检索结果-内蒙古大学图书馆

Disruptive Technologies (ICDT), International Conference on

作者： Praful Sambhare S. Rukmani Devi J. Ramesh Kumar Arul Mary Rexy V Nallabothula Priyanka L. N. Jayanthi Department of Artificial Intelligence and Data Science Dr. D. Y. Patil Institute of Technology Pimpri Pune India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai India Department of ECE K.S.R. College of Engineering Tiruchengode India Department of Commerce Saveetha College of Liberal Arts and Sciences SIMATS Kuthambakkam India Doctor of pharmacy Krishna Teja pharmacy college Tirupati India

Children and newborns are more vulnerable to radiation exposure due to fast cell division, which may interfere with organs and cause skin problems. A system that detects hazardous radiation quickly and efficiently is in great demand. Many new and improved radiation protection and warning technologies are being offered. This research classifies radiation and its effects on newborns to show the development of an IoT-enabled system that utilizes artificial intelligence for radiation monitor and alarms. To help people escape hazardous zones, the suggested system uses audio/visual notifications. Gather the automated sensor system along with a real-time dataset of sensor values and their effects on newborns. Support vector machines, additional trees, bagged classification algorithms, random forests, logistic regression, and boosting adaptive classifiers classify radiation effects based on sensor measurement. This experiment shows the boosting adaptive classifier has the highest precision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-rank reduced biquaternion tensor ring decomposition and tensor completion

引用

Applied Mathematics and Computation 2025年 504卷

作者： Luo, Hui Liu, Xin Liu, Wei Zhang, Yang School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology China Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology China School of Artificial Intelligence at Sun Yat-sen University the Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Mathematics University of Manitoba MB Canada

We define the reduced biquaternion tensor ring (RBTR) decomposition and provide a detailed exposition of the corresponding algorithm RBTR-SVD. Leveraging RBTR decomposition, we propose a novel low-rank tensor completion algorithm RBTR-TV integrating RBTR ranks with total variation (TV) regularization to optimize the process. Numerical experiments on color image and video completion tasks indicate the advantages of our method. © 2025 Elsevier Inc.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Chinese-Myanmar Neural Machine Translation based Model-Uncertainty 20

Semi-Supervised Chinese-Myanmar Neural Machine Translation b...

引用

20th Chinese National Conference on Computational Linguistics, CCL 2021

作者： Wang, Linqin Yu, Zhengtao Mao, Cunli Gao, Shengxiang Man, Zhibo Wang, Zhenhan Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China

The semi-supervised neural machine translation based on back-translation has achieved remarkable results in low-resource neural machine translation. However, due to the scarcity of Chinese-Myanmar bilingual corpus and large structural differences, the self-attention mechanism at the encoder of traditional Transformer based back-translation cannot effectively distinguish the influence of the noise of pseudo parallel data in translation on sentence encoding, resulting in problems such as omission, multiple translation and mistranslation of the translated text. Therefore, this article proposes a semi-supervised Chinese-Myanmar neural machine translation based model uncertainty. In Transformer network, Monte Carlo dropout based on Variational Inference is used to construct model uncertainty attention mechanism to obtain sentence vector representations that can distinguish noise data. On this basis, it is fused with the sentence encoding vector obtained by the self-attention mechanism, so as to obtain the effective sentence encoding representation. Experimental results show that compared with traditional Transformer based back translation, the BLEU score of the proposed method improves by 4.01 and 1.88 points respectively in Chinese-Myanmar and Myanmar-Chinese translation directions, which fully verify the effectiveness of the proposed method in Chinese-Burmese neural machine translation tasks. © 2021 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

SRLinear: Lightweight Long-Term Time Series Forecasting via Symbolic Regression

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2025年

作者： Zhao, Hongbo Zhang, Hengzhe Tian, Chutian Wei, Zhi Zhou, Aimin East China Normal University Lab of Artificial Intelligence for Education School of Computer Science and Technology Shanghai200062 China Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand New Jersey Institute of Technology Department of Computer Science NewarkNJ07102 United States

Long-term Time Series Forecasting (LTSF) plays a crucial role in various fields, including energy consumption and weather prediction. Recent advancements in deep learning, particularly transformer models, have significantly improved LTSF performance. However, these models often face criticism for their lack of transparency, limited interpretability, and high computational requirements, which can hinder their practical application. Simple linear models have emerged as a promising alternative, demonstrating excellent performance in LTSF while offering greater simplicity. Yet, as these models become more complex, they tend to lose their advantages. To address these challenges, we introduce SRLinear, a lightweight and interpretable LTSF framework based on symbolic regression. Our approach first breaks down time series data into seasonal and trend components, then divides these into smaller segments. We use symbolic regression to extract meaningful and interpretable features from these components, which are then combined and processed through a single linear layer for future predictions. This lightweight design ensures computational efficiency, while symbolic regression generates symbolic expressions, providing clear insights into the feature extraction process and enhancing model interpretability. We tested SRLinear on 8 real-world datasets, achieving state-of-the-art results on multiple benchmarks. Importantly, our framework produces highly interpretable features that can be easily visualized, enhancing the overall transparency of the prediction process. © 2020 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Burmese Image Text Recognition Method Fused with Multi-layer Semantic Feature Maps 20

Burmese Image Text Recognition Method Fused with Multi-layer...

引用

20th Chinese National Conference on Computational Linguistics, CCL 2021

作者： Liu, Fuhao Mao, Cunli Yu, Zhengtao Gao, Shengxiang Wang, Linqin Xie, Xuyang Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China

Due to the special structure of character combinations in Burmese language, there are great difficulties in the research of image text recognition. Using directly the existing methods to recognize Burmese images has the problems of missing characters and poor recognition under complex background. Therefore, this paper proposes a Burmese image text recognition method based on fused with multi-layer semantic feature maps. It uses deep convolutional networks to obtain multi-layer image features and fuses them to obtain multi-layer semantic information, which alleviates the problem of feature loss in the case of Burmese combining characters. In addition, during the training phase, the MIX UP strategy is used to optimize the network parameters, which improves the generalization ability of the model and reduces the model's dependence on training samples in the testing phase. The experimental results show that the accuracy of the proposed method is improved by 2.2% compared with the baseline model. © 2021 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ROBUST EARLY-LEARNING: HINDERING THE MEMORIZATION OF NOISY LABELS 9

ROBUST EARLY-LEARNING: HINDERING THE MEMORIZATION OF NOISY L...

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Xia, Xiaobo Liu, Tongliang Han, Bo Gong, Chen Wang, Nannan Ge, Zongyuan Chang, Yi Trustworthy Machine Learning Lab School of Computer Science The University of Sydney Australia Department of Computer Science Hong Kong Baptist University Hong Kong School of Computer Science and Engineering Nanjing University of Science and Technology China ISN State Key Laboratory School of Telecommunications Engineering Xidian University China Medical AI Group Faculty of Engineering Monash University Australia Airdoc Research Monash University Australia School of Artificial Intelligence Jilin University China

The memorization effects of deep networks show that they will first memorize training data with clean labels and then those with noisy labels. The early stopping method therefore can be exploited for learning with noisy labels. However, the side effect brought by noisy labels will influence the memorization of clean labels before early stopping. In this paper, motivated by the lottery ticket hypothesis which shows that only partial parameters are important for generalization, we find that only partial parameters are important for fitting clean labels and generalize well, which we term as critical parameters;while the other parameters tend to fit noisy labels and cannot generalize well, which we term as non-critical parameters. Based on this, we propose robust early-learning to reduce the side effect of noisy labels before early stopping and thus enhance the memorization of clean labels. Specifically, in each iteration, we divide all parameters into the critical and non-critical ones, and then perform different update rules for different types of parameters. Extensive experiments on benchmark-simulated and real-world label-noise datasets demonstrate the superiority of the proposed method over the state-of-the-art label-noise learning methods. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Deep learning-driven multi-user wavelet NOMA for user centric cell-free massive MIMO communications

引用

Alexandria engineering Journal 2025年 128卷 533-543页

作者： Arshad, Rabia Baig, Sobia Aslam, Saad Ahmad, Muneeb Mumtaz, Shahid Department of Computer Science University of Central Punjab Avenue 1 Khayaban-e-Jinnah Road Johar Town Punjab Lahore54000 Pakistan Department of Electrical and Computer Engineering Energy Research Center COMSATS University 1.5 KM Defence Road off Raiwand Road LDA Avenue Phase 1 Punjab Lahore54000 Pakistan School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University Petaling Jaya Selangor47500 Malaysia Department of IT Convergence Engineering Kumoh National Institute of Technology Gumi39177 Korea Republic of Department of Engineering Nottingham Trent University 50 Shakespeare St NottinghamNG1 4BU United Kingdom

The evolution of Cell-Free Massive MIMO (CF-mMIMO) systems in the sixth-generation (6G) communications brings notable benefits including enhanced capacity, broader coverage, and greater reliability. However, these advanced systems may be subjected to critical challenges like, exponential growth in the user connectivity, precise channel estimation, and effective mitigation of the inter-user interference. This article addresses these challenges through Deep Learning (DL) for accurate channel estimation and a robust Wavelet Transform based Non-Orthogonal Multiple Access (NOMA) scheme to mitigate the inter-user interference in a user-centric CF-mMIMO system. By eliminating the reliance on pilot-assisted channel estimation, the DL-based approach achieves higher accuracy and lowers transmission overhead in a multi-user scenario. The results highlight the superiority of DL-based channel estimation for a CF-mMIMO system employing wavelet NOMA scheme over traditional methods, showing a 17% reduction in bit error rate (BER) and a 15% improvement in achievable sum-rate. © 2025 The Authors

关键词： Multiresolution analysis

来源：评论

学校读者我要写书评

暂无评论

Predicting the Impacts of the Environment on the Probability and Severity of Electrical Injuries by AIML

Predicting the Impacts of the Environment on the Probability...

引用

New Frontiers in Communication, Automation, Management and Security (ICCAMS), International Conference on

作者： Araddhana Arvind Deshmukh K Parish Venkata Kumar B.Anjanee Kumar Pramoda Patro Pavitar Parkash Singh N. Ashokkumar Department of Artificial Intelligence and Data science Marathwada Mitra Mandal College of Engineering Pune India Department of Computer Applications Velagapudi Ramakrishna Siddhartha Engineering College (Autonomous) Vijayawada India Electronics and Communication Engineering Dadi institute of engineering and technology Visakhapatnam India Department of Mathematics Koneru Lakshmaiah Education Foundation Hyderabad India Department of Management Lovely Professional University Phagwara India Department of ECE Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupati India

ISBN: (数字)9798350317060

ISBN: (纸本)9798350317077

The acceleration of global warming and environmental degradation has been attributed to industrial growth and fossil fuel utilization. Consequently, this phenomenon has resulted in a rise in the frequency and intensity of natural disasters. Due to their predominantly outdoor installation, generators are subject to significant impacts. The occurrence of natural disasters has led to an increase in accidents associated with electrical equipment. This paper analyses statistical data on electrical fires, electric shock accidents, and electricity-related accidents caused by climate change in domestic settings to determine the associated risk *** this study, we propose a risk assessment model for electrical fires, explicitly focusing on every month. Our approach involves analysing data on electrical hazards in different regional areas, particularly metropolitan cities, considering climatic conditions such as temperature and humidity. Additionally, we aim to evaluate the accident risk rating associated with natural disasters, specifically those related to low and high-voltage equipment. In this study, a risk analysis model has been developed to assess electrical hazards in different regions and equipment types. The model presented herein serves as a foundational predictive tool. Hence, offering electrical security amenities in the forthcoming period is feasible by giving a risk estimation map delineating potential dangers specific to each geographical area and wiring category via web platforms or mobile applications utilizing the investigation data provided. Additionally, it is imperative to enhance the resilience and dependability of electrical components as a proactive measure against electrocute ions resulting from climate change-induced emergencies.

关键词： Wiring Temperature distribution Electric potential Analytical models Disasters Urban areas Humidity

来源：评论

学校读者我要写书评

暂无评论

Penetration trajectory optimization for the hypersonic gliding vehicle encountering two interceptors

arXiv

引用

arXiv 2022年

作者： Shen, Zhipeng Yu, Jianglong Dong, Xiwang Hua, Yongzhao Ren, Zhang School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

The penetration trajectory optimization problem for the hypersonic gliding vehicle (HGV) encountering two interceptors is investigated. The HGV penetration trajectory optimization problem considering the terminal target area is formulated as a nonconvex optimal control problem. The nonconvex optimal control problem is transformed into a second-order cone programming (SOCP) problem, which can be solved by state-of-the-art interior-point methods. In addition, a penetration strategy that only requires the initial line-of-sight angle information of the interceptors is proposed. The convergent trajectory obtained by the proposed method allows the HGV to evade two interceptors and reach the target area successfully. Furthermore, a successive SOCP method with a variable trust region is presented, which is critical to balancing the trade-off between time consumption and optimality. Finally, the effectiveness and performance of the proposed method are verified by numerical simulations. Copyright © 2022, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Machine learning and role of artificial intelligence in optimizing work performance and employee behavior

引用

Materials Today: Proceedings 2022年 51卷 2327-2331页

作者： K.K. Ramachandran A. Apsara Saleth Mary Shibani Hawladar D. Asokk Bandi Bhaskar J.R. Pitroda Professor Management Dr G R D College of Science India Faculty Centre for Tourism and Hotel Management Madurai Kamaraj University Tamil Nadu India Research Scholar BS Abdur Rahman Crescent Institute of Science and Technology Chennai India Faculty BS Abdur Rahman Crescent Institute of Science and Technology Chennai India School of Computer Science and Artificial Intelligence SR University Telangana India Civil Engineering Department BVM Engineering College Gujarat Technological University India

In today’s business world, firms are using analytics to diving deeper into their data to improve productivity, acquire a competitive edge, and boost their bottom lines. That is why businesses are eager to integrate machine learning (ML) and artificial intelligence (AI) because they want a faster, more accurate result. In addition, machine learning and artificial intelligence improved productivity by reducing repetitive tasks. As a result, nearly every sector in the world intends to use artificial intelligence and ML. artificial intelligence and ML have various roles in business, ranging from enhancing employee and customer interactions to discovering patterns in massive amounts of data to automating monotonous activities. The goal is to seize the opportunity that artificial intelligence provides in employee success and productivity. Implementing artificial intelligence and machine learning may be a vital tool for any company seeking quantitative help in their decision-making since it can analyze vast quantities of data and spit forth trend directions and actionable suggestions. AI helps employees and businesses to set and achieve better goals results. This paper highlights the impact of using artificial intelligence and ML to enhance employee behaviour and work outcome. This research also provides insights into artificial intelligence, which will usher in a new era in industry.

关键词： artificial intelligence Machine learning Productivity Employee behaviour Automation

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：