检索结果-内蒙古大学图书馆

Information and Communication Technology (ICTech), International Conference of

作者： Jialiang Li Yicheng Zhu Sussex College of Artificial Intelligence Zhejiang Gongshang University Hangzhou China Faculty of Communication and Information Engineering Shanghai University China

ISBN: (数字)9798350376258

ISBN: (纸本)9798350376265

This article presents an exhaustive exploration of convolutional vectors, a cornerstone concept in deep learning. Initially, it introduces the fundamental principles of convolutional vectors, and then delves into the essential operations that bolster their effectiveness in a broad application scope. The piece begins by examining the basic operations integral to convolutional vectors: convolution, pooling, and flattening. It elucidates how these processes enable convolutional vectors to distill meaningful features from raw data, thereby rendering them exceptionally apt for tasks like image recognition and natural language processing. Following this foundational discussion, the focus shifts to the diverse applications of convolutional vectors across various domains. The article showcases their utility in image classification, object detection, speech recognition, and recommendation systems, among other areas. Through examples and case studies, it illustrates the proficiency of convolutional vectors in addressing real-world challenges. Furthermore, the article ventures into the future trajectory and emerging trends in the realm of convolutional vectors. It highlights ongoing research aimed at enhancing their efficiency and scalability, and discusses their integration with other cutting-edge technologies, such as attention mechanisms and transfer learning. Moreover, the potential implications of convolutional vectors in nascent fields like robotics and autonomous systems are contemplated.

关键词： image recognition Semantic segmentation Transfer learning Object detection Speech recognition Vectors Trajectory Convolutional neural networks Unsupervised learning image classification

来源：评论

学校读者我要写书评

暂无评论

Prediction of Pathogen Causing Rice Plant Disease and Recommendation using Enhanced Machine Learning Technique

Prediction of Pathogen Causing Rice Plant Disease and Recomm...

引用

Applied artificial Intelligence and Computing (ICAAIC), International Conference on

作者： J Suji Priya M Hema Priya M Iyswarya K Kiruthika Department of Master of Computer Applications Sona College of Technology Salem India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Plant diseases pose significant challenges to agricultural productivity, impacting both the quality and quantity of crop yields. Early detection and effective management of these diseases are essential for mitigating their detrimental effects on agricultural output. However, traditional methods of disease monitoring and diagnosis are often costly and require continuous expert intervention. To address these challenges, this study proposes a novel approach that combines image processing techniques and advanced machine learning methodologies for the accurate identification and classification of rice leaf diseases. By utilizing datasets comprising images of diseased rice leaves, environmental data, and historical disease reports, the proposed system utilizes Convolutional neural networks (CNNs) for image analysis and feature extraction. Subsequently, a Support Vector Machine (SVM) classifier is employed for disease detection and classification based on the extracted features. The integration of image processing and machine learning technologies offers a cost-effective and efficient solution for early disease detection and management in agriculture. By automating the process of disease identification, the proposed system facilitates timely interventions, thereby minimizing crop losses and promoting agricultural sustainability.

关键词： Support vector machines Productivity Plant diseases Accuracy image analysis Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Data Driven-based Prediction and Analysis of the Effective Length of Steel Plates 6

Data Driven-based Prediction and Analysis of the Effective L...

引用

6th International Conference on ThermoMechanical processing, TMP 2022

作者： Dong, Zishuo Li, Xu Zhang, Dianhua The State Key Laboratory of Rolling and Automation Northeastern University Shenyang China

ISBN: (纸本)9787502492441

With the increasing industrial productivity and production scale, how to use information technology-related means and intelligent computing methods to gradually improve production efficiency has become a trend in the development of traditional manufacturing industries. The prediction of the effective length of the medium-thick plate is essential to assist in the design of sub-plates and slabs to improve the yield. However, the defect in the head and tail of the plate after rolling makes an accurate prediction of the effective length difficult. In this paper, a data-driven method for effective length prediction of steel plates is proposed for the first time. Machine vision technology is used as a measurement method for the size of steel plates. Through image processing technology, an accurate plane contour of the steel plate is obtained, and the effective length of the steel plate is calculated by removing the irregular parts of the head and tail of the steel plate. The effective length of medium-thick plate prediction performance of a support vector regression (SVM), artificial neural networks (ANN), and random forest (RF) method was evaluated. In order to improve the prediction accuracy of existing models, based on ANN, the WOA-ANN prediction model is proposed. The whale optimization algorithm (WOA) was used to optimize the ANN weights and threshold initialization process. The results show that the WOA-ANN algorithm further improves the prediction accuracy and has a good consistency with the physical law. The model proposed in this paper can be flexibly applied to the actual rolling applications as a supplement to the physical model to improve the prediction accuracy of the effective length of the medium-thick plate, and thus improve the yield. © TMP 2022 - Proceedings. All rights reserved.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimization of Machine Learning and Deep Learning Algorithms for Diagnosis of Cancer 1

Optimization of Machine Learning and Deep Learning Algorithm...

引用

1st International Conference on Technologies for Smart Green Connected Society 2021, ICTSGS 2021

作者： Krishna, Hari Anand, M. Saravanan, D. Pushpalatha, K. Department of ECE B V Raju Institute of Technology Telangana India Department of Networking and Communications College of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of CSE IFET College of Engineering Villupuram India Department of Mathematics KoneruLakshmaiah Educational Foundation Vadedeswaram India

ISBN: (纸本)9781607685395

Machine learning and artificial intelligence has recently become a prominent technology. Given its popularity and strength in pattern recognition and categorization, many corporations and institutions have begun investing in healthcare research to improve illness prediction accuracy. Using these strategies, however, has several drawbacks. One of the primary issues is the lack of huge data sets for medical pictures. An introduction to deep learning in medical image processing, from theoretical foundations to real-world applications. The article examines the general appeal of deep learning (DL), a collection of computer science advances. The next step was to learn the basics of neural networks. That explains the use of deep learning and CNNs. So we can see why deep learning is rapidly advancing in various application fields, including medical image processing. The goal of this research was to use innovative methodologies on cancer datasets to explore the feasibility of combining machine learning and deep learning algorithms for cancer detection. This study used text and picture databases to classify cancer. The datasets are the Liver BUPA disorder database and brain MRI pictures. This article provides optimization methods that outperform the suggested approaches' accuracy. Using two alternative training methods, Levenberg Marquardt (lm) and Resilient back propagation (rp), two classification algorithms were evaluated with different groups of neurons to identify benign and malignant patients. Cascade correlation utilizing the train (rp) outperformed feed forward back propagation using the train (lm). The second deep neural network model presented a technique (based on CNN) for automated brain tumour identification using MRI data. The Water Cycle Algorithm is used to optimise CNN. The established approach is very accurate. The suggested framework examines innovative texture classification algorithms using Discrete Wavelet Transform (DWT) and the Gray Level Co occurrence

关键词： artificial neural Network Batch Normalization Deep Learning Gray Level Co-occurrence Matrix Water Cycle Algorithm

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Tunisian Coin Recognition Embedded System with Deep Learning

Implementation of a Tunisian Coin Recognition Embedded Syste...

引用

artificial Intelligence & Green Energy (ICAIGE), IEEE International Conference on

作者： Amina Kessentini Rania Ghanem Tasnim Ben Mouhamed Nouri Masmoudi National Engineering School of Sfax University of Sfax Laboratory of Electronics and Information Technologies Safx Tunisia Department of industrial computing Higher Institute of Computer Science and Multimedia Gabes Gabes Tunisia

ISBN: (数字)9798350389838

ISBN: (纸本)9798350389845

Managing a large volume of coins poses a complex challenge in various fields, particularly within Tunisian administrations, specifically in terms of counting and classification. In this case, several coin recognition systems are distinguished, such as systems based on mechanical, electromagnetic, and image processing methods. However, these systems may suffer from accuracy and reliability shortcomings and are sensitive to deception. To avoid these problems, we have developed an intelligent system based on convolutional models (CNN) with the aim of automating coin detection, classification, and counting. Additionally, we have expanded our database by integrating a generative neural network model (GAN). The main goal of our paper is to develop a robust and precise solution capable of efficiently processing a large volume of coins quickly and presenting the results in a mobile application connected to the system. Our work combines the latest technologies to assist Tunisian administrations in better managing their finances. The accuracy result has achieved up to 97.8 % with real time detection.

关键词： Deep learning Measurement Accuracy Webcams neural networks Mobile communication Software Real-time systems Software reliability Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Video processing Using Deep Learning Techniques: A Systematic Literature Review

引用

IEEE ACCESS 2021年 9卷 139489-139507页

作者： Sharma, Vijeta Gupta, Manjari Kumar, Ajai Mishra, Deepti Ctr Dev Adv Comp C DAC Pune 411008 Maharashtra India Banaras Hindu Univ Inst Sci Dept Comp Sci DST Ctr Interdisciplinary Math Sci Varanasi 221005 Uttar Pradesh India Norwegian Univ Sci & Technol NTNU Dept Comp Sci IDI N-2815 Gjovik Norway

Studies show lots of advanced research on various data types such as image, speech, and text using deep learning techniques, but nowadays, research on video processing is also an emerging field of computer vision. Several surveys are present on video processing using computer vision deep learning techniques, targeting specific functionality such as anomaly detection, crowd analysis, activity monitoring, etc. However, a combined study is still unexplored. This paper aims to present a Systematic Literature Review (SLR) on video processing using deep learning to investigate the applications, functionalities, techniques, datasets, issues, and challenges by formulating the relevant research questions (RQs). This systematic mapping includes 93 research articles from reputed databases published between 2011 and 2020. We categorize the deep learning technique for video processing as CNN, DNN, and RNN based. We observe significant advancements in video processing between 2017 and 2020, primarily due to the advent of AlexNet, ResNet, and LSTM based deep learning techniques. The prominent fields of video processing research are observed as human action recognition, crowd anomaly detection, and behavior analysis. This SLR is a helpful guide for the researchers to explore the recent literature, available datasets, and existing deep learning techniques for video processing.

关键词： Deep learning Systematics Bibliographies Face recognition Convolutional neural networks Computer vision Anomaly detection Video processing computer vision artificial intelligence deep learning human action recognition systematic literature review

来源：评论

学校读者我要写书评

暂无评论

AI-Powered System for Detecting Offensive Meme Texts on Social Media

AI-Powered System for Detecting Offensive Meme Texts on Soci...

引用

artificial Intelligence and Machine Learning applications Theme: Healthcare and Internet of Things (AIMLA), International Conference on

作者： R Kiruthika G Santhosh R Santhosh S B Surya K Thamizh Amudhan Computer Science and Engineering Mahendra Engineering College Tamilnadu India

ISBN: (数字)9798331538965

ISBN: (纸本)9798331538972

In the current digital environment, Sentiment analysis has become an essential tool for understanding human emotions and perspectives. Memes are a popular internet expression tool that frequently expresses opinions in an eye-catching manner. However, worries regarding the transmission of inappropriate or dangerous information have been raised by the emergence of multimodal content, particularly memes that combine text and graphics. In order This work offers a fresh solution to this problem for categorising objectionable memes in multimodal datasets using deep learning techniques. By closely analyzing both textual and visual components, the primary objective is to accurately detect and categorize inappropriate content. In this study, we use deep learning techniques to propose a novel approach for sentiment analysis of meme photos for text and image categorization using Convolutional neural networks in conjunction with Optical Character Recognition (OCR) technology. Our technology is based on extracting textual information from meme photos using optical character recognition (OCR), which enables sentiment analysis of these textual components. Deep learning techniques are included into this procedure, To classify sentiments extracted from the detected text, natural language processing techniques are used in conjunction with the (VADER). By employing this novel approach, we want to enhance visual content's analytical potential by utilising a pretrained Convolutional neural Network (CNN) model. The suggested method yields promising results, demonstrating the possibility of integrating pretrained CNNs, To better understand online sentiment patterns and interpret the complex emotions present in meme culture, VADER sentiment analysis and OCR are being used.

关键词： Deep learning Text mining Sentiment analysis Visualization Social networking (online) Optical character recognition Medical services Tokenization Complexity theory Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning applications in Medical image Analysis: Advancements, Challenges, and Future Directions

arXiv

引用

arXiv 2024年

作者： Eli, Aimina Ali Ali, Abida Master of Science in Information Technology School of Science & Technology Emporia State University Emporia KS USA Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh

Medical image analysis has emerged as an essential element of contemporary healthcare, facilitating physicians in achieving expedited and precise diagnosis. Recent breakthroughs in deep learning, a subset of artificial intelligence, have markedly revolutionized the analysis of medical pictures, improving the accuracy and efficiency of clinical procedures. Deep learning algorithms, especially convolutional neural networks (CNNs), have demonstrated remarkable proficiency in autonomously learning features from multidimensional medical pictures, including MRI, CT, and X-ray scans, without the necessity for manual feature extraction. These models have been utilized across multiple medical disciplines, including pathology, radiology, ophthalmology, and cardiology, where they aid in illness detection, classification, and segmentation tasks. This study offers a thorough examination of applications for deep learning in medical image processing, addressing both its achievements and obstacles. It underscores the relevance of deep learning in enhancing diagnostic precision in tasks including tumor detection, organ classification, and disease progression prediction. Additionally, we investigate sophisticated deep learning methodologies, such as generative adversarial networks (GANs) for picture creation and augmentation, alongside multimodal and federated learning for the integration of heterogeneous data sources and the improvement of model generalizability. Notwithstanding the encouraging outcomes, the domain continues to encounter obstacles like the necessity for extensive labeled datasets, model understanding, and regulatory impediments. We examine methods to tackle these issues and propose future avenues to enhance the influence of deep learning in clinical practice, especially regarding ethical considerations and real-time implementation. As deep learning advances, its incorporation into healthcare is poised to augment medical picture analysis and boost patient outcomes wo

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Histological tissue classification with a novel statistical filter-based convolutional neural network

引用

ANATOMIA HISTOLOGIA EMBRYOLOGIA 2024年第4期53卷 e13073页

作者： Unlukal, Nejat Ulker, Erkan Solmaz, Merve Uyar, Kubra Tasdemir, Sakir Selcuk Univ Dept Histol & Embryol Konya Turkiye Konya Tech Univ Dept Comp Engn Konya Turkiye Alanya Alaaddin Keykubat Univ Dept Comp Engn Antalya Turkiye Selcuk Univ Dept Comp Engn Konya Turkiye Selcuk Univ Fac Med Dept Histol & Embryol TR-42130 Konya Turkiye

Deep networks have been of considerable interest in literature and have enabled the solution of recent real-world applications. Due to filters that offer feature extraction, Convolutional neural Network (CNN) is recognized as an accurate, efficient and trustworthy deep learning technique for the solution of image-based challenges. The high-performing CNNs are computationally demanding even if they produce good results in a variety of applications. This is because a large number of parameters limit their ability to be reused on central processing units with low performance. To address these limitations, we suggest a novel statistical filter-based CNN (HistStatCNN) for image classification. The convolution kernels of the designed CNN model were initialized by continuous statistical methods. The performance of the proposed filter initialization approach was evaluated on a novel histological dataset and various histopathological benchmark datasets. To prove the efficiency of statistical filters, three unique parameter sets and a mixed parameter set of statistical filters were applied to the designed CNN model for the classification task. According to the results, the accuracy of GoogleNet, ResNet18, ResNet50 and ResNet101 models were 85.56%, 85.24%, 83.59% and 83.79%, respectively. The accuracy was improved by 87.13% by HistStatCNN for the histological data classification task. Moreover, the performance of the proposed filter generation approach was proved by testing on various histopathological benchmark datasets, increasing average accuracy rates. Experimental results validate that the proposed statistical filters enhance the performance of the network with more simple CNN models.

关键词： artificial intelligence CNN deep learning feature extraction image classification statistical filter

来源：评论

学校读者我要写书评

暂无评论

An Enhanced and Efficient approach towards text detection and extracting text in multi-oriented images

An Enhanced and Efficient approach towards text detection an...

引用

artificial Intelligence and Smart Communication (AISC), International Conference on

作者： Ashutosh Shankhdhar Lakshya Daga Gargi Jadaun Department of Computer Science GLA University Mathura

Machine learning is a part of artificial intelligence. It allows a machine to learn on its own and earn knowledge and experience based on the input data set and training set. Text detection and extraction is one of the prominent applications of machine learning. It identifies text in an image with varying orientation, style, alignment, brightness, or contrast in images with complex backgrounds and extracts valuable information from them. Hence solving the problem of reading text in images with text having various variations. The goal here is to help people from different places read the text in languages that the person might not even know. This paper focuses on various challenges in text detection and the techniques used in extracting text in multi-oriented images such as image processing, data mining, or neural network techniques, and a comparative study on them. One such technique is OCR (optical character recognition). This technique helps us to detect and extract text data and convert it into data that can hence be edited and searched. This paper additionally focuses on performance comparison of various techniques that are currently in use. The results of the experimental outcome are judged on parameters like recall, precision, and accuracy.

关键词： Training image edge detection image processing Digital images Optical character recognition neural networks Brightness

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：