检索结果-内蒙古大学图书馆

Probabilistic feature extraction, dose statistic prediction and dose mimicking for automated radiation therapy treatment planning

引用

MEDICAL PHYSICS 2021年第9期48卷 4730-4742页

作者： Zhang, Tianfang Bokrantz, Rasmus Olsson, Jimmy KTH Royal Inst Technol Dept Math SE-10044 Stockholm Sweden RaySearch Labs Stockholm Sweden

Purpose We propose a general framework for quantifying predictive uncertainties of dose-related quantities and leveraging this information in a dose mimicking problem in the context of automated radiation therapy treatment planning. Methods A three-step pipeline, comprising feature extraction, dose statistic prediction and dose mimicking, is employed. In particular, the features are produced by a convolutional variational autoencoder and used as inputs in a previously developed nonparametric Bayesian statistical method, estimating the multivariate predictive distribution of a collection of predefined dose statistics. Specially developed objective functions are then used to construct a probabilistic dose mimicking problem based on the produced distributions, creating deliverable treatment plans. Results The numerical experiments are performed using a dataset of 94 retrospective treatment plans of prostate cancer patients. We show that the features extracted by the variational autoencoder capture geometric information of substantial relevance to the dose statistic prediction problem and are related to dose statistics in a more regularized fashion than hand-crafted features. The estimated predictive distributions are reasonable and outperforms a non-input-dependent benchmark method, and the deliverable plans produced by the probabilistic dose mimicking agree better with their clinical counterparts than for a non-probabilistic formulation. Conclusions We demonstrate that prediction of dose-related quantities may be extended to include uncertainty estimation and that such probabilistic information may be leveraged in a dose mimicking problem. The treatment plans produced by the proposed pipeline resemble their original counterparts well, illustrating the merits of a holistic approach to automated planning based on probabilistic modeling.

关键词： dose mimicking dose-volume histogram prediction knowledge-based planning mixture-of-experts uncertainty modeling variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

VAE-based Deep SVDD for anomaly detection

引用

NEUROCOMPUTING 2021年 453卷 131-140页

作者： Zhou, Yu Liang, Xiaomin Zhang, Wei Zhang, Linrang Song, Xing Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

Anomaly detection is an essential task for different fields in the real world. The imbalanced data and lack of labels make the task challenging. Deep learning models based on autoencoder (AE) have been applied to address the above difficulties successfully. However, in these AE-based deep methods, the AE-based model's optimization and the anomaly detector design are separated. Therefore, the latent representations in AE are less relevant for the anomaly detection task, which reduces the accuracy of anomaly detec-tion. A deep support vector data description based on variational autoencoder (Deep SVDD-VAE) is proposed in this paper to solve this problem. In the proposed model, VAE is used to reconstruct the input instances, while a spherical discriminative boundary is learned with the latent representations simulta-neously based on SVDD. Unlike existing AE-based methods, we seek the model parameters via the joint optimization of VAE and SVDD, which ensures the separability of the latent representations. Experimental results on MNIST, CIFAR-10, and GTSRB datasets show the effectiveness of Deep SVDD-VAE. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Anomaly detection variational autoencoder Deep support vector data description

来源：评论

学校读者我要写书评

暂无评论

Robustness Analysis of Deep Learning Models for Population Synthesis

引用

Transportation Research Procedia 2025年 82卷 3790-3806页

作者： Daniel Opoku Mensah Godwin Badu-Marfo Bilal Farooq Laboratory of Innovations in Transportation (LiTrans) Toronto Metropolitan University Toronto Canada

Deep generative models have become useful for synthetic data generation, particularly population synthesis. The models implicitly learn the probability distribution of a dataset and can draw samples from a distribution. Several models have been proposed, but their performance is only tested on a single cross-sectional sample. The implementation of population synthesis on single datasets is seen as a drawback that needs further studies to explore the robustness of the models on multiple datasets. While comparing with the real data can increase trust and interpretability of the models, techniques to evaluate deep generative models’ robustness for population synthesis remain underexplored. In this study, we present bootstrap confidence interval for the deep generative models, an approach that computes efficient confidence intervals for mean errors predictions to evaluate the robustness of the models to multiple datasets. Specifically, we adopt the tabular-based Composite Travel Generative Adversarial Network (CTGAN) and variational autoencoder (VAE), to estimate the distribution of the population, by generating agents that have tabular data using several samples over time from the same study area. The models are implemented on multiple travel diaries of Montréal Origin-Destination Survey of 2008, 2013, and 2018 and compare the predictive performance under varying sample sizes from multiple surveys. Results show that the predictive errors of CTGAN have narrower confidence intervals indicating its robustness to multiple datasets of the varying sample sizes when compared to VAE. Again, the evaluation of model robustness against varying sample size shows a minimal decrease in model performance with decrease in sample size. This study directly supports agent-based modelling by enabling finer synthetic generation of populations in a reliable environment.

关键词： Generative Adversarial Networks variational autoencoder population synthesis robustness

来源：评论

学校读者我要写书评

暂无评论

From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty

引用

SENSORS 2024年第22期24卷 7257页

作者： Wen, Haobin Zhang, Long Sinha, Jyoti K. Univ Manchester Dept Mech & Aerosp Engn Dynam Lab Manchester M13 9PL England Univ Manchester Dept Elect & Elect Engn Manchester M13 9PL England

Bearings are pivotal components of rotating machines where any defects could propagate and trigger systematic failures. Once faults are detected, accurately predicting remaining useful life (RUL) is essential for optimizing predictive maintenance. Although data-driven methods demonstrate promising performance in direct RUL prediction, their robustness and practicability need further improvement regarding physical interpretation and uncertainty quantification. This work leverages variational neural networks to model bearing degradation behind envelope spectra. A convolutional variational autoencoder for regression (CVAER) is developed to probabilistically predict RUL distributions with confidence measures. Enhanced average envelope spectra (AES) are used as network input for its physical robustness in bearing condition assessment and fault detection. The use of the envelope spectrum ensures that it contains only bearing-related information by removing other rotor-related frequencies, hence it improves the RUL prediction. Unlike traditional variational autoencoders, the probabilistic regressor and latent generator are formulated to quantify uncertainty in RUL estimates and learn meaningful latent representations conditioned on specific RUL. Experimental validations are conducted on vibration data collected using multiple accelerometers whose natural frequencies cover bearing resonance ranges to ensure fault detection reliability. Beyond conventional bearing diagnosis, envelope spectra are extended for statistical RUL prediction integrating physical knowledge of actual defect conditions. Comparative and ablation studies are conducted against benchmark models to demonstrate their effectiveness.

关键词： bearings remaining useful life vibration prognostics and health management variational autoencoder uncertainty quantification physical interpretation

来源：评论

学校读者我要写书评

暂无评论

Learning and Reusing Quadruped Robot Movement Skills from Biological Dogs for Higher-Level Tasks

引用

SENSORS 2024年第1期24卷 28页

作者： Wan, Qifeng Luo, Aocheng Meng, Yan Zhang, Chong Chi, Wanchao Zhang, Shenghao Liu, Yuzhen Zhu, Qiuguo Kong, Shihan Yu, Junzhi Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China Tencent Robot X Shenzhen 518057 Peoples R China Zhejiang Univ Inst Cyber Syst & Control Coll Control Sci & Engn Hangzhou 310027 Peoples R China Chinese Acad Sci Inst Software Sci & Technol Integrated Informat Syst Lab Beijing 100190 Peoples R China

In the field of quadruped robots, the most classic motion control algorithm is based on model prediction control (MPC). However, this method poses challenges as it necessitates the precise construction of the robot's dynamics model, making it difficult to achieve agile movements similar to those of a biological dog. Due to these limitations, researchers are increasingly turning to model-free learning methods, which significantly reduce the difficulty of modeling and engineering debugging and simultaneously reduce real-time optimization computational burden. Inspired by the growth process of humans and animals, from learning to walk to fluent movements, this article proposes a hierarchical reinforcement learning framework for the motion controller to learn some higher-level tasks. First, some basic motion skills can be learned from motion data captured from a biological dog. Then, with these learned basic motion skills as a foundation, the quadruped robot can focus on learning higher-level tasks without starting from low-level kinematics, which saves redundant training time. By utilizing domain randomization techniques during the training process, the trained policy function can be directly transferred to a physical robot without modification, and the resulting controller can perform more biomimetic movements. By implementing the method proposed in this article, the agility and adaptability of the quadruped robot can be maximally utilized to achieve efficient operations in complex terrains.

关键词： quadrupedal robots reinforcement learning motion imitation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

IF-TONIR: Iteration-free Topology Optimization based on Implicit Neural Representations

引用

COMPUTER-AIDED DESIGN 2024年 167卷

作者： Hu, Jiangbei He, Ying Xu, Baixin Wang, Shengfa Lei, Na Luo, Zhongxuan Jiangbei Ying Nanyang Technol Univ Singapore Singapore Dalian Univ Technol Dalian Peoples R China

Topology optimization holds great significance as a research topic in the field of mechanical engineering, aiming to design and optimize structures to achieve desired performance while adhering to specific constraints. However, its high computational complexity and iterative optimization process severely impact the efficiency, which presents substantial obstacles to its practical applications. To tackle this challenge, recent research is dedicated to the advancement of iteration-free topology optimization methods that leverage neural networks and deep learning, aiming to directly predict optimal structures through optimization problem configurations. In this paper, we propose IF-TONIR, a novel data-driven topology optimization method that utilizes implicit neural representations. Our approach employs signed distance fields to represent structures, offering compact and smooth representations that effectively eliminate the checkerboard phenomenon commonly observed in density-based methods. IF-TONIR leverages Conditional variational autoencoders, which use a CNN-based encoder and a MLP-based decoder to learn and reconstruct optimal structures. We employ the features extracted from physical information as conditions to guide the decoder in generating optimal structures that adhere to specific design domain shapes and boundary conditions. Furthermore, we propose the integration of a topological loss based on persistent homology to train the model. This loss function effectively penalizes the existence of structural disconnections in the reconstructed output, thereby enhancing the overall physical reliability of the generated structures. Various experiments have demonstrated that our iteration-free topology optimization method based on implicit representations can accurately identify regions of high strain energy and generate continuous structures with low compliance. The methods also holds the theoretical capability of outputting optimal structures at any desired resolut

关键词： Topology optimization Implicit neural representations variational autoencoder Persistent homology Topological loss

来源：评论

学校读者我要写书评

暂无评论

VAE-GAN3D: Leveraging image-based semantics for 3D zero-shot recognition

引用

IMAGE AND VISION COMPUTING 2024年 147卷

作者： Abdullah, Md Tahmeed Rahman, Sejuti Rahman, Shafin Islam, Md Fokhrul Univ Dhaka Dept Robot & Mechatron Engn Dhaka 1000 Bangladesh North South Univ Dept Elect & Comp Engn Dhaka 1229 Bangladesh

The current state of 3D zero-shot recognition falls short in performance when compared to its counterpart in 2D images. A major challenge is the absence of a robust feature extractor for 3D point cloud data. To overcome this challenge, a large dataset needs to be collected, processed, and fed into a deep-learning model capable of generating distinguishable features after training. To this end, we propose VAE-GAN3D, a model that uses a combination of a variational autoencoder (VAE) and a generative adversarial network (GAN) to supplement the small amount of data available for training with synthetic examples of classes. This allows for the underlying data distribution of large and complex data to be learned by the deep VAE network. When combined with a GAN, this network generates synthetic features that exhibit consistency in both seen and unseen classes. Furthermore, we notice that for tasks involving a small domain of classes, the existing text features do not contribute significantly to zero-shot learning. Therefore, we introduce image representation-based semantic features of classes, which improve the performance of zero-shot recognition for 3D objects. We assess the proposed model using three different datasets and present a technique for partitioning the RGB-D object dataset, which contains real -world objects, into seen and unseen classes. Our approach shows promising results in addressing the challenges of 3D zero-shot recognition and presents a novel solution for improving the accuracy of 3D point cloud recognition.

关键词： Zero-shot learning 3D object recognition Deep learning Generative adversarial network variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Robust errant beam prognostics with conditional modeling for particle accelerators

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2024年第1期5卷 015044页

作者： Rajput, Kishansingh Schram, Malachi Blokland, Willem Alanazi, Yasir Ramuhalli, Pradeep Zhukov, Alexander Peters, Charles Vilalta, Ricardo Thomas Jefferson Natl Accelerator Facil Newport News VA 23606 USA Oak Ridge Natl Lab Oak Ridge 37830 TN USA Univ Houston Dept Comp Sci Houston TX 77204 USA

Particle accelerators are complex and comprise thousands of components, with many pieces of equipment running at their peak power. Consequently, they can fault and abort operations for numerous reasons, lowering efficiency and science output. To avoid these faults, we apply anomaly detection techniques to predict unusual behavior and perform preemptive actions to improve the total availability. Supervised machine learning (ML) techniques such as siamese neural network models can outperform the often-used unsupervised or semi-supervised approaches for anomaly detection by leveraging the label information. One of the challenges specific to anomaly detection for particle accelerators is the data's variability due to accelerator configuration changes within a production run of several months. ML models fail at providing accurate predictions when data changes due to changes in the configuration. To address this challenge, we include the configuration settings into our models and training to improve the results. Beam configurations are used as a conditional input for the model to learn any cross-correlation between the data from different conditions and retain its performance. We employ conditional siamese neural network (CSNN) models and conditional variational auto encoder (CVAE) models to predict errant beam pulses at the spallation neutron source under different system configurations and compare their performance. We demonstrate that CSNNs outperform CVAEs in our application.

关键词： anomaly prediction siamese model variational autoencoder conditional SNS spallational neutron source particle accelerators

来源：评论

学校读者我要写书评

暂无评论

A Radar HRRP Target Recognition Method Based on Conditional Wasserstein VAEGAN and 1-D CNN 5th

A Radar HRRP Target Recognition Method Based on Conditional ...

引用

5th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： He, Jiaxing Wang, Xiaodan Xiang, Qian Air Force Engn Univ Xian Shaanxi Peoples R China

ISBN: (纸本)9783031189067;9783031189074

Radar high resolution range profile (HRRP) contains important structural features such as target size and scattering center distribution, which has attracted extensive attention in the field of radar target recognition. Aiming at the problems of class imbalance and insufficient data quality generated by vanilla GAN, an HRRP target recognition method based on improved conditional Wasserstein variational autoencoder Generative Adversarial Networks (CWVAEGAN) and one-dimensional convolutional neural network (CWVAEGAN-1DCNN) is proposed. CWVAEGAN class-balancing method introduces the concept of variational lower bound in VAE into GAN, and uses the encoded hidden vector instead of Gaussian noise as generator's input, which can significantly improve the fidelity of the generated samples and balance the class distribution of the dataset. The balanced dataset is used for classification through a standard 1D-CNN. The experimental results show that the samples generated by CWVAEGAN class-balancing method greatly improve the detection accuracy of 1D-CNN for minority classes, the fidelity of the samples generated by CWVAEGAN is higher than that of other class-balancing methods, and CWVAEGAN-1DCNN has strong HRRP target recognition ability.

关键词： High resolution range profile Class-balancing method Generative adversarial network variational autoencoder One-dimensional convolution neural network

来源：评论

学校读者我要写书评

暂无评论

Linking Check-in Data to Users on Location-aware Social Networks 19th

Linking Check-in Data to Users on Location-aware Social Netw...

引用

19th Pacific Rim International Conference on Artificial Intelligence (PRICAI)

作者： Li, Yujie Sang, Yu Chen, Wei Zhao, Lei Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi Jiangsu Peoples R China

ISBN: (纸本)9783031208614;9783031208621

Linking check-in data to their owners can benefit many downstream tasks, such as POI (Point of Interest) recommendation, destination prediction, and route planning, since we can obtain redundant information for each user after linking. Consequently, we formulate and investigate the novel problem CUL (Check-in-User Linking) in this work. Notably, the main difference between CUL and the existing problem TUL (Trajectory-User Linking) is that the trajectories used in TUL are continuous, while the check-in records in CUL are discrete. To tackle the problem CUL effectively, we develop a model entitled CULVAE (Check-in-User Linking via variational autoencoder). Firstly, a well-designed grid index is applied to organize the input check-in records. Then, an encoding module is developed to embed a user with corresponding grids. Next, a decoding module is proposed to generate a low-dimensional representation of each user. Finally, a multi-class classifier is proposed to link check-in records to users based on the output of the decoding module. We conduct extensive experiments on four real-world datasets, and the results demonstrate that our proposed model CULVAE performs better than all state-of-art approaches.

关键词： Check-in Data Social networks variational autoencoder

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：