检索结果-内蒙古大学图书馆

A 3D semantic segmentation network for accurate neuronal soma segmentation

Journal of Innovative Optical Health sciences 2025年第1期18卷 67-83页

作者： Li Ma Qi Zhong Yezi Wang Xiaoquan Yang Qian Du School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan 430074P.R.China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics MoE Key Laboratory for Biomedical Photonics Huazhong University of Science and Technology Wuhan 430074 P.R.China Department of Electrical and Computer Engineering Mississippi State University Mississippi StateMS 39762USA

Neuronal soma segmentation plays a crucial role in neuroscience ***,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate *** this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this *** an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding *** MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale ***,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different *** proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed *** achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.

关键词： Neuronal soma segmentation semantic segmentation network multi-scale feature extraction adaptive weighting fusion

来源：评论

学校读者我要写书评

暂无评论

Estimating Chlorophyll Content from Hyperspectral Data Using Gradient Features 23rd

Estimating Chlorophyll Content from Hyperspectral Data Usin...

引用

23rd International Conference on Computational science, ICCS 2023

作者： Ruszczak, Bogdan Wijata, Agata M. Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Opole Poland Faculty of Biomedical Engineering Silesian University of Technology Zabrze Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Gliwice Poland KP Labs Gliwice Poland

ISBN: (纸本)9783031360206

Non-invasive estimation of chlorophyll content in plants plays an important role in precision agriculture. This task may be tackled using hyperspectral imaging that acquires numerous narrow bands of the electromagnetic spectrum, which may reflect subtle features of the plant, and inherently offers spatial scalability. Such imagery is, however, high-dimensional, therefore it is challenging to transfer from the imaging device, store and investigate. We propose a machine learning pipeline for estimating chlorophyll content from hyperspectral data. It benefits from the Savitzky-Golay filtering to smooth the (potentially noisy) spectral curves, and from gradient-based features extracted from such a smoothed signal. The experiments revealed that our approach significantly outperforms the state of the art according to the widely-established estimation quality metrics obtained for four chlorophyll-related parameters. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Proton‑Prompted Ligand Exchange to Achieve High‑Efficiency CsPbI_(3) Quantum Dot Light‑Emitting Diodes

引用

Nano-Micro Letters 2024年第6期16卷 53-62页

作者： Yanming Li Ming Deng Xuanyu Zhang Lei Qian Chaoyu Xiang Laboratory of Advanced Nano‑Optoelectronic Materials and Devices Qianwan Institute of CNITECHNingbo 315300People’s Republic of China Division of Functional Materials and Nanodevices Ningbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201People’s Republic of China Zhejiang Provincial Engineering Research Center of Energy Optoelectronic Materials and Devices Ningbo Institute of Materials Technology&EngineeringChinese Academy of SciencesNingbo 315201People’s Republic of China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211ZhejiangPeople’s Republic of China University of Nottingham Ningbo China Ningbo 315100People’s Republic of China

CsPbI_(3)perovskite quantum dots(QDs)are ideal materials for the next generation of red light-emitting ***,the low phase stability of CsPbI_(3)QDs and long-chain insulating capping ligands hinder the improvement of device *** in-situ ligand replacement and ligand exchange after synthesis were often difficult to ***,we proposed a new ligand exchange strategy using a proton-prompted insitu exchange of short 5-aminopentanoic acid ligands with long-chain oleic acid and oleylamine ligands to obtain stable small-size CsPbI_(3)*** exchange strategy maintained the size and morphology of CsPbI_(3)QDs and improved the optical properties and the conductivity of CsPbI_(3)QDs *** a result,high-efficiency red QD-based light-emitting diodes with an emission wavelength of 645 nm demonstrated a record maximum external quantum efficiency of 24.45%and an operational half-life of 10.79 h.

关键词： CsPbI_(3) perovskite quantum dots Light-emitting diodes Ligand exchange Proton-prompted in-situ exchange

来源：评论

学校读者我要写书评

暂无评论

The applied principles of EEG analysis methods in neuroscience and clinical neurology

引用

Military Medical Research 2024年第6期11卷 907-941页

作者： Hao Zhang Qing-Qi Zhou He Chen Xiao-Qing Hu Wei-Guang Li Yang Bai Jun-Xia Han Yao Wang Zhen-Hu Liang Dan Chen Feng-Yu Cong Jia-Qing Yan Xiao-Li Li School of Systems Science Beijing Normal UniversityBeijing 100875China College of Electrical and Control Engineering North China University of TechnologyBeijing 100041China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China Department of Psychology the State Key Laboratory of Brain and Cognitive Sciencesthe University of Hong KongHong Kong SAR 999077China HKU-Shenzhen Institute of Research and Innovation Shenzhen 518057GuangdongChina Department of Health Technology and Informatics the Hong Kong Polytechnic UniversityHong Kong SAR 999077China Department of Rehabilitation Medicine the First Afliated Hospital of Nanchang UniversityNanchang 330006China Rehabilitation Medicine Clinical Research Center of Jiangxi Province Nanchang 330006China Beijing Key Laboratory of Learning and Cognition School of PsychologyCapital Normal UniversityBeijing 100048China School of Communication Science Beijing Language and Culture UniversityBeijing 100083China Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004HebeiChina School of Computer Science Wuhan UniversityWuhan 430072China School of Biomedical Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalian 116081LiaoningChina Guangdong Artifcial Intelligence and Digital Economy Laboratory(Guangzhou) Guangzhou 510335China.

Electroencephalography(EEG)is a non-invasive measurement method for brain *** to its safety,high resolution,and hypersensitivity to dynamic changes in brain neural signals,EEG has aroused much interest in scientific research and medical *** article reviews the types of EEG signals,multiple EEG signal analysis methods,and the application of relevant methods in the neuroscience feld and for diagnosing neurological ***,3 types of EEG signals,including time-invariant EEG,accurate event-related EEG,and random event-related EEG,are ***,5 main directions for the methods of EEG analysis,including power spectrum analysis,time-frequency analysis,connectivity analysis,source localization methods,and machine learning methods,are described in the main section,along with diferent sub-methods and effect evaluations for solving the same ***,the application scenarios of different EEG analysis methods are emphasized,and the advantages and disadvantages of similar methods are *** article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives,provide references for subsequent research,and summarize current issues and prospects for the future.

关键词： Electroencephalogram analysis methods Applied principles Neuroscience Diagnosis Neurological diseases

来源：评论

学校读者我要写书评

暂无评论

Human Faces Detection and Tracking for Crowd Management in Hajj and Umrah

引用

computers, Materials & Continua 2022年第6期71卷 6275-6291页

作者： Riad Alharbey Ameen Banjar Yahia Said Mohamed Atri Abdulrahman Alshdadi Mohamed Abid Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Electrical Engineering Department College of EngineeringNorthern Border UniversityArarSaudi Arabia Laboratory of Electronics and Microelectronics(LR99ES30) Faculty of Sciences of MonastirUniversity of MonastirTunisia College of Computer Sciences King Khalid UniversityAbhaSaudi Arabia CES Laboratory ENISUniversity of SfaxTunisia

Hajj and Umrah are two main religious duties for *** help faithfuls to perform their religious duties comfortably in overcrowded areas,a crowd management system is a must to control the entering and exiting for each *** the number of people is very high,an intelligent crowd management system can be developed to reduce human effort and accelerate the management *** this work,we propose a crowd management process based on detecting,tracking,and counting human faces using Artificial Intelligence *** detection and counting will be performed to calculate the number of existing visitors and face detection and tracking will be used to identify all the humans for security *** proposed crowd management system is composed form three main parts which are:(1)detecting human faces,(2)assigning each detected face with a numerical identifier,(3)storing the identity of each face in a database for further identification and *** main contribution of this work focuses on the detection and tracking model which is based on an improved object detection *** improved Yolo v4 was used for face detection and *** has been very effective in detecting small objects in highresolution *** novelty contained in thismethod was the integration of the adaptive attention mechanism to improve the performance of the model for the desired *** wise attention mechanism was applied to the output layers while both channel wise and spatial attention was integrated in the building *** main idea from the adaptive attention mechanisms is to make themodel focus more on the target and ignore false positive *** demonstrated the efficiency of the proposed method through expensive experimentation on a publicly available *** wider faces dataset was used for the train and the evaluation of the proposed detection and tracking *** proposed model has achieved good results with 91.2%of mAP and a processing speed

关键词： Crowdmanagement Hajj and Umrah face detection object tracking convolutional neural networks(CNN) adaptive attention mechanisms

来源：评论

学校读者我要写书评

暂无评论

Comparison of decision support models -- a recruitment case study as a multiclass classification problem with limited data

Comparison of decision support models -- a recruitment case ...

引用

International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Artur Morys - Magiera Marek Długosz Paweł Skruch Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Cracow Kraków Poland

We present a comparative case study of machine learning models, evaluating their efficiency in a practical task of multiclass classification of samples being submissions to a recruitment survey and assigning them scores denoting the match level for a given candidate to a given workgroup (committee) in the AGH Students’ Council. This research is based on the Council’s recruitment applications that carried candidates’ responses to a set of 10 hypothetical Council member activity scenarios, where they were to choose one of four given solutions to the problems. The data was collected from a web quiz in 2020, validated on a voluntary insider control group’s responses to these questions and finally the best-performing model was evaluated in practice in the 2021’s recruitment inside an in-browser adventure minigame. This work provides insight into how models ranging from classical methods to deep learning perform in a very specific not yet well-explored in literature, practical non-linear problem that is dependent on individual features of the participants, with the data volume being very limited due to a restricted population of candidates. This information may provide a starting point for applications of machine learning in decision support systems in recruitment processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-tuning Specialized NER Model for Symptom Extraction from Slovenian Medical Texts

Fine-tuning Specialized NER Model for Symptom Extraction fro...

引用

International Conference on Mathematics and computers in sciences and in Industry (MCSI)

作者： Rigon Sallauka Umut Arioz Izidor Mlakar Laboratory of Digital Signal Processing University of Maribor Faculty of Electrical Engineering and Computer Science Maribor Slovenia

ISBN: (数字)9798350377224

ISBN: (纸本)9798350377231

In this study, we aim to develop a robust model capable of accurately extracting symptoms from clinical texts written in the Slovenian language. Our methodology involves several steps to achieve this objective. Initially, we identify datasets containing clinical texts in English and select a specialized model designed for symptom extraction from these texts. Then, we annotate the datasets and undertake the translation process into Slovenian, ensuring the preservation of annotations to maintain data integrity. Utilizing the translated dataset, we proceed to fine-tune the selected model specifically for Slovenian texts. Despite our efforts, optimal performance has not yet been attained. Challenges encountered include the translation methodology employed and the architectural limitations of the chosen model, which is primarily optimized for English texts. However, ongoing efforts are underway to address these challenges and enhance the model's performance. Our study represents a step towards improving automated symptom extraction in Slovenian clinical texts, with ongoing work focused on mitigating identified issues to achieve better outcomes.

关键词： Adaptation models Translation Accuracy Text analysis Annotations Computational modeling Data models Mathematical models Reliability Tuning

来源：评论

学校读者我要写书评

暂无评论

Exploring rhythmic visual cue impacts on gait initiation using functional EEG source connectivity 8

Exploring rhythmic visual cue impacts on gait initiation usi...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Yan, Wenfeng Zhou, Huilin Wu, Jiajia Jiang, Wensong Zuo, Guokun Shi, Changcheng Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang Ningbo315211 China Chinese Academy of Sciences Ningbo Institute of Materials Technology and Engineering Zhejiang Ningbo315201 China Ningbo Cixi Institute of Biomedical Engineering Zhejiang Ningbo315300 China Chinese Academy of Sciences Zhejiang Engineering Research Center for Biomedical Materials Ningbo Institute of Materials Technology and Engineering Zhejiang Ningbo315300 China Wenzhou Medical University Cixi Biomedical Research Institute Zhejiang China

ISBN: (纸本)9798350302455

The underlying neural mechanisms of rhythmic visual cues to improve gait freezing symptoms are still remain unclear. Previous studies of rhythmic visual cues have not taken into account the fact that the brain processes information as a result of the interplay between various brain regions. This study applied the EEG source connectivity method to investigate the cortical response and to evaluate the functional integration relationship of the brain networks under the non-rhythmic and rhythmic visual cues. Results showed that there were more network connectivity under the rhythmic visual cues, which suggested that rhythmic visual cues strengthen the brain's visual processing and cognitive control functions by enhancing the interactions between brain regions. In addition, the brain functional network under rhythmic visual cues possessed stronger functional separation and functional integration. This study suggested that the modulatory mechanism of rhythmic visual cues on gait initiation may be related to the enhanced information processing efficiency of the brain functional network through visual information input. The innovative source localization of EEG signals and the combination of the analysis of functional brain networks complement the methodology of the study of rhythmic visual cues, thus filling a gap in this research. © 2023 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Weak and Extremely Low Frequency Magnetic Fields Alter the Growth Rates of HT-1080 Fibrosarcoma

Weak and Extremely Low Frequency Magnetic Fields Alter the G...

引用

US National Committee of URSI National Radio science Meeting (USNC-URSI NRSM)

作者： Nhat Dang Jason Keller Marek Bajtos Hakki Gurhan Frank Barnes Department of Electrical Computer and Energy Engineering College of Engineering and Applied Science University of Colorado Boulder Boulder Colorado USA Department of Electromagnetics and Biomedical Engineering Faculty of Electrical Engineering and Information Technology University of Zilina Zilina Slovakia

ISBN: (数字)9781946815200

ISBN: (纸本)9798331513979

This study presents experimental results showing that weak, extremely low frequency electromagnetic (EM) fields influence the growth rates of HT-1080 fibrosarcoma cells in vitro and offers a theoretical explanation for these effects. The results demonstrate that weak magnetic fields both increase and decrease the growth rates of fibrosarcoma cells by altering the mitochondrial superoxide $(\mathrm{O}^{2-})$ and calcium ions $(\text{Ca}^{2+})$ concentrations in living cells. Over a 4-day exposure period, fibrosarcoma growth rates were modulated in the presence of low-level alternating current (AC) magnetic fields at a $10 \mu \mathrm{T}$ amplitude at 13.5 Hz to 30 Hz frequency, superimposed on a $45 \mu \mathrm{T}$ static background field. Effects due to changes in amplitude from 10 to $30 \mu \mathrm{T}$ at selected frequencies are also investigated with the same superimposed static field.

关键词： Frequency modulation Calcium Ions Magnetic fields In vitro Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Low-Cost, High-Performance Algorithm and Hardware Architecture for SAO Mode Decision 2

Low-Cost, High-Performance Algorithm and Hardware Architectu...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Hou, Bingjing Liu, Chang Zhang, Yuejun Huang, Leilei Jing, Minge Fan, Yibo Fudan University State Key Laboratory of Integrated Chips and Systems Shanghai China Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China East China Normal University Institute of Microelectronic Circuits and Systems Shanghai China

ISBN: (纸本)9798331515669

Sample adaptive offset (SAO) is applied for reducing sample distortion and attenuating ringing artifacts in both HEVC and VVC standards. The rate-distortion optimization process is used to select the best SAO parameter. It accounts for the majority of SAO complexity and determines the SAO filtering performance. Therefore, the rate-distortion cost calculation should be well handled to achieve both low cost and high coding performance. In this paper, we propose a simplified and optimized rate estimation algorithm based on the characteristics of SAO parameter syntax and entropy coding process. And we propose a hierarchical flow for rate-distortion cost calculation to further reduce the computational cost and storage cost for SAO mode decision hardware. The results show that the proposed algorithm achieves an average YUV loss of -0.10%, and the proposed SAO mode decision hardware architecture can be implemented by only 21.8k gates using TSMC 65nm process under 400 MHz. © 2024 IEEE.

关键词： Electric distortion

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：