检索结果-内蒙古大学图书馆

Class-conditional domain adaptation for semantic segmentation

Computational Visual Media 2024年第5期10卷 1013-1030页

作者： Yue Wang Yuke Li James H.Elder Runmin Wu Huchuan Lu School of Information and Communication Engineering Dalian University of TechnologyDalian 116024China School of Computer Science Wuhan UniversityWuhan 430072China Department of Electrical Engineering and Computer Science York UniversityToronto M3J 1P3Canada Department of Computer Science the University of Hong KongHong Kong 999077China

Semantic segmentation is an important sub-task for many ***,pixel-level ground-truth labeling is costly,and there is a tendency to overfit to training data,thereby limiting the generalization *** domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain(including less expensive synthetic domain)to be adapted to a novel target *** conventional approach involves automatic extraction and alignment of the representations of source and target domains *** limitation of this approach is that it tends to neglect the differences between classes:representations of certain classes can be more easily extracted and aligned between the source and target domains than others,limiting the adaptation over all ***,we address:this problem by introducing a Class-Conditional Domain Adaptation(CCDA)*** incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and ***,they measure the segmentation,shift the domain in a classconditional manner,and equalize the loss over *** results demonstrate that the performance of our CCDA method matches,and in some cases,surpasses that of state-of-the-art methods.

关键词： domain adaptation generative adversarial networks semantic segmentation cityscapes

来源：评论

学校读者我要写书评

暂无评论

Scheduling Bi-Objective Lot-Streaming Hybrid Flow Shops with Consistent Sublots via an Enhanced Artificial Bee Colony Algorithm

引用

Complex System Modeling and Simulation 2025年第1期5卷 46-67页

作者： Benxue Lu Kaizhou Gao Peiyong Duan Adam Slowik School of Computer Science Liaocheng UniversityLiaocheng 252000China Macao Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China School of Information and Automation Engineering Qilu University of TechnologyJinan 250353China Department of Electronics and Computer Science Koszalin University of TechnologyKoszalin 75-453Poland

This work addresses bi-objective hybrid flow shop scheduling problems considering consistent sublots(Bi-HFSP_CS).The objectives are to minimize the makespan and total energy ***,the Bi-HFSP_CS is formalized,followed by the establishment of a mathematical ***,enhanced version of the artificial bee colony(ABC)algorithms is proposed for tackling the Bi-HFSP_***,fourteen local search operators are employed to search for better *** different Q-learning tactics are developed to embed into the ABC algorithm to guide the selection of operators throughout the iteration ***,the proposed tactics are assessed for their efficacy through a comparison of the ABC algorithm,its three variants,and three effective algorithms in resolving 95 instances of 35 different *** experimental results and analysis showcase that the enhanced ABC algorithm combined with Q-learning(QABC1)demonstrates as the top performer for solving concerned *** study introduces a novel approach to solve the Bi-HFSP_CS and illustrates its efficacy and superior competitive strength,offering beneficial perspectives for exploration and research in relevant domains.

关键词： hybrid flow shop scheduling Q-learning lot streaming local search

来源：评论

学校读者我要写书评

暂无评论

iLIAC: An approach of identifying dissimilar groups on unstructured numerical image dataset using improved agglomerative clustering technique

引用

Multimedia Tools and Applications 2024年第39期83卷 86359-86381页

作者： S, Sreedhar Kumar Ahmed, Syed Thouheed Fathima, Afifa Salsabil Mathivanan, Sandeep Kumar Jayagopal, Prabhu Saif, Abdu Gupta, Sachin Kumar Sinha, Garima Department of Computer Science and Engineering School of Engineering and Technology CMR University Karnataka Bengaluru India Department of Electrical Engineering Indian Institute of Technology Hyderabad Telangana Kandi India School of Computer Science and Engineering REVA University Bangalore India School of Computer Science and Engineering Galgotias University Uttar Pradesh Greater Noida203201 India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Communication and Computer Engineering Faculty of Engineering and IT Taiz University Taiz Yemen Katra India Department of Computer Science Engineering Jain University Bangalore India

Unstructured Numerical Image Dataset Separation (UNIDS) method employing an enhanced unsupervised clustering technique. The objective is to delineate an optimal number of distinct groups within the input grayscale (G-S) image content, utilizing the improved limited iteration agglomerative clustering (iLIAC) clustering technique for the separation and enhancement of picture elements. The UNIDS method is structured into two primary stages: partitioning and validation. In the partitioning stage, the UNIDS method identifies an appropriate number of discrete clusters within the grayscale image using the iLIAC technique, eliminating the need for predetermined procedures. Subsequently, the method evaluates the similarity and deviation among data elements within the same group in the resultant image dataset. Additionally, it assesses the proximity and inters severance among clusters in the outcome of the image dataset through the partitioning process. Empirical results indicate that the UNIDS system excels in the spontaneous identification of an optimal number of discrete clusters within the input G-S image. The system demonstrates superior thickness, reduced deviation among data elements within the same cluster, increased inter-separation, and diminished inter-closeness between cluster elements. Furthermore, empirical analysis establishes the superior performance of the UNIDS approach compared to existing clustering techniques. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

High-Secured Image LSB Steganography Using AVL-Tree with Random RGB Channel Substitution

引用

computers, Materials & Continua 2024年第10期81卷 183-211页

作者： Murad Njoum Rossilawati Sulaiman Zarina Shukur Faizan Qamar Center of Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangiSelangor43600Malaysia Computer Science and Cyber Security Faculty of Engineering and Information TechnologyBirZeit UniversityBirZeitRamallahP.O.Box 14Palestine

Random pixel selection is one of the image steganography methods that has achieved significant success in enhancing the robustness of hidden *** property makes it difficult for steganalysts’powerful data extraction tools to detect the hidden data and ensures high-quality stego image ***,using a seed key to generate non-repeated sequential numbers takes a long time because it requires specific mathematical *** addition,these numbers may cluster in certain *** hidden data in these clustered pixels will reduce the image quality,which steganalysis tools can ***,this paper proposes a data structure that safeguards the steganographic model data and maintains the quality of the stego *** paper employs the AdelsonVelsky and Landis(AVL)tree data structure algorithm to implement the randomization pixel selection technique for data *** AVL tree algorithm provides several advantages for image ***,it ensures balanced tree structures,which leads to efficient data retrieval and insertion ***,the self-balancing nature of AVL trees minimizes clustering by maintaining an even distribution of pixels,thereby preserving the stego image *** data structure employs the pixel indicator technique for Red,Green,and Blue(RGB)channel *** green channel serves as the foundation for building a balanced binary ***,the sender identifies the colored cover image and secret *** sender will use the two least significant bits(2-LSB)of RGB channels to conceal the data’s size and associated *** next step is to create a balanced binary tree based on the green *** the channel pixel indicator on the LSB of the green channel,we can conceal bits in the 2-LSB of the red or blue *** first four levels of the data structure tree will mask the data size,while subsequent levels will conceal the remaining digits of secret *** embedding the bits i

关键词： Image steganography pixel random selection(PRS) AVL tree peak signal-to-noise ratio(PSNR) imperceptibility capacity

来源：评论

学校读者我要写书评

暂无评论

Enhancing Accuracy of Handwritten Character Segmentation Using Region-Based Convolutional Neural Networks (R-CNN) 1

Enhancing Accuracy of Handwritten Character Segmentation Usi...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Varpe, Kanchan Sakhare, Sachin Joshi, Rahul Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Department of Computer Science and Engineering Pune India

ISBN: (纸本)9798350355611

Handwritten character segmentation plays a pivotal role in the performance of Optical Character Recognition (OCR) systems. This paper introduces an innovative approach to enhancing segmentation accuracy using Region-Based Convolutional Neural Networks (R-CNN). Traditional methods often struggle with issues such as varying character sizes, overlapping, and inconsistent writing styles, leading to suboptimal recognition results. The proposed R-CNN model addresses these challenges by effectively localizing and segmenting individual characters from handwritten text images. The methodology involves training the R-CNN on a comprehensive dataset of handwritten characters, annotated to capture diverse styles and complexities. The model leverages deep learning's feature extraction capabilities and region-based localization to accurately segment characters, even in challenging scenarios like connected or touching characters. Comparative experiments show that the proposed approach outperforms conventional techniques in terms of segmentation accuracy and robustness. Results demonstrate significant improvements, with the R-CNN model achieving higher precision and recall rates across multiple handwritten datasets, including different languages and scripts. This advancement holds promise for enhancing OCR systems used in applications such as automated document processing and digital archiving. Future work will focus on integrating this segmentation method with advanced recognition models to further boost overall handwritten text recognition performance. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of banana leaf disease by intelligent algorithm through digital image using neural network technique

引用

Multimedia Tools and Applications 2025年 1-17页

作者： Nagu, Bharathiraja Kaur, Gaganpreet Shanmugavelu, Murugesan M.R.M, Veeramanickam Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Information Technology Tagore Engineering College Tamil Nadu Chennai India Apex Institute of Technology-Computer Science and Engineering Chandigarh University Punjab India

A lot of research shows that there could be several reasons why the duality of agricultural products has been reduced. Plant diseases make up one of the most important components of this quality. Therefore, the reduction of plant diseases allows for much higher product quality. The automated diagnosis of plant diseases using CNN techniques is presented in this article. The simple approach alters the 25 color channels and 24H histograms. The Banana Leaf Disease Detection Technique (BLDDT), which uses two attention mechanisms to assess, identify and categorize traits, was also suggested in this research. In the analysis phase, the testing carried out using the reference information reveals that the disease, detection system may be reasonably more appropriate than the current techniques because it both identifies and diagnoses the diseased/infected areas. The researchers were able to identify Esca, black decay, and isariopsis ––––with a 99.93% accuracy level using the suggested disease detector. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A pressure therapy method: Monaural beats sonic resonance

引用

IEEE Potentials 2024年第3期43卷 17-22页

作者： Lin, Tsen-Fang Chen, Liang-Bi Southern Taiwan University of Science and Technology Department of Popular Music Industry Tainan710301 Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu880011 Taiwan

This article introduces a non-invasive pressure therapy method using monaural beats (MB) sonic resonance to promote relaxation and reduce stress. Unlike binaural beats (BB), MB requires no headphones, enhancing accessibility. By targeting ultralow brainwave frequencies, MB effectively relieves anxiety and stress. Compared to BB and other infrasound methods, MB offers advantages in terms of cost, comfort, and flexibility. Potential applications in IoT and AIoT systems for adaptive therapies are also discussed, with further research needed to realize their therapeutic potential fully. © 2024 IEEE.

关键词： Noninvasive medical procedures

来源：评论

学校读者我要写书评

暂无评论

Con-Fog: Consensus-Driven Fog Node Selection in FU-Serve Platform for IoT Applications

引用

IEEE Internet of Things Journal 2025年第13期12卷 24686-24697页

作者： Imandi, Raju Roy, Arijit Sethi, Kamalakanta Pavan, Kumar Guizani, Mohsen Indian Institute of Information Technology Computer Science and Engineering Group Sri City India Indian Institute of Technology Department of Computer Science and Engineering Patna India Mohamed bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

The rapid expansion of Internet of Things (IoT) devices and applications necessitates the need for more efficient computational and data management strategies. The Fog-enabled UAV-as-a-Service (FU-Serve) platform addresses these demands by integrating fog computing to enhance the operational efficiency of UAVs in IoT environments. Despite its advantages, the FU-Serve platform faces significant challenges, including data transmission latency, resource allocation, and energy management, contributing to the underutilization of UAVs and fog nodes. To address these challenges, this paper introduces a consensus-driven approach, Con-Fog, that optimizes the selection of fog nodes for UAVs within the FU-Serve platform. Con-Fog evaluates potential fog nodes within the communication range by computing utility values based on geographical distance, link quality, available computational resources, and residual energy. UAVs rank these nodes according to their utility values and select the most suitable ones through a consensus-based approach, ensuring alignment with the operational demands of IoT devices. Additionally, we apply an optimal best-fit algorithm to refine fog node allocation, maximizing resource utilization while keeping it below each node’s capacity threshold (T%). Our simulation results show that Con-Fog significantly enhances key IoT performance metrics. Transmission time and the number of unassigned UAVs decrease by 10%-30% and 20%-40%, respectively, while residual energy increases by 30%-50% compared to existing systems. These improvements enhance the management of UAV and fog node resources, thereby advancing the effectiveness of IoT applications within the FU-Serve platform. © 2014 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Deep Learning QoS Prediction Model Based on Temporal Context and Feature Fusion

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1232-1244页

作者： Zhang, Peiyun Fan, Jiajun Chen, Yutong Huang, Wenjun Zhu, Haibin Zhao, Qinglin Nanjing University of Information Science & Technology Engineering Research Center of Digital Forensics of Ministry of Education School of Computer Science Nanjing210044 China Nipissing University Department of Computer Science and Mathematics North BayONP1B 8L7 Canada Macau University of Science and Technology School of Computer Science and Engineering Taipa999078 China

Existing end-to-end quality of service (QoS) prediction methods based on deep learning often use one-hot encodings as features, which are input into neural networks. It is difficult for the networks to learn the information that is conducive to prediction. Aiming at the above problem, an end-to-end deep learning QoS prediction model based on a temporal context and feature fusion is proposed. In the proposed model, three blocks are designed for QoS prediction. Firstly, a user-service encoding conversion block is designed to convert the one-hot encodings of users and services into the latent features of users and services, which can make full use of the data in sparse matrices. Then a time feature extraction block is designed to extract time features based on the time-varying characteristics of QoS values. Finally, the time features are fused with the latent features of users and services to predict QoS values. The experimental results show that on existing datasets, the proposed model has better prediction accuracy than other advanced methods in response time and throughput. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Computation Offloading Based on Decentralized Deep Reinforcement Learning in Industrial Internet of Things

引用

IEEE Transactions on Cognitive Communications and Networking 2025年第3期11卷 1940-1953页

作者： Zhao, Yingjie Chai, Zhengyi Li, Yalun Huang, Hao Kang, Hongshen Tiangong University School of Computer Science and Technology Tianjin300387 China Tiangong University School of Electronics and Information Engineering Tianjin300387 China

With the increasing scale of industrial equipments, delay and energy consumption have emerged as critical concerns within the Industrial Internet of Things (Industrial IoT). Mobile edge computing (MEC) offloads tasks to nearby edge servers to meet the demands of delay-sensitive applications. However, the limitations of edge computing resources can lead to significant processing delays or even task failures when offloading numerous tasks. Furthermore, it is difficult for existing centralized algorithms to acquire global information within large-scale industrial environment. To tackle these challenges, the computation offloading problem is transformed into a decentralized partially observable Markov decision process (Dec-POMDP) with rewards for delay and energy consumption, and a decentralized multi-objective computation offloading method is proposed to achieve the long-term reward maximization. Specifically, two deep neural networks, namely the delay and energy network, are designed to estimate the expected rewards for each offloading decision in terms of delay and energy consumption. Meanwhile, to achieve dynamic offloading, gated recurrent unit (GRU) is introduced to predict the occupancy of edge computing resources, and an adaptive weight network is devised to dynamically adjust the weights of optimization objectives based on historical information. Comprehensive experiments demonstrate that the proposed method effectively meets the requirements of delay-sensitive tasks, as well as minimizing long-term delay and energy consumption. © 2015 IEEE.

关键词： Deep reinforcement 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：