检索结果-内蒙古大学图书馆

4th International Conference on Advancements in Computational Sciences, ICACS 2023

作者： Firdous, Saba Akbar, Shahzad Hassan, Syed Ale Khalid, Aima Gull, Sahar Riphah International University Department of Computing Faisalabad Pakistan

ISBN: (纸本)9781665463775

Apples are a popular fruit all around the world, nevertheless, they are mostly farmed in Asia. Moreover, approximately 76 million tons of apples are produced annually around the world. Furthermore, Apples may aid in preventing cancer, metabolic syndrome, cardiovascular disease, diabetes, and a variety of other diseases. However, various environmental conditions and other factors affect Apple leaf plant growth. In addition, the primary cause of the production crisis is apple plant disease. ATLDs such as RUST and SCAB are all popular and significantly impact apple leave yield. Therefore, numerous researches have been carried out to detect apple leave diseases automatically. However, there is still room for improvement in efficiency, computation complexity, time consumption, cost, and variety of techniques. This research employs deep convolutional neural network models VGG-19, ResNet-34, and Dense-121-Net to identify apple leave diseases. Besides, pre-processing of the dataset images enhanced the image quality and remove the noise. Furthermore, Data augmentation methods are also utilized to expand the number of images in the dataset. Moreover, models employing VGG-19, Resnet-34, and Dense-121Net are analyzed through the plant village dataset and attained 98.02%, 97.06%, and 99.75% accuracy respectively. An evaluation of networks in the plant village dataset shows that the developed algorithm performs better and has an advanced methodology suitable for real-Time agricultural disease detection applications. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Multiscale Tensor Summation Factorization as a new neural Network Layer (MTS Layer) for Multidimensional Data processing

arXiv

引用

arXiv 2025年

作者： Yamaç, Mehmet Yousaf, Muhammad Numan Kiranyaz, Serkan Gabbouj, Moncef Tampere University Faculty of Information Technology and Communication Sciences Tampere Finland Department of Electrical Engineering Qatar University Qatar

Multilayer perceptrons (MLP), or fully connected artificial neural networks, are known for performing vector-matrix multiplications using learnable weight matrices;however, their practical application in many machine learning tasks, especially in computer vision, can be limited due to the high dimensionality of input-output pairs at each layer. To improve efficiency, convolutional operators have been utilized to facilitate weight sharing and local connections, yet they are constrained by limited receptive fields. In this paper, we introduce Multiscale Tensor Summation (MTS) Factorization, a novel neural network operator that implements tensor summation at multiple scales, where each tensor to be summed is obtained through Tucker-decomposition-like mode products. Unlike other tensor decomposition methods in the literature MTS is not introduced as a network compression tool;instead, as a new backbone neural layer. MTS not only reduces the number of parameters required while enhancing the efficiency of weight optimization compared to traditional dense layers (i.e., unfactorized weight matrices in MLP layers), but it also demonstrates clear advantages over convolutional layers. The proof-of-the-concepts experimental comparison of the proposed MTS networks with MLPs and Convolutional neural networks (CNNs) demonstrates their effectiveness across various tasks, such as classification, compression, and signal restoration. Additionally, when integrated with modern non-linear units such as the multi-head gate (MHG), also introduced in this study, the corresponding neural network, MTSNet, demonstrates a more favorable complexity-performance tradeoff compared to state-of-the-art transformers in various computer vision applications, including image restoration tasks such as denoising, draining, and deblurring. The software implementation of the MTS layer and the corresponding MTS-based networks, MTSNet(s), is shared at https://***/mehmetyamac/*** Codes 68T07 © 202

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Efficient Region Proposals Generation for Object Detection

Efficient Region Proposals Generation for Object Detection

引用

International Conference on image and Signal processing and their applications (ISPA)

作者： Imene Bourafa Mokhtar Taffar Mohamed-Nadjib Zennir LaRIA Lab Computer Sc. Dpt University of Jijel Jijel Algeria

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

Object detection models based on region proposals, whether those using classic methods or deep neural networks, have provided cutting-edge results and achieved an interesting speed/accuracy ratio. The state-of-the-art methods using local feature detectors to generate region proposals incorporate descriptor information or combine the detected interest points with other methods to generate proposals. In this work, we aim to explore the efficiency of proposals generated only according to the position of the generated SURF keypoints. We propose an object detection approach namely SURF-Fast-RCNN, based on FAST-RCNN framework, that integrates SURF local detector. Instead of using the proposals produced by the selective search method, each 2-combination of interest points is considered as a candidate box which we call keypoint anchors. Based on the intersection over union (IoU) value of each keypoint anchor with ground truth boxes, we discard the excess anchors and assign labels to the retained ones denoting their class labels. The retained anchors are fed into the detector for training, followed by NMS operation to suppress the overlapping boxes. Our SURF-Fast-RCNN model is trained and tested on different region proposals on the MS-COCO dataset examples. With 1000 region proposals, the performances of our model reached an accuracy of about 82% and a mean average precision of 84.04%, which are encouraging results.

关键词： Training Visualization image recognition Search methods Detectors Object detection artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Methods for Kernel Initialization of Convolutional neural Network Model Applied to Plant Disease Classification

Adaptive Methods for Kernel Initialization of Convolutional ...

引用

Electrical, Electronic and Information Sciences (eStream), Open Conference of

作者： Saloua Lagnaoui Khaoula Boumais Saad El Fallah Zakariae En-Naimani Khalid Haddouch Dalius Matuzevičius Laboratory Engineering Systems and Applications ENSA Sidi Mohamed Ben Abdellah University Fez Morocco Laboratory AI Data Science and Emerging Systems Sidi Mohammed ben Abdallah University ENSA Fez Morocco Systems and Sustainable Environment Laboratory Faculty of Engineering Sciences Private University of Fez Fez Morocco Laboratory Computer Science AI and Cyber Security ENSET University of Hassan II Casablanca Mohammedia Morocco Department of Electronic Systems Faculty of Electronics Vilnius Gediminas Technical University Vilnius Lithuania

ISBN: (数字)9798350352412

ISBN: (纸本)9798350352429

Convolutional neural networks are instrumental in artificial intelligence, especially in image processing, where their ability to autonomously learn hierarchical features has led to significant breakthroughs. However, the success of these models is intricately tied to the judicious choice of hyperparameters, which include the configuration of convolutional layers, activation functions, and kernel initialization methods. This research explores kernel initialization methods in Convolutional neural Network models, seven diverse initialization methods (Glorot Uniform, Ones initialization, Zero initialization, Constant initialization, Random initialization, HeNormal initialization, and Orthogonal initialization) are comprehensively compared. The primary objective is to showcase the sensitivity of Convolutional neural networks to these various initialization techniques. The study not only aims to reveal the nuanced impact of kernel initialization but also introduces an adaptive method to enhance model performance. By delving into the intricacies of initialization methods, this research contributes to the improvement of Convolutional neural networks effectiveness, especially in critical applications like Plant Disease classification.

关键词： Training Plant diseases Adaptation models Sensitivity neural networks Convolutional neural networks Kernel

来源：评论

学校读者我要写书评

暂无评论

MR and CT image fusion using three-stage multiscale decomposition and PCNN 2

MR and CT image fusion using three-stage multiscale decompos...

引用

2nd International Conference on artificial Intelligence and Smart Energy, ICAIS 2022

作者： Reddy, Mummadi Gowthami Reddy, Palagiri Veera Narayana Reddy, Patil Ramana Jntu College of Engineering Department of Ece Andhra Pradesh Anantapur India Sri Venkateswara College of Engineering Department of Ece Andhra Pradesh Kadapa India

ISBN: (纸本)9781665400527

Medical imaging plays the crucial role in the current era of scientific enlargement in every medical therapy and diagnosis applications. In this regard, medical image fusion could be a powerful tool to combine multi modal images by using image processing techniques. But conventional approaches, failed to provide the effective image quality assessments and robustness of fused image. To overcome these drawbacks, in this work three stage multi scale decomposition (TSMSD) using pulse-coupled neural networks with adaptive arguments (PCNN-AA) approach is proposed for multiple modality medical image fusion. Initially, nonsubsampled shearlet transform (NSST) is applied onto both source images to decompose them into high and low frequency bands. Then, nonlinear anisotropic filtering with discrete Karhunen-Loeve transform (NLAF-DKLT) methodology is used to fuse the low frequency bands of the source images. Next, high frequency bands obtained from NSST are fused using PCNN-AA approach. Now, low and high frequency fused bands are reconstructed using NSST reconstruction. Finally, band fusion rule algorithm with pyramid reconstruction is applied to get final fused medical image. Extensive simulation outcome discloses the superiority of proposed TSMSD using PCNN-AA approach as compared to conventional medical image fusion approaches in terms of fusion quality assessment metrics such as correlation coefficient (CC), standard deviation (STD), mean (M), mutual information (MI), and entropy (E). © 2022 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Classification of Green Series Fischer's Lovebirds Using Fuzzy Logic Algorithm

Classification of Green Series Fischer's Lovebirds Using Fuz...

引用

IEEE International Conference on artificial Intelligence in Engineering and Technology (IICAIET)

作者： Jobert D. Apilado Aron Miguel R. Jintalan Cyrel O. Manlises School of Electrical Electronics and Computer Engineering Mapua University Manila Philippines

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

This study explores the application of fuzzy logic on the Raspberry Pi platform for classifying Green Series Fischer” s Lovebirds, specifically Green, Jade, Misty, and Olive. African Fischer's lovebirds, known for their vibrant colors and sociable nature, pose a classification challenge due to their varied color mutations. Previous techniques such as image processing, artificial neural networks, and color segmentation have been used for species identification, achieving varying degrees of success. Using a fuzzy logic algorithm combined with membership functions and fuzzy rules, the researchers achieved an accuracy of 72.5% on a testing set of 40 samples, with 10 samples per class. The system integrates a camera module and OpenCV for image capture and processing, offering an efficient alternative to traditional visual inspection methods often inadequate for untrained observers. The methodology involved capturing images using a Raspberry Pi 3 Model B and developing a fuzzy logic model for color-based feature extraction and classification. The results demonstrate the effectiveness of fuzzy logic in distinguishing subtle color differences among lovebird variations. This study underscores the potential of combining fuzzy logic and Raspberry Pi for real-time image classification, contributing to advancements in color image processing and practical applications in avian identification.

关键词： Fuzzy logic Visualization image segmentation image color analysis Observers Inspection Real-time systems Classification algorithms Testing image classification

来源：评论

学校读者我要写书评

暂无评论

图神经网络及其在图像处理领域的研究进展

引用

计算机工程与应用 2023年第7期59卷 15-30页

作者：蒋玉英陈心雨李广明王飞葛宏义河南工业大学粮食信息处理与控制教育部重点实验室郑州450001 河南工业大学人工智能与大数据学院郑州450001 河南省粮食光电检测与控制重点实验室郑州450001 河南工业大学信息科学与工程学院郑州450001

图神经网络(graph neural network,GNN)是一种基于深度学习的图结构数据处理模型,因良好的可解释性和对图结构数据强大的非线性拟合能力而受到研究者广泛关注。随着GNN的逐步优化,GNN与图像处理技术实现融合发展,在图像分类、人体解析... 详细信息

图神经网络(graph neural network,GNN)是一种基于深度学习的图结构数据处理模型,因良好的可解释性和对图结构数据强大的非线性拟合能力而受到研究者广泛关注。随着GNN的逐步优化,GNN与图像处理技术实现融合发展,在图像分类、人体解析和视觉问答等方面取得重大突破。对图像处理技术和传统神经网络理论进行介绍,并对五类GNN的原理、特点和不足进行分析与总结;同时从数据集和性能评估指标两个角度对文中所述的常用模型进行对比与总结,并补充介绍了九种常见的图像处理领域公共数据集;最后深入分析了GNN在图像处理领域中有待改进的方面,并对其应用前景进行展望。

关键词：图神经网络(GNN) 深度学习图结构图像处理

来源：评论

学校读者我要写书评

暂无评论

Trends in digital image processing of isolated microalgae by incorporating classification algorithm

引用

BIOTECHNOLOGY ADVANCES 2023年第1期63卷 108095页

作者： Chong, Jun Wei Roy Khoo, Kuan Shiong Chew, Kit Wayne Ting, Huong-Yong Show, Pau Loke Wenzhou Univ Zhejiang Prov Key Lab Subtrop Water Environm & Mar Wenzhou 325035 Peoples R China Univ Nottingham Malaysia Fac Sci & Engn Dept Chem & Environm Engn Jalan Broga Semenyih 43500 Selangor Darul Malaysia Yuan Ze Univ Dept Chem Engn & Mat Sci Taoyuan Taiwan Nanyang Technol Univ Sch Chem Chem Engn & Biotechnol 62 Nanyang Dr Singapore City 637459 Singapore Univ Technol Sarawak Drone Res & Applicat Ctr 1 Jalan Univ Sibu 96000 Sarawak Malaysia SIMATS Saveetha Sch Engn Dept Sustainable Engn Chennai 602105 India

Identification of microalgae species is of importance due to the uprising of harmful algae blooms affecting both the aquatic habitat and human health. Despite this occurence, microalgae have been identified as a green biomass and alternative source due to its promising bioactive compounds accumulation that play a significant role in many industrial applications. Recently, microalgae species identification has been conducted through DNA analysis and various microscopy techniques such as light, scanning electron, transmission electron, and atomic force -microscopy. The aforementioned procedures have encouraged researchers to consider alternate ways due to limitations such as costly validation, requiring skilled taxonomists, prolonged analysis, and low accuracy. This review highlights the potential innovations in digital microscopy with the incorporation of both hardware and software that can produce a reliable recognition, detection, enumeration, and real-time acquisition of microalgae species. Several steps such as image acquisition, processing, feature extraction, and selection are discussed, for the purpose of generating high image quality by removing unwanted artifacts and noise from the background. These steps of identification of microalgae species is performed by reliable image classification through machine learning as well as deep learning algorithms such as artificial neural networks, support vector machines, and convolutional neural networks. Overall, this review provides comprehensive insights into numerous possibilities of microalgae image identification, image pre-processing, and machine learning techniques to address the challenges in developing a robust digital classification tool for the future.

关键词： Identification Machine learning image processing Microscopy Microalgae

来源：评论

学校读者我要写书评

暂无评论

Research on Financial Early Warning Mechanism of Colleges and Universities Based on neural Network

Research on Financial Early Warning Mechanism of Colleges an...

引用

image processing and Computer applications (ICIPCA), IEEE International Conference on

作者： Yue Hu Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

In this paper, the potential risks and early warning problems in the financial management of Chinese colleges and universities are deeply discussed. With the continuous expansion of the scale of higher education and the increasing complexity of the financial environment, the construction of a scientific, accurate and efficient financial early warning system has become an important issue in the financial management of colleges and universities. This paper first analyzes the main types and formation mechanism of financial risk in colleges and universities, and then introduces the theoretical basis and advantages of neural network model in detail, especially its powerful ability in dealing with nonlinear relations, pattern recognition and prediction, which provides new solutions and technical means for financial early warning in colleges and universities. On this basis, this paper designs and implements a college financial early warning model based on deep neural network. Through training and verification of a large number of college financial data, it realizes real-time monitoring and early warning of college financial risks. The empirical study shows that the model can effectively capture the internal correlation among various financial indicators and accurately predict the possible financial crisis, so as to provide timely and accurate risk decision-making basis for university management.

关键词： Training Accuracy Computational modeling Decision making artificial neural networks Predictive models Financial management Alarm systems Real-time systems Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Analysis of Impact of image Restoration and Segmentation on Classification Model

Analysis of Impact of Image Restoration and Segmentation on ...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Sushma Rahul Vispute K. Rajeswari Aryan Nema Arya Jagtap Mrugendra Kulkarni Pranav Mohite Department of Computer Engineering PCCOE Pune India

A widely studied problem in computer science is the restoration, segmentation, and classification of images, which involves image processing, computer vision, and machine learning techniques. Deep learning has made significant contributions to this field, bringing machine learning closer to artificial intelligence. Deep learning has a broad range of applications, including in surveillance, healthcare, medicine, and sports. Convolutional neural networks (CNN), a combination of artificial neural networks (ANN) and deep learning techniques, have made incredible advancements in deep learning. This survey compares methods for restoring noisy images, such as wiener filter, wavelet method, and wiener filtering with BM3D technique, using Gaussian blurring and noising methods. The survey also examines the RGB colour model and YCbCr colour model for image segmentation. image classification is studied using CNN, where the survey discusses various parameters of convolutional neural networks, including activation functions and pooling methods.

关键词：

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：