检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Songbai Wang, Zeyi Lin, Qiuzhen Chen, Jianyong College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Exploring the complex landscape of constrained multiobjective optimization problems (CMOPs) using evolutionary algorithms presents challenges of harmonizing constraints with optimization objectives. Coevolutionary multitasking (CEMT) emerges as a promising strategy to grapple with these complexities, capitalizing on the potential synergy achievable from distinct yet complementary tasks. Continuing in this research direction, this paper proposes an adaptive CEMT framework, referred to as ACEMT. The goal of ACEMT is to solve CMOPs effeciently by facilitating knowledge sharing from the two adaptive auxiliary tasks that exhibit complementarity to the main task (i.e., the target CMOP). One of these tasks adapts to the evolving landscape by gradually narrowing its constraint boundaries, thus effectively exploring regions with smaller feasible spaces. The second auxiliary task is intentionally structured to focus exclusively on specific constraints, undergoing continuous adaptation throughout the evolutionary process to expedite convergence and uncover potential regions. Moreover, to boost their efficiency, an adaptive constraint relaxation and an adaptive constraint selection strategy are customized for these two auxiliary tasks, respectively. To validate ACEMT's performance, a comprehensive series of experiments is conducted, encompassing three benchmark suites and real-world applications. The experimental findings underscore ACEMT's superiority, as it consistently outperforms or rivals other state-of-the-art related constrained evolutionary algorithms. © 2024, The Authors. All rights reserved.

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

Towards agile collaborative multi-view modeling with inconsistency tolerance

Towards agile collaborative multi-view modeling with inconsi...

引用

2024 Symposium on software Technologies: Applications and Foundations, STAF 2024 Workshops: 2nd International Workshop on Agile Model-Driven engineering, AgileMDE 2024, 1st Large Language Models for Model-Driven engineering Workshop, AgileMDE 2024 and 4th International Workshop on Model-Driven engineering for Smart Internet-of-Things Systems, MeSS 2024

作者： Shahvari, Yaser Sharbaf, Mohammadreza Rahimi, Shekoufeh Kolahdouz Tehrani, Sobhan Yassipour MDSE Research Group Department of Software Engineering University of Isfahan Isfahan Iran School of Arts University of Roehampton London United Kingdom Computer Science Department Faculty of Engineering University College London London United Kingdom

Model-driven engineering (MDE) copes with the complexity of software development by using the principles of separation of concerns and automatic transformation. In MDE, stakeholders from diverse domains collaborate concurrently on different models to quickly analyze, design, and generate complex software-intensive systems. To adopt an agile development approach in MDE, an inconsistency tolerance framework is needed. This framework postpones the resolution phase for incompatibilities caused by online cooperation, allowing temporary incompatibilities to be automatically fixed while requiring resolution only for the remaining conflicts at the appropriate time. In this paper, we propose a general framework for identifying and diagnosing inconsistencies, making decisions regarding inconsistency tolerance or intervention for resolution, and outlining tolerance strategies in agile systems modeled as multi-views. Our framework comprises three primary phases: detection, analysis, and tolerance. It is designed to identify inconsistencies in multi-view models, which are inherently more complex than single-view models. The tolerance phase employs strategies to tolerate inconsistencies, enhancing the flexibility of the agile development approach for collaborative multi-view modeling. © 2024 Copyright for this paper by its authors.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

SLAH: A Siamese Network Vision Tracking Algorithm Using LSTM Adaptive Head 13

SLAH: A Siamese Network Vision Tracking Algorithm Using LSTM...

引用

13th International Conference on Information science and Technology, ICIST 2023

作者： Liu, Zhitao Wang, Dong Luo, Xiaonan Li, Fang School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China College of Mathematics and Informatics College of Software Engineering South China Agricultural Univerrsity Guangzhou China

ISBN: (纸本)9798350313925

In the field of single object tracking, conventional methods often rely on correlation filters or visual image processing. However, these approaches typically focus solely on extracting target object features and consider only the position information in the current frame. They lack integration of contextual and spatial-temporal information, which can limit tracking *** method takes inspiration from single object detection and tracking techniques. It combines efficient model-based object detection with the spatial position of the final target in the image. This approach offers significant advantages in reducing tracking drift (deviation from the target object) and improving tracking accuracy (predicting bounding boxes that closely follow the target).To extract spatial information, we utilize a three-layer ResNet and Convolutional Block Attention Module (CBAM) in conjunction with a siamese network. This combination effectively captures the spatial characteristics of the target object. Additionally, we employ an adaptive processing head with an internal structure of Long Short Term Memory (LSTM) to capture temporal information. By integrating spatial and temporal cues, our method achieves more robust and accurate *** comprehensive comparison and ablation experiments across multiple datasets, we have demonstrated notable improvements with our method. It tightly connects the predicted bounding box with the tracking target and effectively combines spatial and temporal information for precise object tracking. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

AerialFace: A Light Weight Framework for Unmanned Aerial Vehicle Face Recognition

AerialFace: A Light Weight Framework for Unmanned Aerial Veh...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Zhiquan Ou Liang Yao Ting Wu Fan Liu College of Computer Science and Software Engineering Hohai University Nan Jing China

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Unmanned Aerial Vehicle (UAV) are widely applied in multiple fields due to their simple structure and high flexibility. Applying facial recognition technology to UAV can improve their intelligence and diversity of application scenarios. However, UAV face recognition is often hindered by low resolution face, resulting in low accuracy. To alleviate these issues, we propose an efficient face recognition framework named AerialFace. Firstly, we utilize the Residual SRGAN (ResSR-GAN) model to enhance image quality and generate high-resolution face images. Then, we propose Semantic-improved MobileFaceNet (SeMFNet) to relieve the impact of complex backgrounds. Finally, we leverage two pruning algorithms for face detection and recognition models, respectively. It can reduce their parameters to meet the deployment requirements of the algorithm on UAVs. Furthermore, we apply our AerialFace on a UAV face dataset and employ it on an edge computing device. Extensive experiments demonstrate that our approach can effectively improve UAV face recognition accuracy and have real-time performance in embedded UAV devices.

关键词： Performance evaluation Adaptation models Accuracy Face recognition Computational modeling Industry applications Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

A Unified Information Diffusion Prediction Model Based on Multi-task Learning 9th

A Unified Information Diffusion Prediction Model Based on M...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Shang, Yingdan Zhou, Bin Zeng, Xiang Chen, Kai College of Computer Science and Technology National University of Defense Technology Changsha China Key Lab of Software Engineering for Complex Systems School of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9783031466731

The prediction of online information diffusion trends on social networks is crucial for understanding people’s interests and concerns, and has many real-world applications in fields such as business, politics and social security. Existing research on information diffusion prediction has predominantly focused on either macro level prediction of the future popularity of online information or micro level user activation prediction. However, information diffusion prediction on micro or macro level only may lead to one-sided prediction results, and there is a lack of research on implementing micro and macro level diffusion prediction tasks at the same time. Since micro and macro level diffusion prediction tasks are related to each other, we propose a unified information diffusion model which can jointly predicting the micro level user activation probability and macro level information popularity based on multi-task learning framework. We utilize graph neural network to learn user representation from both the information cascades and social network structure. Comparing with micro and macro level baseline methods separately, the prediction results of our proposed model outperform all baseline methods and proves the effectiveness of the proposed method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Self-Attentioned Arcface Towards Improved Efficiency for Deep Face Recognition

SSRN

引用

SSRN 2024年

作者： Xin, Yang Zhou, Yu Jiang, Jianmin College of Computer Science and Software Engineering Shenzhen University Shenzhen518000 China

In this paper, we propose to add a self-attention to the existing ArcFace to alleviate its local restriction and sustain a global correlation in extracting highly discriminative face features. As the introduced self-attention enables the existing ArcFace to focus its extensive learning upon those attentioned regions, our proposed achieves the advantage that its learning intensiveness is enhanced, leading to significant efficiency improvement. To optimize the balance between the existing strength of ArcFace and the added attention, we further introduce a learnable constraint parameter γ to coordinate the influence of attentioned learning. Compared with the existing ArcFace, extensive experiments validate that our proposed SA-ArcFace achieves significantly faster convergence to optimal parameters without compromise on its effectiveness in face recognition. For LFW, specifically, SA-ArcFace achieves 51% faster convergence than ArcFace. For CFP-FP, AGEDB-30, CALFW, and CPLFW, the proposed also achieves 9% to 23% faster convergence than that of ArcFace. © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

CNN Based Multi-Object Segmentation and Feature Fusion for Scene Recognition

引用

computers, Materials & Continua 2022年第12期73卷 4657-4675页

作者： Adnan Ahmed Rafique Yazeed Yasin Ghadi Suliman AAlsuhibany Samia Allaoua Chelloug Ahmad Jalal Jeongmin Park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAl Ain15551UAE Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Engineering Korea Polytechnic UniversitySiheung-siGyeonggi-do237Korea

Latest advancements in vision technology offer an evident impact on multi-object recognition and scene *** sceneunderstanding task is a demanding part of several technologies,like augmented reality-based scene integration,robotic navigation,autonomous driving,and tourist *** visual information in contextually unified segments,convolution neural networks-based approaches will significantly mitigate the clutter,which is usual in classical frameworks during scene *** this paper,we propose a convolutional neural network(CNN)based segmentation method for the recognition of multiple objects in an ***,after acquisition and preprocessing,the image is segmented by using ***,CNN features are extracted from these segmented objects,and discrete cosine transform(DCT)and discrete wavelet transform(DWT)features are *** the extraction of CNN features and computation of classical machine learning features,fusion is performed using a fusion ***,to select theminimal set of features,genetic algorithm-based feature selection is *** order to recognize and understand the multi-objects in the scene,a neuro-fuzzy approach is *** objects in the scene are recognized,the relationship between these objects is examined by employing the object-to-object relation ***,a decision tree is incorporated to assign the relevant labels to the scenes based on recognized objects in the *** experimental results over complex scene datasets including SUN Red Green Blue-Depth(RGB-D)and Cityscapes’demonstrated a remarkable performance.

关键词： Convolutional neural network decision tree feature fusion neurofuzzy system

来源：评论

学校读者我要写书评

暂无评论

VR-Recon: Visual Refiner for Fine-Grained Human Reconstruction

VR-Recon: Visual Refiner for Fine-Grained Human Reconstructi...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Hong Xie Zibin Zhu Xiaoyan Zhang College of Computer Science & Software Engineering Shen Zhen University Shenzhen China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

To reconstruct 3D human figures with fine-grained details from sparse views, this paper proposes a novel framework called VR-Recon, which is based on a viewpoint refiner. In this framework, we first decouple geometric features from multi-scale feature learning by integrating an MSG image encoder, aiming to extract high-quality multi-scale geometric features. Next, we employ a viewpoint refiner to accurately capture critical fine-grained geometric information in each independent view space, thereby avoiding the weighted average fusion of features and eliminating the influence of invalid information. This method is trained using a consistent cosine loss and a cascaded view-space geometric loss. The former encourages the MSG to accurately perceive fine geometric changes from the image, while the latter helps the viewpoint refiner discern critical information in different view spaces. Experimental results demonstrate that, compared to state-of-the-art methods, VR-Recon exhibits robust performance in capturing fine geometric details.

关键词： Representation learning Geometry Visualization Three-dimensional displays Image coding Feature extraction Robustness Digital twins Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Advancements in Cybersecurity Using Deep Learning Techniques Attack Detection for Trojan Horses

Advancements in Cybersecurity Using Deep Learning Techniques...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Hosanna Princye, P. Ahila, A. Lakshmi, A. Anna Ragavendran, N. Purushothaman, K.E. Uma Maheswari, G. Saravanakumar, R. Sri Sairam College of Engineering Department of Electronics and Communication Engineering Anekal Bangalore India R.M.K. Engineering College Department of Information Technology Tamil Nadu Chennai India RMK College of Engineering and Technology Department of Artificial Intelligence and Data Science Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India RMK College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Software Analyst Iconix Software Solution Tamil Nadu Tirunelveli India

ISBN: (纸本)9798350378092

Today's computer networks are threatened by Trojan horse assaults and other cybersecurity dangers. We propose and evaluate deep learning methods using the Kaggle-hosted Trojan Detection dataset to detect Trojan horse assaults. This project uses these approaches. Our malware detection technology uses CNN classification for accuracy. We clean and enhance the dataset to make the model more versatile. Due to extensive testing and optimization, Trojan horse detection rates reach 98.47%. We found that the deep learning architecture accurately identifies malware. We also discuss CNN model features that illuminate Trojan horse attacks. The technique offers complete cyber security and expands our knowledge of harmful software. Deep learning may boost cybersecurity defenses against emerging attacks like Trojan horses, according to our study. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

YOLOv5 for Automatic License Plate Recognition in Smart Cities 4th

YOLOv5 for Automatic License Plate Recognition in Smart Citi...

引用

4th Joint International Conference on Deep Learning, Big Data and Blockchain, DBB 2023

作者： Raza, Abir Badidi, Elarbi Badidi, Basma Al Zahmi, Sarah Department of Computer Science and Software Engineering College of Information Technology UAE University P.O. Box 15551 Al-Ain United Arab Emirates

ISBN: (纸本)9783031423161

Recognition and extraction of license plate information from still images or videos are the basis of modern traffic and security systems. Automatic License Plate Recognition (ALPR) is transforming public safety and transportation in many ways. Such license plate recognition systems enable advanced solutions for toll roads, offer significant operational cost savings through automation, and even open up new market opportunities, such as license plate readers mounted on police vehicles. In this work, we implement license plate recognition based on convolutional neural networks to achieve high accuracy. You Only Look Once (YOLO) algorithm is employed for detection, while, an Optical Character Recognition (OCR) technique is used for text recognition. We use four variants of the YOLOv5 for license plate detection and the EasyOCR for license plate recognition. The results show that YOLOv5x (extra-large) achieves a Mean Average Precision (mAP) of nearly 82% in detecting vehicles and license plates in an image. Furthermore, the recognition of the letters on license plates is achieved with a confidence score of nearly 65%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

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：