检索结果-内蒙古大学图书馆

44th Annual international conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Chatterjee, Tamaghno Ghoshi, Aayushman Sarkar, Sayan Indian Inst Engn Sci & Technol Sibpur India Hong Kong Univ Sci & Technol Hong Kong Peoples R China

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

Photoplethysmography (PPG) signal comprises physiological information related to cardiorespiratory health. High-quality PPG signals are necessary to extract cardiorespiratory information accurately. Motion artifacts can easily corrupt PPG signals due to human locomotion, leading to noise enriched, poor quality signals. Several rule-based and machine-learning (ML) - based approaches for PPG signal quality estimation are available, but those algorithms' efficacy is questionable. So, the authors propose a lightweight CNN architecture for signal quality assessment by employing a novel Quantum pattern recognition (QPR) technique. the proposed algorithm is validated on manually annotated data obtained from the University of Queensland database. A total of 28366, 5s signal segments are preprocessed and transformed into image files of 20 x 500 pixels for input to the 2D CNN architecture. the developed model classifies the PPG signal as 'good' and 'bad' with an accuracy of 98.3% with 99.3% sensitivity, 94.5% specificity and 98.9% F1-score. the experimental analysis concludes that slim module based architecture and novel Spatio-temporal pattern recognition technique improve the system's performance. the proposed approach is suitable for a resource-constrained wearable implementation.

关键词： Deep learning Maximum likelihood estimation Image segmentation Sensitivity System performance Photoplethysmography Physiology

来源：评论

学校读者我要写书评

暂无评论

Mobile Keystroke Biometrics Using Transformers 17

Mobile Keystroke Biometrics Using Transformers

引用

17th IEEE international conference on Automatic Face and Gesture recognition, FG 2023

作者： Stragapede, Giuseppe Delgado-Santos, Paula Tolosana, Ruben Vera-Rodriguez, Ruben Guest, Richard Morales, Aythami Universidad Autonoma de Madrid Biometrics and Data Pattern Analytics Lab Spain School of Engineering University of Kent United Kingdom

ISBN: (纸本)9798350345445

Among user authentication methods, behavioural biometrics has proven to be effective against identity theft as well as user-friendly and unobtrusive. One of the most popular traits in the literature is keystroke dynamics due to the large deployment of computers and mobile devices in our society. this paper focuses on improving keystroke biometric systems on the free-text scenario. this scenario is characterised as very challenging due to the uncontrolled text conditions, the influence of the user's emotional and physical state, and the in-use application. To overcome these drawbacks, methods based on deep learning such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been proposed in the literature, outperforming traditional machine learning methods. However, these architectures still have aspects that need to be reviewed and improved. To the best of our knowl-edge, this is the first study that proposes keystroke biometric systems based on Transformers. the proposed Transformer architecture has achieved Equal Error Rate (EER) values of 3.84% in the popular Aalto mobile keystroke database using only 5 enrolment sessions, outperforming by a large margin other state-of-the-art approaches in the literature. © 2023 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Survey on Human Activity recognition Using Deep learning Techniques and Wearable Sensor data 4th

A Survey on Human Activity Recognition Using Deep Learning T...

引用

4th international conference on machine learning, Image Processing, Network Security and data Sciences (MIND)

作者： Dua, Nidhi Singh, Shiva Nand Challa, Sravan Kumar Semwal, Vijay Bhaskar Kumar, M. L. S. Sai Natl Inst Technol Jamshedpur Jharkhand India MANIT Bhopal Bhopal MP India Vignans Inst Informat Technol Visakhapatnam India

ISBN: (纸本)9783031243516;9783031243523

HAR has attained major attention because of its significant use in reallife scenarios like activity and fitness monitoring, rehabilitation, gaming, prosthetic limbs, healthcare, smart surveillance systems, etc. HAR systems provide ways for monitoring human behaviors and detecting body movements and various activities by using sensor data. the collection of sensors available in the mobile and other wearable devices hasmade most of these HAR applications easily possible. Moreover, Deep learning (DL) has further accelerated the research on HAR using the data obtained via wearable devices. In this paper, we have discussed the overview of HAR, its applications, and popular benchmark datasets available publicly. Further, we discussed various DL techniques applied for HAR applications. We have also presented the challenges associated with the field and the future directions for performing more vital research in HAR.

关键词： Wearable sensors pattern recognition HAR Deep learning

来源：评论

学校读者我要写书评

暂无评论

Impacts of data preprocessing and TF-IDF based feature extraction on chinese spam recognition in machine learning methods

Impacts of data preprocessing and TF-IDF based feature extra...

引用

5th international conference on Artificial Intelligence and Advanced Manufacturing (AIAM 2023)

作者： J. Gao T. Qiu G. Chen School of Information Engineering Nanchang Hangkong University NanChang 330063 People's Republic of China

Spam has been threatening people's life and production safety, in order to reduce its harm, it is necessary to study the topic of spam filtering. In spam identification, data preprocessing and feature extraction are two important aspects. In this paper, the impact of combing TF-IDF (Term Frequency-Inverse Document Frequency) based feature extraction and different preprocessing methods on Chinese spam recognition is investigated. We analyzed the effectiveness of mainstream machine learning methods on Chinese spam identification with or without data preprocessing. We discussed in detail the effect of different sizes of features on the classification results. the SVM (Support Vector machine) model presented in this paper achieves very high accuracy (99.0%) and F1 (99.26%) value in spam filtering. It shows that data preprocessing improves the performance of machine learning models, and the degree of improvement is related to the selected model. Experiments have shown that to achieve the same accuracy, the random forest model requires fewer features than the Bayesian model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Oriented Object Detection Network for Cable Terminal Equipment in Infrared Images

An Oriented Object Detection Network for Cable Terminal Equi...

引用

pattern recognition and machine learning (PRML), IEEE international conference on

作者： Zhenyu Zuo Yuxiang Wu School of Automation Science and Engineering South China University of Technology Guangzhou China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

Cable terminal equipment is an important part of power transmission lines. Detecting cable terminal equipment in infrared images is a prerequisite for realizing temperature measurement of it, which plays an important role in maintaining the transmission line stable. A detection network for cable terminal equipment in infrared images is proposed in this paper, including the feature extraction network, the feature fusion network and the oriented object detection head. the AngleConv module, the 2DDynaConv module and the LCSAM module are proposed and embedded into the feature extraction network. In addition, the LCIoU is proposed to calculate the prediction loss of the position, the long side length and the short side length, which is more suitable for the large ratio of the long side to the short side of cable terminal equipment than CIoU. Some ablation experiments are conducted, which prove the effectiveness of these modules and methods proposed. In the self-made dataset of infrared images of cable terminal equipment, the proposed network achieves mAP. 50 of 95.4% and mAP.75 of 75.3%, and outperforms some mainstream oriented object detection networks.

关键词： Temperature measurement Head Power cables Supervised learning Object detection Manuals Feature extraction Transmission line measurements Magnetic heads pattern recognition

来源：评论

学校读者我要写书评

暂无评论

On Some Scientific Results of the ICPR-2020

引用

pattern recognition AND IMAGE ANALYSIS 2021年第3期31卷 357-363页

作者： Gurevich, I. B. Moroni, D. Pascali, M. A. Yashina, V. V. Russian Acad Sci Fed Res Ctr Comp Sci & Control Bldg 244 Vavilov Str Moscow 119333 Russia Pisa Natl Res Council Natl Res Council Italy Res Area Pisa Inst Informat Sci & Technol A Faedo I-56124 Pisa Italy

this special issue of PRIA is devoted to some scientific results and trends of the 25th international conference on pattern recognition (Virtual, Milano, Italy, January 10-15, 2021). Two important events of ICPR-2020 are represented in this special issue: (1) the paper of Professor Ching Yee Suen (Centre for pattern recognition and machine Intelligence, Department of Computer Science and Software Engineering, Concordia University, Montreal, QC, Canada)-the recent winner of IAPR very prestigious K.S. Fu Prize for a year of 2020. the paper based on his lecture "From handwriting to human personality and facial beauty" presented at the ICPR 2020;(2) Special issue "ICPR-2020 Workshop "Image mining. theory and Applications." the analysis of the scientific contribution of IMTA-VII-2021 allows us to draw the following conclusions: (1) the construction of a unified mathematical theory of image analysis is still far from complete. (2) there is considerable interest in the development of new mathematical methods for analyzing and evaluating information presented in the form of images. (3) there is a tendency to expand the mathematical apparatus in the development of new methods of image analysis and recognition by involving in this process areas of mathematics that were not previously used in image analysis. (4) the gap between the capabilities of new mathematical methods of image analysis and recognition and their actual use in solving applied problems remains significant. (5) there is an excessive use of neural networks in solving applied problems of image analysis and image recognition, and quite often without proper justification and interpretation of the results. the special issue includes articles based on the workshop papers selected by the IMTA-VII-2021 Program Committee for publication in PRIA. the PRIA special issue "Scientific Resume of the 25th international conference on pattern recognition" is prepared by the National Committee for pattern recognition and Image A

关键词： automation of data analysis biomedical applications biomedical images conditional generative adversarial networks data mining descriptive image analysis face beauty identity-preserved image mining intellectual data analysis mathematical theory of image analysis mathematical theory of pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-class Weather Forecasting from Twitter Using machine learning Aprroaches 5

Multi-class Weather Forecasting from Twitter Using Machine L...

引用

5th international conference on Computer Science and Computational Intelligence (ICCSCI)

作者： Purwandari, Kartika Sigalingging, Join W. C. Cenggoro, Tjeng Wawan Pardamean, Bens Bina Nusantara Univ Bioinformat & Data Sci Res Ctr Jakarta 11480 Indonesia Meteorol Climatol & Geophys Agcy Database Ctr Div BMKG Jakarta 10720 Indonesia Bina Nusantara Univ Sch Comp Sci Comp Sci Dept Jakarta 11480 Indonesia Bina Nusantara Univ Comp Sci Dept BINUS Grad Program Comp Sci Program Jakarta 11480 Indonesia

Now in the era of big data, many are applying information methods accurately especially by social media. the aims of this study to classify the weather based on Twitter automatically using text mining by using Support Vector machine (SVM), Multinomial Naive Bayes (MNB), and Logistic Regression (LR) method. the experimental results show that SVM substantially outperforms various other machine learning algorithms for the task of text classification with an accuracy value of 93%. this result proves that SVM is very suitable for text categorization. We use clustering technique to read the pattern in customers' opinion about the restaurant based on some measurement variables. (C) 2021 the Authors. Published by Elsevier B.V.

关键词： weather classification twitter machine learning support vector machine multinomial naive bayes logistic regression

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Representation learning with Input-Aware and Cluster-Aware Regularization

Graph Contrastive Representation Learning with Input-Aware a...

引用

5th international Workshop on learning with Imbalanced Domains - theory and Applications / European conference on machine learning and Principles and Practice of Knowledge Discovery in databases (ECML PKDD)

作者： Li, Jin Li, Bingshi Zhang, Qirong Chen, Xinlong Huang, Xinyang Guo, Longkun Fu, Yang-Geng Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China Fuzhou Univ Sch Math & Stat Fuzhou Peoples R China

ISBN: (纸本)9783031434143;9783031434150

With broad applications in network analysis and mining, Graph Contrastive learning (GCL) is attracting growing research interest. Despite its successful usage in extracting concise but useful information through contrasting different augmented graph views as an outstanding self-supervised technique, GCL is facing a major challenge in how to make the semantic information extracted well-organized in structure and consequently easily understood by a downstream classifier. In this paper, we propose a novel cluster-based GCL framework to obtain a semantically well-formed structure of node embeddings via maximizing mutual information between input graph and output embeddings, which also provides a more clear decision boundary through accomplishing a cluster-level global-local contrastive task. We further argue in theory that the proposed method can correctly maximize the mutual information between an input graph and output embeddings. Moreover, we further improve the proposed method for better practical performance by incorporating additional refined gadgets, e.g., measuring uncertainty of clustering and additional structural information extraction via local-local node-level contrasting module enhanced by Graph Cut. Lastly, extensive experiments are carried out to demonstrate the practical performance gain of our method in six real-world datasets over the most prevalent existing state-of-the-art models.

关键词： Graph neural networks Graph representation learning Contrastive learning Node classification Node clustering

来源：评论

学校读者我要写书评

暂无评论

A Proposal of an Improved Maximum Bayes Boundary-Ness Training Method 22

A Proposal of an Improved Maximum Bayes Boundary-Ness Traini...

引用

5th international conference on Signal Processing and machine learning, SPML 2022

作者： Kishishita, Koki Katagiri, Shigeru Ohsaki, Miho Division of Information Science Nara Institute of Science and Technology Japan Graduate School of Science and Engineering Doshisha University Kyoto Japan

ISBN: (纸本)9781450396912

One ultimate objective of statistical pattern recognition is to achieve the optimal status that produces Bayes error and its corresponding Bayes boundary. To compute such parameters of pattern recognizers without requiring unrealistically long computation times and strict parameter assumptions, the Maximum Bayes Boundary-ness (MBB) training method was proposed, and its effectiveness was demonstrated. this method focuses on the fact that the posterior probabilities on the Bayes boundary are equal among the classes that comprise the boundary and aim to directly achieve it without estimating the Bayes error. In the MBB training method, a loss function is defined for each sample, its weighted average was defined as an empirical average loss, and its minimization was a training objective. However, the loss is defined slightly excessively using a convex function. In this paper, we demonstrate the high utility of a simplified MBB training that is defined by correcting or simplifying the formalization of conventional MBB training by removing the convex function in the loss. We experimentally compared five datasets and gained speed in most of them. © 2022 Association for Computing machinery.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

FAM-Net: A Classification Method for ECG Signals Based on Full Attention Mechanism Network

FAM-Net: A Classification Method for ECG Signals Based on Fu...

引用

pattern recognition and machine learning (PRML), IEEE international conference on

作者： Xiangdong Peng Congcheng Pan Quan Zhang Yong Lu Jing Li Ganbo Cao Yuanbo Zeng School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics Nanchang China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

In recent years, deep learning has become an important research method in different applications, including the field of medical and health care, especially in the detection of abnormal ECG signals. However, the existing ECG signal classification models based on deep learning have the problems of large network model depth and overfitting, and the accuracy of the classification model needs to be improved. In this paper, we propose a FAM-Net-based (full attention mechanism network) ECG signal classification method. this method avoids the commonly used ECG classification models based on CNN and LSTM, adopts a multi-head attention mechanism, and uses position coding and dense interpolation strategies to finally obtain the feature vectors of ECG signals. the overall accuracy, specificity, sensitivity, and Macro-F1 of the final classification test of the model reached 99.27%, 99.33%, 95.06%, and 96.29%, which shortened the depth of the network model and reduced the computational complexity of the model while ensuring the classification performance.

关键词： Deep learning Convolutional codes Interpolation Attention mechanisms Recurrent neural networks Convolution Computational modeling pattern classification Electrocardiography Encoding

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：