scholarly journals PolSAR Image Classification with Lightweight 3D Convolutional Networks

2020 ◽  
Vol 12 (3) ◽  
pp. 396
Author(s):  
Hongwei Dong ◽  
Lamei Zhang ◽  
Bin Zou
Keyword(s):  
Image Classification ◽  
Data Representation ◽  
Model Parameters ◽  
Structure Information ◽  
Convolutional Networks ◽  
Optical Images ◽  
Benchmark Datasets ◽  
3D Cnn ◽  
Almost All ◽  
Fully Connected

Convolutional neural networks (CNNs) have become the state-of-the-art in optical image processing. Recently, CNNs have been used in polarimetric synthetic aperture radar (PolSAR) image classification and obtained promising results. Unlike optical images, the unique phase information of PolSAR data expresses the structure information of objects. This special data representation makes 3D convolution which explicitly modeling the relationship between polarimetric channels perform better in the task of PolSAR image classification. However, the development of deep 3D-CNNs will cause a huge number of model parameters and expensive computational costs, which not only leads to the decrease of the interpretation speed during testing, but also greatly increases the risk of over-fitting. To alleviate this problem, a lightweight 3D-CNN framework that compresses 3D-CNNs from two aspects is proposed in this paper. Lightweight convolution operations, i.e., pseudo-3D and 3D-depthwise separable convolutions, are considered as low-latency replacements for vanilla 3D convolution. Further, fully connected layers are replaced by global average pooling to reduce the number of model parameters so as to save the memory. Under the specific classification task, the proposed methods can reduce up to 69.83% of the model parameters in convolution layers of the 3D-CNN as well as almost all the model parameters in fully connected layers, which ensures the fast PolSAR interpretation. Experiments on three PolSAR benchmark datasets, i.e., AIRSAR Flevoland, ESAR Oberpfaffenhofen, EMISAR Foulum, show that the proposed lightweight architectures can not only maintain but also slightly improve the accuracy under various criteria.

3D long-term recurrent convolutional networks for human sub-assembly recognition in human-robot collaboration

2020 ◽  
Vol 40 (4) ◽  
pp. 655-662 ◽  
Author(s):  
Xianhe Wen ◽  
Heping Chen
Keyword(s):  
High Precision ◽  
Short Term Memory ◽  
Recognition Accuracy ◽  
Model Parameters ◽  
Assembly Process ◽  
Content Type ◽  
Convolutional Networks ◽  
3D Cnn ◽  
Human Robot Collaboration

Purpose Human assembly process recognition in human–robot collaboration (HRC) has been studied recently. However, most research works do not cover high-precision and long-timespan sub-assembly recognition. Hence this paper aims to deal with this problem. Design/methodology/approach To deal with the above-mentioned problem, the authors propose a 3D long-term recurrent convolutional networks (LRCN) by combining 3D convolutional neural networks (CNN) with long short-term memory (LSTM). 3D CNN behaves well in human action recognition. But when it comes to human sub-assembly recognition, the accuracy of 3D CNN is very low and the number of model parameters is huge, which limits its application in human sub-assembly recognition. Meanwhile, LSTM has the incomparable superiority of long-time memory and time dimensionality compression ability. Hence, by combining 3D CNN with LSTM, the new approach can greatly improve the recognition accuracy and reduce the number of model parameters. Findings Experiments were performed to validate the proposed method and preferable results have been obtained, where the recognition accuracy increases from 82% to 99%, recall ratio increases from 95% to 100% and the number of model parameters is reduced more than 8 times. Originality/value The authors focus on a new problem of high-precision and long-timespan sub-assembly recognition in the area of human assembly process recognition. Then, the 3D LRCN method is a new method with high-precision and long-timespan recognition ability for human sub-assembly recognition compared to 3D CNN method. It is extraordinarily valuable for the robot in HRC. It can help the robot understand what the sub-assembly human cooperator has done in HRC.

scholarly journals Exploiting Visual Semantic Reasoning for Video-Text Retrieval

2020 ◽  
Author(s):  
Zerun Feng ◽  
Zhimin Zeng ◽  
Caili Guo ◽  
Zheng Li
Keyword(s):  
Video Retrieval ◽  
Semantic Relations ◽  
Semantic Reasoning ◽  
Semantic Correlation ◽  
Convolutional Networks ◽  
Correlation Graph ◽  
Benchmark Datasets ◽  
Language Areas ◽  
Fully Connected ◽  
The Impact

Video retrieval is a challenging research topic bridging the vision and language areas and has attracted broad attention in recent years. Previous works have been devoted to representing videos by directly encoding from frame-level features. In fact, videos consist of various and abundant semantic relations to which existing methods pay less attention. To address this issue, we propose a Visual Semantic Enhanced Reasoning Network (ViSERN) to exploit reasoning between frame regions. Specifically, we consider frame regions as vertices and construct a fully-connected semantic correlation graph. Then, we perform reasoning by novel random walk rule-based graph convolutional networks to generate region features involved with semantic relations. With the benefit of reasoning, semantic interactions between regions are considered, while the impact of redundancy is suppressed. Finally, the region features are aggregated to form frame-level features for further encoding to measure video-text similarity. Extensive experiments on two public benchmark datasets validate the effectiveness of our method by achieving state-of-the-art performance due to the powerful semantic reasoning.

scholarly journals Attention-Enhanced Graph Convolutional Networks for Aspect-Based Sentiment Classification with Multi-Head Attention

2021 ◽  
Vol 11 (8) ◽  
pp. 3640
Author(s):  
Guangtao Xu ◽  
Peiyu Liu ◽  
Zhenfang Zhu ◽  
Jie Liu ◽  
Fuyong Xu
Keyword(s):  
Sentiment Classification ◽  
Experimental Results ◽  
Sentence Structure ◽  
Convolutional Network ◽  
Structure Information ◽  
Convolutional Networks ◽  
Dependency Tree ◽  
Syntactic Information ◽  
Benchmark Datasets ◽  
Reasonable Use

The purpose of aspect-based sentiment classification is to identify the sentiment polarity of each aspect in a sentence. Recently, due to the introduction of Graph Convolutional Networks (GCN), more and more studies have used sentence structure information to establish the connection between aspects and opinion words. However, the accuracy of these methods is limited by noise information and dependency tree parsing performance. To solve this problem, we proposed an attention-enhanced graph convolutional network (AEGCN) for aspect-based sentiment classification with multi-head attention (MHA). Our proposed method can better combine semantic and syntactic information by introducing MHA and GCN. We also added an attention mechanism to GCN to enhance its performance. In order to verify the effectiveness of our proposed method, we conducted a lot of experiments on five benchmark datasets. The experimental results show that our proposed method can make more reasonable use of semantic and syntactic information, and further improve the performance of GCN.

scholarly journals Comprehensive Wind and Wave Statistics and Extreme Values for Design and Analysis of Marine Structures in the Adriatic Sea

2021 ◽  
Vol 9 (5) ◽  
pp. 522
Author(s):  
Marko Katalinić ◽  
Joško Parunov
Keyword(s):  
Adriatic Sea ◽  
Extreme Values ◽  
Wave Climate ◽  
Offshore Structures ◽  
Model Parameters ◽  
Peak Period ◽  
Significant Wave ◽  
Wave Statistics ◽  
Wave Heights ◽  
Almost All

Wind and waves present the main causes of environmental loading on seagoing ships and offshore structures. Thus, its detailed understanding can improve the design and maintenance of these structures. Wind and wave statistical models are developed based on the WorldWaves database for the Adriatic Sea: for the entire Adriatic Sea as a whole, divided into three regions and for 39 uniformly spaced locations across the offshore Adriatic. Model parameters are fitted and presented for each case, following the conditional modelling approach, i.e., the marginal distribution of significant wave height and conditional distribution of peak period and wind speed. Extreme significant wave heights were evaluated for 20-, 50- and 100-year return periods. The presented data provide a consistent and comprehensive description of metocean (wind and wave) climate in the Adriatic Sea that can serve as input for almost all kind of analyses of ships and offshore structures.

scholarly journals CT based automatic clinical target volume delineation using a dense-fully connected convolution network for cervical Cancer radiation therapy

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Zhongjian Ju ◽  
Wen Guo ◽  
Shanshan Gu ◽  
Jin Zhou ◽  
Wei Yang ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Cancer Patients ◽  
Clinical Target Volume ◽  
Target Volume ◽  
Ct Images ◽  
Clinical Samples ◽  
Model Parameters ◽  
Convolutional Network ◽  
Volume Delineation ◽  
Fully Connected

Abstract Background It is very important to accurately delineate the CTV on the patient’s three-dimensional CT image in the radiotherapy process. Limited to the scarcity of clinical samples and the difficulty of automatic delineation, the research of automatic delineation of cervical cancer CTV based on CT images for new patients is slow. This study aimed to assess the value of Dense-Fully Connected Convolution Network (Dense V-Net) in predicting Clinical Target Volume (CTV) pre-delineation in cervical cancer patients for radiotherapy. Methods In this study, we used Dense V-Net, a dense and fully connected convolutional network with suitable feature learning in small samples to automatically pre-delineate the CTV of cervical cancer patients based on computed tomography (CT) images and then we assessed the outcome. The CT data of 133 patients with stage IB and IIA postoperative cervical cancer with a comparable delineation scope was enrolled in this study. One hundred and thirteen patients were randomly designated as the training set to adjust the model parameters. Twenty cases were used as the test set to assess the network performance. The 8 most representative parameters were also used to assess the pre-sketching accuracy from 3 aspects: sketching similarity, sketching offset, and sketching volume difference. Results The results presented that the DSC, DC/mm, HD/cm, MAD/mm, ∆V, SI, IncI and JD of CTV were 0.82 ± 0.03, 4.28 ± 2.35, 1.86 ± 0.48, 2.52 ± 0.40, 0.09 ± 0.05, 0.84 ± 0.04, 0.80 ± 0.05, and 0.30 ± 0.04, respectively, and the results were greater than those with a single network. Conclusions Dense V-Net can correctly predict CTV pre-delineation of cervical cancer patients and can be applied in clinical practice after completing simple modifications.

Identification of ’Effective’ Linear Joints Using Coupling and Joint Identification Techniques

1998 ◽  
Vol 120 (2) ◽  
pp. 331-338 ◽  
Author(s):  
Y. Ren ◽  
C. F. Beards
Keyword(s):  
Dynamic Properties ◽  
Real Life ◽  
Model Parameters ◽  
Coupling Technique ◽  
Alternative Approach ◽  
Identification Technique ◽  
Joint Identification ◽  
Stiff Joint ◽  
Almost All ◽  
Identification Techniques

Almost all real-life structures are assembled from components connected by various types of joints. Unlike many other parts, the dynamic properties of a joint are difficult to model analytically. An alternative approach for establishing a theoretical model of a joint is to extract the model parameters from experimental data using joint identification techniques. The accuracy of the identification is significantly affected by the properties of the joints themselves. If a joint is stiff, its properties are often difficult to identify accurately. This is because the responses at both ends of the joint are linearly-dependent. To make things worse, the existence of a stiff joint can also affect the accuracy of identification of other effective joints (the term “effective joints” in this paper refers to those joints which otherwise can be identified accurately). This problem is tackled by coupling these stiff joints using a generalized coupling technique, and then the properties of the remaining joints are identified using a joint identification technique. The accuracy of the joint identification can usually be improved by using this approach. Both numerically simulated and experimental results are presented.

Sign in / Sign up

Export Citation Format

Share Document