检索结果-内蒙古大学图书馆

22nd IEEE International Conference on Communication Technology, ICCT 2022

作者： Luo, Kuang Ou, Lu Zhang, Chuangfeng Zhang, Ming Li, Jinxin Liao, Shaolin Guangdong Guangzhou China School of Journalism and Communication Hunan University Hunan Province Key Laboratory of Big Data Research and Applications Hunan Changsha China College of Computer Science and Electronic Engineering Hunan University Hunan Changsha China Illinois Institute of Technology Electrical and Computer Engineering ChicagoIL United States

ISBN: (纸本)9781665470674

Efficient Numerical Singular Integral (NSI) methods have been developed for both 1D and 2D electromagnetics problems, in both the Cartesian and polar coordinates. Through a special type of integration by parts, rigorous mathematics derivation has been performed to decompose the original singular integrals into sum of non-singular integrals that can be evaluated numerically. It can be shown that it is more convenient to evaluate the line-type singularity in the Cartesian coordinate;while it is better to evaluate the point-type singularity in the polar coordinate. Also, numerical schemes to find the order of singularity has been presented. Finally, to validate the 2D numerical singular integral methods, the electromagnetic scattering problem of a 2D reflecting ellipse antenna has been simulated through the Ping-Pong algorithm developed by the authors. © 2022 IEEE.

关键词： Computational electromagnetics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Particle YOLO Detector for Urine Sediment Detection 4th

An Efficient Particle YOLO Detector for Urine Sediment Dete...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Chen, Zejian Hu, Rong Chen, Fukun Fan, Haoyi Ching, Fum Yew Li, Zuoyong Su, Shimei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fujian Fuzhou350118 China School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fujian Fuzhou350121 China School of Electrical Engineering Zhengzhou University Henan Zhengzhou450001 China

ISBN: (纸本)9783031201011

Urine sediment detection is an essential aid in assessing kidney health. Traditional machine learning approaches treat urine sediment particle detection as an image classification task, segmenting particles for detection based on information such as edges or thresholds. However, the segmentation of sediment particles is complex due to the low contrast and weak edge characteristics of urine sediment images. In this paper, we consider urine sediment particle detection as a object detection task and propose the YOLOv5s-CBL, a detector dedicated to particle detection. Specifically, to mitigate the impact of background noise on detection accuracy, we inherit CBAM on the YOLOv5s model to help the network filter useless noise information and find regions of interest to extract target features. Then, we expand the original three-scale feature layer to improve the sensitivity of the model to larger-scale target sediment particles. Finally, we use the BiFPN structure instead of the original PANet combined with the FPN structure, which can more effectively fuse multiple different scales of information to improve the detection performance of the model. We compared state-of-the-art methods on two real-world datasets, and the experimental results demonstrated the effectiveness of YOLOv5s-CBL. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Exploring Advanced Algorithms in Multi-Dimensional Spatial data Modeling for Enhanced Geospatial Analysis

Exploring Advanced Algorithms in Multi-Dimensional Spatial D...

引用

Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI), International Conference on

作者： Asha V S Sreekanth Ginni Nijhawan Vipashi Kansal R.P Ram Kumar Tamam Ali Abd Ulabbas Abedi Department of Computer Applications N.H.C.E Bangalore India Computer Science and Engineering(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad India LPU Phagwara India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Department of CSBS GRIET Bachupally Hyderabad Telangana India College of Medical Technology The Islamic University Najaf Iraq

ISBN: (数字)9798350355338

ISBN: (纸本)9798350355345

This study examines map analysis with the goal of improving current methods by looking at cutting-edge algorithms for modeling multidimensional spatial data. Tensor Decomposition (TD), Convolutional Neural Networks (CNNs), and Spatiotemporal Regression (STR) are all parts of the suggested method that work together to solve the complex problems that come up when representing spatial data. The abstract provides a concise summary of the primary objectives and methodologies of the study, while also elucidating the rationale behind its execution. In our work, we use new developments in deep learning and machine learning to go beyond common ways of looking at space, such as graph-based spatial analysis, geostatistical methods, and space partitioning strategies. When you combine convolutional neural networks with tensor decomposition, you can get hierarchical features out of the data and figure out what the complex spatial patterns mean. Using spatial-temporal regression also helps us understand spatial events better by adding temporal changes to the analysis framework. Our study's goal is to push the boundaries of geographic research by combining the newest techniques. This will make it possible to create more precise and all-encompassing methods that can correctly understand the complex nature of location data in many dimensions.

关键词： Analytical models Adaptation models Tensors Computational modeling Urban planning Spatial databases data models Spatiotemporal phenomena Geospatial analysis Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Sensor Networks: Applying AI for Fault Identification in Challenging Operational Contexts

Robust Sensor Networks: Applying AI for Fault Identification...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： Manjunatha A S Venkatramana Bhat P Ramakrishna M Matti Nidhi Prabhu Dept. of Computer and Communication Engineering NITTE (Deemed to be University) NMAM Institute of Technology Nitte Mangaluru Karnataka Dept. of Computer Science and Engineering NITTE (Deemed to be University) NMAM Institute of Technology Nitte Mangaluru Karnataka Dept. of Data Science and Computer Applications Manipal Academy of Higher Education Manipal Institute of Technology Manipal India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Wireless Sensor Networks (WSNs) are highly implemented in harsh and dynamic environments. In such configurations, faults and anomalies easily occur, causing unwanted disruptions in data accuracy and network performance. In the context of reliability and stability in WSN operations, effective fault detection techniques are vital. This research work discusses how several machine learning models may be applied, including Logistic Regression, Decision Tree, Random Forest, and K-Nearest Neighbors in order to detect fault in WSNs. The performance evaluation was performed based on major criteria, which are accuracy, precision, recall, and Fl score. This, therefore, makes these approaches to machine learning effective in identifying faults efficiently, hence offering a well-balanced solution that is scalable and robust for integrity and operational effectiveness of WSN s.

关键词： Fault diagnosis Wireless sensor networks Logistic regression Accuracy Fault detection Nearest neighbor methods Robustness Decision trees Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

Deep Adaptively Feature Extracting Network for Cervical Squamous Lesion Cell Detection 4th

Deep Adaptively Feature Extracting Network for Cervical Squ...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Peng, Zhonghua Hu, Rong Wang, Fuen Fan, Haoyi Eng, Yee Wei Li, Zuoyong Zhou, Liwei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fujian Fuzhou350118 China School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fujian Fuzhou350121 China Department of Nutrition The First Affiliated Hospital of Zhengzhou University Henan Zhengzhou450052 China

ISBN: (纸本)9783031200984

Cervical cancer is one of the most widespread malignancies affecting women’s health worldwide today. However, the task of detection is particularly difficult due to the complex background of the cervical smear, where cells are previously stacked in clusters. To address this problem, we utilize the YOLOv5 as the baseline and build on YOLOv5 by using the simple Transformer Block which only combines with multi-head self attention layers and MLP to better extract cell features as well as to obtain global information. In addition, we allow the model to refine features adaptively to assist with detection by using Convolutional Block Attention Module (CBAM), an attention module being simple and effective for feed-forward convolutional neural networks, in the complex background information. Finally, we compare the model with YOLOv5 as baseline. In CDetector dataset, our model obtains 52.5% mAP@.5, which is 6% better than baseline. In transfer learning, it is 62.2%, which outperforms baseline by 3.2%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Wireless Body Area Network (WBAN) Centric Healthcare System for Continuous Monitoring

Wireless Body Area Network (WBAN) Centric Healthcare System ...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： M. Anand Kumar V. Valli Mayil T. Ratha Jeyalakshmi Anshul Ghanshala Anshika Gupta Dept of Computer Applications Graphic Era University Dehradun India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh India Department of Data Science Jain University School of Sciences Banglore India Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Stroke is one the most dangerous disease all across the world which would lead to serious disability or death among all aged people due to changes in environmental factors. Recent reports indicate that a mere 75 million people will suffer from stroke-related disabilities by the year 2030. It was also identified that a stroke occurs every 40 seconds on average across the globe. One out of every five stroke-related patients would die in a year. A Recent health survey indicates that most developed countries face a high number of stroke patients in very recent years. There is also a rapid growth in the number of stroke cases in developing countries. To prevent the high-risk factors related to stroke diseases, there is much need for continuous observation of physiological signals in real-time and to analyze the data. One of the main strategies is wearable technology that employs wireless sensor networks to link numerous medical devices and associated systems. They have to ability to function independently across several platforms. Wearable devices are used in most medical applications because of their noteworthy qualities, including adaptability, versatility, inexpensiveness, and efficiency in various platforms. Integration of the Internet of Things (IoT) with wearable devices and Fog Computing provides a more flexible mechanism to deploy a continuous healthcare monitoring system to monitor vital symptoms and to detect the early phase of stroke factors instantly. To predict stroke-related disorders, this research proposes a Wireless Body Area Network (WBAN)-centric healthcare system for continuous monitoring and examination of physiological signals. Initially, the proposed model predicts the nature of the symptoms based on the parameters collected by the IoT sensors. Deep learning techniques are then applied to predict the risk factors that are critical to the stroke patient during the emergency condition. The key contribution of this research work is to provide an emerg

关键词： Wireless communication Wireless sensor networks Wearable computers Medical services Predictive models Stroke (medical condition) Body area networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing the light gradient-boosting machine algorithm for an efficient early detection of coronary heart disease

Informatics and Health

引用

Informatics and Health 2024年第2期1卷 70-81页

作者： Temidayo Oluwatosin Omotehinwa David Opeoluwa Oyewola Ervin Gubin Moung Department of Mathematics and Computer Science Federal University of Health SciencesP.M.B.145OtukpoNigeria Department of Mathematics and Statistics Federal University KashereP.M.B.0182GombeNigeria Data Technologies and Applications(DaTA)Research Group Faculty of Computing and InformaticsUniversiti Malaysia SabahKota Kinabalu 88400SabahMalaysia

Background:Coronary heart disease(CHD)remains a prominent cause of mortality globally,necessitating early and accurate detection *** diagnostic approaches can be invasive,costly,and time-consuming,necessitating the need for more efficient *** aimed to optimize the Light Gradient-Boosting Machine(LightGBM)algorithm to enhance its performance and accuracy in the early detection of CHD,providing a reliable,cost-effective,and non-invasive diagnostic ***:The Framingham Heart Study(FHS)dataset publicly available on Kaggle was used in this *** Imputations by Chained Equations(MICE)were applied separately to the training and testing sets to handle missing ***-SMOTE(Synthetic Minority Over-sampling Technique)was used on the training set to balance the *** LightGBM algorithm was selected for its efficiency in classification tasks,and Bayesian Optimization with Tree-structured Parzen Estimator(TPE)was employed to fine-tune its *** optimized LightGBM model was trained and evaluated using metrics such as accuracy,precision,and AUC-ROC on the test set,with cross-validation to ensure robustness and ***:The optimized LightGBM model showed significant improvement in early CHD *** baseline LightGBM model with dropped missing values had an accuracy of 0.8333,sensitivity of 0.1081,precision of 0.3429,F1 score of 0.1644,and AUC of *** MICE imputation,performance improved to an accuracy of 0.9399,sensitivity of 0.6693,precision of 0.9043,F1 score of 0.7692,and AUC of *** combined approach of Borderline-SMOTE,MICE imputation,and TPE for LightGBM achieved an accuracy of 0.9882,sensitivity of 0.9370,precision of 0.9835,F1 score of 0.9597,and AUC of 0.9963,indicating a highly effective and robust ***:The optimized model demonstrated outstanding performance in early CHD *** study’s strengths include its comprehensive approach to addres

关键词： Clinical decision making Coronary heart disease Light gradient-boosting machine Machine learning MICE Tree-structured Parzen estimator

来源：评论

学校读者我要写书评

暂无评论

Decision Making and Recognition of String Characters using NN-Fuzzy Implication System

引用

Procedia computer science 2025年 258卷 893-902页

作者： Santosh Kumar Henge Avinash Bhagat Sanjeev Kumar Mandal Nikhil Reddy Viraati Ravleen Singh K. Rushi Kedhar Associate Professor Department of Computer Science and Engineering School of Computer Science and Artificial Intelligence SR University Warangal 506371 India Associate Professor School of Computer Applications Lovely Professional University Phagwara Punjab India Assistant Professor Department of CS and IT Jain (Deemed-to-be University) Bangalore India Department of Data Insights Crisp Shared Services 7160 Columbia Gateway Dr Columbia United States of America Assistant Professor Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddewaram AP India BE-CSE RV Institute of Technology and Management Bengaluru India

This research proposes the neural network (NN)-fuzzy logic control (FLC)-based methodology, which is designed with two stages of execution. Stage-1 is composed with the NN approach; it takes the input from the scanned image, the input from the classified clustered group, processes it with hidden layers, and generates the final output, which is input to the FLC in stage 2. The input of stage 2 converts the input into fuzzified data (0s and 1s) and trains the FLC system with fuzzified set values. The trained data has been simulated for further stages in the FLC-based decision-making approach and integrated to identify the character patterns based on the trained dataset. FLC-based planting and normalization techniques are integrated for re-training the data. The dataset has been framed with more than 6200 handwritten image characters, which were written by 235 writers. It aligned with the pre-processing, classification, and filtering stages and achieved a 99.8% recognition rate.

关键词： Fuzzy Logic Control (FLC) Artificial Neural Network (ANN) Multiple Layered Perceptron (MLP) Convolutional Neural Network (CNN) Feed Forward Neural Network (FNN) Optical Character Recognition (OCR) Handwritten (HW)

来源：评论

学校读者我要写书评

暂无评论

A method of fundamental matrix estimation based on nsga-ii and improved quasi-affine transform

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第2期6卷 313-327页

作者： Fan, Yi-Kai Liu, Shi-Jian Kong, Ling-Ping Pan, Jeng-Shyang College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China VSB-Technical University of Ostrava Czech Republic Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Department of Information Management Chaoyang University of Technology Taiwan

The fundamental matrix is the mainstream solution to computer vision problems such as 3D reconstruction, real-time location and map building. Accuracy and efficiency are two main measurement indexes in fundamental matrix estimation. When the accuracy is not enough, it often needs to be corrected through back-end optimization and other costly ways, and low efficiency will affect the real-time performance of the system. In order to solve this problem, this paper proposes a new estimation method of fundamental matrix based on improved quasi affine transformation. Specifically, based on the QUATRE algorithm, this method first proposes a population cooperation method based on a specific "gene-chromosome" pattern. Secondly, combining the advantages of NSGA-II in solving multi-objective problems, the Pareto dominance relationship of the population chromosome was firstly calculated according to the objective function of mean polarity distance and internal points in the way of NSGA-II, and the crowding degree was also calculated. The operations of population initialization, mutation and crossover in the discrete solution space represented by the homogeneous coordinate system are redefined. The selection operation is then performed according to the elite policy of NSGA-II. In addition, a confidence-based method to determine the number of iterations is proposed to accelerate the algorithm. Experimental results show that the proposed method can effectively eliminate noise and mismatching, and is superior to the current mainstream methods in accuracy and efficiency, and can effectively solve the problem of fundamental matrix estimation. © 2021 Global Research Online. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

RailPC: A large-scale railway point cloud semantic segmentation dataset

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1548-1560页

作者： Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal UniversityNanjingChina Technology Innovation Center for Integrated Applications in Remote Sensing and Navigation Ministry of Natural ResourcesNanjingChina Eastern Institute of Technology(EIT) NingboChina Tianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio-temporal Big Data Technology TianjinChina College of Computer Science and Engineering Northwest Normal UniversityLanzhouChina Mckelvey School of Engineering Washington University in St.LouisSt.LouisMissouriUSA School of Electronic and Information Engineering Ningbo University of TechnologyNingboChina

Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value,but its development is severely hindered by the lack of suitable and specific ***,the models trained on existing urban road point cloud datasets demonstrate poor generalisation on railway data due to a large domain gap caused by non-overlapping special/rare categories,for example,rail track,track bed *** harness the potential of supervised learning methods in the domain of 3D railway semantic segmentation,we introduce RailPC,a new point cloud *** provides a large-scale dataset with rich annotations for semantic segmentation in the railway ***,RailPC contains twice the number of annotated points compared to the largest available mobile laser scanning(MLS)point cloud dataset and is the first railway-specific 3D dataset for semantic *** covers a total of nearly 25 km railway in two different scenes(urban and mountain),with 3 billion points that are finely labelled as 16 most typical classes with respect to railway,and the data acquisition process is completed in China by MLS *** extensive experimentation,we evaluate the performance of advanced scene understanding methods on the annotated dataset and present a synthetic analysis of semantic segmentation *** on our findings,we establish some critical challenges towards railway-scale point cloud semantic *** dataset is available at https://***/NNU-GISA/GISA-RailPC,and we will continuously update it based on community feedback.

关键词： data benchmark MLS point clouds railway scene semantic segmentation

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：