检索结果-内蒙古大学图书馆

Complex system anomaly detection via learnable temporal-spatial graph with degradation tendency segmentation

ISA TRANSACTIONS 2024年 152卷 156-166页

作者： Han, Qinfeng Chen, Jinglong Wang, Jun Feng, Yong Xi An Jiao Tong Univ State Key Lab Mfg & Syst Engn Xian 710049 Peoples R China Xian Aerosp Prop Inst Sci & Technol Liquid Rocket Engine Lab Xian 710100 Peoples R China

To guarantee the safety and reliability of equipment operation, such as liquid rocket engine (LRE), carrying out system-level anomaly detection (AD) is crucial. However, current methods ignore the prior knowledge of mechanical system itself, and seldom unite the observations with the inherent relation in data tightly. Meanwhile, they neglect the weakness and nonindependence of system-level anomaly which is different from component fault. To overcome above limitations, we propose a separate reconstruction framework using worsened tendency for system-level AD. To prevent anomalous feature being attenuated, we first propose to divide single sample into two equal-length parts along the temporal dimension. And we maximize the mean maximum discrepancy (MMD) between feature segments to force encoders to learn normal features with different distributions. Then, to fully explore the multivariate time series, we model temporal-spatial dependence by temporal convolution and graph attention. Besides, a joint graph learning strategy is proposed to handle prior knowledge and data characteristics simultaneously. Finally, the proposed method is evaluated on two real multi-sensor datasets from LRE and the results demonstrate the effectiveness and potential of the proposed method on system-level AD.

关键词： Anomaly detection encoder-decoder Liquid rocket engine Multivariate time series Sample segmentation

来源：评论

学校读者我要写书评

暂无评论

An efficient transformer-based surrogate model with end-to-end training strategies for automatic history matching

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2024年 240卷

作者： Zhang, Jinding Kang, Jinzheng Zhang, Kai Zhang, Liming Liu, Piyang Liu, Xingyu Sun, Weijia Wang, Guangyao China Univ Petr East China Sch Petr Engn Qingdao Peoples R China Qingdao Univ Technol Sch Civil Engn Qingdao Peoples R China

In recent years, surrogate models have gained popularity as a tool to tackle the challenges presented by timeconsuming numerical simulations in automatic history matching (AHM). Although there are many different surrogate models designed to alleviate this issue, it is still challenging for most of them to handle the high dimensionality and strong non-linearity in reservoir models and dynamic production data. Inspired by the rapid development of Transformer, we propose a novel hybrid hierarchical Vision Transformer (HHVT) approach for history matching, which utilizes a unified architecture to predict production data for specific physical fields with an end-to-end strategy. For predicting the production data of wells, the Transformer supports parallelism computation among multiple timesteps, which shows more superiority than traditional recurrent neural networks. Specifically, our approach constructs a novel encoder-decoder Transformer architecture to learn the implicit features of high-level spatial parameters to match the features of time-series production data. With this architecture, HHVT achieves fast training and inference, which is suitable for large-scale datasets and highdimensional features. The proposed HHVT model is integrated with a multimodal optimization algorithm to find history-matching solutions. We first validated the effect of hyperparameters of HHVT on a simple 2D reservoir. Moreover, the proposed method was verified on the complex 3D Brugge model. The results demonstrate that the training speed of the Transformer-based model is approximately twice as fast as the surrogates based on convolutional and recurrent neural networks. The proposed HHVT also shows better prediction accuracy in two cases, compared with other surrogate models, which enhances the applicability of surrogate-based history-matching methods in large-scale complex reservoir scenarios.

关键词： History matching Surrogate model Transformer encoder-decoder Multimodal algorithm

来源：评论

学校读者我要写书评

暂无评论

Blind Source Separation of Electromagnetic Signals Based on Swish-Tasnet

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2024年第10期43卷 6620-6636页

作者： Chen, Yang Liu, Jinming Mao, Jian Pang, Xiaoyu Jimei Univ Sch Comp Yinjiang Rd Xiamen 361021 Fujian Peoples R China

Digital devices may leak electromagnetic signals containing important information during operation, posing a risk of information leakage. In order to evaluate the safety level of the equipment, it is necessary to detect electromagnetic leakage signals and separate important information. Traditional methods such as ICA and IVA have limited performance when the signal input is smaller than the output. In recent years, signal separation technology based on deep learning has developed rapidly, demonstrating effective separation performance and potential in signal separation. For the separation of electromagnetic signals, we propose a blind source separation method for electromagnetic signals based on Swish-Tasnet. This method improves the time convolutional network structure and introduces the Swish activation function to optimize the internal functions and stacking layers of the model, thereby achieving efficient blind source separation of electromagnetic signals. The experiment evaluated the separation performance through SISDR, SDR, and SAR, and the results showed that this method performs excellently in reducing background noise interference and accurately separating signal sources from mixed signals. Swish-Tasnet not only provides a practical and effective technical means for electromagnetic signal leakage separation, but also brings substantial progress to the field of equipment information security assessment research. This method has broad prospects in practical applications and is worth further research and promotion.

关键词： Source separation Electromagnetic signals Deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Solving a 3D bin packing problem with stacking constraints

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2024年 188卷

作者： Zhu, Weiwang Chen, Sheng Dai, Min Tao, Jiping Xiamen Univ Sch Aerosp Engn Xiamen Fujian Peoples R China Xiamen Univ Key Lab Big Data Intelligent Anal & Decis making F Xiamen Fujian Peoples R China

We consider a novel variant of the three-dimensional bin packing problem (3DBPP) arising from a maritime shipping port. Unlike the classical bin packing problem, our 3DBPP requires all items to be stacked vertically during the packing process. To tackle this problem effectively, we divide it into two subproblems: the stack packing problem (SPP) and the two-dimensional bin packing problem (2DBPP). We first formulate the SPP as an integer programming model to minimize the total bottom area of the stacks, which is further solved by a branch -and -price method. Then, in the 2DBPP, to pack all stacks into a minimum number of bins, we follow the left -down most extreme point placement strategy. An encoder-decoder model was developed to optimize the packing sequence and orientation of the stacks simultaneously. Industrial instances from shipping ports were collected and extended. The computational results show that our two -stage algorithm performs well in solving the stacking -constrained 3DBPP.

关键词： Three-dimensional bin packing problem Stacking constraints Branch-and-price encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Lower Limb Torque Prediction for Sit-To-Walk Strategies Using Long Short-Term Memory Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2024年 32卷 3977-3986页

作者： Perera, Chamalka Kenneth Gopalai, Alpha. A. Gouwanda, Darwin Ahmad, Siti. A. Teh, Pei-Lee Monash Univ Sch Engn Subang Jaya 47500 Selangor Malaysia Univ Putra Malaysia Fac Engn Serdang 43400 Malaysia Monash Univ Sch Business Subang Jaya 47500 Selangor Malaysia

Joint torque prediction is crucial when investigating biomechanics, evaluating treatments, and designing powered assistive devices. Controllers in assistive technology require reference torque trajectories to set the level of assistance for a patient during rehabilitation or when aiding essential daily tasks such as sit-to-walk (STW). STW itself can be generalized into strategies based on individual needs and movement patterns. In this study, three long short-term memory (LSTM) neural networks were empirically trained for hip and knee torque prediction considering these STW strategies and subject anthropometry. The hip and knee are the drivers of STW, while the network architectures were selected for recognizing temporal and spatial relationships. Performance of the LSTMs were compared and evaluated against the STW strategies to accurately generate strategy-specific and user-oriented torque. As such, train and test STW data were obtained from 65 subjects across three age groups: young, middle-aged, and older adults (19-73 years). Model inputs were hip and knee angles with horizontal center of mass velocity, while windowing allowed the LSTMs to dynamically adapt to real-time changes in STW transitions. The encoder-decoder LSTM showcased optimal performance with robust recognition of temporal features. It produced significantly (P <0.05) low hip and knee root mean square error (0.24 f 0.07 and 0.15 f 0.02 Nm/kg), strong Spearman's correlation (93.43 f 2.86 and 84.83 f 2.96%) and good intraclass correlation coefficients (greater than 0.75), demonstrating model reliability. Hence, this network predicts strategy and user oriented reference torques for personalized controllers in assistive devices, with more natural application of assistance.

关键词： Torque Hip Knee Mathematical models Long short term memory Biological system modeling Biomechanics Assistive devices Training Predictive models encoder-decoder CNN-LSTM strategy classification torque controllers assistive devices

来源：评论

学校读者我要写书评

暂无评论

A Spatial-Temporal Graph Model for Pronunciation Feature Prediction of Chinese Poetry

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第12期34卷 10294-10308页

作者： Wang, Qing Liu, Weiping Wang, Xiumei Chen, Xinghong Chen, Guannan Wu, Qingxiang Fujian Normal Univ Minist Educ Key Lab Optoelect Sci & Technol Med Fuzhou 350007 Peoples R China Fujian Normal Univ Fujian Prov Key Lab Photon Technol Fuzhou 350007 Peoples R China

With the development of artificial intelligence, speech recognition and prediction have become one of the important research domains with wild applications, such as intelligent control, education, individual identification, and emotion analysis. Chinese poetry reading contains rich features of continuous pronunciations, such as mood, emotion, rhythm schemes, lyric reading, and artistic expression. Therefore, the prediction of the pronunciation characteristics of a Chinese poetry reading is the significance for the presentation of high-level machine intelligence and has the potential to create a high-level intelligent system for teaching children to read Tang poetry. Mel frequency cepstral coefficient (MFCC) is currently used to present important speech features. Due to the complexity and high degree of nonlinearity in poetry reading, however, there is a tough challenge facing accurate pronunciation feature prediction, that is, how to model complex spatial correlations and time dynamics, such as rhyme schemes. As for many current methods, they ignore the spatial and temporal characteristics in MFCC presentation. In addition, these methods are subjected to certain limitations on prediction for long-term performance. In order to solve these problems, we propose a novel spatial-temporal graph model (STGM-MHA) based on multihead attention for the purpose of pronunciation feature prediction of Chinese poetry. The STGM-MHA is designed using an encoder-decoder structure. The encoder compresses the data into a hidden space representation, while the decoder reconstructs the hidden space representation as output. In the model, a novel gated recurrent unit (GRU) module (AGRU) based on multihead attention is proposed to extract the spatial and temporal features of MFCC data effectively. The evaluation comparison of our proposed model versus state-of-the-art methods in six datasets reveals the clear advantage of the proposed model.

关键词： Mel frequency cepstral coefficient Predictive models Rhythm Feature extraction Analytical models Data models Computational modeling AGRU Chinese poetry encoder-decoder graph modeling Mel frequency cepstral coefficient (MFCC) pronunciation features spatial-temporal graph model (STGM-MHA)

来源：评论

学校读者我要写书评

暂无评论

FasterMDE: A real-time monocular depth estimation search method that balances accuracy and speed on the edge

引用

APPLIED INTELLIGENCE 2023年第20期53卷 24566-24586页

作者： ZiWen, Dou YuQi, Li Dong, Ye Harbin Inst Technol Sch Instrumentat Sci & Engn 92 Xidazhi St Harbin 150001 Peoples R China

Monocular depth estimation (MDE) is critical in enabling intelligent autonomous systems and has received considerable attention in recent years. Achieving both low latency and high accuracy in MDE is desirable but challenging to optimize, especially on edge devices. In this paper, we present a novel approach to balancing speed and accuracy in MDE on edge devices. We introduce FasterMDE, an efficient and fast encoder-decoder network architecture that leverages a multiobjective neural architecture search method to find the optimal encoder structure for the target edge. Moreover, we incorporate a neural window fully connected CRF module into the network as the decoder, enhancing fine-grained depth prediction based on coarse depth and image features. To address the issue of bad "local minimums" in the multiobjective neural architecture search, we propose a new approach for automatically learning the weights of subobjective loss functions based on uncertainty. We also accelerate the FasterMDE model using TensorRT and implement it on a target edge device. The experimental results demonstrate that FasterMDE achieves a better balance of speed and accuracy on the KITTI and NYUv2 datasets compared to previous methods. We validate the effectiveness of the proposed method through an ablation study and verify the real-time monocular depth estimation performance of FasterMDE in realistic scenarios. On the KITTI dataset, the FasterMDE model achieves a high frame rate of 555.55 FPS with 9.1% Abs Rel on a single NVIDIA Titan RTX GPU and 14.46 FPS on the NVIDIA Jetson Xavier NX.

关键词： Monocular depth estimation Real-time Edge computing Multi-objective neural architecture search encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation by Using Down-Sampling and Subpixel Convolution: DSSC-UNet

引用

Computers, Materials & Continua 2023年第4期75卷 683-696页

作者： Young-Man Kwon Sunghoon Bae Dong-Keun Chung Myung-Jae Lim Department of Medical IT Eulji University553Sanseong-daeroSujeong-guSeongnam-siGyeonggi-do13135Korea

Recently, semantic segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based semantic segmentation, the U-Net with convolutionalencoder-decoder architecture is a representative model which is proposed forimage segmentation in the biomedical field. It used max pooling operationfor reducing the size of image and making noise robust. However, instead ofreducing the complexity of the model, max pooling has the disadvantageof omitting some information about the image in reducing it. So, thispaper used two diagonal elements of down-sampling operation instead ofit. We think that the down-sampling feature maps have more informationintrinsically than max pooling feature maps because of keeping the Nyquisttheorem and extracting the latent information from them. In addition,this paper used two other diagonal elements for the skip connection. Indecoding, we used Subpixel Convolution rather than transposed convolutionto efficiently decode the encoded feature maps. Including all the ideas, thispaper proposed the new encoder-decoder model called Down-Sampling andSubpixel Convolution U-Net (DSSC-UNet). To prove the better performanceof the proposed model, this paper measured the performance of the UNetand DSSC-UNet on the Cityscapes. As a result, DSSC-UNet achieved89.6% Mean Intersection OverUnion (Mean-IoU) andU-Net achieved 85.6%Mean-IoU, confirming that DSSC-UNet achieved better performance.

关键词： Semantic segmentation encoder-decoder U-Net DSSC-UNet subpixel convolution down-sampling

来源：评论

学校读者我要写书评

暂无评论

Brain tumor segmentation with deep learning: Current approaches and future perspectives

引用

JOURNAL OF NEUROSCIENCE METHODS 2025年 418卷 110424页

作者： Verma, Akash Yadav, Arun Kumar NIT Hamirpur Dept Comp Sci & Engn Hamirpur HP India

Background: Accurate brain tumor segmentation from MRI images is critical in the medical industry, directly impacts the efficacy of diagnostic and treatment plans. Accurate segmentation of tumor region can be challenging, especially when noise and abnormalities are present. Method: This research provides a systematic review of automatic brain tumor segmentation techniques, with a specific focus on the design of network architectures. The review categorizes existing methods into unsupervised and supervised learning techniques, as well as machine learning and deep learning approaches within supervised techniques. Deep learning techniques are thoroughly reviewed, with a particular focus on CNN-based, U-Net-based, transfer learning-based, transformer-based, and hybrid transformer-based methods. fScope and Coverage: This survey encompasses a broad spectrum of automatic segmentation methodologies, from traditional machine learning approaches to advanced deep learning frameworks. It provides an in-depth comparison of performance metrics, model efficiency, and robustness across multiple datasets, particularly the BraTS dataset. The study further examines multi-modal MRI imaging and its influence on segmentation accuracy, addressing domain adaptation, class imbalance, and generalization challenges. Comparison with existing methods: The analysis highlights the current challenges in Computer-aided Diagnostic (CAD) systems, examining how different models and imaging sequences impact performance. Recent advancements in deep learning, especially the widespread use of U-Net architectures, have significantly enhanced medical image segmentation. This review critically evaluates these developments, focusing the iterative improvements in U-Net models that have driven progress in brain tumor segmentation. Furthermore, it explores various techniques for improving U-Net performance for medical applications, focussing on its potential for improving diagnostic and treatment planning proced

关键词： Deep learning U-Net Brain tumor segmentation encoder-decoder MRI

来源：评论

学校读者我要写书评

暂无评论

Recent developments in denoising medical images using deep learning: An overview of models, techniques, and challenges

引用

MICRON 2024年 180卷 103615页

作者： Nazir, Nahida Sarwar, Abid Saini, Baljit Singh Lovely Profess Univ Punjab Phagwara Punjab India Univ Jammu Jammu India

Medical imaging plays a critical role in diagnosing and treating various medical conditions. However, interpreting medical images can be challenging even for expert clinicians, as they are often degraded by noise and artifacts that can hinder the accurate identification and analysis of diseases, leading to severe consequences such as patient misdiagnosis or mortality. Various types of noise, including Gaussian, Rician, and Salt -pepper noise, can corrupt the area of interest, limiting the precision and accuracy of algorithms. Denoising algorithms have shown the potential in improving the quality of medical images by removing noise and other artifacts that obscure essential information. Deep learning has emerged as a powerful tool for image analysis and has demonstrated promising results in denoising different medical images such as MRIs, CT scans, PET scans, etc. This review paper provides a comprehensive overview of state-of-the-art deep learning algorithms used for denoising medical images. A total of 120 relevant papers were reviewed, and after screening with specific inclusion and exclusion criteria, 104 papers were selected for analysis. This study aims to provide a thorough understanding for researchers in the field of intelligent denoising by presenting an extensive survey of current techniques and highlighting significant challenges that remain to be addressed. The findings of this review are expected to contribute to the development of intelligent models that enable timely and accurate diagnoses of medical disorders. It was found that 40% of the researchers used models based on Deep convolutional neural networks to denoise the images, followed by encoder -decoder (18%) and other artificial intelligence -based techniques (15%) (Like DIP, etc.). Generative adversarial network was used by 12%, transformer -based approaches (13%) and multilayer perceptron was used by 2% of the researchers. Moreover, Gaussian noise was present in 35% of the images, followed by s

关键词： Deep Learning Denoising Medical Images Convolutional Neural Network encoder-decoder Generative Adversarial Network

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：