noise. The proposed work tackles the denoising problem in several different ways. Firstly , the prior assumption on data in the variational posterior is motivated by the heavy-tailed marginal distribution of image gradients in natural images. This is captured by the sparsity promoting hyper-Laplacian prior on MR data. Similarly, median absolute deviation under Gaussian prior helps in the estimation of noise in the variational lower bound of marginal log likelihood term. Secondly , noise estimation from the background regions of the noisy data under the assumption of Rayleigh distribution prevents the addition of extra subnetwork for the estimation of spatially variant noise level parameters. Thirdly , feature-wise transformation of intermediate layers is performed using anatomical planes segmentation maps (APSM) for context-based network conditioning. Here, affine transformation parameters generated from APSM are modulated with the input features for spatial feature transformation. Fourthly , to capture the long-range dependencies lost in deeper convolutional layers, multiscale global feature fusion block (GFFuB) is used. Lastly , experimental results over synthetically corrupted MR data and real data obtained from MR scanners suggest the potential utility of the proposed model in real time.

关键词： Magnetic resonance imaging Noise estimation Rician distribution variational autoencoder Network conditioning

来源：评论

学校读者我要写书评

暂无评论

Multimodal representation models for prediction and control from partial information

引用

ROBOTICS AND AUTONOMOUS SYSTEMS 2020年 123卷 103312-000页

作者： Zambelli, Martina Cully, Antoine Demiris, Yiannis Imperial Coll London Dept Elect & Elect Engn Personal Robot Lab London England Imperial Coll London Personal Robot Lab London England DeepMind London London England Imperial Coll London Dept Comp London England

Similar to humans, robots benefit from interacting with their environment through a number of different sensor modalities, such as vision, touch, sound. However, learning from different sensor modalities is difficult, because the learning model must be able to handle diverse types of signals, and learn a coherent representation even when parts of the sensor inputs are missing. In this paper, a multimodal variational autoencoder is proposed to enable an iCub humanoid robot to learn representations of its sensorimotor capabilities from different sensor modalities. The proposed model is able to (1) reconstruct missing sensory modalities, (2) predict the sensorimotor state of self and the visual trajectories of other agents actions, and (3) control the agent to imitate an observed visual trajectory. Also, the proposed multimodal variational autoencoder can capture the kinematic redundancy of the robot motion through the learned probability distribution. Training multimodal models is not trivial due to the combinatorial complexity given by the possibility of missing modalities. We propose a strategy to train multimodal models, which successfully achieves improved performance of different reconstruction models. Finally, extensive experiments have been carried out using an iCub humanoid robot, showing high performance in multiple reconstruction, prediction and imitation tasks. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Multimodal learning Autonomous learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Bearing degradation prediction based on deep latent variable state space model with differential transformation

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2024年 220卷

作者： Ran, Bi Peng, Yizhen Wang, Yu Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China Xi An Jiao Tong Univ Coll Mech Engn Xian 710000 Peoples R China

Rolling bearings are a critical component of mechanical transmission equipment. Predicting their degradation trend is crucial for ensuring safe and stable equipment operation. Most existing bearing degradation prediction methods based on state space models (SSMs) use either linear functions or limited nonlinear functions (e.g., exponential/power laws) to construct the state and measurement equations. As such, these models fail to adapt to the complex and varied nonlinear degradation processes that occur in real-world environments. To address this limitation, we developed a deep latent variable-driven state space degradation model and employed it for bearing degradation prediction. Owing to the powerful nonlinear modeling ability of deep learning models, the proposed method extends the applicability of state space equations. In addition, it inherits the advantages of SSMs and can model uncertainties in a structured manner. Furthermore, the model was integrated with differential pre-transformation to improve its longterm prediction performance. Finally, to validate the effectiveness of the proposed model in predicting bearing degradation, experiments were conducted using a bearing dataset from the PRONOSTIA platform and real wind turbine bearing data. Results showed that the proposed method yielded higher bearing degradation prediction accuracy than existing methods, thus demonstrating the superior performance of the proposed model in predicting bearing degradation.

关键词： Bearings Degradation prediction variational autoencoder State space model

来源：评论

学校读者我要写书评

暂无评论

Subtle anomaly detection: Application to brain MRI analysis of de novo Parkinsonian patients

引用

ARTIFICIAL INTELLIGENCE IN MEDICINE 2022年 125卷 102251-102251页

作者： Munoz-Ramirez, Veronica Kmetzsch, Virgilio Forbes, Florence Meoni, Sara Moro, Elena Dojat, Michel Univ Grenoble Alpes INRIA Grenoble INP CNRSLJK F-38000 Grenoble France Univ Grenoble Alpes Inserm U1216 CHU Grenoble Alpes Grenoble Inst Neurosci F-38000 Grenoble France CHU Grenoble Alpes Div Neurol F-38000 Grenoble France

With the advent of recent deep learning techniques, computerized methods for automatic lesion segmentation have reached performances comparable to those of medical practitioners. However, little attention has been paid to the detection of subtle physiological changes caused by evolutive pathologies, such as neurodegenerative diseases. In this work, we leverage deep learning models to detect anomalies in brain diffusion tensor imaging (DTI) parameter maps of recently diagnosed and untreated (de novo) patients with Parkinson's disease (PD). For this purpose, we trained auto-encoders on parameter maps of healthy controls (n = 56) and tested them on those of de novo PD patients (n = 129). We considered large reconstruction errors between the original and reconstructed images to be anomalies that, when quantified, allow discerning between de novo PD patients and healthy controls. The most discriminating brain macro-region was found to be the white matter with a ROC-AUC 68.3 (IQR 5.4) and the best subcortical structure, the GPi (ROC-AUC 62.6 IQR 5.4). Our results indicate that our deep learning-based model can detect potentially pathological regions in de novo PD patients, without requiring any expert delineation. This may enable extracting neuroimaging biomarkers of PD in the future, but further testing on larger cohorts is needed. Such models can be seamlessly extended with additional parameter maps and applied to study the physio-pathology of other neurological diseases.

关键词： Machine learning Unsupervised learning variational autoencoder Neurodegenerative disease Parkinson's disease

来源：评论

学校读者我要写书评

暂无评论

Fast marching method assisted permeability upscaling using a hybrid deep learning method coupled with particle swarm optimization

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2023年 230卷

作者： Yousefzadeh, Reza Ahmadi, Mohammad Amirkabir Univ Technol Dept Petr Engn Tehran Iran

Geo-cellar models contain millions of gridblocks and are very time-consuming to simulate. This challenge necessitates upscaling geo-cellular models to obtain fit-for-purpose models for simulation. Simulation-based upscaling methods are computationally demanding, especially if there is a large number of geological realizations. On the other hand, static methods do not take into account the dynamics of the flow. In this paper, a novel hybrid deep learning-based upscaling method is proposed that can handle highly channelized and layered reservoir models. The proposed method combines the ConvLSTM network with the fast marching method (FMM), which is a computationally efficient method to get the dynamic response of the reservoir without the need for full-physics flow simulation. Since reservoir models have deposited during different geological periods, they have a temporal distribution along the third dimension. ConvLSTM layers can simultaneously extract spatiotemporal dependencies that other networks in the literature were not able to do so. The proposed method follows a twostep training process. In the first step, a variational autoencoder with ConvLSTM blocks (ConvLSTM-VAE) is trained and validated unsupervised using 10,000 permeability realizations. This network learns the datagenerating distribution of the realizations and improves the overall upscaling process. Then, the acquired weights are used to initialize the ConvLSTM-FMM network, which is fine-tuned by the particle swarm optimization to accomplish the upscaling task by minimizing the difference between the pressure drop of the fine-scale and upscaled realizations calculated by the FMM. Validity of the FMM to estimate the BHP drop of the wells was verified on the utilized reservoir model. The advantage of the proposed data-driven method is that it can be trained once and used to upscale new realizations, contrary to conventional simulation-based methods that require running the entire process whenever the fine

关键词： Upscaling Deep learning variational autoencoder Fast marching method Unsupervised

来源：评论

学校读者我要写书评

暂无评论

Uncovering obscured phonon dynamics from powder inelastic neutron scattering using machine learning

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2024年第3期5卷 035080页

作者： Su, Yaokun Li, Chen Univ Calif Riverside Mat Sci & Engn Riverside CA 92507 USA Univ Calif Riverside Mech Engn Riverside CA 92507 USA

The study of phonon dynamics is pivotal for understanding material properties, yet it faces challenges due to the irreversible information loss inherent in powder inelastic neutron scattering spectra and the limitations of traditional analysis methods. In this study, we present a machine learning framework designed to reveal obscured phonon dynamics from powder spectra. Using a variational autoencoder, we obtain a disentangled latent representation of spectra and successfully extract force constants for reconstructing phonon dispersions. Notably, our model demonstrates effective applicability to experimental data even when trained exclusively on physics-based simulations. The fine-tuning with experimental spectra further mitigates issues arising from domain shift. Analysis of latent space underscores the model's versatility and generalizability, affirming its suitability for complex system applications. Furthermore, our framework's two-stage design is promising for developing a universal pre-trained feature extractor. This approach has the potential to revolutionize neutron measurements of phonon dynamics, offering researchers a potent tool to decipher intricate spectra and gain valuable insights into the intrinsic physics of materials.

关键词： phonon dynamics inelastic neutron scattering variational autoencoder domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Normative ascent with local gaussians for unsupervised lesion detection

引用

MEDICAL IMAGE ANALYSIS 2021年 74卷 102208-102208页

作者： Chen, Xiaoran Pawlowski, Nick Glocker, Ben Konukoglu, Ender Swiss Fed Inst Technol Zurich Switzerland Imperial Coll London London England

Unsupervised abnormality detection is an appealing approach to identify patterns that are not present in training data without specific annotations for such patterns. In the medical imaging field, methods taking this approach have been proposed to detect lesions. The appeal of this approach stems from the fact that it does not require lesion-specific supervision and can potentially generalize to any sort of abnormal patterns. The principle is to train a generative model on images from healthy individuals to estimate the distribution of images of the normal anatomy, i.e., a normative distribution , and detect lesions as out-of distribution regions. Restoration-based techniques that modify a given image by taking gradient ascent steps with respect to a posterior distribution composed of a normative distribution and a likelihood term recently yielded state-of-the-art results. However, these methods do not explicitly model ascent directions with respect to the normative distribution, i.e. normative ascent direction, which is essential for successful restoration. In this work, we introduce a novel approach for unsupervised lesion detection by modeling normative ascent directions. We present different modelling options based on the defined ascent directions with local Gaussians. We further extend the proposed method to efficiently utilize 3D information, which has not been explored in most existing works. We experimentally show that the proposed method provides higher accuracy in detection and produces more realistic restored images. The performance of the proposed method is evaluated against baselines on publicly available BRATS and ATLAS stroke lesion datasets;the detection accuracy of the proposed method surpasses the current stateof-the-art results. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ( http://***/licenses/by-nc-nd/4.0/ )

关键词： Unsupervised learning variational autoencoder Lesion detection

来源：评论

学校读者我要写书评

暂无评论

GenCoder: A Generative AI-Based Adaptive Intra-Vehicle Intrusion Detection System

引用

IEEE ACCESS 2024年 12卷 150651-150663页

作者： Smolin, Mikhail Kyrgyz State Tech Univ Dept Appl Math & Comp Sci Bishkek 720044 Kyrgyzstan

With the rapid expansion of the vehicular cybersecurity (VCS) market and the increasing sophistication of cyberthreats, developing an adaptive intra-vehicular intrusion detection system (IDS) is crucial. This paper introduces GenCoder, a generative artificial intelligence (GenAI)-based IDS that uniquely addresses the dynamic and evolving nature of vehicular cyberthreats. GenCoder combines a five-layer deep neural network (DNN) with a variational autoencoder (VAE), overseen by a novel communication layer known as the GenCoder layer. This system dynamically adapts to new intrusion patterns by generating and utilizing new training data when deviations from known patterns are detected. The generated samples have a Shannon entropy (SE) value of 1.65 bits for four classes, indicating standard variety among the synthetic data. GenCoder demonstrates exceptional adaptability, pushing the accuracy, precision, recall, and F1-score from 84.79%, 83.58%, 83.70%, and 83.64% to 92.19%, 90.12%, 90.44%, and 90.28%, respectively, after introducing 50% feature deformation to testing data. The novel concept of an adaptive intra-vehicular IDS, the innovative GenCoder layer that establishes seamless communication among the DNN, the VAE, and the dataset, as well as the unique assessment strategies of adaptability make this research exceptional with the potential to create a new dimension in automotive IDS research.

关键词： Computer crime Automobiles Principal component analysis Intrusion detection Adaptive systems Protocols NSL-KDD Vehicle dynamics Support vector machines Artificial neural networks Artificial intelligence Generative AI Encoding Adaptive intrusion detection automotive cybersecurity deep neural network GenCoder layer generative artificial intelligence variational autoencoder vehicular intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

An Overview of Deep Generative Models in Functional and Evolutionary Genomics

引用

Biomedical Data Science 1000年第1期6卷 173-189页

作者： Burak Yelmen Flora Jay 2Institute of Genomics University of Tartu Tartu Estonia 1Laboratoire Interdisciplinaire des Sciences du Numérique CNRS UMR 9015 INRIA Université Paris-Saclay Orsay France email: flora.jay@lisn.fr

Following the widespread use of deep learning for genomics, deep generative modeling is also becoming a viable methodology for the broad field. Deep generative models (DGMs) can learn the complex structure of genomic data and allow researchers to generate novel genomic instances that retain the real characteristics of the original dataset. Aside from data generation, DGMs can also be used for dimensionality reduction by mapping the data space to a latent space, as well as for prediction tasks via exploitation of this learned mapping or supervised/semi-supervised DGM designs. In this review, we briefly introduce generative modeling and two currently prevailing architectures, we present conceptual applications along with notable examples in functional and evolutionary genomics, and we provide our perspective on potential challenges and future directions.

关键词： deep generative models variational autoencoder generative adversarial network functional genomics evolutionary genetics

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：