检索结果-内蒙古大学图书馆

Downsampling consistency correction-based quality enhancement for CNN-based light field image super-resolution

Multimedia Tools and Applications 2024年第34期83卷 80919-80939页

作者： Chung, Kuo-Liang Hsieh, Tsung-Lun Department of Computer Science and Information Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Road Taipei10672 Taiwan

In recent years, numerous CNN-based light field (LF) image super-resolution (SR) methods have been developed. However, due to the downsampling inconsistency between low-resolution (LR) testing LF images and LR training LF images, they may suffer from quality degradation. To address this quality degradation issue, this paper proposes a downsampling consistency correction-based (DCC-based) quality enhancement method. Firstly, a quality-based voting strategy is introduced to identify the downsampling scheme used in the training step. Next, a cascaded Swin Transformer-based recognizer is proposed to identify the downsampled position and downsampling scheme used in the LR testing LF image, after which the proposed DCC-based method is employed to significantly improve the quality of the upsampled LF image. Comprehensive experiments have been conducted on typical LF image datasets to demonstrate the significant quality improvement achieved by our method in comparison to state-of-the-art LF SR methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A sketch recognition method based on bi-modal model using cooperative learning paradigm

引用

Neural Computing and Applications 2024年第23期36卷 14275-14290页

作者： Zhang, Shihui Wang, Lei Cui, Zhiguo Wang, Shi School of Information Science and Engineering Yanshan University Hebei Street West Section Hebei Province Qinhuangdao066000 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Hebei Street West Section Hebei Province Qinhuangdao066000 China School of Information Technology Hebei University of Business and Economics Xuefu Road Hebei Province Shijiazhuang050061 China School of Mathematics and Information Science and Technology Hebei Normal University of Science and Technology Hebei Street West Section Hebei Province Qinhuangdao066000 China

Static image is an important form of displaying a sketch, representing the appearance information of the sketch. And a stroke sequence composed of several points can also express the shape and contour information of the sketch. Therefore, it is very reasonable to treat a sketch as point-modal data and image-modal data simultaneously. In this paper, a method based on bi-modal model using cooperative learning paradigm is proposed for the sketch recognition task. Specifically, in the point-modal branch, a structural point convolution block is developed by properly dividing local regions to preserve the structural information. In the image-modal branch, the hierarchical residual structure is used to fully extract image-modal features. To reduce the negative impact of noisy samples on the recognition performance, a cooperative learning paradigm is designed based on different perceptual abilities of two modal branches on noisy samples, that is, when training the two branches, the noisy samples can be filtered out through information exchanges and mutual learning. Extensive experiments on the sketch datasets TU-Berlin and QuickDraw show that the proposed method outperforms most baseline methods and has many advantages such as no dependence on additional data and stroke information. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Frozen Food Supply Chain Monitoring with IoT 19

Frozen Food Supply Chain Monitoring with IoT

引用

19th International Conference on Ubiquitous information Management and Communication, IMCOM 2025

作者： Mohd Kassim, Mohd Sallehin Rozman, Muhammad Haziq bin Yahya, Faridah Advanced Telecommunication Technology Cluster International Industrial and Institutional Partnership Department Computer Engineering Technology Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia Internet of Thing Computer Engineering Technology Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia Computer Engineering Technology Section Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia

ISBN: (纸本)9798331507817

This project aimed to implement a prototype capable of real-time monitoring and control of various parameters in information management setting with Internet of Things (IoT). Research methodology involved designing and implementing the system prototype to resemble a supply container or transportation truck with installed sensors controlled by a microcontroller. Main components used temperature sensors (AHT20), RFID reader for access control, GPS module for location tracking, and a web/mobile dashboard for remote monitoring. Additionally, a robust database system was developed to store sensor readings and transaction history, ensuring data integrity and facilitating seamless communication between components for real-time data transmission. Key findings indicate that the system effectively monitors temperature, manages access control through RFID authentication, tracks real-time location via GPS, and provides a user-friendly dashboard interface for data visualization. © 2025 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Synergistic Neural Matrix Factorization: Elevating Complementary Product Recommendations in E-Commerce using Deep Neural Networks 3

Synergistic Neural Matrix Factorization: Elevating Complemen...

引用

3rd IEEE Delhi section Flagship Conference, DELCON 2024

作者： Gupta, Neha Joshi, Vaishali Chourey, Aishwarya Acharya, Ekta School of Computer Science and Information Technology Symbiosis University of Applied Sciences Madhya Pradesh India Jai Narain Vyas University Computer Section Rajasthan Jodhpur India

ISBN: (纸本)9798331518592

This research explores the submission of deep neural networks (DNNs) to enhance corresponding product references in e-commerce stages. By leveraging the Neural Collaborative Filtering (NeuMF) model, which integrates Comprehensive Matrix Factorization (GMF) and Multi-Layer Perceptron (MLP), the study captures both linear and non-linear user-item connections to improve recommendation accuracy. Key performance metrics, including accuracy, loss, ROC curve, and precision-recall curve, were analyzed to assess the model's effectiveness. Results show that the NeuMF model significantly improves recommendation accuracy and user satisfaction, with an AUC of 0.94. However, the precision-recall analysis highlights areas for improvement, mainly in handling imbalanced datasets. This work demonstrates the potential of advanced neural models to drive better user engagement and increase sales in dynamic e-commerce environments while suggesting future directions for optimizing precision-recall trade-offs. © 2024 IEEE.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

End-To-End Encryption Enabled Lightweight Mutual Authentication Scheme for Resource Constrained IoT Network

引用

computers, Materials & Continua 2025年第2期82卷 3223-3249页

作者： Shafi Ullah Haidawati Muhammad Nasir Kushsairy Kadir Akbar Khan Ahsanullah Memon Shanila Azhar Ilyas Khan Muhammad Ashraf Department of Computer Engineering Balochistan University of Information TechnologyEngineering and Management SciencesQuetta87300Pakistan Computer Engineering Section Malaysian Institute of Technology Universiti Kuala LumpurKuala Lumpur50250Malaysia Electrical Engineering Section Universiti Kuala LumpurBritish Malaysian InstituteSalengor53100Malaysia Electrical Engineering Department Mehran UniversityKhairpur-Mirs76062Pakistan Department of Mathematics College of Science Al-ZulfiMajmaah UniversityAl-Majmaah11952Saudi Arabia

Machine-to-machine (M2M) communication networks consist of resource-constrained autonomous devices, also known as autonomous Internet of things (IoTs) or machine-type communication devices (MTCDs) which act as a backbone for Industrial IoT, smart cities, and other autonomous systems. Due to the limited computing and memory capacity, these devices cannot maintain strong security if conventional security methods are applied such as heavy encryption. This article proposed a novel lightweight mutual authentication scheme including elliptic curve cryptography (ECC) driven end-to-end encryption through curve25519 such as (i): efficient end-to-end encrypted communication with pre-calculation strategy using curve25519;and (ii): elliptic curve Diffie-Hellman (ECDH) based mutual authentication technique through a novel lightweight hash function. The proposed scheme attempts to efficiently counter all known perception layer security threats. Moreover, the pre-calculated key generation strategy resulted in cost-effective encryption with 192-bit curve security. It showed comparative efficiency in key strength, and curve strength compared with similar authentication schemes in terms of computational and memory cost, communication performance and encryption robustness.

关键词： Mutual authentication lightweight end-to-end encryption elliptic curve cryptography industrial internet of things curve25519 machine-to-machine communication

来源：评论

学校读者我要写书评

暂无评论

Refining Pseudo Labels With a Teacher-Student Paradigm for Accurate Brain Lesion Segmentation

引用

IEEE Access 2025年 13卷 84474-84487页

作者： Chatterjee, Pubali Das Sharma, Kaushik Chakrabarti, Amlan Department of Computer Science and Engineering Bhubaneswar751030 India University of Calcutta Electrical Engineering Section Department of Applied Physics Kolkata700073 India University of Calcutta A. K. Choudhury School of Information Technology Kolkata700073 India

In medical image segmentation, obtaining large volume of high quality labeled data is a persistent challenge, especially for intricate tasks like brain lesion segmentation, where annotations are time-consuming, costly, and require expert knowledge. This work introduces a novel learning framework where the abundance of labeled data is scarce, and the model learns from both limited number of annotated data as well as from unlabeled data. The framework initially leverages superpixel segmentation to group pixels with similar properties into compact, perceptually coherent regions while preserving critical structural details, and produce coarse segmentation mask on unlabeled data. In the next phase, a teacher-student model is employed, where the teacher module generates pseudo-labels for unlabeled data, and the student model learns from both of these pseudo-labels and minimal amount of annotated data. In addition, a feature refinement module is introduced to further strengthen the teacher-student framework, where the student module also learns from the mutual agreement between superpixel prediction and the pseudo label generated by the teacher module. The overall framework helps in efficiently using the unlabeled data with the help of handful amount of labeled data. Experimental results across multiple datasets demonstrate the effectiveness of the proposed framework in achieving precise, computationally efficient brain lesion segmentation. The integration of superpixel-based grouping and the student-teacher architecture not only improves segmentation accuracy but also offers a scalable solution for scenarios with limited annotated data. This method provides a promising pathway for advancing medical imaging applications, enabling accurate and efficient segmentation while addressing the challenges of data scarcity and annotation constraints. © 2013 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

RC structural system control subjected to earthquakes and TMD

引用

Structural Engineering and Mechanics 2024年第2期89卷 213-223页

作者： Shao, Jenchung Noor, M. Nasir Ken, P. Chang, Chuho Wang, R. College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Taiwan College of Maritime National Kaohsiung University of Science and Technology Taiwan Information and Research Center of China 1/9 Road: 2 Block: D Section: 15 Dhaka1216 Bangladesh

This paper proposes a composite design of fuzzy adaptive control scheme based on TMD RC structural system and the gain of two-dimensional fuzzy control is controlled by parameters. Monitoring and learning in LMI then produces performance indicators with a weighting matrix as a function of cost. It allows to control the trade-off between the two efficiencies by adjusting the appropriate weighting matrix. The two-dimensional Boost control model is equivalent to the LMI-constrained multi-objective optimization problem under dual performance criteria. By using the proposed intelligent control model, the fuzzy nonlinear criterion is satisfied. Therefore, the data connection can be further extended. Evaluation of controller performance the proposed controller is compared with other control techniques. This ensures good performance of the control routines used for position and trajectory control in the presence of model uncertainties and external influences. Quantitative verification of the effectiveness of monitoring and control. The purpose of this article is to ensure access to adequate, safe and affordable housing and basic services. Therefore, it is assumed that this goal will be achieved in the near future through the continuous development of artificial intelligence and control theory. Copyright © 2024 Techno-Press, Ltd.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Factors Influencing Users’ Satisfaction Towards Image Use in Social Media: A PLS-SEM Analysis

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2022年第15期16卷 172-186页

作者： Ilias, Irma Syarlina Che Ramli, Suzaimah Wook, Muslihah Hasbullah, Nor Asiakin Department of Computer Science Faculty of Defense Science and Technology National Defence University of Malaysia Selangor Malaysia Computer Engineering Technology Section Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia

Images for social media are an essential component of any blog or social media post. As we now live in the age of the ‘camera in everyone’s pocket’, a new dynamic era of image creation and content has emerged. However, people use media due to specific motives or gratifications that lead to their satisfaction of social media use. This research study utilized uses and gratification theory (UGT), a sociology theory related to the motives of people using the media. The UGT factors include enjoyment, entertainment, social influence, social interaction, and information sharing. There were 441 data that were collected and analysed. IBM SPSS Statistics 20 and Smart PLS 3.3.3 were used for the data analysis. Result showed that information sharing was the most influencing factors on users’ satisfaction to use image in social media. Therefore, the factors identified in these studies could be used as a guideline and references in future study related to social media awareness and implications. © 2022. International Journal of Interactive Mobile Technologies. All Rights Reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Incorporating Onboard Visual Sensing and Geographic information for Lane-Level Vehicle Localization

引用

IEEE Sensors Journal 2025年第12期25卷 21867-21877页

作者： Lin, Huei-Yung Li, Jun-Yi Su, Ming-Wei National Taipei University of Technology Department of Computer Science and Information Engineering No. 1 Section 3 Zhongxiao East Road Taipei10608 Taiwan National Chung Cheng University Department of Electrical Engineering 168 University Road Chiayi621 Taiwan

With the recent advances in deep learning and artificial intelligence, vehicular technologies are progressing rapidly toward fully autonomous driving. Critical components of advanced driver assistance systems (ADAS) have been extensively investigated in the past decade. In this paper, we address the challenge of precise vehicle localization using visual perception and geographic information. The proposed method incorporates drivable area detection, lane line detection, and image-map matching to achieve lane-level localization accuracy. It takes advantage of digital maps and images from the onboard cameras to simultaneously optimize vehicle localization and lane detection. A confidence estimation is proposed to generate virtual lane lines for the lane marking identification. Our networks are pre-trained on the Cityscapes, CULane and TuSimple datasets, and fine-tuned with the newly proposed TRoad and TLane. In the experiments, the performance evaluated using MAE and RMSE have demonstrated a significant improvement over the conventional GPS/GNSS-based vehicle localization techniques. Source code and datasets are available at https://***/Wally0924/Enhancing-Vehicle-Localization-Using-Lane-Detection-and-Geographic-information. © 2001-2012 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Monkeypox Lesions Detection with a Lightweight Hybrid Model

引用

IEEE Access 2025年 13卷 103709-103732页

作者： Al-Gaashani, Mehdhar S. A. M. Alkanhel, Reem Hassan, Dina S. M. Ba Mahel, Abduljabbar S. Aziz, Ahmed Khayyat, Mashael M. Muthanna, Ammar University of Electronic Science and Technology of China School of Resources and Environment 1st Ring Rd East 2 Section Sichuan Chengdu610056 China Princess Nourah bint Abdulrahman University Department of Information Technology College of Computer and Information Sciences P.O. Box 84428 Riyadh11671 Saudi Arabia University of Electronic Science and Technology of China School of Life Science and Technology Chengdu610054 China Benha university Department of computer science Faculty of computer and Artificial intelligence Egypt Central Asian University Engineering school Tashkent Uzbekistan University of Jeddah Department of Information Systems and Technology Collage of Computer Science and Engineering Jeddah Saudi Arabia Peoples'Friendship University of Russia RUDN University Department of Applied Probability and Informatics 6 Miklukho-Maklaya St Moscow117198 Russia

The increasing global prevalence of monkeypox (mpox) has necessitated the development of accurate, efficient, and interpretable diagnostic models for timely disease identification. Although deep learning has advanced medical image analysis, diagnosing diseases with complex lesions, such as monkeypox, remains challenging in resource-limited settings. Existing methods often rely on large architectures that demand high computational resources and lack interpretability. To address these issues, we propose a lightweight, interpretable architecture that truncates MobileNetV2 for efficient feature extraction, incorporates Ghost Modules to reduce redundancy, and integrates a SA-MobileViT block to capture both local and global dependencies in lesion images. Grad-CAM visualizations enhance interpretability, and Optuna is used for hyperparameter optimization. Our model achieved an accuracy of 98.72%, precision of 98.76%, recall of 98.72%, and F1-score of 98.72%, outperforming existing approaches, especially in handling irregular lesion patterns. The model's design is ideal for deployment in resource-constrained settings, offering a robust solution for real-world healthcare applications. Grad-CAM, saliency maps, and other visualization techniques help improve clinical trust by highlighting relevant regions in input images, emphasizing key features of the lesions. The proposed model is lightweight with only 630,204 parameters, making it 92.3× smaller than ResNet152V2 (58,152,004 parameters) and 28.7× smaller than DenseNet201 (18,100,612 parameters). It requires 321.61M FLOPs, 35.8× fewer than ResNet152V2 (11.51G FLOPs) and 13.4× fewer than DenseNet201 (4.29G FLOPs). With a size of just 72.92 MB, it is 8.14× smaller than ResNet152V2 (594.08 MB) and 4.57× smaller than DenseNet201 (333.47 MB), making it an efficient solution for mobile and edge deployment in resource-constrained environments. © 2013 IEEE.

关键词： Deep 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：