检索结果-内蒙古大学图书馆

Road surface classification using accelerometer and speed data: evaluation of a convolutional neural network model

neural COMPUTING & APPLICATIONS 2023年第19期35卷 14183-14194页

作者： Sabapathy, Ashwin Biswas, Avik Danlaw Inc 1 PrimparkPrimrose Rd Bangalore 560025 India

Assessing the quality of road surfaces for maintenance has typically been an expensive exercise for local government agencies. This paper evaluates the feasibility of using accelerometer and speed data collected from on-board diagnostic (OBD-II) devices and labelled using the PASER system of road classification to classify road quality and identify poor stretches. An ordinal logistic model and a support vector machine (SVM) classifier were first trained on features created from raw data. The SVM and an artificial neural network (ANN) were then trained separately on the raw data parameters followed by a convolutional neural network (CNN) model. All models have comparable results in terms of overall classification accuracy on validation datasets (around 67%) but the ANN and CNN models were superior in their ability to correctly identify 'Poor' and 'Good' stretches. The CNN model had the best performance among all models evaluated. The approach presented offers a low-cost method to map poor roads and identify stretches that require more attention as an alternative to more expensive traditional methods.

关键词： On-board diagnostics (OBD-II) devices Pavement surface Evaluation and rating (PASER) Ordinal logistic model convolutional neural network model

来源：评论

学校读者我要写书评

暂无评论

Estimation of lung volume changes from frontal and lateral views of dynamic chest radiography using a convolutional neural network model: a computational phantom study

Estimation of lung volume changes from frontal and lateral v...

引用

Medical Imaging Conference - Physics of Medical Imaging

作者： Ishihara, Nozomi Tanaka, Rie Segars, William Paul Abadi, Ehsan Samei, Ehsan Kanazawa Univ Kanazawa Ishikawa 9200942 Japan Carl E Ravin Adv Imaging Labs Durham NC 27705 USA

ISBN: (纸本)9781510640207

We aimed to estimate respiratory changes in lung volumes (Alung volume) using frontal and lateral dynamic chest radiography (DCR) by employing a convolutional neural network (CNN) learning approach trained and tested using the four-dimensional (4D) extended cardiac-torso (XCAT) phantom. Twenty XCAT phantoms of males (5 normal, 5 overweight, and 5 obese) and females (5 normal) were generated to obtain 4D computed tomography (CT) of a virtual patient. XCAT phantoms were projected in frontal and lateral directions. We estimated lung volumes of the XCAT phantoms using CNN learning techniques. One dataset consisted of a right- or left-half frontal view, a lateral view, and ground truth (GT) knowledge of each phantom in the same respiratory phase. Alung volume were calculated by subtracting the lung volume estimated at the maximum exhale from that at the maximal inhale, and was compared with Alung volume calculated from the known GT. Alung volume was successfully estimated from frontal and lateral DCR images of XCAT phantoms by a CNN learning approach. There was a correlation for Alung volume between GT and estimation in both lungs. There were no significant differences in the estimation error between the right and left lungs, males and females, and males having different physiques. We confirmed that DCR has potential use in the estimation of Alung volume, which corresponds to vital capacity (VC) in pulmonary function tests (PFT). Pulmonary function could be assessed by DCR even in patients with infectious diseases who can't do PFT using a spirometer.

关键词： Dynamic chest radiography Flat-panel detector XCAT phantom Lung volume Respiratory changes convolutional neural network model Prediction method Simulation study

来源：评论

学校读者我要写书评

暂无评论

Expressway Project Cost Estimation With a convolutional neural network model

引用

IEEE ACCESS 2020年 8卷 217848-217866页

作者： Xue, Xiaojuan Jia, Yuanhua Tang, Yuanjie Beijing Jiaotong Univ Sch Traff & Transportat Beijing 100044 Peoples R China CCCC First Highway Consultants Co Ltd Xian 710075 Peoples R China

With the development of the economy, the prediction of expressway project costs has gained increasing research attention. In this study, based on the convolution neural network (CNN) algorithm, the prediction of the expressway construction cost was analyzed with respect to the conceptual design stage. By summarizing the existing research results, 10 new factors related to the bridge and tunnel are creatively introduced into the cost-prediction index of the expressway conceptual design stage. In addition, the data structure of the expressway project cost prediction is defined and a CNN model is established. Finally, the project information of 415 expressways in China collected in this study is used to verify the research results. The results of the case analysis show that the 10 new indexes related to the bridge and tunnel can improve the prediction accuracy of the model. In addition, the CNN model is more suitable for solving the high-dimensional nonlinear problem of expressway cost prediction than the conventional artificial-neural-network and regression-analysis models, and it can improve the prediction accuracy. The findings of this study can be used to devise financial plans in the early stage of expressway construction and facilitate cost management at the conceptual design stage to help investors acquire project funds in advance.

关键词： Predictive models Meters Licenses Analytical models Prediction algorithms Linear regression Geology Expressway project cost prediction convolutional neural network model artificial neural network regression analysis

来源：评论

学校读者我要写书评

暂无评论

Toward efficient runs of nonlinear gyrokinetic simulations assisted by a convolutional neural network model recognizing wavenumber-space images

引用

NUCLEAR FUSION 2022年第8期62卷 086037-086037页

作者： Narita, E. Honda, M. Maeyama, S. Watanabe, T-H Natl Inst Quantum Sci & Thchnol Naka Ibaraki 3110193 Japan Kyoto Univ Grad Sch Engn Nishikyo Ku Kyoto 6158530 Japan Nagoya Univ Dept Phys Nagoya Aichi 4648602 Japan

A neural-network based innovative model recognizing the wavenumber space images has been developed to accurately forecast when the saturation of turbulent heat fluxes commences, i.e., the saturation time, in nonlinear gyrokinetic simulations. The wavenumber space images of the perturbed distribution function are focused on, which better represent the characteristics of turbulence. The model exploiting the state-of-the-art convolutional neural network model is capable of detecting minuscule differences between the images. Once the wavenumber space image is fed into the developed model, it can quickly and almost perfectly classify which phase of the turbulence evolution in nonlinear gyrokinetic simulations the image is in: the linearly and nonlinearly growing phases and the saturation phase. It can also predict the simulation time at which the image was processed with significantly high accuracy. The model enables us to forecast the saturation time of the gyrokinetic simulation in question by feeding an image at an early stage of the simulation and receiving the degree of progress toward the saturation. The ability of the model makes it possible to easily search out a desirable initial condition that rapidly conducts the simulation to a saturation phase. Such a pre-prediction model is important for running long time simulations on a large scale supercomputer like Fugaku in view of the efficient use of computational resources. In order to improve the predictive capability for the simulation that is going to be performed, several prediction models are trained by data with different major instabilities. The best predictor is selected to be in use based on the result of the pre-performed linear stability calculation with low computational cost.

关键词： turbulent transport nonlinear gyrokinetic simulations wavenumber-space convolutional neural network model deep learning large scale supercomputers

来源：评论

学校读者我要写书评

暂无评论

Research on Recognition of Multiple Partial Discharge Sources in Switchgear Based on the Combination of GST-TEV and ResNet-18

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2025年第1期19卷

作者： Wang, Feng Wang, Ning Zhong, Lipeng Chen, She Sun, Qiuqin Han, Xutao Xu, Puming Liu, Sanwei Peng, Tao Yan, Ying Deng, Xiao Hunan Univ Coll Elect & Informat Engn Changsha Peoples R China Xi An Jiao Tong Univ State Key Lab Elect Insulat & Power Equipment Xian Peoples R China State Grid Hunan Elect Power Co Ltd Res Inst Changsha Peoples R China

Switchgear can develop insulation defects due to electrical, thermal, and chemical stresses during manufacturing or prolonged operation. Moreover, as voltage levels rise, multiple insulation defects can coexist within the switchgear. Traditional partial discharge (PD) recognition methods often suffer from poor generalisation and low accuracy, limiting their practical applications. This paper proposes a method to identify multiple PD sources by combining generalised S-transform (GST) with the ResNet-18 network. PD tests confirm that the designed monitoring device effectively detects transient earth voltage (TEV) signals from diverse single and mixed insulation defects. Given the non-stationary nature of TEV signals, this paper employs the generalised S-transform (GST) for time-frequency analysis. The findings demonstrate that the GST method offers high time-frequency resolution, significantly improving the feature extraction of various partial discharge sources. Additionally, deep learning algorithms are employed to classify the time-frequency image dataset derived from GST-TEV. The results demonstrate that, compared to traditional manual feature extraction methods, the ResNet-18 network efficiently extracts GST-TEV features from both single and mixed partial discharge sources, achieving a recognition accuracy of 99.41%. This study provides new methods and theoretical support for identifying multiple partial discharge sources in switchgear.

关键词： convolutional neural network model GST-TEV multiple partial discharge sources switchgear pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Ensemble of Vision-Language Transformer-Based Captioning model With Rotatory Positional Embeddings

引用

IEEE ACCESS 2025年 13卷 59841-59865页

作者： Sathyanarayana, K. B. Naik, Dinesh Natl Inst Technol Karnataka Dept Informat Technol Surathkal 575025 Karnataka India JNN Coll Engn Dept Informat Sci & Engn Shivamogga 577204 Karnataka India

Image captioning is a dynamic and crucial research area focused on automatically generating image textual descriptions. Traditional models, primarily employing an encoder-decoder framework with convolutional neural networks (CNNs), often struggle to capture the complex spatial and sequential relationships inherent in visual data. This gap in performance underscores the necessity for more sophisticated solutions. The proposed work introduces a groundbreaking ensemble model that integrates CNN, Graph convolutional network (GCN), Bidirectional Long Short-Term Memory (BiLSTM), and Transformer architectures. Our approach achieves an outstanding 97% increase in CIDEr scores on the Flickr30K dataset and a remarkable 28.6% improvement on the Flickr8K dataset, thanks to the innovative implementation of Rotary Positional Encoding (RoPE). By strategically incorporating GCN and BiLSTM layers, our model adeptly captures essential relationships within the data. This groundbreaking research effectively addresses the challenges of image captioning, leveraging a powerful combination of advanced architectures. As a result, our model significantly enhances the generation of accurate and contextually rich captions, positioning it as a game-changer for automated image-to-text applications. The proposed Ensemble model with RoPE, achieved impressive performance on the Flickr8k and Flickr30k datasets, with scores of 80.62 and 95.0 for BLEU-1, 72.01 and 90.51 for BLEU-2, 63.12 and 81.24 for BLEU-3, 48.32 and 68.8 for BLEU-4, 74.26 and 81.89 for METEOR, 80.24 and 84.29 for ROUGE-L, 118.94 and 155.77 for CIDEr, and 48.7 and 39.0 for SPICE, respectively.

关键词： Transformers Feature extraction Computational modeling Computer architecture Bidirectional long short term memory Semantics Decoding Adaptation models Accuracy Data models Attention mechanisms bidirectional long short term memory model convolutional neural network model graph convolution network image caption generation positional embedding rotary positional embedding transformer

来源：评论

学校读者我要写书评

暂无评论

TMT-FL: Enabling Trustworthy model Training of Federated Learning With Malicious Participants

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2723-2740页

作者： Lu, Zhongkai Wang, Lingling Zhang, Zhengyin Huang, Mei Wang, Jingjing Li, Meng Qingdao University of Science and Technology School of Information Science and Technology Shandong Qingdao266061 China Hefei University of Technology School of Computer Science and Information Engineering Anhui Hefei230601 China

Federated learning is a widely used method for collaborative machine learning without sharing local data. In this approach, participants train models using their local data, and the model updates are aggregated into a global model. However, ensuring trustworthy model training is crucial because malicious participants may not use their actual local data or may not train the model as intended, which makes it challenging to guarantee the authenticity of the data and the integrity of the model training. To address these issues, we propose a trustworthy model training scheme (TMT-FL) with verifiable authenticity and integrity. Specifically, we leverage zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK) based proofs to verify the integrity of the training execution. To deal with the performance bottleneck in generating zk-SNARK proofs, we use the Chinese Remainder Theorem to optimize the convolution operation, and present an improved zk-SNARK based proof generating scheme which significantly reduces the online proving time. Besides, we adopt matrix commitment along with bloom filter to ensure the authenticity and integrity of the training datasets. Extensive experimental results demonstrate that our improved zk-SNARK scheme performs nearly 3.1× faster than the state-of-the-art in online proving time. Moreover, we experimentally confirm the efficiency of TMT-FL under diverse datasets in terms of computational costs, storage costs, and communication overheads. © 2004-2012 IEEE.

关键词： Training Data models Computational modeling Security Data Integrity Data Privacy Costs Threat modeling Kernel Gold Federated Learning Trustworthiness model Training Authenticity Integrity Zk SNARK Federated Learning Trustworthy model Malicious Participants Computational Cost Local Data Global model Convolution Operation Updated model Storage Cost Message Authentication Communication Overhead Performance Bottleneck Bloom Filter convolutional neural network Data Integration convolutional Layers Matrix Multiplication convolutional neural network model Dimensional Matrix Privacy Protection Local Training Local Updates Zero Knowledge Proof Integrity Verification MNIST Dataset Training Round Public Parameters Differential Privacy Sample Dimensions Training Subsets

来源：评论

学校读者我要写书评

暂无评论

Pose-based deep gait recognition

引用

IET BIOMETRICS 2019年第2期8卷 134-143页

作者： Sokolova, Anna Konushin, Anton Natl Res Univ Higher Sch Econ 20 Myasnitskaya Str Moscow 101000 Russia Lomonosov Moscow State Univ GSP 1 Moscow 119991 Russia

Human gait or walking manner is a biometric feature that allows identification of a person when other biometric features such as the face or iris are not visible. In this study, the authors present a new pose-based convolutional neural network model for gait recognition. Unlike many methods that consider the full-height silhouette of a moving person, they consider the motion of points in the areas around human joints. To extract motion information, they estimate the optical flow between consecutive frames. They propose a deep convolutional model that computes pose-based gait descriptors. They compare different network architectures and aggregation methods and experimentally assess various body parts to determine which are the most important for gait recognition. In addition, they investigate the generalisation ability of the developed algorithms by transferring them between datasets. The results of these experiments show that their approach outperforms state-of-the-art methods.

关键词： image recognition feature extraction neural nets biometrics (access control) image sequences pose estimation gait analysis image motion analysis pose-based deep gait recognition human gait walking manner biometric feature face convolutional neural network model full-height silhouette moving person human joints motion information deep convolutional model computes pose-based gait descriptors different network architectures aggregation methods

来源：评论

学校读者我要写书评

暂无评论

Spotting micro-movements in image sequence by introducing intelligent cubic-LBP

引用

IET IMAGE PROCESSING 2022年第14期16卷 3814-3830页

作者： Esmaeili, Vida Feghhi, Mahmood Mohassel Shahdi, Seyed Omid Univ Tabriz Fac Elect & Comp Engn 29 Bahman Blvd Tabriz Iran Islamic Azad Univ Dept Elect Engn Qazvin Branch Qazvin Iran

Invisible to naked human eyes, micro-movements are barely noticeable. There are wide ranges of micro-movement applications from spotting subtle changes in a volcano, vascular pulse, and blood vessel to micro-expression detection. In the latter, some evil thoughts can be unveiled, resulting in identifying crooks and lawbreakers and it arises from involuntary subtle and short-duration of facial muscles movements. Precise spotting of these tiny movements is possible only when multiple aspects of temporal images are scrutinized. Meanwhile, since motions often happen in one or two directions, it is rudimentary to extract complete feature sets in textural-based approaches such as cubic Local Binary Pattern (cubic-LBP). Approaches like cubic-LBP also have imposed an unnecessary computation burden. Hence, in this research, a novel method named intelligent cubic-LBP is proposed, which incorporates convolutional neural network (CNN) model. This model learns to select the useful plane(s) automatically. Apex is then detected by applying Partial Autocorrelation Coefficient (PACF) on the selected plane(s). The experimental results show significant improvement in micro-movements identification. The accuracy of the apex frame detection has elevated to 10% and 17% in the Chinese Academy of Sciences Micro-Expressions (CASME) and the CASME II databases, respectively.

关键词： intelligent cubic-LBP blood vessel microexpression detection wide ranges image sequences convolutional neural nets Sciences MicroExpressions naked human eyes micromovements identification convolutional neural network model learning (artificial intelligence) feature extraction image sequence tiny movements face recognition textural-based approaches vascular pulse emotion recognition blood vessels precise spotting image texture micromovement applications facial muscles movements cubic Local Binary Pattern image classification temporal images

来源：评论

学校读者我要写书评

暂无评论

Deep learning model to detect various synchrophasor data anomalies

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2020年第24期14卷 5739-5745页

作者： Deng, Xianda Bian, Desong Wang, Weikang Jiang, Zhihao Yao, Wenxuan Qiu, Wei Tong, Ning Shi, Di Liu, Yilu Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA Global Energy Interconnect Res Inst North Amer San Jose CA 95134 USA Oak Ridge Natl Lab Oak Ridge TN 37830 USA

High-density synchrophasors provide valuable information for power grid situational awareness, operation and control. Unfortunately, due to factors including communication instability and hardware failure, their data quality can be greatly deteriorated by anomalies. Since the anomalies can impact the performance of the synchrophasor applications, it is of paramount significance to propose a model to detect anomalies in synchrophasor. In this study, a convolutional neural network model is established to detect and classify the anomalies in the synchrophasor measurements. Four types of anomalies observed in actual synchrophasors including erroneous patterns, random spikes, missing points and high-frequency interferences are considered in this study. The proposed model is extensively evaluated via field-collected measurements from the synchrophasor network in Jiangsu grid, China. The superior performance of the proposed model indicates the great potential of using deep learning for the detection of abnormal synchrophasor measurements.

关键词： learning (artificial intelligence) phase measurement power system measurement phasor measurement power grids power engineering computing pattern classification convolutional neural nets synchrophasor data anomaly detection high-density synchrophasors communication instability hardware failure data quality convolutional neural network model synchrophasor network abnormal synchrophasor measurements deep learning Jiangsu grid China synchrophasor data anomaly classification

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：