检索结果-内蒙古大学图书馆

A feature-enhanced multiscale attention approach for automated hand bone segmentation

Multimedia Tools and Applications 2024年第16期84卷 1-21页

作者： Nagaraju, Y. Venkatesh Thanu Shree Yadav, P.R. Vaishnavi, A. Tejashree, S.V. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Karnataka Bengaluru560001 India

In the medical field, comprehensive analysis of bone structures is paramount for assessing skeletal health and diagnosing conditions. X-ray imaging serves as a cornerstone in bone age evaluation and the fabrication of implants. In addition to clinical applications, automated bone structure analysis aids students in studying anatomy and radiology by providing accurate and consistent representations. This automation has the potential to significantly reduce processing time and enhance students’ understanding of bone structures and their variations, thereby improving their understanding and training in the medical field. This study presents the Adaptive Multiscale Expansion Segmentation Model (AMESM), a lightweight encoder-decoder-based multiclass semantic segmentation model for segmenting hand bones. The proposed method assists physicians in tasks such as growth analysis, hand movement assessment, and implant design. The model incorporates a Multi-Scale Attention Block that improves feature representation and segmentation accuracy. The experimental results demonstrate promising performance, with a Mean Intersection over Union (mIoU) of 88.47% and a Dice Score of 93.86%. The comprehensive analysis confirms the model’s ability to achieve accurate segmentation while remaining computationally efficient. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Automatic American sign language prediction for static and dynamic gestures using KFM-CNN

引用

Soft Computing 2024年第20期28卷 11703-11715页

作者： Thushara, A. Hani, Reymond Hakkim Baisil Mukundan, Manu Computer Science and Engineering TKM College of Engineering Kollam APJ Abdul Kalam Technological University Thiruvananthapuram India

For human–computer interaction, one of the most important tools is Sign Language Recognition in which one of the significant research topics is static Hand Gesture (HG) and dynamic Hand Gesture Recognition (HGR) of American Sign Language (ASL). However, recognizing them was challenging owing to improper contour models. Thus, this paper proposes a new model for ASL Static and dynamic HGR utilizing Deep Learning (DL). Primarily, the videos from the dataset are collected and transformed into image frames and then given to noise filtering utilizing an Alternative Window Size-Lone Diagonal Sorting Algorithm. The RGB noises are removed in noise filtering and given to Canopy Algorithm-based Minibatch K-Means Clustering clustering of static and dynamic gesture images. After that, by utilizing the YCbCr Palm point and Finger speed-based Threshold in the Region seed Grow Segmentation algorithm, the clustered images are segmented that segments both palm and fingers. Then, the features are extracted, and these features are given to the Kohnen Feature Mapping-based CNN classifier. From the Classifier, HG-recognized character outcomes are obtained. In a software environment, the novel model is implemented;also, for exhibiting the proposed technique’s superiority, the outcomes are analogized with the prevailing approaches. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

MAG-Net: Multi-fusion network with grouped attention for retinal vessel segmentation

引用

Mathematical Biosciences and engineering 2024年第2期21卷 1938-1958页

作者： Jiang, Yun Chen, Jie Yan, Wei Zhang, Zequn Qiao, Hao Wang, Meiqi College of Computer Science and Engineering Northwest Normal University Lanzhou730070 China

Retinal vessel segmentation plays a vital role in the clinical diagnosis of ophthalmic diseases. Despite convolutional neural networks (CNNs) excelling in this task, challenges persist, such as restricted receptive fields and information loss from downsampling. To address these issues, we propose a new multi-fusion network with grouped attention (MAG-Net). First, we introduce a hybrid convolutional fusion module instead of the original encoding block to learn more feature information by expanding the receptive field. Additionally, the grouped attention enhancement module uses high-level features to guide low-level features and facilitates detailed information transmission through skip connections. Finally, the multi-scale feature fusion module aggregates features at different scales, effectively reducing information loss during decoder upsampling. To evaluate the performance of the MAG-Net, we conducted experiments on three widely used retinal datasets: DRIVE, CHASE and STARE. The results demonstrate remarkable segmentation accuracy, specificity and Dice coefficients. Specifically, the MAG-Net achieved segmentation accuracy values of 0.9708, 0.9773 and 0.9743, specificity values of 0.9836, 0.9875 and 0.9906 and Dice coefficients of 0.8576, 0.8069 and 0.8228, respectively. The experimental results demonstrate that our method outperforms existing segmentation methods exhibiting superior performance and segmentation outcomes. © 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://***/licenses/by/4.0)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Novel Optimized Deep Convolutional Neural Network for Efficient Seizure Stage Classification

引用

computers, Materials & Continua 2024年第12期81卷 3903-3926页

作者： Umapathi Krishnamoorthy Shanmugam Jagan Mohammed Zakariah Abdulaziz S.Almazyad K.Gurunathan Department of Biomedical Engineering KIT-Kalaignarkarunanidhi Institute of TechnologyCoimbatore641402India Department of Computer Sciences and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai600062India Department of Computer Sciences and Engineering College of Applied ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Science and Engineering Mount Zion College of Engineering and TechnologyPudukkottai622507India

Brain signal analysis from electroencephalogram(EEG)recordings is the gold standard for diagnosing various neural disorders especially epileptic *** signals are highly chaotic compared to normal brain signals and thus can be identified from EEG *** the current seizure detection and classification landscape,most models primarily focus on binary classification—distinguishing between seizure and non-seizure *** effective for basic detection,these models fail to address the nuanced stages of seizures and the intervals between *** identification of per-seizure or interictal stages and the timing between seizures is crucial for an effective seizure alert *** granularity is essential for improving patient-specific interventions and developing proactive seizure management *** study addresses this gap by proposing a novel AI-based approach for seizure stage classification using a Deep Convolutional Neural Network(DCNN).The developed model goes beyond traditional binary classification by categorizing EEG recordings into three distinct classes,thus providing a more detailed analysis of seizure *** enhance the model’s performance,we have optimized the DCNN using two advanced techniques:the Stochastic Gradient Algorithm(SGA)and the evolutionary Genetic Algorithm(GA).These optimization strategies are designed to fine-tune the model’s accuracy and ***,k-fold cross-validation ensures the model’s reliability and generalizability across different data *** and validated on the Bonn EEG data sets,the proposed optimized DCNN model achieved a test accuracy of 93.2%,demonstrating its ability to accurately classify EEG *** summary,the key advancement of the present research lies in addressing the limitations of existing models by providing a more detailed seizure classification system,thus potentially enhancing the effectiveness of real-time seizure prediction and management systems in clinic

关键词： Bonn EEG dataset cross-validation genetic algorithm batch normalization seizure classification stochastic gradient

来源：评论

学校读者我要写书评

暂无评论

IntelliCrop: Major Cropping Pattern Prediction using Machine Learning Techniques 7

IntelliCrop: Major Cropping Pattern Prediction using Machine...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Attavar, Aditi Manohar, Akshatha Leela Himoshra, D. Harshiya Banu, B. Pooja, M.R. Vidyavardhaka College of Engineering Computer Science And Engineering Mysuru India Vidyavardhaka College of Engineering Department of Computer Science And Engineering Mysuru India

ISBN: (纸本)9798350359299

The sustainable livelihoods of farmers in India hinge upon effective crop management and optimal yield. However, the existing manual system for crop selection is time-consuming, relies heavily on experience, and often leads to suboptimal yields and financial losses. To address this challenge, we propose an automated cropping pattern prediction system that leverages advanced machine learning techniques. Our system aims to empower farmers by providing insights into the diverse range of crops suitable for their specific land. By understanding the intricate relationships between different crop types, farmers can make informed decisions to maximize yield quality. The absence of a robust system for identifying cropping patterns results in random crop choices, leading to yield fluctuations. This study focuses on developing a system that predicts the optimal crop priority, considering various factors such as land characteristics, soil conditions, and climate data. This prioritization minimizes losses due to suboptimal crop combinations. The machine learning algorithms that are used include Naïve Bayes, and Eclat, which aim at disseminating information from the data at once, will enable the agricultural departments to work effectively. This approach allows for a more informed and effective decision-making process in agricultural practices. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An Unified PSO and Fuzzy Satisfaction Framework for Power Flow Optimization

An Unified PSO and Fuzzy Satisfaction Framework for Power Fl...

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Chatterjee, Vedatrayee Roy, Dhiman Maitra, Arnab Ghosh, Soubhik Wania, Rumsha Waqia Asansol Engineering College Computer Science & Engineering Asansol India Bengal College of Engineering & Technology Computer Science & Engineering Durgapur India

ISBN: (纸本)9798350390759

This study introduces a new method for multi-objective optimization (MOO) in electrical power systems, aiming to minimise emission release, power losses and fuel costs concurrently. Diverging from traditional techniques that primarily target cost reduction, the proposed Power Flow Optimization (PFO) framework combines Fuzzy Satisfaction Maximization strategy with Particle Swarm Optimization (PSO), acknowledging the vagueness in decision-makers' objectives. By formulating the optimization problem as a fuzzy satisfaction maximization problem, the method aims to find optimal trade-off solutions that balance conflicting objectives. Testing the PFO on a standard IEEE 30-bus system with six generators demonstrates its effectiveness in providing solutions that optimize both actual and imaginary powers while considering fuel cost, emission reduction, and power loss, thereby offering valuable insights for efficient power system operation. © 2024 IEEE.

关键词： Load flow optimization

来源：评论

学校读者我要写书评

暂无评论

Automated Irrigation System Using Improved Fuzzy Neural Network in Wireless Sensor Networks

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 853-866页

作者： S.Sakthivel V.Vivekanandhan M.Manikandan Department of Computer Science and Engineering Sona College of TechnologySalem 636005TamilnaduIndia Department of Computer Science and Engineering Adhiyamaan College of EngineeringHosur 635109TamilnaduIndia

Irrigation plays a significant role in various agricultural cropping methods deployed in semiarid and arid regions where valuable water applications and managing are considered crucial *** factors such as weather,soil,water,and crop data need to be considered for irrigation maintenance in an efficient besides uniform manner from multifaceted and different information-based systems.A Multi-Agent System(MAS)has been proposed recently based on diverse agent subsystems with definite objectives for attaining global MAS objective and is deployed on Cloud Computing paradigm capable of gathering information from Wireless Sensor Networks(WSNs)positioned in rice,cotton,cassava crops for knowledge discovery and decision *** radial basis function network has been used for irrigation ***,in recent work,the security of data has not focused on where intruder involvement might corrupt the data at the time of data transferring to the cloud,which would affect the accuracy of decision *** handle the above mentioned issues,an efficient method for irrigation prediction is used in this *** factors considered for decision making are soil moisture,temperature,plant height,root *** above-mentioned data will be gathered from the sensors that are attached to the *** data will be forwarded to the local server,where data encryption will be performed using Adaptive Elliptic Curve Cryptography(AECC).After the encryption process,the data will be forwarded to the *** the data stored in the cloud will be decrypted key before being given to the deci-sion-making ***,the uniform distribution-based fuzzy neural network is formulated based on the received data information in the decisionmaking *** decision regarding the level of water required for cropfields would be *** on this outcome,the water volve opening duration and the level of fertilizers required will be *** results demons

关键词： Irrigation multi-agent system precision irrigation accuracy elliptic curve cryptography encryption wireless sensor networks fertilizers

来源：评论

学校读者我要写书评

暂无评论

CVTD: A Robust Car-Mounted Video Text Detector

引用

computers, Materials & Continua 2024年第2期78卷 1821-1842页

作者： Di Zhou Jianxun Zhang Chao Li Yifan Guo Bowen Li Department of Computer Science and Engineering Chongqing University of TechnologyChongqingChina College of Information and Engineering Jingdezhen Ceramic UniversityJingdezhenChina

Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous *** information in car-mounted videos can assist drivers in making ***,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time *** proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary *** model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD *** enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text ***,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s *** further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection *** model holds potential for practical applications in real-world scenarios.

关键词： Deep learning text detection Car-mounted video text detector intelligent driving assistance arbitrary shape text detector

来源：评论

学校读者我要写书评

暂无评论

Stage-Wise Categorization and Prediction of Diabetic Retinopathy Using Ensemble Learning and 2D-CNN

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 499-514页

作者： N.M.Balamurugan K.Maithili T.K.S.Rathish Babu M.Adimoolam Department of Computer Science and Engineering Sri Venkateswara College of EngineeringSriperumbudurChennaiIndia Department of Computer Science and Engineering KG Reddy College of Engineering and Technology(Autonomous)HyderabadTelanganaIndia Department of Computer Science and Engineering Sridevi Women’s Engineering CollegeHyderabadTelanganaIndia Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesThandalamChennaiIndia

Diabetic Eye Disease(DED)is a fundamental cause of blindness in human beings in the medical *** techniques are proposed to forecast and examine the stages in Prognostication of Diabetic Retinopathy(DR).The Machine Learning(ML)and the Deep Learning(DL)algorithms are the predomi-nant techniques to project and explore the images of *** though some solu-tions were adapted to challenge the cause of DR disease,still there should be an efﬁcient and accurate DR prediction to be adapted to reﬁne its *** this work,a hybrid technique was proposed for classiﬁcation and prediction of *** proposed hybrid technique consists of Ensemble Learning(EL),2 Dimensional-Conventional Neural Network(2D-CNN),Transfer Learning(TL)and Correlation ***,the Stochastic Gradient Boosting(SGB)EL method was used to predict the ***,the boosting based EL method was used to predict the DR of *** 2D-CNN was applied to categorize the various stages of DR ***,the TL was adopted to transfer the clas-siﬁcation prediction to training *** this TL was applied,a new predic-tion feature was *** the experiment,the proposed technique has achieved 97.8%of accuracy in prophecies of DR images and 98%accuracy in grading of *** experiment was also extended to measure the sensitivity(99.6%)and speciﬁcity(97.3%)*** predicted accuracy rate was com-pared with existing methods.

关键词： Diabetic retinopathy prediction and classiﬁcation ensemble learning conventional neural network diabetic eye disease

来源：评论

学校读者我要写书评

暂无评论

Accurate segmentation of COVID-19 infected regions in lung CT scans with deep learning

引用

Neural Computing and Applications 2024年第35期36卷 22511-22531页

作者： Lenin Marksia, U. Yesubai Rubavathi, C. Department of Electronics and Communication Engineering Francis Xavier Engineering College Tamil Nadu Tirunelveli India Department of Computer Science and Engineering Saveetha College of Engineering Tamil Nadu Chennai India

The widespread impact of coronavirus disease 2019 (COVID-19) has led to a severe health crisis and loss of life affecting billions of people. Detecting COVID-19 early on and distinguishing it from other illnesses is a major challenge in the pandemic. Computed tomography scans are vital for diagnosis, but they are difficult and slow for radiologists to interpret. So, deep learning technology is being used to speed up disease diagnosis, especially for COVID-19. This research employs a multi-scale feature extraction module that captures features at different scales to detect small and large structures in infection areas. The channel attention module enhances feature representation by focusing on informative channels. A bidirectional pyramid module is utilized to acquire fine-grained details and reduce spatial dimensions. The global dependencies and long-range contextual relationships among the images are captured through global and edge paths, resulting in clear and accurate images. Finally, the outputs from both modules are merged in the feature fusion Network to provide an accurate segmentation mask for COVID-19-related areas. The testing is conducted using the COVID-19 lung scan image dataset. Extensive trials are performed using standard metrics, and the output is compared with recently proposed approaches. The results demonstrate that this method achieves 98.6% accuracy, 96.54% precision, 97.52% sensitivity, 98.55% specificity, 98.59% kappa score, and an execution time of 3.2 s. These results suggest that this method performs better than other comparative methods and accurately identifies regions in the lungs affected by COVID-19. © The Author(s) 2024.

关键词： COVID-19

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：