检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Raj, Amogh Gudumotou, Carol Eunice Bun, Sakol Srinivasa, Keerthana Sarshar, Arash Depratment of Computer Engineering and Computer Science California State University Long BeachCA90840 United States

We present a novel framework combining Deep Operator Networks (DeepONets) with Physics-Informed Neural Networks (PINNs) to solve partial differential equations (PDEs) and estimate their unknown parameters. By integrating data-driven learning with physical constraints, our method achieves robust and accurate solutions across diverse scenarios. Bayesian training is implemented through variational inference, allowing for comprehensive uncertainty quantification for both aleatoric and epistemic uncertainties. This ensures reliable predictions and parameter estimates even in noisy conditions or when some of the physical equations governing the problem are missing. The framework demonstrates its efficacy in solving forward and inverse problems, including the 1D unsteady heat equation and 2D reaction-diffusion equations, as well as regression tasks with sparse, noisy observations. This approach provides a computationally efficient and generalizable method for addressing uncertainty quantification in PDE surrogate *** Codes 65K10, 35R30, 68T07 Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Player Classification Technique Based on Performance for a Soccer Team Using Machine Learning Algorithms 3

Player Classification Technique Based on Performance for a S...

引用

3rd IEEE International Conference on Electrical, computer and Communication Technologies: computer science and engineering, ICECCT 2019

作者： Shahriar, Md. Tanzil Islam, Yashna Amin, Md. Nur Depratment of Computer Science and Engineering American International University Bangladesh Depratment of Computer Science and Engineering Stamford University Bangladesh

ISBN: (纸本)9781538681572

The present scenario of Bangladesh Soccer Team is very much worrying. The absence of playing opportunities due to the miscoordination among the players has led the national team slip to their worst ever FIFA ranking of 194th. The ultimate success of a team depends upon its player selection. Generally, the coach and the management team select the best 11 players for each match from a pool of players by evaluating various attributes of the players. This paper aims to propose a player classification technique for selecting the best players automatically to form a soccer team. The players are classified whether they will play or not based on their performances using multiple machine learning algorithms. The results we achieved based on the performance attributes, we believe would help the coach and management team to build up a successful soccer team. © 2019 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Instantaneous Envelope and Energy Features for LCL Activation based complementary 1D-CNN in EEG Stress classification 15

Instantaneous Envelope and Energy Features for LCL Activatio...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Naren, J. Sathya Durga, V. Hindustan Institute of Technology and Science Depratment of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

The work proposes a stress classification scheme that uses instantaneous envelope and energy features from the electroencephalograph (EEG) signals. The approach uses linear-cosine-linear (LCL) activation function-based complementary kernel 1D-CNN for the classification of stress. Initially, the EEG brain signals are categorized into two components, where the first class corresponds to the components of the delta, theta, and alpha bands (DTA band), while the second class corresponds to the components of the beta band. The instantaneous energy feature is estimated from the DTA band, while the envelope feature is estimated from the B-band. These two features are used to differentiate the induced stress types namely the recognition task, arithmetic task, and color image recognition task each with intense levels of high, medium, and low. The EEG signals collected from the SAM-40 datasets with the measures namely accuracy, F1-score, recall, specificity, and precision are used for analysis. The proposed approach results in accuracy, F1-score, recall, specificity, and precision of 96.61%, 95.99%, 96.57%, 99.57%, and 95.45% respectively which is higher than the traditional stress classification schemes. © 2024 IEEE.

关键词： activation function EEG bands EEG signals feature extraction Stress classification

来源：评论

学校读者我要写书评

暂无评论

Maritime Security - Illegal Fishing Detection Using Deep Learning

Maritime Security - Illegal Fishing Detection Using Deep Lea...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Lalasa, K.Lakshmi Srija, R.J.V. Kumar, K.Praveen Velagapudi Ramakrishna Siddhartha Engineering College Depratment of Artificial Intelligence and Data Science Vijayawada India Velagapudi Ramakrishna Siddhartha Engineering College Depratment of Computer Science and Engineering Vijayawada India

ISBN: (纸本)9798350359688

Illegal fishing is an unresolved and internationally pervasive problem that occurs both on the high seas and in areas within national jurisdiction. Existing technologies use anomaly detection algorithms that examine the data from Automatic Identification System (AIS) and radar cameras having long range. It is capable of covering 44.4 km. These algorithms also include clustering, density-based methods, or neural networks that are used to identify unusual behavior or patterns in fishing vessel data. These algorithms can flag vessels that deviate from typical fishing patterns, helping authorities target suspicious activities. However, they fail to identify the complex patterns and accurately detect illegal fishing. We propose a system that increases the accuracy of algorithms by identifying complex patterns to send an alert to respective authorities. These alerts play a role in decreasing illegal fishing to some extent. Based on [1] US Food and Agriculture Organization's illegal fishing activities have an economic value of US$10-23 billion (estimates) and are responsible for the loss of 11-26 million tons of fish every year. We are proposing a system based on remote sensing data i.e., satellite images with higher resolution © 2024 IEEE.

关键词： Fisheries

来源：评论

学校读者我要写书评

暂无评论

From Pixels to Payouts -A Satellite Based Solution

From Pixels to Payouts -A Satellite Based Solution

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Deepthi, R.S.S.V. Priya, A Leela Revanth, D. Ajay, K. Madhavi, M. Velagapudi Ramakrishna Siddhartha Engineering College Depratment of Artificial Intelligence and Data Science Vijayawada India Velagapudi Ramakrishna Siddhartha Engineering College Depratment of Computer Science and Engineering Vijayawada India

ISBN: (纸本)9798350359688

The Pradhan Mantri Fasal Bima Yojana (PMFBY) stands as a crucial initiative for farmers' protection, yet grapples with challenges like delayed claims, inaccurate loss assessments, and uneven aid distribution [1]. This project proposes an innovative solution that addresses these issues by introducing a precision agriculture and risk management framework. The current crop insurance policies rely on an area-based approach and limited weather indices, resulting in an inadequate assessment of individual crop health and losses [2]. This shortfall leads to unjust aid distribution, leaving deserving farmers underserved [3]. The proposed solution advocates for a paradigm shift, incorporating a personalized and technology-driven approach. By integrating remote sensing technology, machine learning algorithms, and comprehensive data analysis, the system optimizes insurance resource allocation, assessing crop and regional risk profiles with precision. Furthermore, the project implements advanced image processing, segmentation, and machine learning models, such as SVM and CNN, for crop detection and yield estimation. The Google Maps API enhances decision support through geo-mapping, providing a transparent and data-driven basis for aid distribution. This innovative approach fosters equity, transparency, and active farmer participation, overcoming the limitations of existing methodologies. With a focus on precision, transparency, and equity, the proposed solution aims to revolutionize the effectiveness of PMFBY, ensuring accurate assessment and targeted aid distribution for farmers facing crop stress and losses. © 2024 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Noninvasive brain-computer interfaces for augmentative and alternative communication

引用

IEEE Reviews in Biomedical engineering 2014年 7卷 31-49页

作者： Akcakaya, Murat Peters, Betts Moghadamfalahi, Mohammad Mooney, Aimee R. Orhan, Umut Oken, Barry Erdogmus, Deniz Fried-Oken, Melanie Electrical and Computer Engineering Depratment Northeastern University Boston MA 02115 United States Oregon Health and Science University Portland OR 97239 United States

Brain-computer interfaces (BCIs) promise to provide a novel access channel for assistive technologies, including augmentative and alternative communication (AAC) systems, to people with severe speech and physical impairments (SSPI). Research on the subject has been accelerating significantly in the last decade and the research community took great strides toward making BCI-AAC a practical reality to individuals with SSPI. Nevertheless, the end goal has still not been reached and there is much work to be done to produce real-world-worthy systems that can be comfortably, conveniently, and reliably used by individuals with SSPI with help from their families and care givers who will need to maintain, setup, and debug the systems at home. This paper reviews reports in the BCI field that aim at AAC as the application domain with a consideration on both technical and clinical aspects. © 2013 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Hierarchical behavior structure for NAO robot utilizing fuzzy inference systems

Hierarchical behavior structure for NAO robot utilizing fuzz...

引用

International Conference on Electrical and Control engineering, ICECE 2010

作者： Jozi, Bahram Fakharian, Ahamd Karachi, Armita Depratment of Computer and Electrical Engineering Islamic Azad University Qazvin Iran School of Computer Engineering Iran University of Science and Technology Tehran Iran

ISBN: (纸本)9780769540313

Playing soccer is not a simple task, and robot needs a hierarchical behavior structure to decide how to play at any situation during the game, in our previous work, we introduced a behavior structure for NAO humanoid robot. One significant task in playing soccer is proper decision making during the game, in this paper, to achieve better decision making, we benefited from fuzzy inference systems in "ball-handled" skill in the proposed behavior structure, first fuzzy inference system is benefited from mamdani product logic which is local, and the second one uses lucasiewicz logic which is global one, both systems are implemented and compared in this paper. © 2010 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Design of a Secure Blockchain-Based Smart IoV Architecture 3

Design of a Secure Blockchain-Based Smart IoV Architecture

引用

3rd International Conference on Signal Processing and Information Security, ICSPIS 2020

作者： Das, Debashis Banerjee, Sourav Mansoor, Wathiq Biswas, Utpal Chatterjee, Pushpita Ghosh, Uttam Computer Science and Engineering University of Kalyani Kalyani India Computer Science and Engineering Kalyani Government Engineering College Kalyani India University of Dubai Electrical Engineering Department Dubai United Arab Emirates Computer Science Engineering Old Dominion University VA United States Vanderbilt University Depratment of Computer Science TN United States

ISBN: (纸本)9781728189987

Blockchain is developing rapidly in various domains for its security. Nowadays, one of the most crucial fundamental concerns is internet security. Blockchain is a novel solution to enhance the security of network applications. However, there are no precise frameworks to secure the Internet of Vehicle (IoV) using Blockchain technology. In this paper, a blockchain-based smart internet of vehicle (BSIoV) framework has been proposed due to the cooperative, collaborative, transparent, and secure characteristics of Blockchain. The main contribution of the proposed work is to connect vehicle-related authorities together to fix a secure and transparent vehicle-to-everything (V2X) communication through the peer-to-peer network connection and provide secure services to the intelligent transport systems. A key management strategy has been included to identify a vehicle in this proposed system. The proposed framework can also provide a significant solution for the data security and safety of the connected vehicles in blockchain network. © 2020 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Consecutive k-out-of-n:W system signature reliability appraisal via structure–function approach and u-function approach

引用

Life Cycle Reliability and Safety engineering 2024年第3期13卷 231-242页

作者： Sadiya Kumar, Akshay Ram, Mangey Department of Mathematics Graphic Era Deemed to be University Depratment of Mathematics Graphic Era Hill University Department of Mathematics Computer Science and Engineering Graphic Era Deemed to be University

The signature reliability of the consecutive k-out-of-n:W system is studied using two different approaches: the structure–function approach and the u-function approach. The connection is supposed to comprise n total components, where only k components are in a functioning or working state. Firstly, a consecutive 3-out-of-5:W system is modelled to estimate the reliability function of the system via polynomial function. Secondly, the tail-signature of the consecutive 3-out-of-5 system has been evaluated, which would allow the signature reliability evaluation. Thirdly, the determination of the degree of reliability, by using Barlow-Proschan index of the system is evaluated. Lastly, the minimal signature, predicted lifespan, and actual cost rate are derived for the proposed system. The purpose of this work is to evaluate all these outcomes and then compare their values, which are yielded by both applied approaches, i.e., the universal generating function approach and the structure–function approach. © The Author(s), under exclusive licence to Society for Reliability and Safety (SRESA) 2024.

关键词： Consecutive k-out-of-n:W system Cumulative signature Predicted lifespan Signature reliability Structure–function approach u-Function approach

来源：评论

学校读者我要写书评

暂无评论

Instantaneous Envelope and Energy Features for LCL Activation based complementary 1D-CNN in EEG Stress classification

Instantaneous Envelope and Energy Features for LCL Activatio...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： J Naren V Sathya Durga Depratment of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The work proposes a stress classification scheme that uses instantaneous envelope and energy features from the electroencephalograph (EEG) signals. The approach uses linear-cosine-linear (LCL) activation function-based complementary kernel 1D-CNN for the classification of stress. Initially, the EEG brain signals are categorized into two components, where the first class corresponds to the components of the delta, theta, and alpha bands (DTA band), while the second class corresponds to the components of the beta band. The instantaneous energy feature is estimated from the DTA band, while the envelope feature is estimated from the B-band. These two features are used to differentiate the induced stress types namely the recognition task, arithmetic task, and color image recognition task each with intense levels of high, medium, and low. The EEG signals collected from the SAM-40 datasets with the measures namely accuracy, F1-score, recall, specificity, and precision are used for analysis. The proposed approach results in accuracy, F1-score, recall, specificity, and precision of $96.61 \%, 95.99 \%, 96.57 \%$, ${9 9. 5 7 \%}$, and 95.45% respectively which is higher than the traditional stress classification schemes.

关键词： Accuracy Image recognition Color Feature extraction Brain modeling Electroencephalography Mirrors Kernel Stress Arithmetic

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：