检索结果-内蒙古大学图书馆

Multi-feature Fusion Deep Network for Skin Disease Diagnosis

Multimedia Tools and Applications 2025年第1期84卷 419-444页

作者： Gairola, Ajay Krishan Kumar, Vidit Sahoo, Ashok Kumar Diwakar, Manoj Singh, Prabhishek Garg, Deepak Department of Computer Science and Engineering Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era deemed to be university Dehradun India School of Computer Science Engineering and Technology Bennett University Greater Noida India School of Computer Science and Artificial Intelligence SR University Warangal Telangana Warangal506371 India

The skin acts as an important barrier between the body and the external environment, playing a vital role as an organ. The application of deep learning in the medical field to solve various health problems has generated increasing interest. The objective of this research is to create a new model using a deep network with multi-feature fusion that enables accurate identification of various skin diseases. This paper proposes a fully fused network (FFN), which includes an improved single block (ISB) and an improved fusion block (IFB) to achieve optimal performance. To implement this, a convolutional neural network-based model for multi-class recognition of skin images has been developed, in which ISB is used to segment diseases in skin images. The IFB module is designed to enhance the effectiveness of the fused network. The model is built and evaluated using our proprietary dataset (Skin_disease_v1) along with publicly available datasets, namely ISIC2016, ISIC2017, and HAM10000. The highest accuracy achieved in experiments was 86% for ISB, 90% for IFB, and 92% for FFN using HAM10000 (for ResNet101V2), HAM10000 (for Resnet50 + ResNet101V2), and HAM10000 (for Resnet50 + ResNet101V2). This shows an accuracy improvement of 9.2%, 13.2%, and 15.2% compared to the state-of-the-art ISB, IFB, and FFN approaches, respectively. Our network outperforms existing networks in terms of performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Approach for Privacy-Aware Mobile App Package Recommendation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6240-6252页

作者： Liu, Shanpeng Cao, Buqing Liu, Jianxun Kang, Guosheng Shi, Min Li, Xiong Fletcher, Kenneth K. Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan411201 China Hunan University of Technology School of Computer Zhuzhou412007 China Harvard University Harvard Medical School BostonMA02138 United States School of Computer Science and Engineering Chengdu611731 China University of Massachusetts School of Computer Science BostonMA02125 United States

With the prosperity of the mobile Internet, the abundance of data makes it difficult for users to choose their favorite app. Thus, mobile app recommendation as an emerging topic attracts lots of attention. However, existing methods for app recommendation rarely consider recommendation accuracy under the privacy representation of user preferences. To address this problem, we propose a privacy-aware app package recommendation method named APP-Rec. Specifically, in this method: 1) treat an app and its associated heterogeneous entities (APP-Rec considers not only the apps themselves but also a variety of related factors-collectively referred to as heterogeneous entities, such as app category and app neighbors) as an app package and extract comprehensive features from the app package using an intrapackage attention network and an interpackage attention network to improve app recommendation;and 2) design a privacy module utilizing Laplace noise to achieve privacy preservation of user preferences. Experimental results show that APP-Rec outperforms the state-of-the-art methods in terms of area under the curve (AUC). Moreover, the privacy preservation of user preferences in APP-Rec is proved by theoretical analysis and experimental results. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Damaged apple detection with a hybrid YOLOv3 algorithm

引用

Information Processing in Agriculture 2024年第2期11卷 163-171页

作者： Meng Zhang Huazhao Liang Zhongju Wang Long Wang Chao Huang Xiong Luo Schoolof Computer and Communication Engineering University of Science and Technoogy BejingBejing 1083China lShunde Innovation SchoolUniversity of Science and Technology BeijingFoshan 528399China

This paper proposes an improved You Only Look Once(YOLOv3)algorithm for automatically detecting damaged apples to promote the automation of the fruit processing *** the proposed method,a clustering method based on Rao-1 algorithm is introduced to optimize anchor box *** clustering method uses the intersection over the union to form the objective function and the most representative anchor boxes are generated for normal and damaged apple *** verify the feasibility and effectiveness of the proposed method,real apple images collected from the Internet are *** with the generic YOLOv3 and Fast Region-based Convolutional Neural Network(Fast R-CNN)algorithms,the proposed method yields the highest mean average precision value for the test ***,it is practical to apply the proposed method for intelligent apple detection and classification tasks.

关键词： Rao algorithm Apple detection Clustering Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Lightweight Dual-Stage Multi-Exposure Image Fusion 5

FPGA-Based Lightweight Dual-Stage Multi-Exposure Image Fusio...

引用

5th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2024

作者： Yang, Xuziqian Tu, Tao Liu, Yongbin Chen, Huaian Jin, Yi The School of Electrical Engineering and Automation Anhui University Anhui China The School of Engineering Science University of science and technology of china Anhui China

ISBN: (纸本)9798331529192

Deep learning-based multi-exposure image fusion (MEF) methods have demonstrated robust performance. However, these methods require considerable computational resources and energy, which greatly limits their practical deployment. To address this issue, we propose a lightweight, dual-stage MEF method, termed LDMEF. By effectively deploying on field-programmable gate array (FPGA), this method significantly enhances its range of applications and flexibility. Specifically, in the initial stage, LDMEF preprocesses the input sequences by leveraging the parallel processing capabilities of FPGA to compute a preliminary image through pixel-wise addition and averaging, ensuring both simple and rapid execution. Subsequently, in the second stage, our proposed method incorporates depthwise separable convolution with the preliminary image to facilitate a lightweight network that is both straightforward to deploy and simple in design. This network meticulously fine-tunes the preliminary image at the pixel level, achieving high-quality fusion results. Extensive evaluations on publicly available datasets confirm that LDMEF not only achieves remarkable results but also outperforms many GPU-based learning MEF methods. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Bridging molecular photosensitizer and catalyst on carbon nanotubes toward enhanced selectivity and durability for CO_(2)photoreduction

引用

Journal of Environmental sciences 2024年第6期140卷 157-164页

作者： Xiaofeng Cui Xueting Wang Lijun Zhao Jixin Wang Tingting Kong Yujie Xiong Anhui Engineering Research Center of Carbon Neutrality The Key Laboratory of Functional Molecular SolidsMinistry of EducationAnhui Laboratory of Molecular-Based MaterialsCollege of Chemistry and Materials ScienceAnhui Normal UniversityWuhu 241002China School of Chemistry and Chemical Engineering Anqing Normal UniversityAnqing 246011China School of Chemistry and Materials Science University of Science and Technology of ChinaHefei 230026China

Homogenous molecular photocatalysts for CO_(2)reduction,especially metal complex-based photosensitizer-catalyst assemblages,have been attracting extensive research interests due to their efficiency and ***,their low durability and recyclability limit practical *** this work,we immobilized the catalysts of metal terpyridyl complexes and the photosensitizer of[Ru(bpy)3]Cl2onto the surface of carbon nanotubes through covalent bonds and electrostatic interactions,respectively,transforming the homogeneous system into a heterogeneous *** characterizations prove that these metal complexes are well dispersed on CNTs with a high loading(ca.12 wt.%).Photocatalytic measurements reveal that catalytic activity is remarkably enhanced when the molecular catalysts are anchored,which is three times higher than that of homogeneous molecular ***,when the photosensitizer of[Ru(bpy)3]Cl2is immobilized,the side reaction of hydrogen evolution is completely suppressed and the selectivity for CO production reaches 100%,with its durability also significantly *** work provides an effective pathway for constructing heterogeneous photocatalysts based on rational assembly of efficient molecular photosensitizers and catalysts.

关键词： durability selectivity catalyst

来源：评论

学校读者我要写书评

暂无评论

A Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism

引用

computers, Materials & Continua 2024年第3期78卷 3001-3019页

作者： Nannan Wu Xianyi Chen James Msughter Adeke Junjie Zhao School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China

Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information ***,these approaches have some *** example,a cover image lacks self-adaptability,information leakage,or weak *** address these issues,this study proposes a universal and adaptable image-hiding ***,a domain attention mechanism is designed by combining the Atrous convolution,which makes better use of the relationship between the secret image domain and the cover image ***,to improve perceived human similarity,perceptual loss is incorporated into the training *** experimental results are promising,with the proposed method achieving an average pixel discrepancy(APD)of 1.83 and a peak signal-to-noise ratio(PSNR)value of 40.72 dB between the cover and stego images,indicative of its high-quality ***,the structural similarity index measure(SSIM)reaches 0.985 while the learned perceptual image patch similarity(LPIPS)remarkably registers at ***,self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces,making it suitable for diverse computer vision tasks.

关键词： Deep image hiding attention mechanism privacy protection data security visual quality

来源：评论

学校读者我要写书评

暂无评论

Research on Network Traffic Classification Based on Graph Neural Network

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第12期51卷 2043-2050页

作者： Han, Yue Dai, Hong University of Science and Technology Liaoning Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan China

Network traffic classification is a critical concern in network security and management, essential for accurately differentiating among various network applications, optimizing service quality, and improving user experience. The exponential increase in worldwide Internet users and network traffic is continuously augmenting the diversity and complexity of network applications, rendering the Internet environment increasingly intricate and dynamic. Conventional machine learning techniques possess restricted processing abilities for network traffic attributes and struggle to address the progressively intricate traffic classification tasks in contemporary networks. In recent years, the swift advancement of deep learning technologies, particularly Graph Neural Networks (GNN), has yielded significant improvements in network traffic classification. GNN can capture the structured information among network nodes and extract the latent features of network traffic. Nonetheless, current network traffic classification models continue to exhibit deficiencies in the thoroughness of feature extraction. To tackle the problem, this research proposes a method for constructing traffic graphs utilizing numerical similarity and byte distance proximity by exploring the latent correlations among bytes, and it constructs a model, SDA-GNN, based on Graph Isomorphic Networks (GIN) for the categorization of network traffic. In particular, the Dynamic Time Warping (DTW) distance is employed to evaluate the disparity in byte distributions, a channel attention mechanism is utilized to extract additional features, and a Long Short-Term Memory Network (LSTM) enhances the stability of the training process by extracting sequence characteristics. Experimental findings on two actual datasets indicate that the SDA-GNN model surpasses other baseline techniques across multiple assessment parameters in the network traffic classification task, achieving classification accuracy enhancements of 2.19% and 1.49%

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Central Attention Mechanism for Convolutional Neural Networks

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第10期51卷 1642-1648页

作者： Geng, Y.X. Wang, L. Wang, Z.Y. Wang, Y.G. School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China Automation Design Institute Metallurgical Engineering Technology Co. Ltd. Dalian116000 China

Model performance has been significantly enhanced by channel attention. The average pooling procedure creates skewness, lowering the performance of the network architecture. In the channel attention approach, average pooling is used to collect feature information to provide representative values. By leveraging the central limit theorem, we hypothesize that the strip-shaped average pooling operation will generate a one-dimensional tensor by considering the spatial position information of the feature map. The resulting tensor, obtained through average pooling, serves as the representative value for the features, mitigating skewness during the process. By incorporating the concept of the central limit theorem into the channel attention operation process, this study introduces a novel attention mechanism known as the"Central Attention Mechanism (CAM)." Instead of directly using average pooling to generate channel representative values, the central attention approach employs star-stripe average pooling to normalize multiple feature representative values into a single representative value. In this way, strip-shaped average pooling can be utilized to collect data and generate a one-dimensional tensor, while star-stripe average pooling can provide feature representative values based on different spatial directions. To generate channel attention for the complementary input features, the activation of the feature representation value is performed for each channel. Our attention approach is flexible and can be seamlessly incorporated into various traditional network structures. Through rigorous testing, we demonstrate the effectiveness of our attention strategy, which can be applied to a wide range of computer vision applications and outperforms previous attention techniques. © (2024), (International Association of Engineers). All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A novel method using matrix coding on-chain and sharing multimedia data for improved usability and reliability

引用

Multimedia Tools and Applications 2024年第40期83卷 87727-87748页

作者： Yang, Lizhu Qin, Yong School of Computer Science and Engineering Guangzhou Institute of Science and Technology Guangzhou China School of Cyberspace Security Dongguan University of Technology Dongguan China

Blockchain technology has the characteristics of non-tampering and forgery, traceability, and so on, which have good application advantages for the storage of multimedia data. So we propose a novel method using matrix coding on-chain and sharing multimedia data for improved usability and reliability. Based on matrix code, we provide the block matrix coding-based on-chain storing method and the block invertible matrix decoding-based sharing method. The method progressively converts the block to create linearly coupled coded chunks, so the blockchain only sends the chunk sets that have been encoded. Each node also maintains just the ledger relevant to its own operations, which lessens the node’s storage burden. Meanwhile, we make several replications of the chunk set by adding a replication factor to increase the feasibility of chunks. Only when all of the target nodes fail is decoding reconstruction necessary, which further enhances the read performance of the blockchain. Many experimental tests are conducted to evaluate the performance based on various parameters such as time overhead, storage overhead, compression factor, failure factor, and so on. According to theoretical analysis and experimental verification, the method offers good read performance with a high recovery success rate and minimal storage occupation, while guaranteeing the availability and dependability of the block data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An Effective Dynamic Gradient Calibration Method for Continual Learning 41

An Effective Dynamic Gradient Calibration Method for Continu...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lin, Weichen Chen, Jiaxiang Huang, Ruomin Ding, Hu School of Data Science University of Science and Technology of China Anhui China Duke University United States School of Computer Science and Technology University of Science and Technology of China Anhui China

Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the "catastrophic forgetting" problem, i.e., the performance on the previous tasks can substantially decrease because of the missing information in the latter period. Though a number of elegant methods have been proposed, the catastrophic forgetting phenomenon still cannot be well avoided in practice. In this paper, we study the problem from the gradient perspective, where our aim is to develop an effective algorithm to calibrate the gradient in each updating step of the model;namely, our goal is to guide the model to be updated in the right direction under the situation that a large amount of historical data are unavailable. Our idea is partly inspired by the seminal stochastic variance reduction methods (e.g., SVRG and SAGA) for reducing the variance of gradient estimation in stochastic gradient descent algorithms. Another benefit is that our approach can be used as a general tool, which is able to be incorporated with several existing popular CL methods to achieve better performance. We also conduct a set of experiments on several benchmark datasets to evaluate the performance in practice. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

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：