检索结果-内蒙古大学图书馆

European Conference on optical Communication (ECOC)

作者： Robin Matzner Ruijie Luo Georgios Zervas Polina Bayvel University College London

ISBN: (数字)9781957171159

ISBN: (纸本)9781665475570

Using maximum achievable throughput as an objective, message passing neural networks (MPNN) are applied to larger optical networks (25-100 nodes), enabling physical properties-aware large-scale topology optimisation in record time, reducing computation time by 5 orders of magnitude, with close to perfect throughput correlation (ρ = 0.986).

关键词： Correlation Computational modeling optical recording Training data optical computing optical fiber networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

Exploration of Image Blur Detection Methods on Globally Blur Images 10

Exploration of Image Blur Detection Methods on Globally Blur...

引用

10th International Conference on Information and Communication Technology, ICoICT 2022

作者： Almustofa, Anas Nafis Nugraha, Yudhistira Sulasikin, Andi Bhaswara, Irfan Dwiki Kanggrawan, Juan Intan Jakarta Smart City Departement of Communication Informatics Statistics Jakarta Indonesia School of Computing Telkom University Bandung Indonesia

ISBN: (数字)9781665481656

ISBN: (纸本)9781665481656

Digital image has played an essential role in computer vision. However, it often suffers from blurriness. Thus, computer vision systems require an automated blur detection process to exclude blurred images. Furthermore, blur detection could prevent misinterpretation by a subsequent operation, such as image classification. This study explores some existing blur detection methods, including focus measure thresholding, support vector machine (SVM) classifiers, and convolutional neural networks (CNN) on globally blurred images. Those methods are robust for abroad applications such as blur detection, region segmentation, multi-class blur classification, autofocus, and shape-from-focus (SFF). Nevertheless, those methods theoretically could also be used for blur detection on globally blur images. We evaluate the techniques on a public and private dataset. The result indicates that the proposed CNN model performs the best blur detection among other methods. This model achieves 0.900 in accuracy, 0.857 in specificity, 0.942 in sensitivity, 0.868 in precision, 0.937 in negative predictive value (NPV), 0.904 in f1-score, and has an average execution time of 0.233 seconds. This model could be helpful in other computer vision system that requires blur image detection, such as identity card recognition, optical character recognition, and image data cleaning. © 2022 IEEE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Advancing optical Character Recognition for Handwritten Text: Enhancing Efficiency and Streamlining Document Management

Advancing Optical Character Recognition for Handwritten Text...

引用

International Conference on computing and networking Technology (ICCNT)

作者： Benedict Vinusha. V Indhuja. V Varshitha Reddy M Nikhitha N Naga Venkata Siva Reddy Department of Artificial Intelligence and Data Science R.M.K. Engineering College Kavaraipettai India

This research paper explores the challenge of converting handwritten text into editable digital text, in both native and English languages. We propose optical character recognition (OCR) as a solution, leveraging algorithms and machine learning models to recognize and convert text into various digital formats. The paper highlights the significance of OCR in digitizing paper documents and streamlining document management across diverse industries. Specifically, the study focuses on developing OCR software capable of identifying regional languages, providing a comprehensive assessment of its precision and effectiveness. The findings demonstrate how OCR technology can significantly improve efficiency and cost-effectiveness for businesses dealing with large volumes of paper documents. Our approach involves using image inputs, analyzing them with Keras and OpenCV, and implementing Convolutional neural network (CNN) techniques and Natural Language Processing (NLP) libraries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of artificial neural networks for the detection of esophagus tumor cells in microscopic hyperspectral images 25

Evaluation of artificial neural networks for the detection o...

引用

25th Euromicro Conference on Digital System Design (DSD)

作者： Schroeder, Anna Maktabi, Marianne Thieme, Rene Jansen-Winkeln, Boris Gockel, Ines Chalopin, Claire Univ Leipzig Innovat Ctr Comp Assisted Surg ICCAS Leipzig Germany Univ Leipzig Med Ctr Dept Visceral Transplantat Thorac & Vasc Surg Leipzig Germany St Georg Hosp Leipzig Dept Gen Visceral Thorac & Vasculary Surg Leipzig Germany

ISBN: (纸本)9781665474047

Microscopic analysis of histological slides of cancer tissue samples is standardly performed under white light microscopy. Researchers demonstrated the potential of artificial intelligence (AI) methods for the automatic identification of tumor cells. Hyperspectral imaging (HSI) combined with AI approaches can improve the accuracy, reliability, and time of the analysis. In this work, a HSI camera was coupled with a standard microscope to acquire microscopic hyperspectral (HS) images of stained histological slides of esophagus cancer tissue of 95 patients. The HS images were analyzed with deep learning algorithms to discriminate healthy cells (squamous epithelium) and tumors (stroma tumor and esophagus adenocarcinoma EAC). Five models were considered: a 2D CNN, a 2D CNN preserving the spatial relationship between spectral layers, a 3D CNN, a pre-trained 3D CNN and a recurrent neural network (RNN). They were evaluated using a leave-one-patient-out cross-validation. The predicted two classes were visualized with false colors. The RNN obtained the highest quantitative results with an accuracy of 0.791, an AUC of 0.79 and a computing time of 7.57 s per 10,000 patches. The best visual result was obtained on two selected HS images with the 2D CNN model. The performance of the automatic classification was higher on tissue which has not been treated with previous neoadjuvant therapy. The combination of HSI with deep learning method is promising for the automatic analysis of histological slides for cancer diagnosis.

关键词： Pathology cancer optical imaging deep learning analysis

来源：评论

学校读者我要写书评

暂无评论

Algorithm-Supervised Millimeter Wave Indoor Localization using Tiny neural networks

arXiv

引用

arXiv 2024年

作者： Shastri, Anish Blandino, Steve Gentile, Camillo Lai, Chiehping Casari, Paolo DISI University of Trento TN Povo38123 Italy GaithersburgMD20899 United States Prometheus Computing LLC BethesdaMD20814 United States The Radio Access and Propagation Metrology Group National Institute of Standards and Technology GaithersburgMD20899 United States

The quasi-optical propagation of millimeter-wave (mmWave) signals enables high-accuracy localization algorithms that employ geometric approaches or machine learning models. However, most algorithms require information on the indoor environment, may entail the collection of large training datasets, or bear an infeasible computational burden for commercial off-the-shelf (COTS) devices. In this work, we propose to use tiny neural networks (NNs) to learn the relationship between angle difference-of-arrival (ADoA) measurements and locations of a receiver in an indoor environment. To relieve training data collection efforts, we resort to an algorithm-supervised approach by bootstrapping the training of our neural network through location estimates obtained from a state-of-the-art localization algorithm. We evaluate our scheme via mmWave measurements from indoor 60-GHz double-directional channel sounding. We process the measurements to yield dominant multipath components, use the corresponding angles to compute ADoA values, and finally obtain location fixes. Results show that the tiny NN achieves sub-meter errors in 74% of the cases, thus performing as good as or even better than the state-of-the-art algorithm, with significantly lower computational complexity. © 2024, CC BY.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Daily rainfall modeling using neural network 28

Daily rainfall modeling using Neural Network

引用

28th Simposium Kebangsaan Sains Matematik, SKSM 2021

作者： Permai, S.D. Ohyver, M. Aziz, M.K.B.M. Statistics Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Centre for Mathematical Sciences College of Computing and Applied Sciences Universiti Malaysia Pahang Lebuhraya Tun Razak Pahang Gambang Kuantan26300 Malaysia

In the early 2020, Indonesia experienced flooding in several areas. This disaster caused a lot of damage and losses. One of the causes of flooding in Indonesia is due to high rainfall. This was not anticipated beforehand so there was a flood. Therefore, research on rainfall in Indonesia is very important to anticipate floods. If it is predicted that rainfall is very high and conditions do not allow it to accommodate, the government can prepare watersheds so that rainwater can flow and not be trapped. In this research, the rainfall data were obtained from Meteorological, Climatological, and Geophysical Agency (BMKG Indonesia), then the analysis of rainfall data in Indonesia was carried out. There are several statistical methods that can be used. There are ARIMA and neural network. In this research, the results of ARIMA model are used as input variables in the neural network model. Then there are several numbers of hidden layer in the neural network model that are compared. The results of ARIMA model and neural network model showed that neural network model is better than ARIMA model, because the mean square error (MSE) value of neural network model is smaller than ARIMA model. © Published under licence by IOP Publishing Ltd.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Cotton Crop for Detection of Pests and Diseases Using ML and DL Techniques

An Analysis of Cotton Crop for Detection of Pests and Diseas...

引用

Intelligent and Innovative Technologies in computing, Electrical and Electronics (IITCEE), International Conference

作者： K. Sai Susheel R Rajkumar School of Computer Science and Engineering Vellore Institute of Technology Vellore Tamil Nadu India

Agriculture is a significant source of energy that includes several well-known crops that supply food for the population and income for agronomists in India. Cotton is one of the attractive, drought-tolerant crops that can be cultivated commercially in every environment, among many other renowned crops. Although, this cotton harvest is plagued by many diseases and pests that may vary depending on climatic conditions, resulting in significant yield losses. The most liable to pests and diseases are the leaf and seedling stages of the plant, which destroy the whole crop. The cotton pests and diseases based on prior knowledge of IP, ML, and DL techniques are analyzed. Along with studies the comparison of the cotton crop with other crops, and also analyses the status of the area, production, and yield of the cotton crop. Eventually, the SVM classifier models applied fewer portraits than different algorithms regarding reliability and efficiency, while the multi-dimensional convolutional neural network provided better accuracy and effectiveness than further models in this deep analysis.

关键词： Support vector machines Analytical models Soft sensors Crops Production optical fiber networks Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Accelerating Quantum Emitter Characterization with Latent neural Ordinary Differential Equations

arXiv

引用

arXiv 2024年

作者： Proppe, Andrew H. Lee, Kin Long Kelvin Sun, Weiwei Krajewska, Chantalle J. Tye, Oliver Bawendi, Moungi G. Department of Chemistry Massachusetts Institute of Technology CambridgeMA02139 United States Accelerated Computing Systems and Graphics Intel Corporation HillsboroOR97124 United States

Deep neural network models can be used to learn complex dynamics from data and reconstruct sparse or noisy signals, thereby accelerating and augmenting experimental measurements. Evaluating the quantum optical properties of solid-state single-photon emitters is a time-consuming task that typically requires interferometric photon correlation experiments, such as Photon correlation Fourier spectroscopy (PCFS) which measures time-resolved single emitter lineshapes. Here, we demonstrate a latent neural ordinary differential equation model that can forecast a complete and noise-free PCFS experiment from a small subset of noisy correlation functions. By encoding measured photon correlations into an initial value problem, the NODE can be propagated to an arbitrary number of interferometer delay times. We demonstrate this with 10 noisy photon correlation functions that are used to extrapolate an entire de-noised interferograms of up to 200 stage positions, enabling up to a 20-fold speedup in experimental acquisition time from ∼3 hours to 10 minutes. Our work presents a new approach to greatly accelerate the experimental characterization of novel quantum emitter materials using deep learning. Copyright © 2024, The Authors. All rights reserved.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Learning optical Flow from a Few Matches

Learning Optical Flow from a Few Matches

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jiang, Shihao Lu, Yao Li, Hongdong Hartley, Richard Australian Natl Univ Canberra ACT Australia ACRV Canberra ACT Australia CSIRO Data61 Canberra ACT Australia

ISBN: (纸本)9781665445092

State-of-the-art neural network models for optical flow estimation require a dense correlation volume at high resolutions for representing per-pixel displacement. Although the dense correlation volume is informative for accurate estimation, its heavy computation and memory usage hinders the efficient training and deployment of the models. In this paper, we show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it. Based on this observation, we propose an alternative displacement representation, named Sparse Correlation Volume, which is constructed directly by computing the k closest matches in one feature map for each feature vector in the other feature map and stored in a sparse data structure. Experiments show that our method can reduce computational cost and memory use significantly, while maintaining high accuracy compared to previous approaches with dense correlation volumes.

关键词： Training Solid modeling Correlation Limiting Computational modeling Memory management Estimation

来源：评论

学校读者我要写书评

暂无评论

Automatic Epidermis Segmentation in Fluorescence Images Based on a U-Shaped network Model

Automatic Epidermis Segmentation in Fluorescence Images Base...

引用

International Joint Conference on neural networks (IJCNN)

作者： Herng-Hua Chang Yu-Xuan Chou Chi-Chao Chao Sung-Tsang Hsieh Department of Engineering Science and Ocean Engineering Scientific Computing and Intelligent Learning Laboratory National Taiwan University Taipei Taiwan Department of Neurology and Stroke Center National Taiwan University Hospital Taipei Taiwan Graduate Institute of Anatomy and Cell Biology National Taiwan University Taipei Taiwan

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Small fiber neuropathy analysis in the epidermis of the skin is critical to the diagnosis of various diseases such as diabetes mellitus and familial amyloid polyneuropathy. Intraepidermal nerve fiber examination plays an important role to serve as a highly sensitive indicator of sensory nerve fiber damage. Segmentation of the epidermis region is a prior image processing task for subsequent image analysis. Due to the lack of suitable and available tools for this specific task, this paper investigates an automatic epidermis segmentation framework in skin fluorescence images. To maintain the high resolution and increase the image amount, the original image is decomposed into a series of sub-images for model input. A U-shaped network structure consisting of five block layers with different depths is proposed for epidermis segmentation. Each model block is designed in a multi-scale manner, which is composed of two different convolution kernel pipelines. By combining and sharing the information from these model blocks with skip connections between them, we can effectively increase the diversity of the feature maps for more accurate segmentation. Experiments on in-house epidermis images demonstrated the advantages of the proposed epidermis segmentation network, which outperformed many state-of-the-art deep learning-based segmentation models. The proposed network architecture is potential in facilitating the epidermis segmentation task for further small fiber neuropathy research.

关键词： Image segmentation optical fiber sensors Nerve fibers Accuracy Image resolution Pipelines Diversity reception

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：