检索结果-内蒙古大学图书馆

2022 International Symposium on Computer Applications and Information Systems, ISCAIS 2022

作者： Jin, Wei Sun, Cuimin You, Hui Chao, Pingfu School of Information Technology and Electrical Engineering The University of Queensland Brisbane Australia School of Computing and Electronic Information Guangxi University Nanning China School of Mechanical Engineering Guangxi University Nanning China Institute of Artificial Intelligence Soochow University Suzhou China

ISBN: (纸本)9781510655010

Load forecasting is an essential part of the energy field. The excellent performance of the prediction algorithm can directly reduce the operation and maintenance cost of the equipment. Therefore, making load forecasting more accurate is a concern to energy experts. In the types of load forecasting, short-term load forecasting (STLF) is usually used to test the accuracy of new algorithms. In the previous papers, amounts authors provided various methods to improve load forecasting accuracy. In recent years, STLF based on the neural network has been proposed by researchers. But few papers mentioned combined energy disaggregation technique and neural networks to improve the forecasting model. Therefore, this paper proposed a new method that combined energy disaggregation and long-short term memory (LSTM) to enhance the accuracy of traditional STLF. In this article, the author will introduce a non-intrusive load monitoring tool kit (NILMTK) for getting each household appliance consumption from the total consumption and then predicting the future load value of each appliance based on its load data. Finally, sum the predicted values to get the result. Through experiments, the results of our proposed new method reduce the root mean squared error (RMSE) of traditional forecasting models by 7% and the mean absolute error (MAE) of it by 15%, respectively. © 2022 SPIE

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A comparison of five commonly used machine learning algorithms applied to potable water detection

A comparison of five commonly used machine learning algorith...

引用

2021 International Conference on Computational Modeling, Simulation, and Data Analysis, CMSDA 2021

作者： Liu, Siyuan Yang, Yunfan Yao, Muhan Department of Computing Science Faculty of Science University of Alberta AB Canada Department of Computer Science Faculty of Science University of Calgary AB Canada School of Science Beijing Jiaotong University Beijing China

ISBN: (纸本)9781510651968

Potable water detection is an important issue in human society. Whether human have access to water with drinkable quality is crucial due to health concern. Before developing some techniques to ensure the water quality, it is important to understand some properties of the water, which can give a general view of how water quality is affected. Nowadays, machine learning is getting increasingly popular and it can be applied to many fields and solve plenty of problems in practice. Designing a machine learning predictor based on water properties can be drastically helpful to determine whether a water source is safe to consume. This article is based on the research which uses five common machine learning algorithms: k Nearest Neighbors, Decision Tree, Random Forest, neural network, and Support Vector Machine to train a model which predicts whether the water in the dataset is human consumable. By comparing the performance among these five models, as a conclusion, we find Random Forest and Support Vector Machine have the highest accuracy. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Potable water

来源：评论

学校读者我要写书评

暂无评论

Automatic Routability Predictor Development Using neural Architecture Search 40

Automatic Routability Predictor Development Using Neural Arc...

引用

40th IEEE/ACM International Conference on Computer Aided Design (ICCAD)

作者： Chang, Chen-Chia Pan, Jingyu Zhang, Tunhou Xie, Zhiyao Hu, Jiang Qi, Weiyi Lin, Chun-Wei Liang, Rongjian Mitra, Joydeep Fallon, Elias Chen, Yiran Duke Univ Durham NC 27708 USA Texas A&M Univ College Stn TX 77843 USA Cadence San Jose TX USA Natl Taiwan Univ Taipei Taiwan

ISBN: (纸本)9781665445078

The rise of machine learning technology inspires a boom of its applications in electronic design automation (EDA) and helps improve the degree of automation in chip designs. However, manually crafted machine learning models require extensive human expertise and tremendous engineering efforts. In this work, we leverage neural architecture search (NAS) to automate the development of high-quality neural architectures for routability prediction, which can help to guide cell placement toward routable solutions. Our search method supports various operations and highly flexible connections, leading to architectures significantly different from all previous human-crafted models. Experimental results on a large dataset demonstrate that our automatically generated neural architectures clearly outperform multiple representative manually crafted solutions. Compared to the best case of manually crafted models, NAS-generated models achieve 5.85% higher Kendall's tau in predicting the number of nets with DRC violations and 2.12% better area under ROC curve (ROC-AUC) in DRC hotspot detection. Moreover, compared with human-crafted models, which easily take weeks to develop, our efficient NAS approach finishes the whole automatic search process with only 0.3 days.

关键词： Analytical models Maximum likelihood estimation Design automation optical design Search methods Microprocessors Lithography

来源：评论

学校读者我要写书评

暂无评论

Enhanced Detection of Diabetic Retinopathy Stages Using RetinaNet-DR: A Deep Learning-Based Approach

Enhanced Detection of Diabetic Retinopathy Stages Using Reti...

引用

International Conference on Computer and Communications Technologies (ICCCT)

作者： Sangeetha Krishnan K. Valarmathi Department of CSE KCG College of Technology Chennai India Department of CSE Panimalar Engineering College Chennai India

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

Diabetic Retinopathy (DR) is a leading cause of vision loss, particularly in individuals with prolonged diabetes. Timely detection and classification of DR stages are crucial for effective management and prevention of further complications. This paper introduces a novel automated classification model named RetinaNet-DR, specifically designed to categorize DR into five progressive stages: Normal, Mild, Moderate, Severe, and Proliferative DR, utilizing optical Coherence Tomography (OCT) and Fundus images. The proposed system begins with a tailored preprocessing pipeline, enhancing image quality by applying normalization and noise reduction, followed by region-of-interest (ROI) extraction to ensure high-precision feature input. RetinaNet-DR incorporates a Convolutional neural network (CNN) with a ResNet-based architecture for accurate feature extraction, paired with an attention mechanism to highlight critical retinal features corresponding to DR severity. Experimental evaluations show that RetinaNet-DR achieves an impressive classification accuracy rate of 97.39% across all stages, surpassing conventional methods and exhibiting robust performance compared to recent models. This classification system has the potential to support clinicians by enabling more precise and early detection of DR stages, thereby improving patient care and facilitating timely intervention. Future developments will explore integrating multi-modal imaging sources to further enhance the model's clinical applicability and diagnostic performance.

关键词： Diabetic retinopathy Accuracy Attention mechanisms Prevention and mitigation Pipelines Imaging Feature extraction Retina Convolutional neural networks Proposals

来源：评论

学校读者我要写书评

暂无评论

Predicting methane adsorption ability of MOFs based on the crystal structural information by convolutional neural network 5

Predicting methane adsorption ability of MOFs based on the c...

引用

5th International Conference on Material Science and Technology, ICMST 2025

作者： Lu, Gang Jiang, Xiuyi Yang, Qingyuan Zhao, Zhengyang Gu, Weiwei Li, Ruiqi College of Information Science and Technology Beijing University of Chemical Technology Beijing100029 China State Key Laboratory of Organic-Inorganic Composites Beijing University of Chemical Technology Beijing100029 China

ISBN: (纸本)9781510691742

High-throughput computational screening (HTCS) methods have been widely used in addressing the challenges of screening metal-organic framework (MOF) materials with high performance from large datasets. Accurately predicting the performance of MOFs with hypothetical structures, such as adsorption capacity for methane, can be a great help to HTCS. Traditional molecular dynamics simulation methods are computationally cumbersome and costly. Feature engineering-based machine learning methods have a high reliance on expert experience to extract effective features, some of which can be time-consuming to calculate. Although some classical machine learning models can already achieve good performance, the heavy burden for features computation prior to model training would eventually limit their practical applications, flexibility and generality. In this paper, an approach is proposed for predicting the methane adsorption ability of MOFs directly from their crystal structural information recorded in Crystallographic Information File (CIF)-formatted files, without the need for molecular dynamics simulation or calculating any physical or chemical properties. By expressing the structural information in the crystal cells of MOFs as matrices, a deep convolutional neural network model based on residual structure is applied to train an end-to-end model to predict their methane adsorption ability. The experimental results show that the model accomplishes the prediction task with high accuracy, giving the mean square correlation coefficient (R2) as 0.925 and the mean absolute error (MAE) as 22.28 cm3g-1, which demonstrates a good performance over baselines. © 2025 SPIE. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Principle Driven Parameterized Fiber Model based on GPT-PINN neural network

arXiv

引用

arXiv 2024年

作者： Zang, Yubin Hua, Boyu Tang, Zhenzhou Lin, Zhipeng Zhang, Fangzheng Li, Simin Zhang, Zuxing Chen, Hongwei College of Electronic and Optical Engineering Nanjing University of Posts and Telecommunications Nanjing210023 China College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China Department of Electronic Engineering Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China

In cater the need of Beyond 5G communications, large numbers of data driven artificial intelligence based fiber models has been put forward as to utilize artificial intelligence's regression ability to predict pulse evolution in fiber transmission at a much faster speed compared with the traditional split step Fourier method. In order to increase the physical interpretabiliy, principle driven fiber models have been proposed which inserts the Nonlinear Schodinger Equation into their loss functions. However, regardless of either principle driven or data driven models, they need to be re-trained the whole model under different transmission conditions. Unfortunately, this situation can be unavoidable when conducting the fiber communication optimization work. If the scale of different transmission conditions is large, then the whole model needs to be retrained large numbers of time with relatively large scale of parameters which may consume higher time costs. computing efficiency will be dragged down as well. In order to address this problem, we propose the principle driven parameterized fiber model in this manuscript. This model breaks down the predicted NLSE solution with respect to one set of transmission condition into the linear combination of several eigen solutions which were outputted by each pre-trained principle driven fiber model via the reduced basis method. Therefore, the model can greatly alleviate the heavy burden of re-training since only the linear combination coefficients need to be found when changing the transmission condition. Not only strong physical interpretability can the model posses, but also higher computing efficiency can be obtained. The model's performance was demonstrated by the pulses with different shapes under 1000 different transmission conditions over the maximum 100 km fiber. The model's computational complexity is 0.0113% of split step Fourier method and 1% of the previously proposed principle driven fiber model. Copyright © 2024, T

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Astronomical image denoising based on Convolutional neural network 10

Astronomical image denoising based on Convolutional Neural N...

引用

10th IEEE International Conference on Intelligent computing and Information Systems, ICICIS 2021

作者： Elhakiem, Ahmed. A. Elsaid Ghoniemy, Tarek Salama, Gouda I. Military Technical College Computer Engineering and Artificial Intelligence Department Cairo Egypt

ISBN: (纸本)9781665440769

Astronomical images captured using optical telescopes usually suffer from severe noise effects which makes the denoising step inevitable for image analysis. This paper proposes a denoising framework for astronomical images based on Convolutional neural network (Astro U-net). The modified Astro U-net model has been learned in four ways, the first method is using astronomical images from the Hubble Space Telescope data set with three types of noise (dark noise, read- out noise, shot noise) added, the second method is learned using the same data set with the dark noise (dn) added only, the third method is using the same data set with the read-out noise (ron) overlaid, the fourth method is using the same data set with the shot noise (sn) added. The proposed framework for denoising the astronomical images is based on a fusion of the image that was improved by the model learned in the first method with the image that was improved by the three models that were learned by the second, third and fourth methods sequentially. Experimentally, the proposed framework shows a significant improvement in both the peak signal-to-noise ratio (PSNR) and the structural similarity index (SSIM) as compared to the Astro U-net model on different exposure time ratios. © 2021 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Detection Using Capsule network Modelled Deep Learning

Diabetic Retinopathy Detection Using Capsule Network Modelle...

引用

Emerging Technologies and Innovation for Sustainability (EmergIN), International Conference on

作者： Govindharaj I Vijayarajeswari R Anbuthiruvarangan K Hannah Rose Esther T Anandh R Dinesh Kumar K Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Information Technology Sona College of Technology Salem Tamil Nadu India Department of Artificial Intelligence and Data Science Velammal Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Sri Manakula Vinayagar Engineering College Puducherry Tamil Nadu India

ISBN: (数字)9798350391268

ISBN: (纸本)9798350391275

Presently, glaucoma, an acute eye disorder, if untreated, leads to permanent blindness is a major challenging in healthcare system for the complexities of diagnosis. Historical diagnosis models greatly rely on practical assessments of retinal images in addition to, rim width, optic cup and optic disc size, and any abnormalities within the eyes. Advancements of the last few years in AI have brought recent opportunities in diagnosis of glaucoma disorder. The work focuses on a composite learning model that combines UN et++ and CapsN et design for accurate detection and diagnosis of glaucoma. Using UNet++, semantic segmentation is applied together with OD and OC segmented region being critical to the identification of illness. The hybrid model leverage of CapsNet ability to detect hierarchical relationship Successful in better detection of glaucomatous change in comparison to standard Convolutional neural networks. The method uses state-of-the-art approaches like CLAHE method to preprocess retinal images, as a result, to improve the image quality. When examined with algorithm models, this research survey has been trained and tested on benchmark datasets for optic curves, optic segmentation and glaucoma detection wherein it has outperformed all of them. This automated solution for glaucoma detection offers promising potential in the fight against blindness, as evidenced by the methods robust trained performance and diagnostic accuracy. The integration in UNet++ and CapsNet Offers a unique and effective solution for prior and accuracy in detection of glaucoma, potentially revolutionizing the field of ophthalmic diagnostics.

关键词： Glaucoma Deep learning Diabetic retinopathy Technological innovation Accuracy Biomedical optical imaging optical computing Blindness Retina optical imaging

来源：评论

学校读者我要写书评

暂无评论

Automated Archaeological Feature Detection Using Deep Learning on optical UAV Imagery: Preliminary Results

引用

REMOTE SENSING 2022年第3期14卷 553-553页

作者： Altaweel, Mark Khelifi, Adel Li, Zehao Squitieri, Andrea Basmaji, Tasnim Ghazal, Mohammed UCL Inst Archeol London WC1E 6BT England Abu Dhabi Univ Comp Sci & Informat Technol Abu Dhabi 59911 U Arab Emirates Heidelberg Univ Inst Fruhgeschichte Vorderasiat Archol Sandgasse 7 D-69117 Heidelberg Germany Abu Dhabi Univ Elect Comp & Biomed Engn Dept Abu Dhabi 59911 U Arab Emirates

This communication article provides a call for unmanned aerial vehicle (UAV) users in archaeology to make imagery data more publicly available while developing a new application to facilitate the use of a common deep learning algorithm (mask region-based convolutional neural network;Mask R-CNN) for instance segmentation. The intent is to provide specialists with a GUI-based tool that can apply annotation used for training for neural network models, enable training and development of segmentation models, and allow classification of imagery data to facilitate auto-discovery of features. The tool is generic and can be used for a variety of settings, although the tool was tested using datasets from the United Arab Emirates (UAE), Oman, Iran, Iraq, and Jordan. Current outputs suggest that trained data are able to help identify ruined structures, that is, structures such as burials, exposed building ruins, and other surface features that are in some degraded state. Additionally, qanat(s), or ancient underground channels having surface access holes, and mounded sites, which have distinctive hill-shaped features, are also identified. Other classes are also possible, and the tool helps users make their own training-based approach and feature identification classes. To improve accuracy, we strongly urge greater publication of UAV imagery data by projects using open journal publications and public repositories. This is something done in other fields with UAV data and is now needed in heritage and archaeology. Our tool is provided as part of the outputs given.

关键词： unmanned aerial vehicles optical deep learning archaeology feature detection software high-performance computing

来源：评论

学校读者我要写书评

暂无评论

A dual-network micro-expression recognition model based on optical flow features

A dual-network micro-expression recognition model based on o...

引用

International Conference on Big Data computing and Communications (BIGCOM)

作者： Xiaofang Mu Jiaji Liu Yue Li Hui Qi Zhenyu Liu Hao Li Department of Computer Science Taiyuan Normal University Taiyuan China Department of Big Data and Intelligent Engineering Shanxi Institute of Technology Yangquan China

Human micro-expressions are difficult to detect, and their duration is approximately 1/25 to 1/5 s. Recognition and research on micro-expression can help determine the real psy-chological state of human beings, and the application scenarios are very wide. In this research, in addition to computer vision knowledge, a deep convolutional neural network for detecting facial key points and a deep learning method for extracting optical flow features were combined to construct a dual-network micro-expression recognition model based on optical flow features. The facial region of interest was divided in accordance with the key points of the face, and the optical flow features in the regions of interest were statistically analyzed. Because the original optical flow features contained in the micro-expression video clips have many dimension and high redundancy, an improved optical flow direction histogram was adopted. The histogram of oriented optical flow removed redundant features and enhanced the ability of optical flow features to describe micro-expression. Finally, the classification algorithm of the support vector machine was used to realize micro-expression recognition. The experimental results on the video-based facial micro-macro-expression database MMEW showed that the dual-network model constructed here improved the accuracy of micro-expression recognition and better completed the task of micro-expression recognition.

关键词： Support vector machines Histograms Face recognition Computational modeling Redundancy Feature extraction Data models

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：