检索结果-内蒙古大学图书馆

6th IEEE International conference on Power, Intelligent Computing and systems, ICPICS 2024

作者： Yuan, Qikun University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798350374315

Wavelet theory has been widely applied in image processing, and machine learning techniques have permeated various fields, significant improvements in image denoising remain possible. This paper introduces a novel image denoising method. It leverages wavelet transform and machine learning algorithms, presenting a synergistic approach that combines discrete wavelet transform coefficients with Random Forests and CNNs. This method significantly enhanced image clarity without increasing computational demand. This article utilized wavelet transform to extract image features, and then trained the model with wavelet coefficients as training data through machine learning methods, integrating Random Forests and Convolutional Neural Networks to analyze the effectiveness of different wavelet coefficients, thereby optimizing the model's denoising performance. It has been proved effective in denoising performance after rigorous validation through quantitative comparisons of Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) on the high-quality stereo image dataset Flickr1024. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-exposure image Fusion via Adaptive Multi-Branch Input 6

Multi-exposure Image Fusion via Adaptive Multi-Branch Input

引用

6th International conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Yan, Shengbo Bai, Bendu School of Communication and Information Engineering Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (纸本)9798400707674

In this paper, we propose an adaptive multi-exposure image fusion (AMEF) framework using self-supervised learning. Our encoder-decoder network can adaptively increase the number of feature extraction branches to fuse low dynamic range (LDR) images of arbitrary size and number without adding parameters. We incorporate channel and pixel attention mechanisms into the feature extraction branches to provide greater flexibility in processing image information with different exposures. By focusing more attention on complementary features, our framework can achieve better image fusion. In addition, we introduce a local residual channel attention module (LRCA) in the decoder, which assigns different weights to the fused features, extending the representation capability of convolutional neural networks (CNNs). Finally, We evaluate our method on a multi-exposure image fusion benchmark dataset (SICE) and compare it with recent deep learning-based methods objectively and subjectively. Three of our quantitative measures achieve the best results, and the remaining measures are close to existing algorithms. © 2023 ACM.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent slag removal system in power plant based on image recognition

Design of intelligent slag removal system in power plant bas...

引用

2024 International conference on algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2024

作者： Fu, Changliang Zhang, Yongbin xie, xiaodong Zong, Zhiqiang Wei, xiao Wang, xinyue Beijing guodian futong science and technology development co. ltd. Tainjin China

ISBN: (纸本)9781510685840

The accurate identification of large and medium slag in power plant slag transport system has an important impact on the safety, efficiency, environmental protection and economic benefits of power plant. The timely processing of large slag can effectively improve the operation efficiency and maintenance cost of power plant, and with the rapid development of image recognition technology, the recognition of large slag in power plant slag transport system is gradually intelligent. In this paper, based on CenterNet image recognition algorithm, through the adaptive spatial feature fusion module is added in the backbone network, and combined with the feature of the pyramid networks structure. The low-level feature information is fused with the high-level feature information. The loss function is replaced by the distributed focus loss, and the effectiveness of the system is verified by experiments. The results show that the system has good convergence, can accurately identify the size and position of large slag block, can respond to the slag removal command quickly, improve the operation efficiency of the power plant slag delivery system, reduce the manual maintenance cost, and improve the operation safety of the power plant. © 2024 SPIE.

关键词： Detection and tracking algorithms Intelligence systems Target recognition Convolution image processing Feature fusion Safety Infrared radiation Combustion Thermal modeling

来源：评论

学校读者我要写书评

暂无评论

A two-stage task scheduling algorithm for Unmanned Aerial Vehicles-assisted Mobile Edge Computing 3

A two-stage task scheduling algorithm for Unmanned Aerial Ve...

引用

3rd International conference on Signal image processing and Communication, ICSIPC 2023

作者： Qu, Hua Xue, Yucheng Zhao, Jihong Gao, Qian Li, xing School of Software Engineering Xi’an Jiaotong University Xi’an China School of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China School of Communication and Information Engineering Xi’an University of Posts& Telecommunications Xi’an China

ISBN: (纸本)9781510670945

Unmanned Aerial Vehicle (UAV) into Mobile Edge Computing (MEC) systems can effectively expand their flexibility and coverage. The current research trend in UAV-assisted MEC is mainly focused on optimizing flight control and minimizing energy consumption. However, there is a lack of research on task scheduling in UAV-assisted MEC scenarios. This paper proposes a two-stage task scheduling method that minimizes the task processing cost while optimizing task execution order to reduce the execution time of tasks. The results of the study show that the proposed algorithm outperforms other baseline methods in terms of completing all tasks with the shortest execution time. This further validates the efficiency of the proposed algorithm and its potential for improving the system efficiency of UAV-assisted MEC. © 2023 SPIE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multimodal Conversational AI Using Speech and image Integration 5th

Enhanced Multimodal Conversational AI Using Speech and Image...

引用

5th International conference on Computing, Communications, and Cyber Security, IC4S 2023

作者： Dixit, Deepali Tyagi, Mihul Kandoi, Raunak Singh, Raghuraj School of Engineering and Technology Sharda University Greater Noida201310 India

ISBN: (纸本)9789819773701

The development of conversational artificial intelligence (AI) is examined in this research paper, with a focus on how speech and image recognition technologies can be combined to transform and interact with systems. The emphasis is on cutting-edge developments in multimodal conversational AI, particularly the smooth fusion of sophisticated image and speech processing methods to improve user experiences. The study addresses the applications, difficulties and potential applications of multimodal conversational AI by conducting a thorough review of the existing literature and case studies. By emphasizing the significance of enhancing voice recognition algorithms and utilizing advanced image processing techniques, the study promotes contextual understanding and customization. We have developed an innovative multimodal conversational AI system that integrates speech, text and image processing capabilities for seamless human–computer interactions. This study presents an improved multimodal conversational AI system that integrates several techniques, such as Google Text-to-Speech (gtts), speech recognition, sound playback and Convolutional Neural Networks (CNN). Our model architecture combines RNNs for sequential data analysis, CNNs for image processing and attention mechanisms for context extraction. Trained on diverse datasets, our model is optimized for accuracy and robustness. Evaluation against existing models demonstrates superior performance in terms of accuracy, speed and resource efficiency. Our study highlights how improved multimodal conversational AI can advance the field of human–computer interaction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Secure Storage System for Financial Data based on Fuzzy Recognition algorithms

A Secure Storage System for Financial Data based on Fuzzy Re...

引用

2024 International conference on Intelligent algorithms for Computational Intelligence systems, IACIS 2024

作者： Yu, xi Timbang, Ferdinand Lapus Guangdong University of Science and Technology College of Finance and Economics Dongguan China ChanRobles Professional Review Inc Manila Philippines

ISBN: (纸本)9798350360660

This electronic document is a "live"template and already defines the coThe purpose of this paper is to develop a secure storage system for financial data based on fuzzy recognition algorithm to improve the security, accuracy and reliability of financial data and its applications. The system adopts the fuzzy C-means clustering algorithm to carry out intelligent analysis and processing of financial data. This paper begins to carry out specific research on the part of algorithm selection and algorithm implementation, and elaborates on the whole process, so as to explain the algorithm clearly and provide support for its subsequent application. The system test results show that the data encryption method and strict access control mechanism are used to ensure the security of data and the system has excellent performance in terms of data storage performance, encryption and decryption speed, API response time and system availability, throughput and error rate, etc., which can effectively meet the needs of safe, reliable and efficient financial data storage and management. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

DualGGAN: A New Facial Style Transfer Network 5

DualGGAN: A New Facial Style Transfer Network

引用

2023 5th International conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Zhao, Yu Peng, Chunyan Zhang, xiaojuan School of Computer Science Qinghai Normal University Xi'ning810016 China State Key Laboratory of Intelligent Processing of Tibetan Language Qinghai Xi'ning810016 China

In response to the background penetration problem of unsupervised style transfer algorithms in most cases, a Transformer style transfer network DualGGAN based on dual generators and fusion of relative position encoding is proposed. The network is trained using the least squares generative adversarial network, and the neural network is used as the image feature extractor to generate feature maps to obtain facial image features with attention weights from the feature maps, utilizing relative position encoding and mask loss to jointly constrain feature region style transfer. The experimental results show that the DualGGAN network effectively reduces artifact generation when implementing facial style transfer, maintains good background consistency, and has good generalization ability. Experiments have shown that the FID and KID indicators on the cat2dog and older2adult datasets are significantly improved compared to other algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Blind watermarking algorithm based on redistributed invariant integer wavelet transform and BP network 3

Blind watermarking algorithm based on redistributed invarian...

引用

3rd International conference on Signal image processing and Communication, ICSIPC 2023

作者： Deng, Yang School of Mathematics and Statistics Xidian University Xi’an China

ISBN: (纸本)9781510670945

In this paper, a blind watermarking algorithm based on redistributed invariant integer wavelet transform (RI-IWT) and BP network is proposed. The host image is processed by RI-DWT and QR decomposition, and the watermark is embedded in the low frequency and high frequency sub-band of the host image, so as to increase the embedding capacity. Moreover, we realize the blind extraction of watermark through BP network. In the extraction stage, the host image information and part of the watermark information are no longer required, thus improving the security of the algorithm. Finally, we simulate the algorithm and compare it with the relative algorithms. Simulation results show that the proposed algorithm has high invisibility and good robustness against JPEG attacks, rotation attacks, noise attacks. © 2023 SPIE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in tunnel construction: A comprehensive review of hotspots and frontier topics

引用

Geohazard Mechanics 2024年第1期2卷 1-12页

作者： Lianbaichao Liu Zhanping Song Xu Li School of Civil Engineering Xi'an University of Architecture and TechnologyXi'an710055China Shaanxi Key Lab of Geotechnical and Underground Space Engineering Xi'an710055China Institute of Tunnel and Underground Structure Xi'an University of Architecture and TechnologyXi'an710055China

Application of Artificial Intelligence(AI)in tunnel construction has the potential to transform the industry by improving efficiency,safety,and *** paper presents a comprehensive literature review and analysis of hotspots and frontier topics in artificial intelligence-related research in tunnel construction.A total of 554 articles published between 2011 and 2023 were collected from the Web of Science(WOS)core collection database and analyzed using CiteSpace *** analysis identified three main study areas:Tunnel Boring Machine(TBM)performance,construction optimization,and rock and soil *** review highlights the advancements made in each area,focusing on design and operation,performance prediction models,and fault detection in TBM performance;computer vision and image processing,neural network algorithms,and optimization and decision-making in construction optimization;and geo-properties and behaviours,tunnel stability and excavation,and risk assessment and safety management in rock and soil *** paper concludes by discussing future research directions,emphasizing the integration of AI with other advanced technologies,realtime decision-making systems,and the management of environmental impacts in tunnel *** comprehensive review provides valuable insights into the current state of AI research in tunnel engineering and serves as a reference for future studies in this rapidly evolvingfield.

关键词： Literature review Underground construction CiteSpace Artificial intelligent Bibliometrics analysis

来源：评论

学校读者我要写书评

暂无评论

Accurate identification and Advanced mapping for comprehensive Skin Cancer Staging

Accurate identification and Advanced mapping for comprehensi...

引用

Control Instrumentation System conference (CISCON) - Guiding Tomorrow - Emerging Trends in Control, Instrumentation, and systems Engineering

作者： Praneethal, Devulapalli Pandala, Madhavi Latha Sai, Gopu Nithin Velagapudi Ramakrishna Siddhartha Engn Coll Dept IT Vijayawada AP India

ISBN: (纸本)9798350375480;9798350375497

The most prevalent and dangerous kind of cancer in humans is skin cancer. Melanoma is a kind of skin cancer that is fatal. One of the deadliest cancers in the world, melanoma will spread to other body parts if it is not detected at an early stage. It is easily curable if detected in its early stages. The goal's highlights the issues of a global increase in skin cancer cases, excessive medical expenses, and an exponential rise in the effect of death from delayed diagnosis due to missed opportunities for early intervention. The biopsy procedure is the official way for melanoma diagnosis and detection. This approach can be extremely painful and time-consuming. In the modern years, deep learning techniques have shown promise in automating the detection process, offering the potential for more accurate and timely diagnoses. This system is a deep learning-based predictive algorithm that uses dermoscopic image analysis to dynamically forecast melanoma skin cancer. The main objectives of this research are to find skin cancer more accurately and quickly in its early stages. This work provides a computer-aided detection technique for melanoma early detection. Our research work suggests using InceptionV3 and Resnet50 algorithms, along with image processing techniques, to create an effective diagnosis system in this study. An image of the impacted skin is captured and subjected to a few pre-processing methods to produce an improved and smoothed image. Next, the picture is subjected to morphological, thresholding, and grey scaling techniques during the data augmentation phase. It categorizes the provided image as either Stage 1 or Stage 2 melanoma. An impressive 84.5% accuracy is attained. Clinical diagnosis of many disorders is increasingly dependent on harmless clinical computer vision or medical image processing. These methods offer an automatic evaluation of images tool for a quick and precise assessment. Overall, the suggested technique is a major improvement in the identif

关键词： Skin Cancer Melanoma image processing InceptionV3 ResNet50 Healthcare technology

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：