检索结果-内蒙古大学图书馆

Small time asymptotics of the entropy of the heat kernel on a Riemannian manifold

APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS 2024年 71卷

作者： Menkovski, Vlado Portegies, Jacobus W. Ravelonanosy, Mahefa Ratsisetraina Eindhoven Univ Technol Dept Math & Comp Sci Eindhoven Netherlands Eindhoven Univ Technol EAISI Eindhoven Netherlands Eindhoven Univ Technol Dept Math & Comp Sci POB 513 NL-5600 MB Eindhoven Netherlands

We give an asymptotic expansion of the relative entropy between the heat kernel q(Z)(t, z, w) of a compact Riemannian manifold Z and the normalized Riemannian volume for small values of t and for a fixed element z is an element of Z. We prove that coefficients in the expansion can be expressed as universal polynomials in the components of the curvature tensor and its covariant derivatives at z, when they are expressed in terms of normal coordinates. We describe a method to compute the coefficients, and we use the method to compute the first three coefficients. The asymptotic expansion is necessary for an unsupervised machine-learning algorithm called the Diffusion variational autoencoder.

关键词： Kullback-Leibler divergence Entropy Heat kernel Parametrix expansion variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

User preference-aware content caching strategy for video delivery in cache-enabled IoT networks

引用

COMPUTER NETWORKS 2024年 240卷

作者： Firouzjaee, Mostafa Taghizade Jamshidi, Kamal Moghim, Neda Shetty, Sachin Univ Isfahan Dept Comp Engn Esfahan *** Iran Old Dominion Univ Virginia Modeling Anal & Simulat Ctr Dept Computat Modeling & Simulat Engn Suffolk VA 23435 USA

The escalating growth of content-dependent services and applications within the Internet of Things (IoT) platform has led to a surge in traffic, necessitating real-time data processing. Content caching has emerged as an effective solution to counteract this traffic upswing. Caching not only improves network efficiency but also enhances user service quality. Critical to the development of an optimal caching algorithm is the accurate prediction of future content popularity. This prediction hinges on the ability to anticipate users' content preferences, which is a pivotal method for assessing content popularity. In this study, we introduce a novel caching strategy termed User Preference-aware content Caching Strategy (UPCS) tailored for an IoT platform, where users access multimedia services offered by remote Content Providers (CPs). The UPCS encompasses three key algorithms: a content popularity prediction algorithm that utilizes variational autoencoders (VAE) to forecast users' future content preferences based on their prior requests, an online algorithm for dynamic cached content replacement, and a cooperative caching algorithm to augment caching efficiency. The proposed content caching strategy outperforms alternative methods, exhibiting superior cache hit rates and reduced Content Retrieval Delays (CRD).

关键词： Content caching Cooperative caching IoT Networks Popularity prediction Deep learning 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

Deep Learning for Size-Agnostic Inverse Design of Random-Network 3D Printed Mechanical Metamaterials

引用

ADVANCED MATERIALS 2024年第6期36卷 2303481-2303481页

作者： Pahlavani, Helda Tsifoutis-Kazolis, Kostas Saldivar, Mauricio C. Mody, Prerak Zhou, Jie Mirzaali, Mohammad J. Zadpoor, Amir A. Delft Univ Technol TU Delft Fac Mech Maritime & Mat Engn Dept Biomech Engn Mekelweg 2 NL-2628 CD Delft Netherlands Leiden Univ Med Ctr LUMC Div Image Proc LKEB Radiol Albinusdreef 2 NL-2333 ZA Leiden Netherlands

Practical applications of mechanical metamaterials often involve solving inverse problems aimed at finding microarchitectures that give rise to certain properties. The limited resolution of additive manufacturing techniques often requires solving such inverse problems for specific specimen sizes. Moreover, the candidate microarchitectures should be resistant to fatigue and fracture. Such a multi-objective inverse design problem is formidably difficult to solve but its solution is the key to real-world applications of mechanical metamaterials. Here, a modular approach titled "Deep-DRAM" that combines four decoupled models is proposed, including two deep learning (DL) models, a deep generative model based on conditional variational autoencoders, and direct finite element (FE) simulations. Deep-DRAM integrates these models into a framework capable of finding many solutions to the posed multi-objective inverse design problem based on random-network unit cells. Using an extensive set of simulations as well as experiments performed on 3D printed specimens, it is demonstrate that: 1) the predictions of the DL models are in agreement with FE simulations and experimental observations, 2) an enlarged envelope of achievable elastic properties (e.g., rare combinations of double auxeticity and high stiffness) is realized using the proposed approach, and 3) Deep-DRAM can provide many solutions to the considered multi-objective inverse design problem. Mechanical metamaterials are architected engineered materials whose unprecedented properties originate from their designs at the microscale. Here, deep-learning techniques are utilized to develop a modular approach titled "Deep-DRAM" that generates numerous microstructures for mechanical metamaterials with predefined elastic properties and dimensions for various applications in high-tech industries, such as soft robotics and biomedical ***

关键词： additive manufacturing deep learning numerical simulations random-network mechanical metamaterials size-agnostic variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction Based on Self-Supervised Learning for Remaining Useful Life Prediction

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING 2024年第2期24卷 021004-021004页

作者： Yu, Zhenjun Lei, Ningbo Mo, Yu Xu, Xin Li, Xiu Huang, Biqing Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Tsinghua Shenzhen Int Grad Sch Div Informat Sci Shenzhen 518055 Peoples R China China Nucl Power Engn Co Ltd Beijing 100840 Peoples R China

The prediction of the remaining useful life (RUL) is of great significance to ensure the safe operation of industrial equipment and to reduce the cost of regular preventive maintenance. However, the complex operating conditions and various fault modes make it difficult to extract features containing more degradation information with existing prediction methods. We propose a self-supervised learning method based on variational automatic encoder (VAE) to extract features of data's operating conditions and fault modes. Then the clustering algorithm is applied to the extracted features to divide data from different failure modes into different categories and reduce the impact of complex working conditions and fault modes on the estimation accuracy. In order to verify the effectiveness of the proposed method, we conduct experiments with different network structures on the C-MAPSS dataset, and the results verified that our method can effectively improve the feature extraction capability of the model. In addition, the experimental results further demonstrate the superiority and necessity of using hidden features for clustering rather than raw data.

关键词： fault prognosis remaining useful life prediction self-supervised learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Two-pronged feature reduction in spectral clustering with optimized landmark selection

引用

APPLIED SOFT COMPUTING 2024年 161卷

作者： Rouhi, Alireza Bouyer, Asgarali Arasteh, Bahman Liu, Xiaoyang Azarbaijan Shahid Madani Univ Fac Informat Technol & Comp Engn Tabriz Iran Istinye Univ Fac Engn & Nat Sci Dept Software Engn Istanbul Turkiye Khazar Univ Dept Comp Sci Baku Azerbaijan Chongqing Univ Technol Sch Comp Sci & Engn Chongqing 400054 Peoples R China

Spectral clustering is widely employed for clustering data points, particularly for non-linear and non-convex structures in high-dimensional spaces. However, it faces challenges due to the high computational cost of eigen decomposition operations and the performance limitations with high-dimensional data. In this paper, we introduce BVA_LSC, a novel spectral clustering algorithm designed to address these challenges. Firstly, we incorporate an advanced feature reduction stage utilizing Barnes-Hut t-SNE and a deep variational autoencoder (VAE) to efficiently reduce the dimensionality of the data, thereby accelerating eigen decomposition. Secondly, we propose an adaptive landmark selection strategy that combines the Grey Wolf Optimizer (GWO) with a novel objective function and K-harmonic means clustering. This strategy dynamically determines an optimal number of landmarks, enhancing the representativeness of the data and reducing the size of the similarity matrix. We assess the performance of our algorithm on various standard datasets, demonstrating its superiority over state-of-the-art methods in terms of accuracy and efficiency.

关键词： Spectral Clustering variational autoencoder Landmark Grey Wolf Optimization K-harmonic means Unsupervised Learning

来源：评论

学校读者我要写书评

暂无评论

Threat Intelligence System for Internet of Things based Smart Environments using Unsupervised Learning 19

Threat Intelligence System for Internet of Things based Smar...

引用

19th IEEE-India-Council International Conference (INDICON)

作者： Sumitra Shenoy, Meetha V. Birla Inst Technol & Sci Dept Elect & Elect Engn Pilani Rajasthan India

ISBN: (纸本)9781665473507

With the advent of the Internet of Things (IoT), our environments have become pervasive. Studies indicate that most of the existing IoT devices have inherent security flaws and are vulnerable to both internal and external attacks. Threat identification is generally done by either identification of the specific type of attack in the network or by distinguishing benign traffic from anomalous traffic. Most of the recent works for threat identification rely on supervised machine learning techniques which involve training a model using datasets containing labeled samples of prior attacks. A supervised network can thus only understand the categories on which it has been trained. Due to the enormous volume and variety of data collected by the IoT devices, and the attacks to which the networks are prone, the supervised techniques are of limited use in practical applications. We propose a novel threat identification strategy using the Clustering based variational autoencoder (CVA) for detecting threats (anomalous behaviors) in IoT networks. The proposed strategy uses an unsupervised technique and hence the model needs to be trained only on traffic under benign scenarios for the identification of threats. Also, the proposed technique is scalable to accommodate a large number of devices.

关键词： Anomaly detection variational autoencoder Threat Intelligence Internet of Things Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Perioperative Predictions with Interpretable Latent Representation 22

Perioperative Predictions with Interpretable Latent Represen...

引用

28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KKD)

作者： Xue, Bing Jiao, York Kannampallil, Thomas Fritz, Bradley King, Christopher Abraham, Joanna Avidan, Michael Lu, Chenyang Washington Univ McKelvey Sch Engn St Louis MO 63110 USA Washington Univ Sch Med St Louis MO 63110 USA

ISBN: (纸本)9781450393850

Given the risks and cost of hospitalization, there has been significant interest in exploiting machine learning models to improve perioperative care. However, due to the high dimensionality and noisiness of perioperative data, it remains a challenge to develop accurate and robust encoding for surgical predictions. Furthermore, it is important for the encoding to be interpretable by perioperative care practitioners to facilitate their decision making process. We propose clinical variational autoencoder (cVAE), a deep latent variable model that addresses the challenges of surgical applications through two salient features. (1) To overcome performance limitations of traditional VAE, it is prediction-guided with explicit expression of predicted outcome in the latent representation. (2) It disentangles the latent space so that it can be interpreted in a clinically meaningful fashion. We apply cVAE to two real-world perioperative datasets to evaluate its efficacy and performance in predicting outcomes that are important to perioperative care, including postoperative complication and surgery duration. To demonstrate the generality and facilitate reproducibility, we also apply cVAE to the open MIMIC-III dataset for predicting ICU duration and mortality. Our results show that the latent representation provided by cVAE leads to superior performance in classification, regression and multi-task predictions. The two features of cVAE are mutually beneficial and eliminate the need of a predictor. We further demonstrate the interpretability of the disentangled representation and its capability to capture intrinsic characteristics of hospitalized patients. While this work is motivated by and evaluated in the context of clinical applications, the proposed approach may be generalized for other fields using high-dimensional and noisy data and valuing interpretable representations.

关键词： clinical prediction healthcare variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Image-to-Video Translation Using a VAE-GAN with Refinement Network 1

引用

18th International Conference on Intelligent Computing (ICIC)

作者： Wang, Shengli Xieshi, Mulin Zhou, Zhangpeng Zhang, Xiang Liu, Xujie Tang, Zeyi Xiahou, Jianbing Lin, Pingyuan Xu, Xuexin Dai, Yuxing Maintenance Co State Grid Power Co Gansu Prov Lanzhou 730000 Gansu Peoples R China State Grid Infotelecom Great Power Sci & Technol Fuzhou 350000 Peoples R China Xiamen Univ Sch Informat Xiamen 361005 Peoples R China

ISBN: (数字)9783031138706

ISBN: (纸本)9783031138706;9783031138690

With the development of deep learning technology, various techniques for image processing have emerged in the field of computer vision in recent years, and have excellent performance in a variety of application scenarios. In contrast to the prediction task of predicting video with multiple consecutive frames before and after the input to predict the missing images in the middle, the task of image-to-video generation proposed in this paper does not require multiple consecutive frames, but rather the directional content generation of images by inputting the first frame image with the embedding vector of motion features, and to address some of the existing problems, this paper innovates the network architecture to solve the generated video problems such as incoherence, frame loss and blurring. For multiple image-to-video translation tasks, we propose a VAE-RGAN network with a further refinement network. We add a refinement network and use new identity matching loss and connected feature matching loss to eliminate VAE and GAN's respective shortcomings and enhance the visual quality of the generated videos. Weizmann datasets have been the subject of a wide range of qualitative and quantitative experiments. We draw the following conclusions from this empirical study: (1) Compared with state-of-the-art approaches, our approach (VAE-RGAN) exhibits significant improvements in generative capability;(2) Experiments shows that our designed VAE-RGAN structure achieves better results and the refinement network significantly improves the problems of a blur.

关键词： Video generation variational autoencoder Generative Adversarial Network Refinement network

来源：评论

学校读者我要写书评

暂无评论

Detecting Anomalies with LatentOut: Novel Scores, Architectures, and Settings 26th

Detecting Anomalies with LatentOut: Novel Scores, Architectu...

引用

26th International Symposium on Methodologies for Intelligent Systems (ISMIS)

作者： Angiulli, Fabrizio Fassetti, Fabio Ferragina, Luca Univ Calabria DIMES I-87036 Arcavacata Di Rende CS Italy

ISBN: (纸本)9783031165641;9783031165634

LatentOut is a recently introduced algorithm for unsupervised anomaly detection which enhances latent space-based neural methods, namely (variational) autoencoders, GANomaly and ANOGan architectures. The main idea behind it is to exploit both the latent space and the baseline score of these architectures in order to provide a refined anomaly score performing density estimation in the augmented latent-space/baseline-score feature space. In this paper we extend the research on the LatentOut methodology in three directions: first, we provide a novel score performing a different kind of density estimation at a reduced computational cost;second, we experiment the combination of LatentOut with GAAL architectures, a novel type of Generative Adversarial Networks for unsupervised anomaly detection;third, we investigate performances of LatentOut acting as a one-class classifier. The experiments show that all the variants of LatentOut here introduced improve performances of the baseline methods to which they are applied, both in the unsupervised and in the semi-supervised settings.

关键词： Anomaly detection variational autoencoder Generative adversarial network Density estimation

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：