检索结果-内蒙古大学图书馆

Study of Hybrid Machine Learning Multiaxial Low-Cycle Fatigue Life Prediction Model of CP-Ti

FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES 2025年第5期48卷 2309-2324页

作者： Ma, Tian-Hao Zhang, Wei Chang, Le Zhao, Jian-Ping Zhou, Chang-Yu Nanjing Tech Univ Sch Mech & Power Engn Nanjing Peoples R China

Symmetric and asymmetric multiaxial low-cycle fatigue tests were conducted on commercially pure titanium under different control modes and multiaxial strain/stress ratios to establish a reliable hybrid physics and data-driven method. Optimized analysis formula-based models are proposed to provide reliable physical information first. Based on the dataset enhanced by the nonlinear variational autoencoder method, a hybrid VAE-ANN model is established and trained, developed using the Pearson correlation coefficient analysis and Leaky ReLU activation function. Through a series of fatigue life prediction validations under both symmetric and asymmetric loading conditions, the VAE-ANN model demonstrates excellent prediction accuracy, broad generalization capability, and strong compatibility, achieving the lowest average absolute relative error of 6.76% under symmetric and 22.61% under asymmetric loading conditions.

关键词： artificial neural network commercial pure titanium life prediction multiaxial low-cycle fatigue variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Machine learning assisted crystallographic reconstruction from atom probe tomographic images

引用

JOURNAL OF PHYSICS-CONDENSED MATTER 2025年第3期37卷 035901-035901页

作者： Pu, Jie-Ming Chen, Shuai Zhang, Tong-Yi Shanghai Univ Mat Genome Inst Shanghai 200444 Peoples R China Shanghai Univ Shanghai Frontier Sci Ctr Mechanoinformat Shanghai 200444 Peoples R China Hong Kong Univ Sci & Technol Guangzhou Guangzhou Municipal Key Lab Mat Informat Sustainab Adv Mat Thrust Guangzhou 511400 Guangdong Peoples R China

Atom probe tomography (APT) is a powerful technique for three-dimensional (3D) atomic-scale imaging, enabling the accurate analysis on the compositional distribution at the nanoscale. How to accurately reconstruct crystallographic information from APT data, however, is still a great challenge due to the intrinsic nature of the APT technique. In this paper, we propose a novel approach that consists of the modified forward simulation process and the backward machine learning process to recover the tested crystal from APT data. The high-throughput forward simulations on Al single crystals of different orientations generate 10 000 original 3D images and data augmentation is implemented on the original images, resulting in 100 000 3D images. The big data allows the development of deep learning models and three deep learning algorithms of Convolutional Neural Network (CNN), Vision Transformer (ViT), and variational autoencoder (VAE) are used in the backward process. After training, the ViT model performs superior than the CNN and VAE models, which can recover the crystalline orientation outstandingly, as evaluated by the coefficient of determination R-2 and the Mean Percent Error (MPE), viz., R-2 = 0.93 and MPE = 0.43%, R-2 = 0.97 and MPE = 0.35%, and R-2 = 0.93 and MPE = 0.77% for the rotation angles phi, psi and theta, respectively, on the test dataset. The present work clearly demonstrates the capability of deep learning models in the recovery of the tested crystals from APT data, thereby paving the way for the further development of large artificial intelligent models of APT.

关键词： atom probe tomography high-throughput simulation convolutional neural network vision of transformer variational autoencoder machine learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Speech Synthesizer: A Hybrid Monotonic Architecture for Text-to-speech via VAE & LPC-Net with Independent Sentence Length

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2025年 1-25页

作者： Nallabala, Naveen Kumar Souprayen, Balamurugan Ramasamy, Maruthamuthu Penumarti, Seshu Kumar Navuluri, Nuthan Chandu Madanapalle Inst Technol & Sci Dept Comp Applicat Madanapalle Andhra Pradesh India JAIN Sch Comp Sci & Informat Technol Bengaluru Karnataka India Univ East London Dept Architecture Comp & Engn London England

This research delineates the development of a hybrid architecture for text-to-speech (TTS) synthesis, termed the Efficient Speech Synthesizer (ESS). ESS leverages an end-to-end training paradigm to holistically optimize all the parameters, thereby facilitating the synthesis of high-fidelity speech with remarkable efficiency, irrespective of sentence length. The architecture integrates state-of-the-art feed-forward methodologies, including variational autoencoders and linear predictive coding techniques, which impose monotonic constraints on sequence alignment while incurring negligible computational overhead. The primary objective of this study is to engineer a TTS model characterized by minimal complexity and latency, rendering it suitable for deployment across a broad spectrum of computational platforms, ranging from high-performance systems to resource-constrained IoT devices and smartphones.

关键词： Efficient Speech Synthesizer Non-autoregressive Autoregressive Monotonic alignment Linear predictive coding variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Machine sound anomaly detection based on dual-channel feature fusion variational auto-encoder

引用

APPLIED INTELLIGENCE 2025年第7期55卷 1-17页

作者： Zhang, Chen Wei, Yongkang Wang, Xiaofeng Wu, Xiaoxuan Zhu, Xuhui Hefei Univ Dept Artificial Intelligence & Big Data Hefei 230601 Anhui Peoples R China Hefei Univ Technol Intelligent Interconnected Syst Lab Anhui Prov Hefei 230009 Anhui Peoples R China

With the increasing intelligence and automation of industrial equipment, the technology for detecting equipment anomalies has become increasingly important. Compared to image-based anomaly detection methods, sound-based anomaly detection methods have the advantages of being non-intrusive, real-time and having lower data collection costs. These advantages make them highly valuable for research. Currently, deep learning methods that focus on spectrogram reconstruction have become widely utilized in the field of machine sound anomaly detection research. However, previous methods only attempted to mitigate the impact of noise without enabling the model to fully learn the distribution of sound features during the reconstruction process. In this paper, a novel Dual-Channel Feature Fusion variational autoencoder (DCFF-VAE) is proposed to effectively improve its reconstruction ability and help it better learn the normal sound features. In this method, the deep features extracted from the convolution layer and bidirectional gated cycle unit in the encoder are integrated by means of concatenation to make full use of the important features in the sound. Subsequently, grouped deconvolution is applied in the decoder to reduce model complexity while enhancing its perceptual ability for features. Additionally, during the anomaly detection phase, anomaly scores are calculated based on the Mahalanobis distance to better capture the differences between normal and abnormal sounds. Anomaly detection experiments conducted on five types of machines demonstrate that DCFF-VAE not only achieves the best stability but also surpasses the best comparison method by 3.14% and 1.21% in AUC and pAUC metrics, respectively.

关键词： Anomalous sound detection Unsupervised learning Feature fusion variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A deep learning model for inter-fraction head and neck anatomical changes in proton therapy

引用

PHYSICS IN MEDICINE AND BIOLOGY 2025年第6期70卷 065011-065011页

作者： Burlacu, Tiberiu Hoogeman, Mischa Lathouwers, Danny Perko, Zoltan Delft Univ Technol Fac Appl Sci Delft Netherlands Univ Med Ctr Rotterdam Erasmus MC Canc Inst Dept Radiotherapy Rotterdam Netherlands HollandPTC Consortium Delft Netherlands

Objective. To assess the performance of a probabilistic deep learning based algorithm for predicting inter-fraction anatomical changes in head and neck patients. Approach. A probabilistic daily anatomy model (DAM) for head and neck patients DAM (DAMHN) is built on the variational autoencoder architecture. The model approximates the generative joint conditional probability distribution of the repeat computed tomography (rCT) images and their corresponding masks on the planning CT images (pCT) and their masks. The model outputs deformation vector fields, which are used to produce possible rCTs and associated masks. The dataset is composed of 93 patients (i.e. 315 pCT-rCT pairs), 9 (i.e. 27 pairs) of which were set aside for final testing. The performance of the model is assessed based on the reconstruction accuracy and the generative performance for the set aside patients. Main results. The model achieves a DICE score of 0.83 and an image similarity score normalized cross-correlation of 0.60 on the test set. The generated parotid glands, spinal cord and constrictor muscle volume change distributions and center of mass shift distributions were also assessed. For all organs, the medians of the distributions are close to the true ones, and the distributions are broad enough to encompass the real observed changes. Moreover, the generated images display anatomical changes in line with the literature reported ones, such as the medial shifts of the parotids glands. Significance. DAMHN is capable of generating realistic anatomies observed during the course of the treatment and has applications in anatomical robust optimization, treatment planning based on plan library approaches and robustness evaluation against inter-fractional changes.

关键词： proton therapy deep learning variational autoencoder anatomy changes

来源：评论

学校读者我要写书评

暂无评论

Glissando-Net: Deep Single View Category Level Pose Estimation and 3D Reconstruction

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第4期47卷 2298-2312页

作者： Sun, Bo Kang, Hao Guan, Li Li, Haoxiang Mordohai, Philippos Hua, Gang Adobe Inc San Jose CA 95110 USA ByteDance Inc Bellevue WA USA Meta Real Labs Menlo Pk CA USA Pixocial Technol Bellevue WA USA Stevens Inst Technol Hoboken NJ USA Dolby Labs Bellevue WA USA

We present a deep learning model, dubbed Glissando-Net, to simultaneously estimate the pose and reconstruct the 3D shape of objects at the category level from a single RGB image. Previous works predominantly focused on either estimating poses (often at the instance level), or reconstructing shapes, but not both. Glissando-Net is composed of two auto-encoders that are jointly trained, one for RGB images and the other for point clouds. We embrace two key design choices in Glissando-Net to achieve a more accurate prediction of the 3D shape and pose of the object given a single RGB image as input. First, we augment the feature maps of the point cloud encoder and decoder with transformed feature maps from the image decoder, enabling effective 2D-3D interaction in both training and prediction. Second, we predict both the 3D shape and pose of the object in the decoder stage. This way, we better utilize the information in the 3D point clouds presented only in the training stage to train the network for more accurate prediction. We jointly train the two encoder-decoders for RGB and point cloud data to learn how to pass latent features to the point cloud decoder during inference. In testing, the encoder of the 3D point cloud is discarded. The design of Glissando-Net is inspired by codeSLAM. Unlike codeSLAM, which targets 3D reconstruction of scenes, we focus on pose estimation and shape reconstruction of objects, and directly predict the object pose and a pose invariant 3D reconstruction without the need of the code optimization step. Extensive experiments, involving both ablation studies and comparison with competing methods, demonstrate the efficacy of our proposed method, and compare favorably with the state-of-the-art.

关键词： Shape Three-dimensional displays Point cloud compression Solid modeling Training Decoding Pose estimation Image reconstruction Predictive models Transforms 3D shape reconstruction 3D pose estimation single view 3D shape estimation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

VAE-Surv: A novel approach for genetic-based clustering and prognosis prediction in myelodysplastic syndromes

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2025年 261卷 108605-108605页

作者： Rollo, Cesare Pancotti, Corrado Sartori, Flavio Caranzano, Isabella D'Amico, Saverio Carota, Luciana Casadei, Francesco Birolo, Giovanni Lanino, Luca Sauta, Elisabetta Asti, Gianluca Buizza, Alessandro Delleani, Mattia Zazzetti, Elena Bicchieri, Marilena Maggioni, Giulia Fenaux, Pierre Platzbecker, Uwe Diez-Campelo, Maria Haferlach, Torsten Castellani, Gastone Porta, Matteo Giovanni Della Fariselli, Piero Sanavia, Tiziana Univ Torino Computat Biomed Unit Dept Med Sci Via Santena 19 I-10126 Turin Italy IRCCS Humanitas Res Hosp Via Manzoni 56 I-20089 Rozzano Milan Italy Train Srl via Alessandro Manzoni 56 I-20089 Rozzano Milan Italy Univ Bologna Dept Med & Surg Sci DIMEC I-40126 Bologna Italy IRCCS Ist Sci Neurol Bologna I-40138 Bologna Italy Hop St Louis Hematol Bone Marrow Transplantat Paris France Univ Hosp Leipzig Med Clin & Policlin 1 Hematol & Cellular Therapy Leipzig Germany Hosp Univ Salamanca Hematol Dept Salamanca Spain MLL Munich Leukemia Lab Max Lebsche Pl 31 Munich Germany IRCCS Azienda Osped Univ Bologna S Orsola I-40138 Bologna Italy Humanitas Univ Dept Biomed Sci Via Montalcini 4 I-20072 Pieve Emanuele Milan Italy

Background and Objectives Several computational pipelines for biomedical data have been proposed to stratify patients and to predict their prognosis through survival analysis. However, these analyses are usually performed independently, without integrating the information derived from each of them. Clustering of survival data is an underexplored problem, and current approaches are limited for biomedical applications, whose data are usually heterogeneous and multimodal, with poor scalability for high-dimensionality. Methods We introduce VAE-Surv, a multimodal computational framework for patients' stratification and prognosis prediction. VAE-Surv integrates a variational autoencoder (VAE), which reduces the high-dimensional space characterizing the molecular data, with a deep survival model, which combines the embedded information with the clinical features. The VAE embedding step prioritizes local coherence within the feature space to detect potential nonlinear relationships among the molecular markers. The latent representation is then exploited to perform K-means clustering. To test the clinical robustness of the algorithm, VAE-Surv was applied to the Genomed4all cohort of Myelodysplastic Syndromes (MDS), comparing the identified subtypes with the World Health Organization (WHO) classification. The survival outcome was compared with the state-of-the-art Cox model and its penalized versions. Finally, to assess the generalizability of the results, the method was also validated on an external MDS cohort. Results Tested on 2,043 patients in the GenomMed4All cohort, VAE-Surv achieved a median C-index of 0.78, outperforming classical approaches. In addition, the latent space enhanced the clustering performance compared to a traditional approach that applies the clustering directly to the input data. Compared to the WHO 2016 MDS subtypes, the analysis of the identified clusters showed that the proposed framework can capture existing clinical categorizations while also sug

关键词： Survival analysis Deep Learning variational autoencoder Myelodysplastic syndrome Genetic-based clustering

来源：评论

学校读者我要写书评

暂无评论

Advancing Agile Software Cost Estimation Through Data Synthesis: A Comparative Analysis of Five Generation Techniques

引用

IEEE ACCESS 2025年 13卷 63219-63236页

作者： Zhao, Xiaoyan Mansor, Zulkefli Razali, Rozilawati Nazri, Mohd Zakree Ahmad Xiong, Xin Univ Kebangsaan Malaysia Fac Informat Sci & Technol Bangi 43600 Selangor Malaysia Univ Kebangsaan Malaysia Ctr Software Technol & Management Bangi 43600 Selangor Malaysia Univ Kebangsaan Malaysia Ctr Artificial Intelligence Technol Bangi 43600 Selangor Malaysia

Agile has been used in software development for over 20 years and is the preferred development method for more than 85% of software companies. However, cost estimation in agile development remains a significant challenge. This is reflected in the fact that the accuracy of estimation still needs improvement, and most cost estimation techniques still rely on the team's experience and knowledge. While machine learning algorithms have performed better in this area, the lack of sufficient agile cost data hinders large-scale training and in-depth research. To address this issue, this study selected five data generation techniques-variational autoencoder (VAE), Wasserstein Generative Adversarial Network (WGAN), Synthetic Minority Over-sampling Technique for Nominal and Continuous Features (SMOTE-NC), Data Augmentation for Tabular Data (Augmentation), and Tabular Data Diffusion Probabilistic Models (TabDDPM)-based on the characteristics of agile cost data. Using cost data from 75 agile projects, these techniques were employed to generate three sets of data with sizes of 200, 500, and 1000. A performance evaluation model was created based on consistency, authenticity, diversity, and effectiveness to verify the performance of these generated data. The experimental results show that WGAN consistently scored 16 out of 20 points across all three data sets, excelling in data consistency and authenticity. SMOTE-NC and Augmentation Were followed. SMOTE-NC scored 15 out of 20 points for all data sizes and performed best in terms of effectiveness, with an MMRE of 88.16% and a PRED (0.2) of 84.5%. Augmentation performed the best when generating 1000 data points. These findings highlight the potential of data generation technologies, particularly WGAN, in enhancing agile cost estimation and providing guidance on selecting the appropriate amount of data. This lays a foundation for further development of machine learning algorithms in this field and offers valuable insights for other res

关键词： Costs Estimation Generative adversarial networks Training Agile software development Data models Hidden Markov models Data collection Data augmentation autoencoders Data generation technique software cost estimation agile software development variational autoencoder Wasserstein generative adversarial network synthetic minority over-sampling technique for nominal and continuous features data augmentation for tabular data tabular data diffusion probabilistic model

来源：评论

学校读者我要写书评

暂无评论

LPUWF-LDM: Enhanced latent diffusion model for precise late-phase UWF-FA generation on limited dataset

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 270卷

作者： Fang, Zhaojie Yu, Xiao Zhou, Guanyu Zhuang, Ke Chen, Yifei Ge, Ruiquan Wang, Changmiao Jia, Gangyong Wu, Qing Ye, Juan Nuliqiman, Maimaiti Xu, Peifang Elazab, Ahmed Hangzhou Dianzi Univ Hangzhou 310018 Peoples R China Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China Shenzhen Univ Sch Biomed Engn Shenzhen 518037 Peoples R China Misr Higher Inst Commerce & Comp Mansoura 35516 Egypt Zhejiang Univ Affiliated Hosp 2 Eye Ctr Zhejiang Prov Key Lab OphthalmolSch Med Hangzhou 310000 Peoples R China

Ultra-Wide-Field Fluorescein Angiography (UWF-FA) enables precise identification of ocular diseases using sodium fluorescein, which can be potentially harmful. Existing research has developed methods to generate UWF-FA from Ultra-Wide-Field Scanning Laser Ophthalmoscopy (UWF-SLO) to reduce the adverse reactions associated with injections. However, these methods have been less effective in producing high-quality late- phase UWF-FA, particularly in lesion areas and fine details. Two primary challenges hinder the generation of high-quality late-phase UWF-FA: the scarcity of paired UWF-SLO and early/late-phase UWF-FA datasets, and the need for realistic generation at lesion sites and potential blood leakage regions. This study introduces an improved latent diffusion model framework to generate high-quality late-phase UWF-FA from limited paired UWF images. To address the challenges as mentioned earlier, our approach employs a module utilizing Cross- temporal Regional Difference Loss, which encourages the model to focus on the differences between early and late phases. Additionally, we introduce a low-frequency enhanced noise strategy in the diffusion forward process to improve the realism of medical images. To further enhance the mapping capability of the variational autoencoder module, especially with limited datasets, we implement a gated convolutional encoder to extract additional information from conditional images. Our Latent Diffusion Model for Ultra-Wide-Field Late-Phase Fluorescein Angiography (LPUWF-LDM) effectively reconstructs fine details in late-phase UWF-FA and achieves state-of-the-art results compared to other existing methods when working with limited datasets. Our source code is available at: https://***/Tinysqua/LPUWF-LDM.

关键词： Diffusion model Loss enhancement Cross-modal generation Ultra-wide-field fundus photo variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A novel user preference-aware content caching algorithm in mobile edge networks

引用

JOURNAL OF SUPERCOMPUTING 2024年第9期80卷 12273-12296页

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

One of the most important strategies used to mitigate the adverse impacts of traffic growth on mobile networks is caching. By caching at the edge, the backhaul traffic load is reduced, and the quality of service for the user is increased. Developing an effective caching algorithm requires accurate prediction of the future popularity of the content, which is a challenging issue. In recent years, deep learning models have achieved high predictive accuracy due to advancements in data availability and increased computing power. In this paper, we present a caching algorithm called the user preference-aware content caching algorithm (UPACA). This algorithm is specifically designed for an edge content delivery platform where users can access content services provided by a remote content provider. UPACA operates in two steps. In the first step, the proposed collaborative filtering-based popularity prediction algorithm (CFPA) is used to predict future content popularities. CFPA utilizes a gated residual variational autoencoder collaborative filtering model to predict users' future preferences and calculate the future popularity of content. This algorithm considers the popularity of the content as well as the number and timing of content requests. Experimental results demonstrate that UPACA outperforms previous methods in terms of cache hit rates and user utilities.

关键词： Content caching Popularity prediction Deep learning variational autoencoder Collaborative filtering

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：