scholarly journals Improved 3D U-Net for COVID-19 Chest CT Image Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Ruiyong Zheng ◽  
Yongguo Zheng ◽  
Changlei Dong-Ye
Keyword(s):  
Automatic Segmentation ◽  
Image Features ◽  
Chest Ct ◽  
Feature Representation ◽  
Global Information ◽  
Similarity Coefficients ◽  
Information Interaction ◽  
Channel Information ◽  
High Level ◽  
Different Levels

Coronavirus disease 2019 (COVID-19) has spread rapidly worldwide. The rapid and accurate automatic segmentation of COVID-19 infected areas using chest computed tomography (CT) scans is critical for assessing disease progression. However, infected areas have irregular sizes and shapes. Furthermore, there are large differences between image features. We propose a convolutional neural network, named 3D CU-Net, to automatically identify COVID-19 infected areas from 3D chest CT images by extracting rich features and fusing multiscale global information. 3D CU-Net is based on the architecture of 3D U-Net. We propose an attention mechanism for 3D CU-Net to achieve local cross-channel information interaction in an encoder to enhance different levels of the feature representation. At the end of the encoder, we design a pyramid fusion module with expanded convolutions to fuse multiscale context information from high-level features. The Tversky loss is used to resolve the problems of the irregular size and uneven distribution of lesions. Experimental results show that 3D CU-Net achieves excellent segmentation performance, with Dice similarity coefficients of 96.3% and 77.8% in the lung and COVID-19 infected areas, respectively. 3D CU-Net has high potential to be used for diagnosing COVID-19.

scholarly journals Hybrid Attention Network for Language-Based Person Search

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5279
Author(s):  
Yang Li ◽  
Huahu Xu ◽  
Junsheng Xiao
Keyword(s):  
Image Features ◽  
Attention Mechanism ◽  
Feature Representation ◽  
Semantic Features ◽  
Retrieval Task ◽  
Attention Network ◽  
Fine Grained ◽  
Person Search ◽  
High Level ◽  
Language Description

Language-based person search retrieves images of a target person using natural language description and is a challenging fine-grained cross-modal retrieval task. A novel hybrid attention network is proposed for the task. The network includes the following three aspects: First, a cubic attention mechanism for person image, which combines cross-layer spatial attention and channel attention. It can fully excavate both important midlevel details and key high-level semantics to obtain better discriminative fine-grained feature representation of a person image. Second, a text attention network for language description, which is based on bidirectional LSTM (BiLSTM) and self-attention mechanism. It can better learn the bidirectional semantic dependency and capture the key words of sentences, so as to extract the context information and key semantic features of the language description more effectively and accurately. Third, a cross-modal attention mechanism and a joint loss function for cross-modal learning, which can pay more attention to the relevant parts between text and image features. It can better exploit both the cross-modal and intra-modal correlation and can better solve the problem of cross-modal heterogeneity. Extensive experiments have been conducted on the CUHK-PEDES dataset. Our approach obtains higher performance than state-of-the-art approaches, demonstrating the advantage of the approach we propose.

scholarly journals Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition

2017 ◽  
Author(s):  
Xinge Zhu ◽  
Liang Li ◽  
Weigang Zhang ◽  
Tianrong Rao ◽  
Min Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
Emotion Recognition ◽  
Feature Fusion ◽  
Feature Representation ◽  
Low Level ◽  
Learning Framework ◽  
Independent Entity ◽  
Internet Images ◽  
High Level ◽  
Different Levels

Visual emotion recognition aims to associate images with appropriate emotions. There are different visual stimuli that can affect human emotion from low-level to high-level, such as color, texture, part, object, etc. However, most existing methods treat different levels of features as independent entity without having effective method for feature fusion. In this paper, we propose a unified CNN-RNN model to predict the emotion based on the fused features from different levels by exploiting the dependency among them. Our proposed architecture leverages convolutional neural network (CNN) with multiple layers to extract different levels of features with in a multi-task learning framework, in which two related loss functions are introduced to learn the feature representation. Considering the dependencies within the low-level and high-level features, a new bidirectional recurrent neural network (RNN) is proposed to integrate the learned features from different layers in the CNN model. Extensive experiments on both Internet images and art photo datasets demonstrate that our method outperforms the state-of-the-art methods with at least 7% performance improvement.

scholarly journals Aircraft Requirements for Sustainable Regional Aviation

Aerospace ◽  
2021 ◽  
Vol 8 (3) ◽  
pp. 61
Author(s):  
Dominik Eisenhut ◽  
Nicolas Moebs ◽  
Evert Windels ◽  
Dominique Bergmann ◽  
Ingmar Geiß ◽  
...  
Keyword(s):  
Systems Engineering ◽  
System Level ◽  
Policy Initiative ◽  
The European Union ◽  
Calculation Methods ◽  
Figures Of Merit ◽  
Performance Requirements ◽  
High Level ◽  
Different Levels ◽  
The Eu

Recently, the new Green Deal policy initiative was presented by the European Union. The EU aims to achieve a sustainable future and be the first climate-neutral continent by 2050. It targets all of the continent’s industries, meaning aviation must contribute to these changes as well. By employing a systems engineering approach, this high-level task can be split into different levels to get from the vision to the relevant system or product itself. Part of this iterative process involves the aircraft requirements, which make the goals more achievable on the system level and allow validation of whether the designed systems fulfill these requirements. Within this work, the top-level aircraft requirements (TLARs) for a hybrid-electric regional aircraft for up to 50 passengers are presented. Apart from performance requirements, other requirements, like environmental ones, are also included. To check whether these requirements are fulfilled, different reference missions were defined which challenge various extremes within the requirements. Furthermore, figures of merit are established, providing a way of validating and comparing different aircraft designs. The modular structure of these aircraft designs ensures the possibility of evaluating different architectures and adapting these figures if necessary. Moreover, different criteria can be accounted for, or their calculation methods or weighting can be changed.

scholarly journals A Lightweight Fusion Distillation Network for Image Deblurring and Deraining

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5312
Author(s):  
Yanni Zhang ◽  
Yiming Liu ◽  
Qiang Li ◽  
Jianzhong Wang ◽  
Miao Qi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Deblurring ◽  
Image Features ◽  
Image Feature ◽  
Model Complexity ◽  
Small Scale ◽  
Feature Maps ◽  
Learning Framework ◽  
Channel Information ◽  
Scale Spaces

Recently, deep learning-based image deblurring and deraining have been well developed. However, most of these methods fail to distill the useful features. What is more, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from a high computational burden. We propose a lightweight fusion distillation network (LFDN) for image deblurring and deraining to solve the above problems. The proposed LFDN is designed as an encoder–decoder architecture. In the encoding stage, the image feature is reduced to various small-scale spaces for multi-scale information extraction and fusion without much information loss. Then, a feature distillation normalization block is designed at the beginning of the decoding stage, which enables the network to distill and screen valuable channel information of feature maps continuously. Besides, an information fusion strategy between distillation modules and feature channels is also carried out by the attention mechanism. By fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring and deraining results with a smaller number of parameters and outperform the existing methods in model complexity.

scholarly journals Mutual Impact between Clock Gating and High Level Synthesis in Reconfigurable Hardware Accelerators

Electronics ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 73
Author(s):  
Francesco Ratto ◽  
Tiziana Fanni ◽  
Luigi Raffo ◽  
Carlo Sau
Keyword(s):  
Low Power ◽  
Integrated Circuit ◽  
Systems Design ◽  
Hardware Acceleration ◽  
High Level Synthesis ◽  
Clock Gating ◽  
Technology Application ◽  
Positive Effects ◽  
High Level ◽  
Different Levels

With the diffusion of cyber-physical systems and internet of things, adaptivity and low power consumption became of primary importance in digital systems design. Reconfigurable heterogeneous platforms seem to be one of the most suitable choices to cope with such challenging context. However, their development and power optimization are not trivial, especially considering hardware acceleration components. On the one hand high level synthesis could simplify the design of such kind of systems, but on the other hand it can limit the positive effects of the adopted power saving techniques. In this work, the mutual impact of different high level synthesis tools and the application of the well known clock gating strategy in the development of reconfigurable accelerators is studied. The aim is to optimize a clock gating application according to the chosen high level synthesis engine and target technology (Application Specific Integrated Circuit (ASIC) or Field Programmable Gate Array (FPGA)). Different levels of application of clock gating are evaluated, including a novel multi level solution. Besides assessing the benefits and drawbacks of the clock gating application at different levels, hints for future design automation of low power reconfigurable accelerators through high level synthesis are also derived.

scholarly journals Application of an Artificial Neural Network to Automate the Measurement of Kinematic Characteristics of Punches in Boxing

2021 ◽  
Vol 11 (3) ◽  
pp. 1223
Author(s):  
Ilshat Khasanshin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Kinematic Parameters ◽  
Constant Control ◽  
Measurement Units ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Effective Development ◽  
High Level ◽  
Different Levels

This work aimed to study the automation of measuring the speed of punches of boxers during shadow boxing using inertial measurement units (IMUs) based on an artificial neural network (ANN). In boxing, for the effective development of an athlete, constant control of the punch speed is required. However, even when using modern means of measuring kinematic parameters, it is necessary to record the circumstances under which the punch was performed: The type of punch (jab, cross, hook, or uppercut) and the type of activity (shadow boxing, single punch, or series of punches). Therefore, to eliminate errors and accelerate the process, that is, automate measurements, the use of an ANN in the form of a multilayer perceptron (MLP) is proposed. During the experiments, IMUs were installed on the boxers’ wrists. The input parameters of the ANN were the absolute acceleration and angular velocity. The experiment was conducted for three groups of boxers with different levels of training. The developed model showed a high level of punch recognition for all groups, and it can be concluded that the use of the ANN significantly accelerates the collection of data on the kinetic characteristics of boxers’ punches and allows this process to be automated.

Chinese Image Captioning via Fuzzy Attention-based DenseNet-BiLSTM

2021 ◽  
Vol 17 (1s) ◽  
pp. 1-18 ◽  
Author(s):  
Huimin Lu ◽  
Rui Yang ◽  
Zhenrong Deng ◽  
Yonglin Zhang ◽  
Guangwei Gao ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Contextual Information ◽  
Image Features ◽  
Context Information ◽  
Global Information ◽  
Image Description ◽  
Image Captioning ◽  
Image Content ◽  
Single Feature ◽  
Proposed Model

Chinese image description generation tasks usually have some challenges, such as single-feature extraction, lack of global information, and lack of detailed description of the image content. To address these limitations, we propose a fuzzy attention-based DenseNet-BiLSTM Chinese image captioning method in this article. In the proposed method, we first improve the densely connected network to extract features of the image at different scales and to enhance the model’s ability to capture the weak features. At the same time, a bidirectional LSTM is used as the decoder to enhance the use of context information. The introduction of an improved fuzzy attention mechanism effectively improves the problem of correspondence between image features and contextual information. We conduct experiments on the AI Challenger dataset to evaluate the performance of the model. The results show that compared with other models, our proposed model achieves higher scores in objective quantitative evaluation indicators, including BLEU , BLEU , METEOR, ROUGEl, and CIDEr. The generated description sentence can accurately express the image content.

scholarly journals Model-Driven Architectural Framework towards Safe and Secure Nuclear Power Reactors

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5136
Author(s):  
Bassem Ouni ◽  
Christophe Aussagues ◽  
Saadia Dhouib ◽  
Chokri Mraidha
Keyword(s):  
Nuclear Power ◽  
Nuclear Reactors ◽  
System Development ◽  
Levels Of Abstraction ◽  
Model Driven ◽  
Case System ◽  
Architectural Framework ◽  
Performance Check ◽  
High Level ◽  
Different Levels

Sensor-based digital systems for Instrumentation and Control (I&C) of nuclear reactors are quite complex in terms of architecture and functionalities. A high-level framework is highly required to pre-evaluate the system’s performance, check the consistency between different levels of abstraction and address the concerns of various stakeholders. In this work, we integrate the development process of I&C systems and the involvement of stakeholders within a model-driven methodology. The proposed approach introduces a new architectural framework that defines various concepts, allowing system implementations and encompassing different development phases, all actors, and system concerns. In addition, we define a new I&C Modeling Language (ICML) and a set of methodological rules needed to build different architectural framework views. To illustrate this methodology, we extend the specific use of an open-source system engineering tool, named Eclipse Papyrus, to carry out many automation and verification steps at different levels of abstraction. The architectural framework modeling capabilities will be validated using a realistic use case system for the protection of nuclear reactors. The proposed framework is able to reduce the overall system development cost by improving links between different specification tasks and providing a high abstraction level of system components.

Research on Biological Materials by Applied Technology with an Algorithm for Identifying and Counting Cells in Microscopic Particle Image

2014 ◽  
Vol 540 ◽  
pp. 352-355
Author(s):  
Sui Yuan Zhang ◽  
Rui Wang ◽  
Xian Qiao Chen ◽  
Ze Wu Jiang ◽  
Xiang Cai
Keyword(s):  
Particle Image ◽  
Dynamic Threshold ◽  
Biological Cells ◽  
Edge Detecting ◽  
Applied Technology ◽  
Channel Information ◽  
High Level ◽  
The Impact ◽  
Fundamental Units ◽  
Rule Out

Cells are fundamental units of life, and the key point in the field of biomaterial. Biological cells are always with high density, small nucleus and much impurities. Based on the technology of image processing, we propose a new method to count cells on the image of microscopic cells with high level of recognition. To precisely count the number, our method includes edge detecting and marking, efficient usage of three channel information of enhanced nucleus, binaryzation of dynamic threshold in separated areas and finally denoising. The experiment shows that the method is precise and quickly-reacted, moreover it can effectively rule out the impact of impurities. With little adjustment, it can apply to some other fields, not only decrease the labor involved, but the budget as well.

Sign in / Sign up

Export Citation Format

Share Document