检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Li, Muyun Cai, Qingyue Lai, Huayi Ning, Honglong Kong, Sifan Guo, Chenxiao Jiang, Bocheng Su, Guoping Yao, Rihui Peng, Junbiao Guangdong Basic Research Center of Excellence for Energy & Information Polymer Materials State Key Laboratory of Luminescent Materials and Devices School of Materials Sciences and Engineering South China University of Technology Guangzhou510640 China Aberdeen Institute of Data Science and Artificial Intelligence South China Normal University Foshan528225 China School of Software South China Normal University Foshan528225 China

Electrochromic devices (ECDs), serving as thermal insulation and decorative components, have been extensively employed across various domains. To meet diverse application demands in different contexts, the product parameters of ECDs exhibit continual variations, notably within the electrochromic layer. In this work, a multilayer perceptron neural network was leveraged to comprehend the transition from material parameter alterations to device performance parameter changes. Specifically, 336 groups of electrochromic solutions containing different concentrations and voltages were prepared. Subsequently, a model comprising three hidden layers and three output neurons was developed, expanding the dataset simulation to 2000 groups, yielding an R2 of 0.975 on modulation amplitude. Through this model, accurate estimations of performance parameters of numerous unmanufactured liquid-based ECDs were achieved, with projected outcomes highlighting a peak modulation amplitude of 78.38%@620nm. It has been verified that the modulation amplitude prediction error was below 5% and demonstrated stable cyclic performance over 1000 times (97.93%@1.45V) , thereby underscoring the feasibility of our approach. This research serves as a pertinent instance of the synergy between multilayer perceptron neural networks and ECDs, thereby advancing the deployment of neural network in the innovation and application of chemical engineering, materials and other fields. © 2024, The Authors. All rights reserved.

关键词： Thermal insulation

来源：评论

学校读者我要写书评

暂无评论

A Structural Feature-Based Approach for Comprehensive Graph Classification

arXiv

引用

arXiv 2024年

作者： Islam, Saiful Hasan, Md Nahid Khanra, Pitambar Institute for Artificial Intelligence and Data Science University at Buffalo State University of New York BuffaloNY14260 United States Department of Mathematics University of Dhaka Dhaka1000 Bangladesh Department of Mathematics Bangladesh University of Engineering and Technology Dhaka1000 Bangladesh Jacobs School of Medicine & Biomedical Sciences University at Buffalo State University of New York BuffaloNY14203 United States

The increasing prevalence of graph-structured data across various domains has intensified greater interest in graph classification tasks. While numerous sophisticated graph learning methods have emerged, their complexity often hinders practical implementation. In this article, we address this challenge by proposing a method that constructs feature vectors based on fundamental graph structural properties. We demonstrate that these features, despite their simplicity, are powerful enough to capture the intrinsic characteristics of graphs within the same class. We explore the efficacy of our approach using three distinct machine learning methods, highlighting how our feature-based classification leverages the inherent structural similarities of graphs within the same class to achieve accurate classification. A key advantage of our approach is its simplicity, which makes it accessible and adaptable to a broad range of applications, including social network analysis, bioinformatics, and cybersecurity. Furthermore, we conduct extensive experiments to validate the performance of our method, showing that it not only reveals a competitive performance but in some cases surpasses the accuracy of more complex, state-of-the-art techniques. Our findings suggest that a focus on fundamental graph features can provide a robust and efficient alternative for graph classification, offering significant potential for both research and practical *** Codes 68R10, 05C85, 68R10 © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Third Generation Security System for Face Detection in ATM Machine Using Computer Vision

Third Generation Security System for Face Detection in ATM M...

引用

Computer, Power and Communications (ICCPC), International Conference on

作者： S Sridevi K.M. Monica G. A Senthil R. Prabha A. Sathya J Ramya Dept. of Computer Science and Engineering Sri Ramachandra Engineering and Technology Chennai India Dept. of Computer Science and Engineering VIT Chennai Campus Chennai India Dept. of Information Technology Agni College of Technology Chennai India Dept. of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Dept. of Artificial Intelligence and Data Science Sri Sai Ram Institute of Technology Chennai India Dept. of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India

A workflow is proposed for the detection of unauthorized persons in an ATM. Certain assumptions, including the context of identification are made by training their features and storing the datasets. However, not every individual will be a suspect. Suspicious activity on ATMs that are located in remote areas and to reduce the risk of fraudulent transactions. such as using another person's card to withdraw money etc., Various video survey and image processing have been discussed in relation to surveillance methods. It discusses the various processes, preprocessing, classification, feature extraction and the corresponding video processing methods.

关键词： Training Online banking Shape Face recognition Surveillance Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Aquila-Based Resource Allocation for Efficient Indoor IoT Visible Light Communication

An Enhanced Aquila-Based Resource Allocation for Efficient I...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Selma Yahia Yassine Meraihi Sylia Mekhmoukh Taleb Seyedali Mirjalili Amar Ramdane-Cherif Tu Dac Ho Hossien B. Eldeeb Sami Muhaidat LIST Laboratory University of M’Hamed Bougara Boumerdes Boumerdes Algeria Centre for Artificial Intelligence Research and Optimisation Torrens University Australia Brisbane Australia LISV Laboratory University of Versailles St-Quentin-en-Yvelines Velizy France Department of Electrical Engineering Faculty of Engineering Science and Technology UiT Arctic University of Norway Electrical Engineering Computer Science Center of Cyber-Physical Systems Khalifa University UAE

Visible light communication (VLC) is a rapidly growing wireless communication technology for the Internet of Things (IoT) that offers high data rates and low latency, making it ideal for massive connectivity. Efficient resource allocation is essential in VLC networks to minimize inter-symbol and cochannel interferences, which can greatly improve network performance and user satisfaction. This paper focuses on an indoor IoT-based VLC system that utilizes photodetectors (PDs) on users’ cell phones as receivers, with the goal of maximizing system performances and reducing power consumption by selectively activating some PDs while deactivating others. However, this objective presents a challenge due to the inherent non-convex nature of the multi-objective optimization problem, which cannot be solved by analytical means. To address this, we propose an enhanced Aquila optimization (EAO) scheme that improves upon the Aquila Optimizer (AO) by incorporating a fitness distance balance (FDB) function. We evaluate our proposed EAO in various scenarios under different settings, considering both capacity and fairness metrics. Through simulations, we demonstrate the effectiveness of our approach and its superiority over classical algorithms such as Aquila Optimizer (AO), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO) in finding the optimal solution. Our results confirm that the proposed EAO algorithm can efficiently optimize the system capacity and ensure fairness among all users, providing a promising solution for indoor VLC systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud Based Intelligent Nutrient Management System for Precision Agriculture Using CNN

Cloud Based Intelligent Nutrient Management System for Preci...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： M. Shafiya Banu Arshadh Ariff Mohamed Abuthahir R. Mohandas D. Antony Joseph Rajan B. Meenakshi N. Mohankumar Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai Tamil Nadu India Riazulhameed Architect - Data Engineer Blackstraw Technologies Pvt Ltd Chennai Tamil Nadu India Department of Electronics and Communication Engineering Chenai Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Sri Sairam Engineering College Chennai Tamil Nadu India Symbiosis Institute of Technology Symbiosis International (Deemed University) Nagpur Maharashtra India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

Precision agriculture struggles with scalability, data integration, and decision-making, prompting innovative solutions. Recent advancements like CNNs and cloud computing provide interesting answers but confront challenges. data quality, processing needs, interoperability, and real-time decision-making are issues. These difficulties demand innovative data synchronization, model dependability, and system scalability methods. This project uses sophisticated analytics and cloud technology to improve nutrient management systems. Improving scalability, accuracy, and efficiency while presenting unique data fusion and user-friendly interfaces are goals. Clear problems and goals guide the study's scope and purpose. Wireless soil nutrient sensors can capture real-time data on important soil factors such as pH levels, the amount of nitrogen, phosphate, and potassium present, and more. This information is then sent to a platform hosted in the cloud, where it is processed using sophisticated data analytics and machine learning algorithms, in addition to previous crop performance data and agronomic models. The program will create tailored suggestions for nutrient management, including topics such as the kinds of fertilizer, application rates, and the best time. These proposals give farmers more agency, allowing them to make educated decisions via an easily navigable interface. Because of the system's ability to react to changing circumstances and its continual monitoring, nutrient management techniques are kept in sync with those changes throughout the crop's life cycle.

关键词： Precision agriculture Cloud computing Scalability Decision making Soil Nutrients Real-time systems

来源：评论

学校读者我要写书评

暂无评论

SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow

arXiv

引用

arXiv 2022年

作者： Li, Xiangtai Zhang, Jiangning Yang, Yibo Cheng, Guangliang Yang, Kuiyuan Tong, Yunhai Tao, Dacheng National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China SenseTime Research Hong Kong Zhejiang University China School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia Xiaomi Car China JD Explore Academy China

In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feature maps with strong semantic representation. Two strategies are widely used: atrous convolutions and feature pyramid fusion, while both are either computationally intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels and broadcast high-level features to high-resolution features effectively and efficiently. Furthermore, integrating our FAM to a standard feature pyramid structure exhibits superior performance over other real-time methods, even on lightweight backbone networks, such as ResNet-18 and DFNet. Then to further speed up the inference procedure, we also present a novel Gated Dual Flow Alignment Module to directly align high-resolution feature maps and low-resolution feature maps where we term the improved version network as SFNet-Lite. Extensive experiments are conducted on several challenging datasets, where results show the effectiveness of both SFNet and SFNet-Lite. In particular, when using Cityscapes test set, the SFNet-Lite series achieve 80.1 mIoU while running at 60 FPS using Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Interpretation of polycystic ovarian syndrome (PCOS) employing computational neural network CNN

引用

AIP Conference Proceedings 2024年第1期3131卷

作者： Rakshitha Shivamadhaiah Sudeep Sriramasagara Devaraju Sahana Sathyamurthy Ashwini Kodipalli Trupthi Rao Hosur Sriramareddy Manjunath Reddy Department of Electronics and Communication Engineering Global Academy Of Technology Bangalore Karnataka India Department of Artificial Intelligence & Data Science Global Academy of Technology Bangalore Karnataka India

Polycystic ovarian syndrome is one of the major diseases hampering the fertility of women between the age of 15 to 50. The PCOS prone women are affected both mentally and physically, which claims difficulty to conceive. There are several ways to detect this disease, but untimely detection can reduce the effect of it. we are presenting an established model for the early detection of PCOS applying CNN. The previous models built utilizing machine learning produces an accuracy of 89%, Fuzzy TOPSIS provided an accuracy of 98% and SVM (Support Vector Machine) algorithm provided an accuracy of 94%. But the newly established model utilizes the ultrasound images of the ovary to detect the cysts that are formed and classifies into infected and non-infected. The conducted research extracts the feature from the ultrasound images which are taken out from the Kaggle repository and the outcome is measured in terms of accuracy since classification is the problem basis. This emphasized model provides the best accuracy among all the previously developed models. The research is done with the motto of enhancing the sexual health of women and to provide better methods for detection in the region of biomedical technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Masked Autoencoder and Comprehensive Evaluations for Reconstructing 12-Lead ECG from Arbitrary Single-Lead ECG

arXiv

引用

arXiv 2024年

作者： Chen, Jiarong Wu, Wanqing Liu, Tong Hong, Shenda National Institute of Health Data Science Peking University Beijing100191 China School of Biomedical Engineering Sun Yat-sen University Guangdong Shenzhen518107 China Department of Micro/Nano Electronics and MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai200240 China Tianjin Key Laboratory of lonic-Molecular Function of Cardiovascular Disease Department of Cardiology Tianjin Institute of Cardiology Second Hospital of Tianjin Medical University Tianjin300211 China Institute of Medical Technology Health Science Center of Peking University Beijing100191 China Institute for Artificial Intelligence Peking University Beijing100871 China

Electrocardiogram (ECG) has emerged as a widely accepted diagnostic instrument for cardiovascular diseases (CVD). The standard clinical 12-lead ECG configuration causes considerable inconvenience and discomfort, while wearable devices offers a more practical alternative. To reduce information gap between 12-lead ECG and single-lead ECG, this study proposes a multi-channel masked autoencoder (MCMA) for reconstructing 12-Lead ECG from arbitrary single-lead ECG, and a comprehensive evaluation benchmark, ECGGenEval, encompass the signal-level, feature-level, and diagnostic-level evaluations. MCMA can achieve the state-of-the-art performance. In the signal-level evaluation, the mean square errors of 0.0317 and 0.1034, Pearson correlation coefficients of 0.7885 and 0.7420. In the feature-level evaluation, the average standard deviation of the mean heart rate across the generated 12-lead ECG is 1.0481, the coefficient of variation is 1.58%, and the range is 3.2874. In the diagnostic-level evaluation, the average F1-score with two generated 12-lead ECG from different single-lead ECG are 0.8233 and 0.8410. © 2024, CC BY.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Cloud-magnetic resonance imaging system: In the era of 6G and artificial intelligence

引用

Magnetic Resonance Letters 2025年 57-68页

作者： Yirong Zhou Yanhuang Wu Yuhan Su Jing Li Jianyu Cai Yongfu You Jianjun Zhou Di Guo Xiaobo Qu Department of Electronic Science Intelligent Medical Imaging R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance National Institute for Data Science in Health and Medicine Xiamen University Department of Electronic Science Key Laboratory of Digital Fujian on IoT Communication Xiamen University Shanghai Electric Group Co. Ltd China Telecom Group China Mobile Group Department of Radiology Zhongshan Hospital (Xiamen) Fudan University Xiamen Municipal Clinical Research Center for Medical Imaging Fujian Province Key Clinical Specialty Construction Project (Medical Imaging Department) Xiamen Key Laboratory of Clinical Transformation of Imaging Big Data and Artificial Intelligence School of Computer and Information Engineering Xiamen University of Technology

Magnetic resonance imaging(MRI) plays an important role in medical diagnosis,generating petabytes of image data annually in large *** voluminous data stream requires a significant amount of network bandwidth and extensive storage ***,local data processing demands substantial manpower and hardware *** isolation across different healthcare institutions hinders crossinstitutional collaboration in clinics and *** this work,we anticipate an innovative MRI system and its four generations that integrate emerging distributed cloud computing,6G bandwidth,edge computing,federated learning,and blockchain *** system is called Cloud-MRI,aiming at solving the problems of MRI data storage security,transmission speed,artificial intelligence(AI) algorithm maintenance,hardware upgrading,and collaborative *** workflow commences with the transformation of k-space raw data into the standardized Imaging Society for Magnetic Resonance in Medicine Raw data(ISMRMRD) ***,the data are uploaded to the cloud or edge nodes for fast image reconstruction,neural network training,and automatic ***,the outcomes are seamlessly transmitted to clinics or research institutes for diagnosis and other *** Cloud-MRI system will save the raw imaging data,reduce the risk of data loss,facilitate inter-institutional medical collaboration,and finally improve diagnostic accuracy and work efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of data Mining Techniques in Healthcare

Implementation of Data Mining Techniques in Healthcare

引用

International Conference on Innovative Sustainable Computational Technologies (CISCT)

作者： Nirosha Veeramachaneni V. Vaishnavee Nikhil Ranjan Rashi Saxena K Vandana Sarvesh Kumar Department of CSE B V Raju Institute of Technology Narsapur Department of Artificial Intelligence and Data Science SNS College of Engineering Coimbatore Department of Computing Science and Engineering Galgotias University Greater Noida Computer Science & Engineering Koneru Lakshmaiah Education Foundation (KLEF) Hyderabad Department of CSE G L Bajaj Institute of Technology and Management Greater Noida Department of CSE BBD University Lucknow

ISBN: (纸本)9781665474177

Healthcare sector is having lots of data about various disease and newly discovered viruses and bacteria’s and so on. The data has been resided for a long at various data warehouses of each country’s healthcare department but due to lack of collaboration and employment of advanced machine learning algorithms the meaningful insights which may conclude from data research and association, remain hidden from world. Hence this paper proposes the application of various machine algorithms like linear regression and multi-layer perceptron on a target dataset which is having the attributes of related to healthcare industry. With implementation of algorithm the detection of diabetes in various areas covered in 80 attributes of selected dataset.

关键词： Industries Machine learning algorithms Computer viruses Error analysis Linear regression Medical services Diabetes

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：