检索结果-内蒙古大学图书馆

A deep learning perspective on electro-hydrodynamic micro-droplet interface deformation characteristics

CHEMICAL ENGINEERING SCIENCE 2023年第1期276卷

作者： Hao, Guanqiu Li, Enhui Li, Jia-Xin Zhang, He Zhong, Mingliang Liu, Xiangdong Wang, Ji-Xiang Chen, Yongping Yangzhou Univ Coll Elect Energy & Power Engn Yangzhou 225009 Peoples R China Hong Kong Univ Sci & Technol Dept Mech & Aerosp Engn Kowloon Hong Kong Peoples R China Southeast Univ Sch Energy & Environm Key Lab Energy Thermal Convers & Control Minist Educ Nanjing 210096 Peoples R China Beijing Inst Elect Engn Beijing 100854 Peoples R China China Acad Launch Vehicle Technol Beijing 100076 Peoples R China Chinese Acad Sci Inst Opt & Elect Chengdu 610209 Peoples R China Hong Kong Polytech Univ Dept Mech Engn Hung Hom Hong Kong Peoples R China

Micro-droplet electro-hydrodynamic deformations under combined shear flow and electric fields were investi-gated experimentally where droplet deformation mechanisms were revealed. Here two deep learning algorithms (DNN and deepFM) were applied for better prediction accuracy in deformation characteristics (deformation parameter D and tilt angle phi). The DNN model showed better universal predicting accuracy (verified not for our experimental data but for data from previous publications). Specifically, the majority of DNN-based predictions were within a relative error of +/- 8 %, gaining a major superiority compared with previous prediction models. Additionally, the use of a unique smart-sized training dataset for high accuracy without a large-scale data pool is another innovation, pioneering the deep-learning-based high-accuracy small-sample modeling. Considering the low accuracy from traditional models and the reduction in data scale requirement of the deep-learning-based method developed here, such a method can be extended to other complex multiphysics-controlled micro -fluidic droplet modeling in chemical and thermo-fluid engineering.

关键词： Micro-droplet regulation deep learning algorithm Multi-physics fields Interfacial sciences Fluid dynamics Deformation prediction

来源：评论

学校读者我要写书评

暂无评论

Screening the phytotoxicity of micro/nanoplastics through non-targeted metallomics with synchrotron radiation X-ray fluorescence and deep learning: Taking micro/nano polyethylene terephthalate as an example

引用

JOURNAL OF HAZARDOUS MATERIALS 2024年 463卷 132886页

作者： Xie, Hongxin Wei, Chaojie Wang, Wei Chen, Rui Cui, Liwei Wang, Liming Chen, Dongliang Yu, Yong-Liang Li, Bai Li, Yu-Feng Northeastern Univ Coll Sci Dept Chem Shenyang 110819 Liaoning Peoples R China Chinese Acad Sci Inst High Energy Phys CAS HKU Joint Lab Met Hlth & Environm Beijing 100049 Peoples R China Chinese Acad Sci Inst High Energy Phys CAS Key Lab Biomed Effects Nanomat & Nanosafety Beijing 100049 Peoples R China Chinese Acad Sci Inst High Energy Phys Beijing Met Facil Beijing 100049 Peoples R China Chinese Acad Sci Inst High Energy Phys Natl Consortium Excellence Met Beijing 100049 Peoples R China China Agr Univ Coll Engn Beijing 100083 Peoples R China Beijing Acad Sci & Technol Inst Urban Safety & Environm Sci Beijing Key Lab Occupat Safety & Hlth Beijing 100054 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci Inst High Energy Phys Beijing Synchrotron Radiat Facil Beijing 100049 Peoples R China

Microplastics (MPs) and nanoplastics (NPs) are global pollutants with emerging concerns. Methods to predict and screen their toxicity are crucial. Elemental dyshomeostasis can be used to assess toxicity of environmental pollutants. Non-targeted metallomics, combining synchrotron radiation X-ray fluorescence (SRXRF) and machine learning, has successfully differentiated cancer patients from healthy individuals. The whole idea of this work is to screen the phytotoxicity of nano polyethylene terephthalate (nPET) and micro polyethylene terephthalate (mPET) through non-targeted metallomics with SRXRF and deep learning algorithms. Firstly, Seed germination, seedling growth, photosynthetic changes, and antioxidant activity were used to evaluate the toxicity of mPET and nPET. It was showed that nPET, at 10 mg/L, was more toxic to rice seedlings, inhibiting growth and impairing chlorophyll content, MDA content, and SOD activity compared to mPET. Then, rice seedling leaves exposed to nPET or mPET was examined with SRXRF, and the SRXRF data was differentiated with deep learning algorithms. It was showed that the one-dimensional convolutional neural network (1D-CNN) model achieved 98.99% accuracy without data preprocessing in screening mPET and nPET exposure. In all, non-targeted metallomics with SRXRF and 1D-CNN can effectively screen the exposure and phytotoxicity of nPET/mPET and potentially other emerging pollutants. Further research is needed to assess the phytotoxicity of different types of MPs/NPs using non-targeted metallomics.

关键词： Polyethylene terephthalate Toxicity Rice plant Synchrotron radiation X-ray fluorescence deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on identification and zoning control of territorial spatial risk pattern based on deep learning: A case study of Shenzhen, China

引用

JOURNAL OF CLEANER PRODUCTION 2024年 481卷

作者： Xia, Chenhong Ma, Donghui Wang, Wei Guo, Xiaodong Beijing Univ Technol Sch Architecture & Urban Planning Beijing 100124 Peoples R China

In the era of globalization, digitalization, and diversification, currently societal cities face risks intertwined by uncertainty and complexity. Thus, it is crucial to address risks concerns to achieve modernization of spatial management. Moreover, how to scientifically identify the risk pattern of territorial space and how to map and control it in space becomes a critical and urgent issue to be addressed for achieving modernization of spatial management. Understanding the intricate relationship between land use, environmental factors, and population density is essential for identifying risk patterns that can inform effective disaster management strategies. By employing advanced analytical methods, this study aims to provide a comprehensive framework for recognizing and mitigating territorial spatial risks in an increasingly complex urban landscape. This study used a case study to conduct the unsupervised algorithm of stack autoencoder self-organizing map to analyze the distribution and spatial clustering of Shenzhen's land spatial risk pattern and reveal the driving mechanism of its risk pattern formation in detail. It was found that: (1) The overall territorial spatial risk pattern of Shenzhen presents a distribution trend of "high in the west and low in the east, high in the south and low in the north";that is, I and II risk areas are clustered in the hilly areas in the northeast and IV and V risk areas in the coastal areas in the southwest;(2) Population density, land use intensity, seawater intrusion, geological disasters, relief amplitude, soil type, soil erosion intensity are the main driving forces for the formation of Shenzhen's territorial spatial risk pattern. In particular, seawater intrusion, population density and land use intensity, soil type were found having significantly synergistic impact on the risk pattern.

关键词： Territorial space Risk pattern identification Spatial clustering analysis Zoning control deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

deep-learning-Based Pitch Controller for Floating Offshore Wind Turbine Systems with Compensation for Delay of Hydraulic Actuators

引用

ENERGIES 2022年第9期15卷 3136页

作者： Roh, Chan In Je Univ Dept Energy Engn 197 Inje Ro Gimhaesi 50834 South Korea

The pitch controller of a floating offshore wind power system has an important influence on the power generation and movement of the floating body. It drives the turbine blade pitch using a hydraulic actuator, whose inherent characteristics cause a delay in response, which increases with the system capacity. As a result, the power generation is reduced, and the pitch motion of the floating body is increased. This paper proposes an advanced pitch controller designed to compensate for the delay in the hydraulic actuator response. The proposed pitch controller applies an artificial-intelligence-based deep learning algorithm to predict the delay time in the hydraulic actuator. This delay is compensated for by preferentially predicting the blade pitch control angle even if a delay occurs in the hydraulic actuator. The performance of the proposed pitch controller was analyzed using the Fatigue, Aerodynamics, Structures, and Turbulence (FAST) v8 model developed by the US National Renewable Energy Laboratory and was compared against that of the ideal pitch controller and the pitch controller that reflects the response delay. Compared with the latter, the proposed method increased the average power generation by approximately 5% and reduced the standard deviation of the floating body's pitch motion by approximately 50%.

关键词： floating offshore wind turbine pitch controller hydraulic actuator time delay deep learning algorithm long short-term memory Fatigue Aerodynamics Structures and Turbulence (FAST)

来源：评论

学校读者我要写书评

暂无评论

Decoupled Temperature-Pressure Sensing System for deep learning Assisted Human-Machine Interaction

引用

ADVANCED FUNCTIONAL MATERIALS 2024年第52期34卷

作者： Chen, Zhaoyang Liu, Shun Kang, Pengyuan Wang, Yalong Liu, Hu Liu, Chuntai Shen, Changyu Zhengzhou Univ Natl Engn Res Ctr Adv Polymer Proc Technol State Key Lab Struct Anal Optimizat & CAE Software Zhengzhou 450002 Henan Peoples R China

With the rapid development of intelligent wearable technology, multimodal tactile sensors capable of data acquisition, decoupling of intermixed signals, and information processing have attracted increasing attention. Herein, a decoupled temperature-pressure dual-mode sensor is developed based on single-walled carbon nanotubes (SWCNT) and poly(3,4-ethylenedioxythiophene): poly(styrenesulfonate) (PEDOT:PSS) decorated porous melamine foam (MF), integrating with a deep learning algorithm to obtain a multimodal input terminal. Importantly, the synergistic effect of PEDOT:PSS and SWCNT facilitates the sensor with ideal decoupling capability and sensitivity toward both temperature (38.2 mu V K-1) and pressure (10.8% kPa-1) based on the thermoelectric and piezoresistive effects, respectively. Besides, the low thermal conductivity and excellent compressibility of MF also endow it with the merits of a low-temperature detection limit (0.03 K), fast pressure response (120 ms), and long-term stability. Benefiting from the outstanding sensing characteristics, the assembled sensor array showcases good capacity for identifying spatial distribution of temperature and pressure signals. With the assistance of a deep learning algorithm, it displays high recognition accuracy of 99% and 98% corresponding to "touch" and "press" actions, respectively, and realizes the encrypted transmission of information and accurate identification of random input sequences, providing a promising strategy for the design of high-accuracy multimodal sensing platform in human-machine interaction. SWCNT/PEDOT:PSS@melamine foam (SPMF) sensor with 3D porous structure are available for fully decoupled temperature-pressure dual-mode sensing with high sensitivity, ultralow temperature detection limits, fast response times, and excellent fatigue resistance. Meanwhile, with the assistance of deep learning model, the multimodal input terminal of SPMF sensor arrays achieved encrypted transmission of information and ac

关键词： decoupled temperature-pressure sensing deep learning algorithm dual-mode sensor human-machine interface thermoelectric effects

来源：评论

学校读者我要写书评

暂无评论

Aboveground biomass estimates of tropical mangrove forest using Sentinel-1 SAR coherence data - The superiority of deep learning over a semi-empirical model

引用

COMPUTERS & GEOSCIENCES 2021年 150卷 104737-104737页

作者： Ghosh, S. M. Behera, M. D. IIT Kharagpur CORAL SAM Lab Kharagpur W Bengal India

The availability of advanced Machine learning algorithms has made the estimation process of biophysical parameters more efficient. However, the efficiency of those methods seldom compared with the efficiency of already established semi-empirical procedures. Aboveground biomass (AGB) of mangrove forests is a crucial biophysical parameter as it is positively correlated to the carbon stocks and fluxes. The free availability of Sentinel-1 C-band SAR data and machine learning algorithms hold promises in estimating AGB of tropical mangrove forests. We reported high AGB (70 t/ha to 666 t/ha) using 185 field quadrats of 0.04ha each from Bhitarkanika Wildlife Sanctuary, located on the eastern Indian coast that could be attributed to species composition. The AGB maps generated using Interferometric Water Cloud Model (IWCM) and deep learning models were different from each other as they rely on different variables. IWCM was more dependent, especially on ground and vegetation components of coherence, while canopy height acted as the most crucial variable in the deep learning model. However, the negligible variations in deep learning-based AGB maps can be attributed to interpreting the importance of coherence and VH backscatter. Due to low canopy penetration power of C-band SAR, high temporal decorrelation resulting from longer time gap between interferometric image pairs, and high spatial heterogeneity of mangrove forests, IWCM found as an unsuitable method for AGB estimation. Interestingly, a deep learning algorithm could translate the exact relationship between predictor variables and mangrove AGB in Bhitarkanika Wildlife Sanctuary. The AGB estimation studies in mangrove forests using Sentinel data should focus more on using machine learning algorithms like deep learning rather than semi-empirical models.

关键词： Interferometric Water Cloud Model SAR remote sensing Machine learning Temporal decorrelation deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimization of Physical Layer Security for Channel Estimation based on deep learning

International Core Journal of Engineering

引用

International Core Journal of Engineering 2023年第7期9卷 124-133页

作者： Yuzhou Ning

Wireless channel estimation is the basis of communication security. In the communication system, due to the time-varying channel, there is a certain error between the channel state information(CSI) of the channel estimation and the real CSI, In this paper, considering the condition that the CSI of eavesdropping channel is unidentified, the legitimate channel is estimated by pilot frequency. the correlation between the main channel and eavesdropping channel is used to estimate the CSI of eavesdropping channel, introducing deep Neural Network(DNN) to extract channel features. At the same time, improving the algorithm by adding the pre-training process to avoid the error caused by random initialization. After obtaining the channel characteristics, the channel security capacity is calculated to evaluate the performance of the physical layer security. The simulation results show that the scheme can improve the accuracy of channel estimation, enhance the channel secrecy capacity.

关键词： Time-varying Channel Estimation deep learning algorithm Physical Layer Security

来源：评论

学校读者我要写书评

暂无评论

Explainable deep learning Model for Predicting Serious Adverse Events in Hospitalized Geriatric Patients Within 72 Hours

引用

Clinical interventions in aging 2024年 19卷 1051-1063页

作者： Ting-Yu Hsu Chi-Yung Cheng I-Min Chiu Chun-Hung Richard Lin Fu-Jen Cheng Hsiu-Yung Pan Yu-Jih Su Chao-Jui Li Department of Emergency Medicine Kaohsiung Chang Gung Memorial Hospital Chang Gung University College of Medicine Kaohsiung Taiwan. Department of Computer Science and Engineering National Sun Yat-Sen University Kaohsiung Taiwan. Department of Internal Medicine Division of Rheumatology Allergy and Immunology Kaohsiung Chang Gung Memorial Hospital Kaohsiung Taiwan.

Background:The global aging population presents a significant challenge, with older adults experiencing declining physical and cognitive abilities and increased vulnerability to chronic diseases and adverse health outcomes. This study aims to develop an interpretable deep learning (DL) model to predict adverse events in geriatric patients within 72 hours of hospitalization. Methods:The study used retrospective data (2017-2020) from a major medical center in Taiwan. It included non-trauma geriatric patients who visited the emergency department and were admitted to the general ward. Data preprocessing involved collecting prognostic factors like vital signs, lab results, medical history, and clinical management. A deep feedforward neural network was developed, and performance was evaluated using accuracy, sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC). Model interpretation utilized the Shapley Additive Explanation (SHAP) technique. Results:The analysis included 127,268 patients, with 2.6% experiencing imminent intensive care unit transfer, respiratory failure, or death during hospitalization. The DL model achieved AUCs of 0.86 and 0.84 in the validation and test sets, respectively, outperforming the Sequential Organ Failure Assessment (SOFA) score. Sensitivity and specificity values ranged from 0.79 to 0.81. The SHAP technique provided insights into feature importance and interactions. Conclusion:The developed DL model demonstrated high accuracy in predicting serious adverse events in geriatric patients within 72 hours of hospitalization. It outperformed the SOFA score and provided valuable insights into the model's decision-making process.

关键词： adverse events deep learning algorithm explainable machine learning mortality

来源：评论

学校读者我要写书评

暂无评论

deep learning approach for automatic out-of-plane needle localisation for semi-automatic ultrasound probe calibration

引用

HEALTHCARE TECHNOLOGY LETTERS 2019年第6期6卷 204-209页

作者： Groves, Leah A. Vanberlo, Blake Peters, Terry M. Chen, Elvis C. S. Univ Western Ontario Sch Biomed Engn London ON Canada Univ Western Ontario Robarts Res Inst London ON Canada Univ Western Ontario Schulich Sch Med London ON Canada Univ Western Ontario Med Biophys London ON Canada

The authors present a deep learning algorithm for the automatic centroid localisation of out-of-plane US needle reflections to produce a semi-automatic ultrasound (US) probe calibration algorithm. A convolutional neural network was trained on a dataset of 3825 images at a 6 cm imaging depth to predict the position of the centroid of a needle reflection. Applying the automatic centroid localisation algorithm to a test set of 614 annotated images produced a root mean squared error of 0.62 and 0.74 mm (6.08 and 7.62 pixels) in the axial and lateral directions, respectively. The mean absolute errors associated with the test set were 0.50 +/- 0.40 mm and 0.51 +/- 0.54 mm (4.9 +/- 3.96 pixels and 5.24 +/- 5.52 pixels) for the axial and lateral directions, respectively. The trained model was able to produce visually validated US probe calibrations at imaging depths on the range of 4-8 cm, despite being solely trained at 6 cm. This work has automated the pixel localisation required for the guided-US calibration algorithm producing a semi-automatic implementation available open-source through 3D Slicer. The automatic needle centroid localisation improves the usability of the algorithm and has the potential to decrease the fiducial localisation and target registration errors associated with the guided-US calibration method.

关键词： medical image processing calibration learning (artificial intelligence) needles image registration mean square error methods biomedical ultrasonics convolutional neural nets out-of-plane needle localisation semiautomatic ultrasound probe calibration deep learning algorithm needle reflection probe calibration algorithm convolutional neural network automatic centroid localisation algorithm probe calibrations pixel localisation semiautomatic implementation automatic needle centroid localisation target registration errors calibration method size 6 0 cm size 4 0 cm to 8 0 cm

来源：评论

学校读者我要写书评

暂无评论

deep learning based remote sensing technique for environmental parameter retrieval and data fusion from physical models

引用

ARABIAN JOURNAL OF GEOSCIENCES 2021年第13期14卷 1230-1230页

作者： Vemuri, Ratna Kumari Reddy, Pundru Chandra Shaker Kumar, B. S. Puneeth Ravi, Jayavadivel Sharma, Sudhir Ponnusamy, Sivakumar PVP Siddhartha Inst Technol Dept Elect & Commun Engn Vijayawada 520007 Andhra Pradesh India CMR Coll Engn & Technol Dept Comp Sci & Engn Hyderabad Telangana India St Josephs Coll Dept Comp Sci Lalbagh Rd Bengaluru India Lovely Profess Univ Dept Comp Sci & Engn GT Rd Phagwara 144411 Punjab India Birla Inst Appl Sci Dept CSE Naini Tal 263136 Uttarakhand India SRM Inst Sci & Technol Dept Comp Sci & Engn Ghaziabad 201204 Uttar Pradesh India

Signal and data processing has established a new standard by using deep learning (DL) and deep neural network (DNN). This is done by obtaining advanced performance in terms of audio, image, and understanding of the language naturally. The major research in remote sensing has been given to the DL (deep learning) applications. The main application of deep learning in remote sensing is the classification of the data. The quality of the data received from the remote sensing sensors is insufficient. Thus, equal importance has to be given to the challenges associated with the magnification of these low-quality images. Addressing such challenges becomes predominant as it involves different environmental conditions, the tradeoff in the imaging system, and varying altitude images. This becomes the reason for the low quality of observations, thus making classification and identification a difficult task. Another huge challenge faced in the process of classification and identification is the heterogeneous nature of the remote sensing sensors. This also affects the efficiency and effectiveness of the data from remote sensing. The approaches for processing the remote sensing data can be improved by using the multi-modal datasets from the increasing sensing and additional secondary datasets when handy applications primary consideration. This makes researchers around the world get more interest in the fusion of data from multi-source for application diversity. The temporal data integration with spectral or spatial information is made possible using the spaceborne sensor's revisit capabilities. It helps in the representation of data structures with fresh data that is time variable, as well as data extraction techniques. Thus, this paper involves the development of the deep learning technique which is based on the remote sensing data for the extraction of features from the environmental parameters.

关键词： deep learning algorithm Remote sensing technique Temporal data fusion deep neural 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：