检索结果-内蒙古大学图书馆

SSRT: Intra- and cross-view attention for stereo image super-resolution

Multimedia Tools and Applications 2024年 1-29页

作者： Yang, Qixue Zhang, Yi Chandler, Damon M. Farias, Mylene C. Q. School of Information and Communications Engineering Xi’an Jiaotong University Xi’an710049 China College of Information Science and Engineering Ritsumeikan University Osaka567-8570 Japan Department of Computer Science Texas State University San MarcosTX78666 United States

Abstract: Stereo image super-resolution (SR) aims to increase the spatial resolutions of the left and right views of a stereo image in an attempt to generate higher-resolutions views that appear visually equivalent to those obtained with a higher-resolution stereo camera. The field of stereo image SR has seen rapid significant progress due in large part to the application of deep-learning-based techniques and its associated recent research advancements. Yet, despite this progress, stereo images captured under real-world conditions (e.g., using consumer-level cameras in non-laboratory settings) often contain irregular disparities between the left and right views, a fact that has not been fully considered nor properly addressed in previous works. To address this issue, in this paper, we propose a stereo image super-resolution Transformer (SSRT) network which consists of two blocks, a multi-kernel Transformer block and a cross-merging block, to fully extract intra-view features and capture cross-view dependencies. The multi-kernel Transformer block is proposed to increase the number of representation subspaces for intra-view feature extraction. The cross-merging block utilizes patch-wise attention which efficiently expands the search area to tackle stereo image pairs with arbitrary pixel offsets. Experimental results demonstrate that, for 2× stereo image super-resolution, our model with a comparable number of network parameters achieves 37.57 dB on ETH3D, 35.88 dB on Middlebury, 29.56 dB on Flickr1024, 31.52 dB on KITTI 2012, and 31.15 dB on KITTI2015 in terms of PSNR, and surpasses the state-of-the-art method by a large margin of +0.80 dB on ETH3D, +0.57 dB on Middlebury, +0.36 dB on Flickr1024, +0.14 dB on KITTI 2012, and +0.06 dB on KITTI 2015. The code is available at https://***/yanksx233/SSRT. Graphical abstract: Network architecture of the proposed SSRT model, which consists of multi-kernel Transformer blocks (MKTBs) and crossmerging blocks (CMBs) alterna

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Modeling Local Demand for Mobile Spectrum: An Interpretable Machine Learning Approach

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the communications Society 2025年 6卷 4063-4082页

作者： Parekh, Janaki Yackoboski, Elizabeth Ghasemi, Amir Yanikomeroglu, Halim Communications Research Centre Canada Department of Data Science OttawaONK2H 8S2 Canada Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

With the expansion of 5G networks and the ongoing development of future 6G networks, the demand for mobile spectrum is expected to continue to grow, particularly at a local level. In response, spectrum regulators globally are exhibiting growing interest in enhancing their understanding of current mobile spectrum demand. The goal is twofold: to maximize the socioeconomic benefits of this finite resource and to ensure that spectrum policy and licensing decisions continue to drive innovation within the wireless industry. Despite its importance, research in modeling mobile spectrum demand has been notably scarce, particularly at the granularity required in the spectrum regulatory domain. To address this gap, this paper presents a data-driven approach to estimate localized mobile spectrum demand within the context of spectrum regulation. A novel demand proxy is first introduced, derived from a large and diverse dataset of crowdsourced commercial mobile measurements. Subsequently, spectrum demand modeling is formulated as a regression task and a variety of classical machine learning models are explored, leveraging publicly available geospatial data as input features. The top-performing model successfully achieves an R2 of 0.76 and a Root Mean Square Error of 51.02 on the hold-out test set. Finally, a machine learning interpretability technique is applied to demonstrate how these models can be used for regulatory decision-making, particularly in scenarios requiring transparency and accountability. © 2020 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Quaternion double random phase encoding for privacy-preserving cancelable biometrics

引用

Multimedia Tools and Applications 2024年第37期83卷 85065-85078页

作者： Nasr, Mahmoud Piórkowski, Adam Abd El-Samie, Fathi E. Department of Biocybernetics and Biomedical Engineering AGH University of Krakow Krakow Poland Faculty of Engineering and Technology Future University in Egypt Cairo Egypt Computer Vision Sano Centre for Computational Medicine Kraków Poland Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Manoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Biometrics has become a fundamental aspect in the constantly-changing field of security solutions. Nevertheless, the ongoing risk of hacking and the possibility of biometric data being compromised in security breaches emphasize the urgent need for inventive and reliable biometric authentication methods. Introducing cancelable biometrics is an advanced approach to enhance the security of biometric templates. Our research paper presents a unique variation of this approach that depends on the powerful Double Random Phase Encoding (DRPE) algorithm. By incorporating an auxiliary input biometric template and using quaternion mathematics, we get an exceptional level of performance that surpasses previous performance standards. The cancelable biometric recognition system we present demonstrates exceptional performance in simulation experiments, demonstrating its ability to remain robust even in the presence of noise. More precisely, the proposed cancelable face recognition system attains a notable area under the Receiver Operating Characteristic (ROC) curve of 0.994 and an exceptionally-low Equal Error Rate (EER) of 0.00174. The efficiency of our solution is amazing, with an average time of 0.056263 seconds for each generated secure template. This demonstrates both speed and efficacy in addressing current security concerns. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Fusion Approach for Weakly Supervised Segmentation of MRI Medical Images 17

A Multimodal Fusion Approach for Weakly Supervised Segmentat...

引用

17th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2024

作者： Lu, Yingzhu Tang, Chengyu Wang, Chaoyuan Fan, Yawen Nanjing University of Posts and Telecommunications Department of Computer Science and Technology Nanjing China Nanjing Forestry University Department of Computer Science and Technology Nanjing China School of Communications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9798331507398

Due to the scarcity and high cost of acquiring labeled data in the field of image segmentation, weakly supervised semantic segmentation (WSSS) methods based on Class Activation Mapping (CAM) have been proposed. In the medical image segmentation domain, current research on weakly supervised learning primarily focuses on single-modal methods. However, multimodal imaging provides richer information. Magnetic Resonance Imaging (MRI) is commonly used for brain tumor segmentation. We propose a novel optimized CAM method tailored for MRI brain tumor segmentation, with the core idea being multimodal fusion. Initially, we generate CAM for different MRI modalities (in our experiments, we selected T2 and FIAIR modalities), employing weakly supervised methods. Subsequently, we fuse these CAM to obtain optimized CAM for segmentation. Our method is evaluated on the BraTS dataset, and experimental results demonstrate its superiority over existing techniques at the same level of supervision. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Optimization for Mobile Robot Navigation Based on Path Planning

引用

computers, Materials & Continua 2022年第11期73卷 2241-2255页

作者： El-Sayed M.El-kenawy Zeeshan Shafi Khan Abdelhameed Ibrahim Bandar Abdullah Aloyaydi Hesham Arafat Ali Ali E.Takieldeen Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Computer Science Department College of Engineering and Computer ScienceMustaqbal UniversityBuraidahSaudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Mechanical Engineering Qassim UniversityBuraidah51452Saudi Arabia

Recently,the path planning problem may be considered one of the most interesting researched topics in autonomous *** is why finding a safe path in a cluttered environment for a mobile robot is a significant requisite.A promising route planning for mobile robots on one side saves time and,on the other side,reduces the wear and tear on the robot,saving the capital *** route planning methods for the mobile robot have been developed and *** to our best knowledge,no method offers an optimum solution among the existing *** Swarm Optimization(PSO),a numerical optimization method based on the mobility of virtual particles in a multidimensional space,is considered one of the best algorithms for route planning under constantly changing environmental *** the researchers,reactive methods are increasingly common and extensively used for the training of neural networks in order to have efficient route planning for mobile *** paper proposes a PSO Weighted Grey Wolf Optimization(PSOWGWO)*** is a hybrid algorithm based on enhanced Grey Wolf Optimization(GWO)with *** order to measure the statistical efficiency of the proposed algorithm,Wilcoxon rank-sum and ANOVA statistical tests are *** experimental results demonstrate a 25%to 45%enhancement in terms of Area Under Curve(AUC).Moreover,superior performance in terms of data size,path planning time,and accuracy is demonstrated over other state-of-the-art techniques.

关键词： Mobile robot swarm optimization robot route planning neural networks

来源：评论

学校读者我要写书评

暂无评论

Cancellable Multi-Biometric Feature Veins Template Generation Based on SHA-3 Hashing

引用

computers, Materials & Continua 2023年第1期74卷 733-749页

作者： Salwa M.Serag Eldin Ahmed Sedik Sultan S.Alshamrani Ahmed M.Ayoup Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Robotics and Intelligent Machine Faculty of Artificial IntelligentKafrelsheikh UniversityEgypt Department of Information Technology College of Computer and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Electrical Communications Engineering Faculty of EngineeringMinia UniversityMinia61111Egypt

In this paper,a novel cancellable biometrics technique calledMulti-Biometric-Feature-Hashing(MBFH)is *** MBFH strategy is utilized to actualize a single direction(non-invertibility)biometric *** is a typical model security conspire that is distinguished in the utilization of this protection insurance framework in numerous sorts of biometric feature strategies(retina,palm print,Hand Dorsum,fingerprint).A more robust and accurate multilingual biological structure in expressing human loneliness requires a different format to record clients with inseparable comparisons from individual biographical *** may raise worries about their utilization and security when these spread out designs are subverted as everybody is acknowledged for another biometric *** proposed structure comprises of four sections:input multi-biometric acquisition,feature extraction,Multi-Exposure Fusion(MEF)and secure hashing calculation(SHA-3).Multimodal biometrics systems that are more powerful and precise in human-unmistakable evidence require various configurations to store a comparative customer that can be contrasted with biometric wellsprings of *** top words,biometrics graphs can’t be denied and change to another request for positive Identifications(IDs)while *** biometrics is may be the special procedure used to recognize this issue.

关键词： Feature extraction multi-biometrics SHA-3 MEF

来源：评论

学校读者我要写书评

暂无评论

Remodeling E-Commerce Through Decentralization: A Study of Trust, Security and Efficiency 1

引用

7th International Conference on Microelectronics and Telecommunication engineering, ICMETE 2023

作者： Ahmed, Adnan Shakeel Rizvi, Danish Raza Prasad, Dinesh Khan, Amber Department of Electronics and Communications Engineering Faculty of Engineering and Technology Jamia Millia Islamia New Delhi110025 India Department of Computer Engineering Faculty of Engineering and Technology Jamia Millia Islamia New Delhi110025 India

ISBN: (数字)9789819995622

ISBN: (纸本)9789819995615

While there has been a massive growth in online shopping platforms. There data has been mostly stored in centralized storages which mean they can be an easy target to fraud and theft. It is important to preserve the data of the product and the user in a secure and decentralized manner. With the advent of blockchain technology across the horizon, it is necessary to build a marketplace model that works in a reliable way on this technology while combating the shortcomings of the previous models. Aim of this paper is to address the issues and propose a model that can get reduced fees costs while uploading the data to the blockchain that is uploading the item for sale and while purchasing the item, we also as well as find a solution to collusion from different parties. The end result of this paper should be a fully functional application that is capable of reducing gas fees and increases user reliability on the platform. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Hardware-Trojan Detection by Ensemble Learning Model for Circuits Inserted with a Trojan by an Automated Framework

Evaluation of Hardware-Trojan Detection by Ensemble Learning...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Sho Yoshimi Yuka Ikegami Ryotaro Negishi Kota Hisafuru Nozomu Togawa Department of Computer Science and Communications Engineering Waseda University

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

During the design and manufacturing stages of IoT devices, there is a risk of Hardware Trojans (HTs) being inserted into circuits due to the intervention of outside companies. One method for effectively detecting HTs from gate-level netlists is to use an ensemble learning model. In this paper, we use four ensemble learning models: Random Forest, XGBoost, LightGBM, and CatBoost, and evaluate the accuracy of HT detection by adding a new Trojan circuit generated using an automatic HT generation framework as a netlist for training and evaluation. We also use SMOTE, ADASYN, and Borderline-SMOTE as oversampling methods used in training, and evaluate the HT detection accuracy when the hyperparameters of each method are optimized.

关键词： Training Accuracy Circuits Logic gates Hardware Manufacturing Trojan horses Ensemble learning Integrated circuit modeling Random forests

来源：评论

学校读者我要写书评

暂无评论

Classifying Grape Leaf Disease using an Optimized YOLOv7 Deep Learning Model 4

Classifying Grape Leaf Disease using an Optimized YOLOv7 Dee...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Abraham, John T Hussain, Mohammad Manzoor Srividhya, R. Linda, P Edith Karthik, S. Nareshkumar, R. Bharata Mata College Department of Computer Science Kochi India B v Raju Institute of Technology Department of Computer Science and Engineering Telangana Medak India Dr G R Damodaran College of Science Department of Computer Science Coimbatore India Kristu Jayanti College Department of Computer Science Bengaluru India SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Networking and Communications Tamilnadu Kattankulathur India

ISBN: (纸本)9798331515720

The prevalence of grape leaf diseases has had a profound influence on the worldwide grape industry, resulting in considerable financial setbacks. For effective disease management, it is essential to classify the disease quickly and accurately. This research presents an enhanced YOLOv7 deep-learning model for accurately classifying grape leaf diseases. The dataset is obtained from Kaggle and consists of four categories: black rot, leaf blight, black measles, and healthy. The Adam optimizer is utilized to optimize hyperparameters in order to enhance the performance of the model. The refined YOLOv7 model achieved a remarkable accuracy of 99.24% on the test set, showcasing its potential for detecting grape leaf diseases at an early stage. The model in precision agriculture can aid in the management of grape production, categorization of leaf diseases, and monitoring of operations. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Positioning and Quantification of Cracks by Sensors Using Algorithms 1

引用

International Conference on Sustainable Infrastructure: Innovation, Opportunities and Challenges, SIIOC 2023

作者： Gowda, S. L. Arpitha Ananya, H. Kumar, B. Pradeep Chethan, D.L. Gowda, P. Advith Mahantesh, K. Sugam, K.S. Department of Civil Engineering SJB Institute of Technology Bangalore India Department of Electronics and Communications SJB Institute of Technology Bangalore India Department of Computer Science Engineering SJB Institute of Technology Bangalore India

ISBN: (数字)9789819748440

ISBN: (纸本)9789819748433

A crack or other type of damage causes a sharp discontinuity in the rotational displacement curve of a load-bearing structure. However, if the beam is not sufficiently loaded or the crack depth is very small, the discontinuity may be impossible to detect using conventional methods. To understand cracks in concrete, important parameters such as characteristic length, fracture energy, and critical crack width are used. In this project, the crack width is estimated as either crack mouth opening displacement (CMOD/COD) or crack tip opening displacement (CTOD). This project involves early detection of cracks by sensors and quantification of the cracks with help of algorithms. For the testing, three basic structural members, i.e., concrete cubes, beams, and T-beam are used. Internal cracks are detected by ultrasonic sensors with the help of IoT. A GPS module will be used for finding the position of the cracks and GSM module going to send the SMS to the phone whenever the cracks are formed. To quantify the cracks and show the position of the cracks, algorithms are used. Therefore, to monitor the damages at the early stage thereby avoiding the degradation of the structure, we are proposing a regular monitoring system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fracture energy

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：