检索结果-内蒙古大学图书馆

A multi-modal vehicle trajectory prediction framework via conditional diffusion model: A coarse-to-fine approach

KNOWLEDGE-BASED SYSTEMS 2023年 280卷

作者： Li, Zhiyuan Liang, Huawei Wang, Hanqi Zheng, Xiaokun Wang, Jian Zhou, Pengfei Chinese Acad Sci Hefei Inst Phys Sci Hefei 230031 Peoples R China Univ Sci & Technol China Hefei 230026 Peoples R China Anhui Engn Lab Intelligent Driving Technol & Appli Hefei 230031 Peoples R China Chinese Acad Sci Innovat Res Inst Robot & Intelligent Mfg Hefei 230031 Peoples R China

Accurate prediction of the future motion of surrounding vehicles is crucial for ensuring the safety of motion planning in autonomous vehicles. However, it is challenging to perform because of the complex interactions between vehicles. In this study, we propose a novel multi-modal vehicle trajectory prediction framework that utilizes a coarse-to-fine approach by first generating initial trajectory proposals with a conditional variational autoencoder (CVAE) and then refining them using the conditional diffusion model. We first address the problems of data sparsity and irregularity by converting the trajectory coordinates to the Frenet coordinate system. To enable the model to better distinguish between different features, we employ a temporal encoder to extract trajectory features and a long short-term memory (LSTM) network to extract lane features. The target lane evaluator is utilized to calculate the attention weights for each lane candidate, thereby generating more deterministic future trajectories. We then use the CVAE to generate initial multiple trajectory proposals based on the surrounding scene context and the trajectory features of the target vehicle. Finally, we formulate the trajectory refinement task as a reverse process of the conditional diffusion model, which effectively enhances the multi-modal trajectory proposals. Experiments conducted on Argoverse and nuScenes demonstrate that our method outperforms state-of-the-art methods in some evaluation metrics while achieving the optimal trade-off between predictive accuracy and efficiency. Field experiments conducted in urban environments further validate the effectiveness of the proposed approach. (c) 2023 Elsevier B.V. All rights reserved.

关键词： Trajectory prediction Autonomous vehicles variational autoencoder Diffusion model

来源：评论

学校读者我要写书评

暂无评论

Characterization of porous membranes using artificial neural networks

引用

ACTA MATERIALIA 2023年 253卷

作者： Zhao, Yinghan Altschuh, Patrick Santoki, Jay Griem, Lars Tosato, Giovanna Selzer, Michael Koeppe, Arnd Nestler, Britta Karlsruhe Inst Technol Inst Appl Mat Microstruct Modelling & Simulat Str Forum 7 D-76131 Karlsruhe Germany Karlsruhe Univ Appl Sci Inst Digital Mat Moltkestr 30 D-76133 Karlsruhe Germany

Porous membranes have been utilized intensively in a wide range of fields due to their special characteristics and a rigorous characterization of their microstructures is crucial for understanding their properties and improving the performance for target applications. A promising method for the quantitative analysis of porous structures leverages the physics-based generation of porous structures at the pore scale, which can be validated against real experimental microstructures, followed by building the process-structure-property relationships with data-driven algorithms such as artificial neural networks. In this study, a variational autoencoder (VAE) neural network model is used to characterize the 3D structural information of porous materials and to represent them with low-dimensional latent variables, which further model the structure-property relationship and solve the inverse problem of process-structure linkage combined with the Bayesian optimization method. Our methods provide a quantitative way to learn structural descriptors in an unsupervised manner which can characterize porous microstructures robustly.

关键词： Porous membranes Microstructure characterization Machine learning variational autoencoder Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Conditional feature disentanglement learning for anomaly detection in machines operating under time-varying conditions

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2023年第1期191卷

作者： Zhou, Haoxuan Lei, Zihao Zio, Enrico Wen, Guangrui Liu, Zimin Su, Yu Chen, Xuefeng Xi An Jiao Tong Univ Sch Mech Engn Xian 710049 Peoples R China MINES ParisPSL Univ Ctr Rech Risques & Crises CRC Sophia Antipolis France Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Peoples R China Politecn Milan Energy Dept Via Masa 34 I-20156 Milan Italy

Anomaly detection(AD) is an important task of machines' condition monitoring(CM). Data-driven policies can be used in a more intelligent way to achieve anomaly detection and effectively avoid the introduction of expert experience, thus having a broader scope of application. However, Machines like wind turbines often work under time-varying operating conditions(TVOCs), and the performance of traditional data-driven AD methods is significantly degraded because TVOCs can lead to "false alarms" and "missed alarms" in the implementation due to the monitoring data shifting caused by variation of operating conditions(OCs). To address this problem, this paper proposes a novel conditional feature disentanglement learning framework to solve the distur-bance in AD on account of entanglement between OCs and health states. The proposed approach performs conditional self-supervised AD by utilizing the variational autoencoder(VAE) and OCs information. Then, a feature disentanglement conditional VAE(FDCVAE) network is developed to realize the disentanglement of OCs and health states. Subsequently, An anomaly indicator(ANI) is constructed by the dimension reduction of the disentangled health state-related feature and combined with the statistics anomaly threshold for AD. Experiments on accelerated fatigue degradation of bearings under TVOCs validate the effectiveness of the proposed method and further demonstrate the superiority of the constructed ANI in eliminating TVOC interference, compared with common fault mechanisms-based and data-driven ANI. The proposed method not only achieves anomaly detection under TVOCs but also provides a new way for representation learning under variable working conditions in machine health management applications in the foreseeable future.

关键词： Time-varying operating conditions Anomaly detection Machines Feature disentanglement learning variational autoencoder Bearing

来源：评论

学校读者我要写书评

暂无评论

Generative geomodeling based on flow responses in latent space

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2022年第0期211卷 110177-110177页

作者： Jo, Suryeom Ahn, Seongin Park, Changhyup Kim, Jaejun Korea Inst Geosci & Mineral Resources GeoICT Convergence Res Team Daejeon 34132 South Korea Kangwon Natl Univ Dept Energy & Resources Engn Chunchon 24341 Kangwon South Korea Seoul Natl Univ Dept Energy Syst Engn Seoul 08826 South Korea

This paper presents a new deep-learning-based generative method applicable to history matching without an inverse scheme. Multiple-point geostatistics is used to construct a prior population stochastically. A convolutional variational autoencoder (VAE) with probabilistic latent space is trained as the generative method, and kmeans clustering, nondominated sorting, and multilevel geomodel generations are performed based on flow responses. The applicability of the developed workflow was confirmed using a waterflooding problem with multiple wells in fluvial channel reservoirs. The VAE generates new geomodels based on the latent features and builds equiprobable models neighboring the representative models that reflect the observed production performance. The geomodels match the oil production profiles reliably as the steps progress and accurately forecast the water breakthrough time and liquid production trajectories. The density map of plausible geomodels explains reasonably the uncertainty of channel connectivity. The structural similarity index confirms that the generated geomodels become similar to the target reservoir and thus that the developed VAE-based framework creates geomodels that preserve geological realism. This proposed method involves relatively less time-consuming simulations without any inverse or optimization processes;nonetheless, it generates plausible geomodels in dimensionality-reduced latent space. The study methods and findings are thus applicable to scale-variant data integration and uncertainty assessment.

关键词： Generative model variational autoencoder Latent space History matching Uncertainty Flow response

来源：评论

学校读者我要写书评

暂无评论

Improved history matching of channelized reservoirs using a novel deep learning-based parametrization method

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2023年 229卷

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

Most of the geological parametrization techniques used in history matching of sub-surface formations including the deep learning-based methods could not capture the non-linear and non-Gaussian dependencies and were limited to facies realizations. This paper proposes a novel method for parametrization of permeability realizations using ConvLSTM layers to build a variational autoencoder, named ConvLSTM-VAE, for the first time in this study. Since geological layers of the reservoir models are deposited during different periods, reservoir properties have a spatial distribution along the third dimension that can be regarded as a temporal distribution. To evaluate the proposed method, its parametrization results were compared with those of 3D convolutional VAE (3DCNN-VAE), which was recently used in the literature. Quantitative and visual results showed that the proposed method was far better than the 3DCNN-VAE, where the train, validation, and test losses obtained by the ConvLSTM-VAE was 0.3663, 0.3695, and 0.3710, and by the 3DCNN-VAE was 0.3980, 0.4086, 0.4095, respectively. In addition, history matching with parametrized realizations by the ConvLSTM-VAE could preserve the geologic realism in the conditioned realizations with significantly low data mismatch errors in the historical and prediction phases;however, history matching with 3DCNN-VAE parametrization and without any parametrization could not preserve the geologic realism. Finally, this paper can guide reservoir engineers to select a proper parametrization method for highly channelized, 3D, complex reservoirs with non-linear and non-Gaussian distribution of the uncertain parameters.

关键词： Data assimilation variational autoencoder History matching Deep learning Geological parametrization

来源：评论

学校读者我要写书评

暂无评论

GenRadar: Self-Supervised Probabilistic Camera Synthesis Based on Radar Frequencies

引用

IEEE ACCESS 2021年 9卷 148994-149042页

作者： Ditzel, Carsten Dietmayer, Klaus Inst Measurement Control & Microtechnol D-89081 Ulm Germany

Autonomous systems require a continuous and dependable environment perception for navigation and decision-making, which is best achieved by combining different sensor types. Radar continues to function robustly in compromised circumstances in which cameras become impaired, guaranteeing a steady inflow of information. Yet, camera images provide a more intuitive and readily applicable impression of the world. This work combines the complementary strengths of both sensor types in a unique self-learning fusion approach for a probabilistic scene reconstruction in adverse surrounding conditions. After reducing the memory requirements of both high-dimensional measurements through a decoupled stochastic self-supervised compression technique, the proposed algorithm exploits similarities and establishes correspondences between both domains at different feature levels during training. Then, at inference time, relying exclusively on radio frequencies, the model successively predicts camera constituents in an autoregressive and self-contained process. These discrete tokens are finally transformed back into an instructive view of the respective surrounding, allowing to visually perceive potential dangers for important tasks downstream.

关键词： Radar Cameras Radar imaging Robot sensing systems Probabilistic logic Task analysis Signal processing algorithms Radar signal processing computer vision sensor fusion deep learning machine learning variational autoencoder self-supervised learning annotation-free learning scene understanding

来源：评论

学校读者我要写书评

暂无评论

Improving disentanglement in variational auto-encoders via feature imbalance-informed dimension weighting

引用

KNOWLEDGE-BASED SYSTEMS 2024年 296卷

作者： Liu, Yue Yu, Zhenyao Liu, Zitu Yu, Ziyi Yang, Xinyan Li, Xingyue Guo, Yike Liu, Qun Wang, Guoyin Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Shanghai Engn Res Ctr Intelligent Comp Syst Shanghai 200444 Peoples R China Imperial Coll London Dept Comp London SW7 2AZ England Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Chongqing 400065 Peoples R China Shanghai Univ Coll Sci Shanghai 200444 Peoples R China

Using variational Auto-Encoder (VAE) to learn disentangled representation holds great promise. But there is a feature imbalance in the learning process of VAEs, and the model usually concentrates on the learning of some dimensions at the expense of others. Instead of attempting to rectify it, we exploit feature imbalance to propose a Dimension Weighting method that can boost the disentanglement effect of VAE-based models. In order to conduct disentanglement learning under a fixed size of the latent space, the intrinsic dimension of raw data is estimated by a Dimension Number Estimator and set as the latent space size. Then, leveraging the feature imbalance, a Dimension Importance Evaluator is constructed to separate each dimension in the latent variable into important, unimportant, and general dimensions. By exerting different learning pressures on specific dimensions, we further optimize the variational lower bound of model and retrain it, thus promoting the disentanglement of important dimensions. The experiments on four benchmark datasets show that the Dimension Weighting can further improve the disentangling effect without compromising model performance, and in approximately 80% of cases, the results in disentangling metric evaluation experiments achieve better disentangling scores than the original models. This reveals that not all dimensions of the latent variables are equally influential. By focusing on the crucial dimensions within the latent representation, the model can achieve better performance.

关键词： variational autoencoder Latent space Disentangled representation Dimension weighting

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Discovery of 2D Materials for Solar Water Splitting

引用

FRONTIERS IN MATERIALS 2021年 8卷

作者： Agarwal, Abhishek Goverapet Srinivasan, Sriram Rai, Beena Tata Consulatncy Serv Ltd TCS Res Pune Maharashtra India

Hydrogen economy, wherein hydrogen is used as the fuel in the transport and energy sectors, holds significant promise in mitigating the deleterious effects of global warming. Photocatalytic water splitting using sunlight is perhaps the cleanest way of producing the hydrogen fuel. Among various other factors, widespread adoption of this technology has mainly been stymied by the lack of a catalyst material with high efficiency. 2D materials have shown significant promise as efficient photocatalysts for water splitting. The availability of open databases containing the "computed" properties of 2D materials and advancements in deep learning now enable us to do "inverse" design of these 2D photocatalysts for water splitting. We use one such database (Jain et al., ACS Energ. Lett. 2019, 4, 6, 1410-1411) to build a generative model for the discovery of novel 2D photocatalysts. The structures of the materials were converted into a 3D image-based representation that was used to train a cell, a basis autoencoder and a segmentation network to ascertain the lattice parameters as well as position of atoms from the images. Subsequently, the cell and basis encodings were used to train a conditional variational autoencoder (CVAE) to learn a continuous representation of the materials in a latent space. The latent space of the CVAE was then sampled to generate several new 2D materials that were likely to be efficient photocatalysts for water splitting. The bandgap of the generated materials was predicted using a graph neural network model while the band edge positions were obtained via empirical correlations. Although our generative modeling framework was used to discover novel 2D photocatalysts for water splitting reaction, it is generic in nature and can be used directly to discover novel materials for other applications as well.

关键词： generative modeling variational autoencoder inverse design photocatalysts water splitting reaction

来源：评论

学校读者我要写书评

暂无评论

Incremental learning model for dynamical identification and classification of abnormal vibration in operational underground facilities

引用

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY 2023年第1期140卷

作者： Chai, Fu Zhou, Biao Xie, Xiongyao Zhang, Zixin Wang, Chen Tongji Univ Key Lab Geotech & Underground Engn Minist Educ Shanghai 200092 Peoples R China Tongji Univ Dept Geotech Engn Shanghai 200092 Peoples R China State Grid Shanghai Municipal Elect Power Co Shanghai 200072 Peoples R China

Underground infrastructures are rapidly growing in size and complexity. However, their operations are affected by several hazards, including hidden structural deterioration and effects of random external constructions. Dynamic monitoring of these hazards is essential to provide early warning. We propose a vibration-based self-supervised incremental learning model for dynamic monitoring of emerging operational threats by recognizing abnormal responses. The model comprises teacher and student models based on a variational autoencoder (VAE) with a metric function. When the teacher model detects a new category of abnormal vibration, the student model is trained to recognize this abnormality through sample rehearsals and knowledge distillations. Subsequently, it becomes the teacher model for the next round of incremental learning. We demonstrate through a case study that catastrophic forgetting can be avoided and memory consumption can be reduced during dynamic network updates. Moreover, the use of a metric function in the VAE increases the vibration identification accuracy.

关键词： Underground infrastructure Monitoring Incremental learning variational autoencoder Metric function

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network-based Optimization Framework for Safety Evacuation Route during Toxic Gas Leak Incidents

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2022年第PartA期218卷 108102-108102页

作者： Seo, Seung-Kwon Yoon, Young-Gak Lee, Ju-sung Na, Jonggeol Lee, Chul-Jin Chung Ang Univ Sch Chem Engn & Mat Sci 84 Heukseok Ro Seoul 06979 South Korea Samsung Engn Proc Engn Team Seoul 05288 South Korea Ewha Womans Univ Dept Chem Engn & Mat Sci Grad Program Syst Hlth Sci & Engn Seoul 03760 South Korea Chung Ang Univ Dept Intelligent Energy & Ind Seoul 06979 South Korea

Evacuation planning is important for reducing casualties in toxic gas leak incidents. However, most evacuation plans are too qualitative to be applied to unexpected practical situations. Here, we suggest an evacuation route proposal system based on a quantitative risk evaluation that provides the safest route for individual evacuees by predicting dynamic gas dispersion with a high accuracy and short calculation time. Detailed evacuation scenarios, including weather conditions, leak intensity, and evacuee information, were considered. The proposed system evaluates the quantitative risk in the affected area using a deep neural network surrogate model to determine optimal evacuation routes by integer programming. The surrogate model was trained using data from computational fluid dynamics simulations. A variational autoencoder was applied to extract the geometric features of the affected area. The predicted risk was combined with linearized integer programming to determine the optimal path in a predefined road network. A leak scenario of an ammonia gas pipeline in a petrochemical complex was used for the case study. The results show that the developed model offers the safest route within a few seconds with minimum risk. The developed model was applied to a sensitivity analysis to determine variable influences and safe shelter locations.

关键词： Evacuation Toxic gas leak Computational fluid dynamics Surrogate model 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：