检索结果-内蒙古大学图书馆

7th International Conference on Computer Vision and Image Processing, CVIP 2022

作者： Kumar, Priyush Sinha, Indrajeet Kumar Singh, Krishna Pratap Machine Learning and Optimization Lab Department of Information Technology Indian Institute of Information Technology Allahabad Uttar Pradesh Prayagraj India

ISBN: (纸本)9783031314162

Deep learning models have achieved state-of-the-art in many challenging domains, whereas it is a data-hungry method. Collecting sensitive and labelled medical data sets is challenging and costly. Recently, federated learning has been used to train a model without sharing the data at a central place for a single task. We propose a novel Multi-task federated learning (MTFL) approach to utilize the data sets of various similar kinds of tasks. We used two binary class X-ray data sets: Pneumonia disease classification and TB disease classification. We compared MTFL with federated learning for a single task and CNN with data in one place. Results show that MTFL has achieved better specificity and accuracy than other models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Community Through User Similarity Analysis on Twitter 18

Detecting Community Through User Similarity Analysis on Twit...

引用

18th International Conference on Ubiquitous information Management and Communication, IMCOM 2024

作者： Hasan, Md Ahsan Ul Bakar, Azuraliza Abu Yaakub, Mohd Ridzwan Universiti Kebangsaan Malaysia Sentiment Analysis Lab Center for Artificial Intelligence Technology Faculty of Information Science and Technology Selangor Bangi43600 Malaysia Universiti Kebangsaan Malaysia Data Mining and Optimization Lab Center for Artificial Intelligence Technology Faculty of Information Science and Technology Selangor Bangi43600 Malaysia

ISBN: (纸本)9798350331011

Community detection in social relationship networks is a significant research domain within the field of social network analysis. However, Twitter sets itself apart from conventional friends' and followers' networks due to its users' distinct focus on sharing thoughts and ideas related to specific topics rather than prioritising personal connections. As a result, relying solely on friends' and followers' relations in Twitter networks for community detection would be insufficient and incomplete. In this paper, we proposed a Twitter community detection method that measures similarity using user profiles, tweet subjects, and tweet sentiment in this research. We constructed a similarity network using real-time Twitter API data and compared it to Zachary's Karate Network. The proposed approach enhances the quality function of modularity and conductance in the Louvain community detection algorithm, resulting in a more precise and meaningful community structure within the Twitter network. © 2024 IEEE.

关键词： Graph Databases

来源：评论

学校读者我要写书评

暂无评论

AKDC: Ambiguous Kernel Distance Clustering Algorithm for COVID-19 CT Scans Analysis

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2024年第10期54卷 6218-6229页

作者： Singh, Pritpal Huang, Yo-Ping The Quantum Optimization Research Lab Department of Data Science and Analytics Central University of Rajasthan Ajmer305817 India National Taipei University of Technology Department of Electrical Engineering Taipei10608 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City23741 Taiwan Chaoyang University of Technology Department of Information and Communication Engineering Taichung41349 Taiwan

Conventional soft clustering algorithms perform well on linearly distributed features, but their performance degrades on nonlinearly distributed features in high-dimensional space. In this study, a novel soft clustering algorithm, the ambiguous kernel distance clustering (AKDC) algorithm, is presented. This algorithm is developed by applying ambiguous set theory and the Gaussian kernel function. The ambiguous set theory defines the ambiguities inherent in each feature with four membership values: 1) true;2) false;3) true-ambiguous;and 4) false-ambiguous. The degree of membership values here forms a low-dimensional feature space that is not linearly distributed. Therefore, these nonlinearly distributed membership values are mapped into a high-dimensional feature space using the Gaussian kernel function. This study focuses on performing cluster analysis of computerized tomography scans of COVID-19 (CTSC-19) cases using AKDC. COVID-19, recognized as one of the most life-threatening diseases of this century, is highly contagious, and early diagnosis may prevent one-to-one transmission. Extensive empirical studies have been conducted with different types of CTSC-19 to demonstrate its effectiveness against existing kernel-based clustering and nonkernel-based clustering algorithms, namely mercer kernel fuzzy c-mean (MKFCM), kernel generalized FCM (KGFCM), kernel intuitionistic fuzzy entropy c-means (KIFECMs), morphological reconstruction and membership filtering clustering (FRFCM), and intuitionistic FCM based on membership information transferring and similarity measurements (IFCM-MS). The effectiveness of the proposed algorithm compared to the existing algorithms is evaluated using standard statistical metrics, such as dice index (DI), Jaccard index (JI), structural similarity index (SI), and correlation coefficient (CC). The empirical results show that AKDC is more effective than existing algorithms based on DI, JI, SI, and CC. © 2013 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

PI-Based Set-Point Learning Control for Batch Processes with Unknown Dynamics and Nonrepetitive Uncertainties

引用

IEEE Transactions on Automatic Control 2024年第6期70卷 3649-3664页

作者： Hao, Shoulin Liu, Tao Rogers, Eric Wang, Youqing Paszke, Wojciech Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Eduction The Institute of Advanced Measurement and Control Technology Dalian116024 China Beijing University of Chemical Technology College of Information Science and Technology Beijing100029 China University of Zielona Góra Institute of Automation Electronic and Electrical Engineering Zielona Góra65-246 Poland

For industrial batch processes with unknown dynamics subject to nonrepetitive initial conditions and disturbances, this paper develops a novel adaptive data-driven set-point learning control (ADDSPLC) scheme based on only the measured process input and output data, which has two loops, one for the dynamics within a batch and the other for the batch-to-batch dynamics. In the former case, a model-free tuning strategy is firstly presented for determining the closed-loop PI controller parameters. For the latter case, a set-point learning control law with adaptive set-point learning gain and gradient estimation is developed for batch run optimization. Robust convergence of the output tracking error is rigorously analyzed together with the boundedness of adaptive learning gain and real-time updated set-point command. Moreover, another iterative extended state observer based (ADDSPLC) scheme is developed with rigorous convergence and boundedness analysis, to enhance the robust tracking performance against nonrepetitive uncertainties. Finally, two illustrative examples from the literature are used to demonstrate the effectiveness and superiority of the new schemes over the recently developed data-driven learning control designs. © 1963-2012 IEEE.

关键词： Batch data processing

来源：评论

学校读者我要写书评

暂无评论

An Ambiguous Edge Detection Method for Computed Tomography Scans of Coronavirus Disease 2019 Cases

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2024年第1期54卷 352-364页

作者： Singh, Pritpal Huang, Yo-Ping Central University of Rajasthan Quantum Optimization Research Lab Department of Data Science and Analytics Ajmer305817 India Department of Electrical Engineering National Penghu University of Science and Technology Magong88046 Taiwan The Department of Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan The Department of Computer Science and Information Engineering National Taipei University New Taipei City23741 Taiwan The Department of Information and Communication Engineering Chaoyang University of Technology Taichung41349 Taiwan

Recently, the coronavirus disease of 2019 (COVID-19), as named by the World Health Organization (WHO), has spread to over 200 countries. The WHO has declared this disease as a worldwide public health emergency. One of the most difficult tasks in combating this epidemic is to identify and segregate the afflicted people. The reverse transcription-polymerase chain reaction test (RT-PCR) is the most common pathology test used to diagnose this infection. Studies show that the RT-PCR test has a low-positive rate and sometimes becomes ineffective in diagnosing infection. In some cases, computed tomography (CT) scans reveal acute pneumonia and pulmonary anomalies. Therefore, CT scans are used together with RT-PCR tests to confirm infected people. Existing artificial intelligence and machine learning techniques require a large number of CT scans for training, which is a time-consuming process. Visual inspection shows that most CT scans of COVID-19 cases have broken, blurred, and ambiguous edges for infectious areas. Another major issue with these images is the heterogeneous intensity of the pixels, high noise, and low resolution. As a result of all these issues, the problem of effective edges/boundaries of various areas of CT scans of COVID-19 cases cannot be resolved by the current edge detection approach. Indeed, improper selection of edges can lead to an incorrect diagnosis of diseases through CT scans of COVID-19 cases. Therefore, there is an urgent need for a diagnostic method in addition to the RT-PCR test that can extract useful information from the minimum number of chest CT scans of suspected COVID-19 cases. This study introduces a new ambiguous edge detection method (AEDM) for identifying the edges/boundaries of different regions in CT scans of COVID-19 cases. The proposed AEDM is developed on the basis of ambiguous set (AS) theory, which is highly efficient in processing ambiguous pixel information. For simulation purposes, various CT scans of COVID-19 cases are c

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

DenseBAM-GI: Attention Augmented DeneseNet with momentum aided GRU for HMER

arXiv

引用

arXiv 2023年

作者： Pal, Aniket Singh, Krishna Pratap Machine Learning & optimization lab Department of Information technology Indian Institute of Information Technology Allahabad India

The task of recognising Handwritten Mathematical Expressions (HMER) is crucial in the fields of digital education and scholarly research. However, it is difficult to accurately determine the length and complex spatial relationships among symbols in handwritten mathematical expressions. In this study, we present a novel encoder-decoder architecture (DenseBAM-GI) for HMER, where the encoder has a Bottleneck Attention Module (BAM) to improve feature representation and the decoder has a Gated Input-GRU (GI-GRU) unit with an extra gate to make decoding long and complex expressions easier. The proposed model is an efficient and lightweight architecture with performance equivalent to state-of-the-art models in terms of Expression Recognition Rate (exprate). It also performs better in terms of top 1, 2, and 3 error accuracy (≤ 1(%), ≤ 2(%) and ≤ 3(%)) across the CROHME 2014, 2016, and 2019 datasets. DenseBAM-GI achieves the best exprate among all models on the CROHME 2019 dataset. Importantly, these successes are accomplished with a drop in the complexity of the calculation and a reduction in the need for GPU memory. © 2023, CC BY.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Densebam-Gi: Attention Augmented Denesenet with Momentum Aided Gru for Hmer

SSRN

引用

SSRN 2023年

作者： Pal, Aniket Singh, Krishna Pratap Machine Learning & optimization lab Department of Information technology Indian Institute of Information Technology Allahabad India

The task of recognising Handwritten Mathematical Expressions (HMER) is crucial in the fields of digital education and scholarly research. However, it is difficult to accurately determine the length and complex spatial relationships among symbols in handwritten mathematical expressions. In this study, we present a novel encoder-decoder architecture (DenseBAMGI) for HMER, where the encoder has a Bottleneck Attention Module (BAM) to improve feature representation and the decoder has a Gated Input-GRU (GI-GRU) unit with an extra gate to make decoding long and complex expressions easier. The proposed model is an efficient and lightweight architecture with performance equivalent to state-of-the-art models in terms of Expression Recognition Rate (exprate). It also performs better in terms of top 1, 2, and 3 error accuracy (≤ 1(%), ≤ 2(%) and ≤ 3(%)) across the CROHME 2014, 2016, and2019 datasets. DenseBAM-GI achieves the best exprate among all models on the CROHME 2019 dataset. Importantly, these successes are accomplished with a drop in the complexity of the calculation and a reduction in the need for GPU memory. © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Four-Valued Ambiguous Logic: Application in Designing Ambiguous Inference System for Control Systems

引用

International Journal of Fuzzy Systems 2023年第8期25卷 2921-2938页

作者： Singh, Pritpal Huang, Yo-Ping Quantum Optimization Research Lab Department of Data Science and Analytics Central University of Rajasthan Rajasthan Ajmer305817 India Department of Electrical Engineering National Penghu University of Science and Technology Penghu88046 Taiwan Department of Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan Department of Information and Communication Engineering Chaoyang University of Technology Taichung41349 Taiwan

Ambiguous set has recently been introduced as a new branch of mathematics and computer science dealing with the nature of ambiguity of uncertain events. There is much scope for the development of new theories based on the principles of the ambiguous set. In this direction, an idea of ambiguous logic is proposed, which can be regarded as a family of four-valued logic. In this study, the limitations of existing theories such as fuzzy logic, intuitionistic fuzzy logic, and neutrosophic logic that are used to deal with uncertainty are first discussed. Then an introduction to the ambiguous set and ambiguous logic is given. In ambiguous logic, there are four membership degrees for each proposition, which can be characterized as true, false, true-ambiguous, and false-ambiguous. We then analyze the membership degrees of propositions using various connectives, including negation, conjunction, and disjunction. In this study, we discuss various laws that support the different algebraic operations for comparing propositions in terms of membership degrees. An approach is presented to define a rule using a proposition consisting of membership degrees, called an ambiguous rule. The modus ponens rule of inference is defined by combining various ambiguous rules, and is called ambiguous inference. Finally, to demonstrate the real-time application of ambiguous logic, an ambiguous inference system is designed that can be used in machine control systems. © 2023, The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Fault identification of rotating machinery based on multiscale convolution and deep residual networks 9

Fault identification of rotating machinery based on multisca...

引用

9th International Symposium on Sensors, Mechatronics, and Automation System, ISSMAS 2023

作者： Wang, Huihui Fan, Tianqi Qiu, Sen Liu, Long School of Intelligence and Electronic Engineering Dalian Neusoft University of Information Dalian116023 China Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education The School of Control Science and Engineering Dalian University of Technology Dalian116024 China

ISBN: (纸本)9781510672802

Rotating machinery and equipment have a wide range of industrial applications, and it is important to perform intelligent fault detection during their operation. In order to fully capture the multi-scale features of mechanical fault data while solving the degradation problem of deep networks, we propose an intelligent fault detection model combining multi-scale convolution and deep residual networks. We validate it on four publicly available datasets, and the results demonstrate the excellent performance of the proposed method. © 2024 SPIE.

关键词： Convolution Feature extraction Deep learning Machine learning Vibration Data modeling Lithium Convolutional neural networks Data centers Signal processing

来源：评论

学校读者我要写书评

暂无评论

Few Shots Learning: Caricature to Image Recognition Using Improved Relation Network 1

引用

5th International Conference on Computer Vision and Image Processing, CVIP 2020

作者： Agrawal, Rashi Singh, Upendra Pratap Singh, Krishna Pratap Machine Learning and Optimization Lab Indian Institute of Information Technology Allahabad Prayagraj India

ISBN: (数字)9789811611032

ISBN: (纸本)9789811611025

Inspired by the human ability to learn instance-label associations given only a handful of examples, few-shots learning is gaining increased attention from the researchers. In this direction, we have proposed a modified relation network to perform few shots caricature to image recognition. Since caricature and real images come from different modalities, we have extended the relation network to contain separate feature extracting networks for the two modalities in the embedding module. This extension was necessitated by the fact that since caricature and real images come from different modalities and hence different distributions, a single feature extracting network in the embedding module may not learn cross-modal features. Experiment results on caricature recognition dataset and subsequent comparison of our proposed network against the baseline model quantitatively substantiates our hypothesis. While comparing the performance of our modified network against the baseline, we were able to improve the recognition accuracy by 26.3 % for 5 - way, 1 - shot setting and by 25.5 % for 5 - way, 5 - shot setting. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Embeddings

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：