检索结果-内蒙古大学图书馆

Skyr-Net: deep learning approach for image classification of magnetic structures

JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS 2025年 621卷

作者： Cimen, Mahmut Onel, Aykut Can Yarimbiyik, A. Emre Arikan, Mustafa Tulum, Gokalp Uskudar Univ TR-34662 Istanbul Turkiye Gebze Tech Univ Dept Phys TR-41400 Gebze Kocaeli Turkiye Natl Metrol Inst UBITAK UME POB 54 TR-41470 Gebze Kocaeli Turkiye Topkapi Univ TR-34662 Zeytinburnu Turkiye

We investigate magnetic Skyrmions in Co/Pt ferromagnet-heavy metal bilayers via micromagnetic simulations and deep learning algorithms. Skyrmions can be described as small, knot-like magnetic structures that can provide high data density and offer rapid data processing with low energy consumption. Spin textures at the Co/Pt bilayer interface were simulated by solving Landau-Lifshitz-Gilbert equation using MuMax3 software and pre-trained deep learning methods are used for classifying simulated magnetic structure images. Here we introduce Skyr-Net, a novel deep learning model, which was created for classifying magnetic structure images, for the first time. The Skyr-Net achieves best result among deep learning methods for magnetic spin texture classifying in terms of the combination of computing time and accuracy (99.9%).

关键词： Magnetic skyrmions Micromagnetic simulations deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Natural Language Processing Model Transfer Strategy Tailored for deep learning Platforms

引用

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 2025年第2期34卷

作者： Wang, Zhixue Kang, Kai Ningxia Normal Univ Sch Math & Comp Sci Guyuan 550001 Ningxia Peoples R China

As artificial intelligence technology continues to evolve, numerous advancements enable smoother communication and collaboration between humans and computers. Natural language processing (NLP), as a key direction in the field of computer and artificial intelligence, has been attracting much attention. It focuses on the language used by people in daily life, devoting itself to improving the ability of language generation and understanding, thus making communication between people and computers more fluent and natural, effectively breaking through the problem of human-computer interaction. With the advancement of deep learning technology, the migration of NLP models onto deep learning platforms has emerged as a key trend. Model transfer, a crucial aspect of deep learning, holds significant value in enhancing the performance and efficiency of NLP models. This paper begins by outlining the fundamentals of deep learning platforms and NLP model transfer, followed by a comprehensive examination of current research progress and challenges in this field. Subsequently, we introduce a novel NLP model transfer strategy tailored for deep learning platforms and validate its effectiveness through rigorous experiments. In conclusion, the paper highlights our noteworthy advancements, pointing toward promising future developments.

关键词： deep learning algorithm transfer of natural language processing model migration of the model

来源：评论

学校读者我要写书评

暂无评论

A Highly Sensitive, Conductive, and Flexible Hydrogel Sponge as a Discriminable Multimodal Sensor for deep-learning-Assisted Gesture Language Recognition

引用

ADVANCED FUNCTIONAL MATERIALS 2025年第10期35卷

作者： Fu, Yu Yang, Chen Zhang, Boqiang Wan, Zhenshuai Wang, Shuangkun Zhang, Kun Yang, Liuhua Wei, Ronghan Henan Univ Technol Sch Mech & Elect Engn Zhengzhou 450001 Peoples R China Zhengzhou Univ Sch Mech & Safety Engn Zhengzhou 450001 Peoples R China Henan Polytech Univ Sch Civil Engn Jiaozuo 454000 Peoples R China

Flexible multimodal sensors have gained increasing popularity for applications in healthcare and extreme environment operations owing to their all-around environmental perception and data acquisition capabilities. However, fabricating a magnetism-mechanics-humidity multimodal sensor that possesses high sensitivity without signal overlapping while in a facile methodology remains a great challenge. Herein, a highly sensitive, conductive, and flexible hydrogel sponge sensor with discriminable magnetism, mechanics, and humidity sensing capability is proposed, which shows stable pore size (19.30 mu m) and satisfactory mechanical properties based on the synergistic hydrogen bonding among sodium alginate, poly(vinyl alcohol) and glycerol. The proposed sensors can not only display favorable humidity sensing ability with rapid response/recovery time (2.5/4 s) but also possess enhanced sensitivities (a gauge factor of 0.46 T-1 for magnetic field, -1.16 kPa-1 for pressure), superior stability and durability (over 8000 cycles). Benefiting from the separated capacitive and resistive response signals, the sensors can precisely distinguish the magnetic, mechanical, and humidity stimuli without cross-talk. Further, the sensor arrays assisted by the deep learning algorithm are developed to realize gesture language recognition with a high accuracy of 99.17%. It can be believed that this high-performance sensor will have good prospects in future soft electronics and human-machine interaction systems. A flexible hydrogel sponge sensor with discriminable multimodal sensing capability is fabricated by a multilayer assembly strategy, displaying favorable sensitivities, stability, and durability. Benefiting from the separated capacitive and resistive responses, it can precisely distinguish the magnetic, mechanical, and humidity stimuli without cross-talk. The sensor arrays assisted by deep learning algorithms are developed to realize gesture language recognition. image

关键词： deep learning algorithm discriminable magnetism-mechanics-humidity sensing gesture language recognition hydrogel sponge multimodal sensor

来源：评论

学校读者我要写书评

暂无评论

deep learning-assisted detection of intracranial hemorrhage: validation and impact on reader performance

引用

NEURORADIOLOGY 2025年 1-9页

作者： Kang, Dong-Wan Kim, Museong Park, Gi-Hun Kim, Yong Soo Han, Moon-Ku Lee, Myungjae Kim, Dongmin Ryu, Wi-Sun Jeong, Han-Gil Seoul Natl Univ Bundang Hosp Coll Med Div Intens Care Med Seongnam South Korea Seoul Natl Univ Bundang Hosp Coll Med Dept Neurosurg Seongnam South Korea Seoul Natl Univ Bundang Hosp Coll Med Dept Neurol Seongnam South Korea Seoul Natl Univ Bundang Hosp Coll Med Hosp Med Ctr Seongnam South Korea JLK Inc Artificial Intelligence Res Ctr Seoul South Korea

PurposeIntracranial hemorrhage (ICH) requires urgent treatment, and accurate and timely diagnosis is essential for improving outcomes. This pivotal clinical trial aimed to validate a deep learning algorithm for ICH detection and assess its clinical utility through a reader performance *** CT scans from patients with and without ICH were collected from a tertiary hospital. Two experts evaluated all scans, with a third expert reviewing disagreements for the final diagnosis. We analyzed the performance of the deep learning algorithm, JLK-ICH, for all cases and ICH subtypes. Additional external validation was performed using a multi-ethnic U.S. dataset. A reader performance study included six non-expert readers who evaluated 800 CT scans, with and without JLK-ICH assistance, following a washout period. ICH presence and five-point scale confidence level for decisions were *** total of 1,370 CT scans were evaluated. The deep learning model showed 98.7% sensitivity (95% confidence interval [CI] 97.8-99.3%), 88.5% specificity (95% CI, 83.6-92.3%), and an area under the receiver operating characteristic curve (AUROC) of 0.936 (95% CI, 0.915-0.957). The model maintained high accuracy across all ICH subtypes, and additional external validation confirmed these results. In the reader performance study, AUROC with JLK-ICH assistance (0.967 [0.953-0.981]) surpassed that without assistance (0.953 [0.938-0.957];P = 0.009). JLK-ICH particularly improved performance when readers were highly *** JLK-ICH algorithm demonstrated high accuracy in detecting all ICH subtypes. Non-expert readers significantly improved diagnostic accuracy for brain CT scans with deep learning assistance.

关键词： Intracranial hemorrhage deep learning algorithm Diagnostic accuracy Computed tomography Reader performance Clinical utility

来源：评论

学校读者我要写书评

暂无评论

Age and gender-related changes in choroidal thickness: Insights from deep learning analysis of swept-source OCT images

引用

PHOTODIAGNOSIS AND PHOTODYNAMIC THERAPY 2025年 52卷 104511-104511页

作者： Song, Dan Wang, Guanzheng Liu, Guangfeng Zhang, Chengxia Lv, Bin Ni, Yuan Xie, Guotong Peking Univ Int Hosp Dept Ophthalmol 1 Shengmingyuan RdZhongguancun Life Sci Pk Beijing Peoples R China Ping An Technol 12F Bldg B PingAn IFC 1-3 Xinyuan South Rd Beijing 100027 Peoples R China Ping An Hlth Cloud Co Ltd PingAn IFC 12F Bldg BPingAn IFC1-3 Xinyuan South Rd Beijing 100027 Peoples R China

Background: The choroid is a vital vascular layer of the eye, essential for maintaining ocular health. Understanding its structural variations, particularly choroidal thickness (CT), is crucial for the early detection of diseases, such as age-related macular degeneration (AMD), high myopia (HM), and diabetes mellitus (DM). Recent advancements in deep learning have significantly improved the segmentation and measurement of choroidal layers. Objective: This study aims to investigate age- and gender-related changes in CT and its components through deep learning analysis of swept-source optical coherence tomography (SS-OCT) images. Methods: A total of 262 participants (136 females and 126 males) were recruited from Peking University International Hospital. Exclusion criteria included ocular pathologies and systemic conditions. SS-OCT was utilized for CT, Sattler layer-choriocapillaris complex thickness (SLCCT), and Haller layer thickness (HLT) measurements. auto-measurement method, based on deep learning algorithms, ensured accuracy. Ethics approval and informed consent were obtained from all participants. Findings: Significant thinning of CT and SLCCT was observed after the age of 60, with HLT declining after the age of 30. Females exhibited marked thinning between the ages of 40 and 50, while males began to show thinning at age 60. Conclusion and Implications: This research highlights age-related changes in choroidal thickness, with a particular emphasis on gender differences. The findings suggest that females experience earlier thinning, potentially attributable to hormonal changes. Additionally, the study validates the efficiency of deep learning algorithms in measuring choroidal thickness, thereby enhancing the reliability of clinical practice.

关键词： Choroidal thickness Haller layer thickness Sattler layer-choriocapillaris complex thickness deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

An algorithm for using deep learning convolutional neural networks with three dimensional depth sensor imaging in scoliosis detection

引用

SPINE JOURNAL 2021年第6期21卷 980-987页

作者： Kokabu, Terufumi Kanai, Satoshi Kawakami, Noriaki Uno, Koki Kotani, Toshiaki Suzuki, Teppei Tachi, Hiroyuki Abe, Yuichiro Iwasaki, Norimasa Sudo, Hideki Hokkaido Univ Hosp Dept Orthoped Surg Kita Ward Nishi 5 Chome Kita 14 Jo Sapporo Hokkaido 0608648 Japan Eniwa Hosp Dept Orthoped Surg Koganechuo 2-1-1 Eniwa Hokkaido 0611449 Japan Hokkaido Univ Div Syst Sci & Informat Grad Sch Informat Sci & Technol Kit Ward Nishi 9 Chome Kita 13 Jo Sapporo Hokkaido 0600813 Japan Ichinomiyanishi Hosp Dept Orthoped Surg Aza Hira 1 Kaimei Aichi 4940001 Japan Natl Hosp Org Kobe Med Ctr Dept Orthoped Surg Suma Ward 3 Chome 1-1 Nishiochiai Kobe Hyogo 6540155 Japan Seirei Sakura Citizen Hosp Dept Orthoped Surg 2 Chome 36-2 Ebaradai Sakura Chiba 2858765 Japan Hokkaido Univ Fac Med Dept Adv Med Spine & Spinal Cord Disorders N15W7 Sapporo Hokkaido 0608638 Japan Hokkaido Univ Grad Sch Med N15W7 Sapporo Hokkaido 0608638 Japan

BACKGROUND CONTEXT: Timely intervention in growing individuals, such as brace treatment, relies on early detection of adolescent idiopathic scoliosis (AIS). To this end, several screening methods have been implemented. However, these methods have limitations in predicting the Cobb angle. PURPOSE: This study aimed to evaluate the performance of a three-dimensional depth sensor imaging system with a deep learning algorithm, in predicting the Cobb angle in AIS. STUDY DESIGN: Retrospective analysis of prospectively collected, consecutive, nonrandomized series of patients at five scoliosis centers in Japan. PATIENT SAMPLE: One hundred and-sixty human subjects suspected to have AIS were included. OUTCOME MEASURES: Patient demographics, radiographic measurements, and predicted Cobb angle derived from the deep learning algorithm were the outcome measures for this study. METHODS: One hundred and sixty data files were shuffled into five datasets with 32 data files at random (dataset 1, 2, 3, 4, and 5) and five-fold cross validation was performed. The relationships between the actual and predicted Cobb angles were calculated using Pearson's correlation coefficient analyses. The prediction performances of the network models were evaluated using mean absolute error and root mean square error between the actual and predicted Cobb angles. The shuffling into five datasets and five-fold cross validation was conducted ten times. There were no study-specific biases related to conflicts of interest. RESULTS: The correlation between the actual and the mean predicted Cobb angles was 0.91. The mean absolute error and root mean square error were 4.0 degrees and 5.4 degrees, respectively. The accuracy of the mean predicted Cobb angle was 94% for identifying a Cobb angle of >= 10 degrees and 89% for that of >= 20 degrees. CONCLUSIONS: The three-dimensional depth sensor imaging system with its newly innovated convolutional neural network for regression is objective and has significant ability

关键词： Accuracy Adolescent idiopathic scoliosis Cobb angle Convolutional neural network for regression Correlation coefficient analyses deep learning algorithm Mean absolute error Noncontact and noninvasive system Three-dimensional depth sensor

来源：评论

学校读者我要写书评

暂无评论

Liquid Biopsy Instrument for Ultra-Fast and Label-Free Detection of Circulating Tumor Cells

引用

Research 2025年第1期2024卷 803-814页

作者： Shu Zhu Zhixian Zhu Chen Ni Zheng Zhou Yao Chen Dezhi Tang Kefan Guo Shuai Yang Kang Liu Zhonghua Ni Nan Xiang School of Mechanical Engineering and Jiangsu Key Laboratory for Design and Manufacture of Micro-Nano Biomedical InstrumentsSoutheast UniversityNanjing 211189China School of Electrical and Automation Engineering and Jiangsu Key Laboratory of 3D Printing Equipment and ManufacturingNanjing Normal UniversityNanjing 210023China

Rapid diagnosis and real-time monitoring are of great important in the fight against ***,most available diagnostic technologies are time-consuming and labor-intensive and are commonly ***,we describe CytoExam,an automatic liquid biopsy instrument designed based on inertial microfluidics and impedance cytometry,which uses a deep learning algorithm for the analysis of circulating tumor cells(CTCs).In silico and in vitro experiments demonstrated that CytoExam could achieve label-free detection of CTCs in the peripheral blood of cancer patients within 15 *** clinical applicability of CytoExam was also verified using peripheral blood samples from 10 healthy donors and>50 patients with breast,colorectal,or lung *** differences in the number of collected cells and predicted CTCs were observed between the 2 groups,with variations in the dielectric properties of the collected cells from cancer patients also being *** ultra-fast and minimally invasive features of CytoExam may pave the way for new paths for cancer diagnosis and scientific research.

关键词： analysis circulating tumor cells ctcs liquid biopsy liquid biopsy instrument impedance cytometrywhich diagnostic technologies vitro experiments deep learning algorithm inertial microfluidics

来源：评论

学校读者我要写书评

暂无评论

YOLO-SDH: improved YOLOv5 using scaled decoupled head for object detection

引用

INTERNATIONAL JOURNAL OF MACHINE learning AND CYBERNETICS 2025年第3期16卷 1643-1660页

作者： Ren, Zhijie Yao, Kang Sheng, Silong Wang, Beibei Lang, Xianli Wan, Dahang Fu, Weiwei Univ Sci & Technol China Sch Biomed Engn Suzhou Div Life Sci & Med Hefei 230026 Peoples R China Chinese Acad Sci Suzhou Inst Biomed Engn & Technol Suzhou 215163 Peoples R China Hefei Univ Technol Sch Instrument Sci & Optoelect Engn Hefei 230009 Peoples R China

As a crucial component of computer vision tasks, object detection serves a significant role in a variety of fields, including autonomous driving, defect detection, and remote sensing image recognition. However, the majority of current object detection networks fail to achieve a decent balance between detection accuracy and detection efficiency, and there is room for improvement in terms of detection accuracy. In response, to improve detection accuracy, a more efficient network framework, YOLO-SDH, was proposed in this paper based on You Only Look Once v5 (YOLOv5). In addition, a decoupled head that automatically adjusts the number of channels according to the model size was proposed, which can enhance the network's detection effect by separating the classification and regression *** the premise of requiring less computation, a lightweight deformable convolution module is proposed so that the convolution can extract ROI over a wider range, thereby enhancing the accuracy of the object detection network. Experiments were run on the datasets of PASCAL VOC2012, NEU-DET, AW, and RSOD. In comparison to the original YOLOv5, the mAP 0.5 of YOLO-SDH improved by 1.29-3.03%, the F1-score improved by 1.2-3.2%, the Precision improved by 0.7-4.2%, demonstrating the algorithm's efficacy and superiority.

关键词： Object detection deep learning algorithm Convolutional neural network Deformable CovNets Decoupled head

来源：评论

学校读者我要写书评

暂无评论

Non-invasive detection of systemic lupus erythematosus using SERS serum detection technology and deep learning algorithms

引用

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2024年 320卷 124592页

作者： Wang, Xuehua Hou, Junwei Chen, Chen Jia, Zhenhong Zuo, Enguang Chang, Chenjie Huang, Yuhao Chen, Cheng Lv, Xiaoyi Xinjiang Univ Coll Phys Sci & Technol Urumqi 830046 Peoples R China China Univ Petr Beijing Karamay State Key Lab Heavy Oil Proc Karamay 834000 Peoples R China Xinjiang Univ Coll Informat Sci & Engn Urumqi 830046 Peoples R China Xinjiang Univ Coll Software Urumqi 830046 Peoples R China

Systemic lupus erythematosus (SLE) is an autoimmune disease with multiple symptoms, and its rapid screening is the research focus of surface-enhanced Raman scattering (SERS) technology. In this study, gold@silver-porous silicon (Au@Ag-PSi) composite substrates were synthesized by electrochemical etching and in-situ reduction methods, which showed excellent sensitivity and accuracy in the detection of rhodamine 6G (R6G) and serum from SLE patients. SERS technology was combined with deep learning algorithms to model serum features using selected CNN, AlexNet, and RF models. 92 % accuracy was achieved in classifying SLE patients by CNN models, and the reliability of these models in accurately identifying sera was verified by ROC curve analysis. This study highlights the great potential of Au@Ag-PSi substrate in SERS detection and introduces a novel deep learning approach for SERS for accurate screening of SLE. The proposed method and composite substrate provide significant value for rapid, accurate, and noninvasive SLE screening and provide insights into SERS-based diagnostic techniques.

关键词： Surface Enhanced Raman Scattering (SERS) Au@Ag-PSi substrate Systemic lupus erythematosus (SLE) Classification diagnosis deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel solar irradiance calculation method for distributed photovoltaic power plants based on K-dimension tree and combined CNN-LSTM method

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 122卷

作者： Zhu, Honglu Zhang, Xi Wu, Ji Hu, Siyu Wang, Yuhang North China Elect Power Univ State Key Lab Alternate Elect Power Syst Renewable Beijing Peoples R China North China Elect Power Univ Sch New Energy Beijing Peoples R China China Elect Power Res Inst State Key Lab Renewable Energy Grid Integrat Beijing 100192 Peoples R China Dept New Energy Beinong Rd Beijing Peoples R China

Accurate solar irradiance calculation is the foundation of power forecasting and performance computation for distributed photovoltaic (DPV)plants. To solve the problems of the absence of dedicated meteorological stations and the challenges posed by low-quality power data in DPV plants, the research developed a method that integrates K-dimension tree and deep learning for DPV solar irradiance calculation. The paper's main work includes: by studying the output characteristics of regional DPV plants, the feasibility of using DPV plant power data for solar irradiance calculations has been confirmed, and further analyzed the detrimental impact of poor data quality on solar irradiance calculation models. By deploying K-dimension tree for representing the spatial distribution of DPV plants and 3 sigma algorithm for DPV plants data availability classification and data cleaning, the proportion of DPV plants with high-reliability data increased from 43.61 % to 85.71 %. Ultimately, a CNN-LSTM model based solar irradiance model is built, its performance was verified by measured solar irradiance, and the coefficient of determination for all results stay above 0.96, substantiating the efficacy of the proposed method. The research provides a cost-effective and high-precision solution for solar irradiance measurement in DPV plants, it helps to improve the safe and efficient operation of DPV plants.

关键词： Distributed photovoltaic plants Solar irradiance calculation deep learning algorithm K-dimension tree Data cleaning

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：