检索结果-内蒙古大学图书馆

Segmentation method of multiple sclerosis lesions based on 3d-CNN networks

IET IMAGE PROCESSING 2020年第9期14卷 1806-1812页

作者： Xiang, Yan Liu, Han Wang, Shuo Ma, Lei Xiong, Xin Xu, Chunrong Shao, dangguo Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Artificial Intelligence Kunming Yunnan Peoples R China Guangzhou Coll Commerce Sch Informat Technol & Engn Guangzhou Peoples R China

Histopathology image segmentation is an important area in the field of computer aided diagnosis using image processing. The segmentation of Multiple sclerosis (MS) lesions from MR images can establish the basis for subsequent lesion reconstruction, volume estimation, and course evaluation. This study proposes a method for automatically segmenting MS lesions based on 3d convolutional neural network (CNN). The method is divided into two stages, each of which includes two convolution layers and two pooling layers. The alternative lesion voxels are selected in the first stage, while in the second stage, the final lesion voxels are segmented from the lesion voxels which are obtained in the first stage by restricting the conditions. The method has been tested on the MICCAI 2008 and 2016 datasets and compared to the other baseline methods. The experiment results show that the method has better performance than the other baseline methods on different evaluation indicators, including dice similarity coefficient, absolute difference in lesion volume, true positive rate, false positive rate, and predictive positivity value.

关键词： medical image processing image segmentation neural nets biomedical MRI MS lesions 3d convolutional neural network convolution layers pooling layers alternative lesion voxels final lesion voxels MICCAI 2008 datasets 2016 datasets baseline methods different evaluation indicators lesion volume segmentation method multiple sclerosis lesions 3d-CNN networks histopathology image segmentation computer aided diagnosis image processing MR images subsequent lesion reconstruction volume estimation course evaluation

来源：评论

学校读者我要写书评

暂无评论

Fall detection using optical level anonymous image sensing system

引用

OPTICS ANd LASER TECHNOLOGY 2019年 110卷 44-61页

作者： Ma, Chao Shimada, Atsushi Uchiyama, Hideaki Nagahara, Hajime Taniguchi, Rin-ichiro Kyushu Univ Grad Sch Informat Sci & Elect Engn Nishi Ku 744 Motooka Fukuoka Fukuoka 8190395 Japan Osaka Univ Inst Databil Sci 2-8 Yamadaoka Suita Osaka 5650871 Japan

Fall is one of the leading causes of injury for the elderly individuals. Systems that automatically detect falls can significantly reduce the delay of assistance. Most of commercialized fall detection systems are based on wearable devices, which elderly individuals tend to forget wearing. Using surveillance cameras to detect falls based on computer vision is ideal, because anyone in the monitoring scopes can be under protection. However, the privacy protection issue using surveillance cameras has been bothering people. To effectively protect the privacy, we proposed an optical level anonymous image sensing system, which can protect the privacy by hiding the facial regions optically at the video capturing phase. We apply the system to fall detection. In detecting falls, we propose a neural network by combining a 3d convolutional neural network for feature extraction and an autoencoder for modelling the normal behaviors. The learned autoencoder reconstructs the features extracted from videos with normal behaviors with smaller average errors than those extracted from videos with falls. We evaluated our neural network by a hold-out validation experiment, and showed its effectiveness. In field tests, we showed and discussed the applicability of the optical level anonymous image sensing system for privacy protection and fall detection. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Optical level anonymous Computational imaging Privacy protection Fall detection 3d convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

3d residual spatial-spectral convolution network for hyperspectral remote sensing image classification

引用

neural COMPUTING & APPLICATIONS 2023年第6期35卷 4479-4497页

作者： Firat, Huseyin Asker, Mehmet Emin Bayindir, Mehmet Ilyas Hanbay, davut Dicle Univ Vocat Sch Tech Sci Dept Comp Technol Diyarbakir Turkey Dicle Univ Vocat Sch Tech Sci Dept Elect & Energy Diyarbakir Turkey Firat Univ Vocat Sch Tech Sci Dept Elect & Automat Elazig Turkey Inonu Univ Engn Fac Dept Comp Engn Malatya Turkey

Hyperspectral remote sensing images (HRSI) are 3d image cubes that contain hundreds of spectral bands and have two spatial dimensions and one spectral dimension. HRSI analysis are commonly used in a wide variety of applications such as object detection, precision agriculture and mining. HRSI classification purposes to assign each pixel in HRSI to a unique class. deep learning is seen as an effective method to improve HRSI classification. In particular, convolutional neural networks (CNNs) are increasingly used in remote sensing field. In this study, a hybrid 3d residual spatial-spectral convolution network (3d-RSSCN) is proposed to extract deep spatiospectral features using 3d CNN and ResNet18 architecture. Simultaneously spatiospectral features extraction is provided using 3d CNN. In deeper CNNs, ResNet architecture is used to achieve higher classification performance as the number of layers increases. In addition, thanks to the ResNet architecture, problems such as degradation and vanishing gradient that may occur in deep networks are overcome. The high dimensionality of the HRSIs increases the computational complexity. Thus, most of studies apply dimension reduction as preprocessing. In the proposed study, principal component analysis (PCA) is used as the preprocessing step for optimum spectral band extraction. The proposed 3d-RSSCN method is tested with Indian pines, Pavia University and Salinas datasets and compared against various deep learning-based methods (SAE, RPNet, 2d CNN, 3d CNN, M3d CNN, HybridSN, FC3d CNN, SSRN, FuSENet, S3EResBoF). As a result of the applications, the best classification accuracy among these methods compared in all datasets is obtained with the proposed 3d-RSSCN. The proposed 3d-RSSCN method has the best accuracy and time performance in classifying.

关键词： Remote sensing Hyperspectral image classification ResNet 3d convolutional neural network Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Surrogate permeability modelling of low -permeable rocks using convolutional neural networks

引用

COMPUTER METHOdS IN APPLIEd MECHANICS ANd ENGINEERING 2020年 366卷 113103-113103页

作者： Tian, Jianwei Qi, Chongchong Sun, Yingfeng Yaseen, Zaher Mundher Univ Western Australia Sch Engn Perth WA 6009 Australia Cent South Univ Sch Resources & Safety Engn Changsha 410083 Peoples R China China Univ Min & Technol Sch Emergency Management & Safety Engn Beijing 100083 Peoples R China Ton Duc Thang Univ Fac Civil Engn Sustainable Dev Civil Engn Res Grp Ho Chi Minh City Vietnam

Permeability is an important mechanical property of low-permeable rocks, the prediction of which plays a significant role in forecasting many engineering problems like gas production and CO₂ geo-sequestration. However, the ultra-low permeability and strong heterogeneity of low-permeable rocks hinder the accurate determination of permeability experimentally and numerically. In this study, 3d convolutional neural networks (CNNs) were trained to rapidly evaluate the permeability of low-permeable porous media. An improved quartet structure generation set considering pore size distribution (PSd) acquired by experiment and anisotropy (QSGS) was proposed to generate low-permeable porous media. Together with the permeability calculation using d3Q19 model of Lattice Boltzmann Method (LBM), the whole dataset with a size of 4,500 was prepared for CNN modelling. Moreover, a parametric study was conducted to investigate the influence of CNN architecture and training epochs on its performance. The performance discrepancy corresponding to the magnitude of absolute permeability was also discussed. The modelling results indicate that the CNNs architecture has an important effect on its performance. The best architecture achieved an average validating loss of 1.20×10⁻³ while the worst architecture achieved an average validating loss of 3.60×10⁻³. The CNN modelling suffered a little from over-fitting when the epoch was over 20. The optimum 3d CNN achieved remarkably high accuracy of permeability prediction with high correlation coefficient (R=0.996) and low errors (MAE=0.017, RMSE=0.03) on the testing set. Furthermore, it was found that the testing error of the lower permeability groups was relatively larger than that of larger permeability groups.

关键词： Permeability prediction 3d convolutional neural network Lattice Boltzmann method Low-permeable rocks

来源：评论

学校读者我要写书评

暂无评论

MIMO-OFdM Modulation Classification Using Three-dimensional convolutional network

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2022年第6期71卷 6738-6743页

作者： Thien Huynh-The Toan-Van Nguyen Quoc-Viet Pham da Costa, daniel Benevides Kim, dong-Seong Kumoh Natl Inst Technol ICT Convergence Res Ctr Gumi 39177 Gyeongsangbuk D South Korea Kumoh Natl Inst Technol Dept IT Convergence Gumi 39177 Gyeongsangbuk D South Korea Utah State Univ Dept Elect & Comp Engn Logan UT 84321 USA Pusan Natl Univ Korean Southeast Ctr Ind Revolut Leader 4 Yangsan 50612 Gyeongsangnam D South Korea Technol Innovat Inst AI & Telecom Res Ctr Abu Dhabi 9639 U Arab Emirates Natl Yunlin Univ Sci & Technol Future Technol Res Ctr Touliu 64002 Yunlin Taiwan

Automatic modulation classification (AMC) plays a vital role in cognitive radio to improve spectrum utilization efficiency, however, most of the existing works have focused on single-carrier communications in single-input single-output systems. In this paper, we propose an efficient AMC method for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFdM) communication systems with the assumption of unknown frequency-selective fading channels and signal-to-noise ratio. At the receiver, the complex envelope samples of a burst signal acquired by multiple antennas are decomposed into in-phase and quadrature samples, which are then structured into a high-dimensional data array. To learn the modulation patterns from received signals, we develop a deep network, namely three-dimensional MIMO-OFdM convolutional neural network (MONet). With cuboidal convolution filters, the proposed MONet allows the network to capture underlying features as intra- and inter-antenna correlations at multi-scale signal representations. Relying on simulations, MONet achieves the classification accuracy of over 95% at 0 dB SNR under various channel impairments and shows the robustness with different MIMO antenna configurations.

关键词： Modulation Receiving antennas OFdM Correlation Convolution Transmitting antennas Three-dimensional displays Automatic modulation classification 3d convolutional neural network orthogonal frequency-division multiplexing multiple-input multiple-output

来源：评论

学校读者我要写书评

暂无评论

Air Pollution detection Using a Novel Snap-Shot Hyperspectral Imaging Technique

引用

SENSORS 2022年第16期22卷 6231页

作者： Mukundan, Arvind Huang, Chia-Cheng Men, Ting-Chun Lin, Fen-Chi Wang, Hsiang-Chen Natl Chung Cheng Univ Ctr Innovat Res Aging Soc CIRAS Adv Inst Mfg High Tech Innovat AIM HI Dept Mech Engn 168 Univ Rd Chiayi 62102 Taiwan Kaohsiung Armed Forces Gen Hosp Ophthalmol 2Zhongzheng 1st Rd Kaohsiung 80284 Taiwan

Air pollution has emerged as a global problem in recent years. Particularly, particulate matter (PM2.5) with a diameter of less than 2.5 mu m can move through the air and transfer dangerous compounds to the lungs through human breathing, thereby creating major health issues. This research proposes a large-scale, low-cost solution for detecting air pollution by combining hyperspectral imaging (HSI) technology and deep learning techniques. By modeling the visible-light HSI technology of the aerial camera, the image acquired by the drone camera is endowed with hyperspectral information. Two methods are used for the classification of the images. That is, 3d convolutional neural network Auto Encoder and principal components analysis (PCA) are paired with VGG-16 (Visual Geometry Group) to find the optical properties of air pollution. The images are classified into good, moderate, and severe based on the concentration of PM2.5 particles in the images. The results suggest that the PCA + VGG-16 has the highest average classification accuracy of 85.93%.

关键词： hyperspectral imaging technology air pollution PM2 5 deep neural network 3d convolutional neural network auto encoding

来源：评论

学校读者我要写书评

暂无评论

Crossing or Not? Context-Based Recognition of Pedestrian Crossing Intention in the Urban Environment

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第6期23卷 5338-5349页

作者： Yang, Biao Zhan, Weiqin Wang, Pin Chan, Chingyao Cai, Yingfeng Wang, Nan Changzhou Univ Sch Microelect & Control Engn Changzhou 213000 Peoples R China Univ Calif Berkeley Calif PATH Richmond CA 94804 USA Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Jiangsu Peoples R China Ocean Univ China Coll Informat Sci & Engn Dept Elect Engn Qingdao 266100 Peoples R China

The booming self-driving cars need to understand the behaviors of other road users for better performance. Recognizing pedestrians' crossing intentions is one of the most critical capabilities of self-driving cars to guarantee safe operations in the urban environment. Some researchers try to predict the future trajectories of pedestrians to avoid a potential collision. Others extract skeleton features from pedestrians to detect specific actions related to the crossing intention. All these methods either neglect the abundant appearance information of pedestrians, or work poorly under severe conditions, e.g., pedestrians standing far away, dim light, and occlusions. In this work, a pedestrian crossing intention recognition (PCIR) framework is proposed to recognize pedestrians' crossing intention. A module for searching targets of interest is introduced to find the pedestrians who are likely to cross the streets, and perform scene perception simultaneously. An action recognition module utilizes a 3d convolutional neural network (CNN) to automatically extract spatiotemporal features that imply early actions before crossing, like limb movements. A distance encoding module makes full use of the contextual cues, e.g., distances between pedestrians and the oncoming vehicle, local traffic scenes around pedestrians, and vehicle speeds, to improve the recognition accuracy obtained from the action recognition module only. Finally, the PCIR framework fuses these factors to predict pedestrians' crossing intentions by minimizing a focal loss. Experimental evaluations verify the effectiveness of the proposed method in recognizing pedestrians' crossing intentions. Comparisons with the skeleton-based methods reveal the robustness of the PCIR framework in the urban environment.

关键词： Trajectory Feature extraction Three-dimensional displays Skeleton Autonomous automobiles Automobiles Spatiotemporal phenomena Crossing intention 3d convolutional neural network action recognition contextual information self-driving car

来源：评论

学校读者我要写书评

暂无评论

Hand Pose Estimation in the Task of Egocentric Actions

引用

IEEE ACCESS 2021年 9卷 10533-10547页

作者： Hruz, Marek Kanis, Jakub Krnoul, Zdenek Univ West Bohemia Pilsen Fac Appl Sci Dept Cybernet Plzen 30614 Czech Republic Univ West Bohemia Pilsen Fac Appl Sci New Technol Informat Soc Plzen 30100 Czech Republic

In this article we tackle the problem of hand pose estimation when the hand is interacting with various objects from egocentric viewpoint. This entails a frequent occlusion of parts of the hand by the object and also self-occlusions of the hand. We use a Voxel-to-Voxel approach to obtain hypotheses of the hand joint locations, ensemble the hypotheses and use several post-processing strategies to improve on the results. We utilize models of prior hand pose in the form of Truncated Singular Value decomposition (SVd) and the temporal context to produce refined hand joint locations. We present an ablation study of the methods to show the influence of individual features of the post-processing. With our method we were able to constitute state-of-the-art results on the HANdS19 Challenge: Task 2 - depth-Based 3d Hand Pose Estimation while Interacting with Objects, with precision on unseen test data of 33.09 mm.

关键词： Three-dimensional displays Pose estimation Task analysis Two dimensional displays Solid modeling Prediction algorithms Location awareness 3d convolutional neural network egocentric hand pose TruncatedSVd volumetric data

来源：评论

学校读者我要写书评

暂无评论

LipSyncNet: A Novel deep Learning Approach for Visual Speech Recognition in Audio-Challenged Situations

引用

IEEE ACCESS 2024年 12卷 110891-110904页

作者： Jeevakumari, S. A. Amutha dey, Koushik Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India

In recent lip-reading technologies, deep learning methodologies have emerged as the key, transcending the limitations of traditional hybrid deep neural network-Hidden Markov Model (dNN-HMM) frameworks based on discrete Cosine Transform (dCT) features. LipSyncNet comprises a three-dimensional-convolutional neural network (3d-CNN) that consists of a maximum depth of four layers and is responsible for extracting visual features by integrating EfficientNetB0, which results in excellent feature extraction capabilities. Following this, the network architecture incorporates a backend that utilizes a Bidirectional Long Short-Term Memory (Bi-LSTM)-a component of the recurrent neural network family-combined with Connectionist Temporal Classification (CTC) loss, enhancing its ability to perform classification tasks. The effectiveness of the proposed method is demonstrated through the evaluation of the Graphics Research International database (GRId) corpus, a challenging word-level lip-reading dataset. Initially, facial features are extracted from the mouth area of an individual's face. Subsequently, these features are combined with available audio information to identify spoken words precisely. The lip-reading method aims to create a system that achieves accurate speech recognition by observing visual cues, thereby reducing the reliance on audio. The model utilizes information from various levels in a unified structure, enabling it to differentiate between words that sound alike and to improve its ability to handle changes in physical appearance.

关键词： Visualization Accuracy Speech recognition Feature extraction deep learning Speech enhancement Long short term memory convolutional neural networks bidirectional long short-term memory long-short-term memory visual cues lip reading 3d convolutional neural network connectionist temporal classification

来源：评论

学校读者我要写书评

暂无评论

A novel spatiotemporal 3d CNN framework with multi-task learning for efficient structural damage detection

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2024年第4期23卷 2270-2287页

作者： Kord, Sadeq Taghikhany, Touraj Akbari, Mohammad Amirkabir Univ Technol Dept Civil Engn Tehran Iran Amirkabir Univ Technol Dept Math & Comp Sci Tehran Iran Amirkabir Univ Technol Dept Civil Engn Hafez Ave Tehran 159163431 Iran

In recent years, convolutional neural networks (CNNs) have demonstrated promising results in detecting structural damage. However, their architectures often overlook spatial and temporal effects simultaneously. This limitation can result in the loss of valuable information and an incapability to fully capture the complexity of the data, ultimately leading to reduced accuracy and suboptimal performance. This study proposes an intuitive three-dimensional CNN architecture that takes into account vibration history along with sensor spatial relations based on their relative positions. Furthermore, a multi-task learning (MTL) approach is suggested, which is a powerful approach for performing multiple tasks with a single network. The proposed 3d CNN method has been employed to detect single and double damage cases in an experimental steel frame through conventional classification alongside the transfer learning (TL). Moreover, MTL is used to detect single and double damage scenarios with a single unified network, which evaluates damage presence in separate tasks. The 3d CNN fulfilled state-of-the-art performance and 100% accuracy in detecting structural damage in almost all experiments. Additionally, the MTL model achieved promising results even in the presence of severe imbalanced classes of data. Furthermore, it was observed that the utilization of TL resulted in a notable reduction of computation time by 68% and the number of trainable parameters by 90% with the same level of accuracy in double-damage cases.

关键词： Structural damage detection 3d convolutional neural network spatial and temporal analysis multi-task learning transfer learning

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：