检索结果-内蒙古大学图书馆

Deep learning at the service of metaheuristics for solving numerical optimization problems

Neural Computing and Applications 2025年 1-36页

作者： Oyelade, Olaide N. Ezugwu, Absalom E. Saha, Apu K. Thieu, Nguyen V. Gandomi, Amir H. School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Bangladesh Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 United States Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India Faculty of Computer Science Phenikaa University Yen Nghia Hanoi Ha Dong12116 Viet Nam Department of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Integrating deep learning methods into metaheuristic algorithms has gained attention for addressing design-related issues and enhancing performance. The primary objective is to improve solution quality and convergence speed within solution search spaces. This study investigates the use of deep learning methods as a generative model to learn historical content, including global best and worst solutions, solution sequences, function evaluation patterns, solution space characteristics, population modification trajectories, and movement between local and global search processes. An LSTM-based architecture is trained on dynamic optimization data collected during the metaheuristic optimization process. The trained model generates an initial solution space and is integrated into the optimization algorithms to intelligently monitor the search process during exploration and exploitation phases. The proposed deep learning-based methods are evaluated on 55 benchmark functions of varying complexities, including CEC 2017 and compared with 13 biology-based, evolution-based, and swarm-based metaheuristic algorithms. Experimental results demonstrate that all the deep learning-based optimization algorithms achieve high-quality solutions, faster convergence rates, and significant performance improvements. These findings highlight the critical role of deep learning in addressing design issues, enhancing solution quality, trajectory, and performance speed in metaheuristic algorithms. © The Author(s) 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Enhanced Feature Learning for Remote Sensor Image Object Detection

Efficient Enhanced Feature Learning for Remote Sensor Image ...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Chen, Dazhi Gou, Gang State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guizhou Guiyang550025 China

ISBN: (纸本)9789819708543

The realm of computer vision has witnessed a profound interest from the scholarly community in the task of remote sensing object detection. Within this article, we present a pioneering and refined approach to feature learning, wherein we harness the potential of the backbone and neck network. We have devised a sophisticated threshold network for the backbone network, facilitating the extraction of profound insights and bolstering our capacity to acquire features by effectively addressing the challenge of high-noise perturbations present in remote sensing imagery. We propose an upgraded feature network paradigm for the neck network, primarily consisting of the Adaptive Feature Enhanced Module (AFEM) and the Gated Convolution Module (GCM). The AFEM is designed to capture contextual information at larger scales, extending the receptive field and preventing feature resolution degradation. On the other hand, the GCM utilizes gated convolution with high-order spatial interactions to adaptively reduce superfluous semantic information. We have undertaken comprehensive experiments on remote sensing image datasets, including DOTA and HRSC, showcasing the exceptional performance of our approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Symmetric Linear Bandits with Hidden Symmetry 38

Symmetric Linear Bandits with Hidden Symmetry

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tran, Nam Phuong Ta, The Anh Mandal, Debmalya Tran-Thanh, Long Department of Computer Science University of Warwick Coventry United Kingdom CSIRO's Data61 MarsfieldNSW Australia

High-dimensional linear bandits with low-dimensional structure have received considerable attention in recent studies due to their practical significance. The most common structure in the literature is sparsity. However, it may not be available in practice. Symmetry, where the reward is invariant under certain groups of transformations on the set of arms, is another important inductive bias in the high-dimensional case that covers many standard structures, including sparsity. In this work, we study high-dimensional symmetric linear bandits where the symmetry is hidden from the learner, and the correct symmetry needs to be learned in an online setting. We examine the structure of a collection of hidden symmetry and provide a method based on model selection within the collection of low-dimensional subspaces. Our algorithm achieves a regret bound of (Equation presented), where d is the ambient dimension which is potentially very large, and d0 is the dimension of the true low-dimensional subspace such that d0 d. With an extra assumption on well-separated models, we can further improve the regret to (Equation presented). © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visual Comfort Classification for Stereoscopic Videos Based on Two-Stream Recurrent Neural Network with Multi-level Attention 22

Visual Comfort Classification for Stereoscopic Videos Based ...

引用

5th International Conference on Control and computer Vision, ICCCV 2022

作者： Gan, Weize Peng, Danhong Niu, Yuzhen College of Computer and Data Science Fuzhou University China

ISBN: (纸本)9781450397315

Due to the differences in visual systems between children and adults, a professional stereoscopic 3D video may not be comfortable for children. In this paper, we aim to answer whether a stereoscopic video is comfortable for children to watch by solving the visual comfort classification for stereoscopic videos. In particular, we propose a two-stream recurrent neural network (RNN) with multi-level attention for the visual comfort classification for stereoscopic videos. Firstly, we propose a two-stream RNN to extract and fuse spatial and temporal features from video frames and disparity maps. Furthermore, we propose using multi-level attention to effectively enhance the features in frame level, shot level, and finally video level. In addition, to our best knowledge, we establish the first high-definition stereoscopic 3D video dataset for performance evaluation. Experimental results show that our proposed model can effectively classify professional stereoscopic videos into visually comfortable for children or adults only. © 2022 ACM.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Trajectory Tracking System for Zebrafish Based on Embedded Edge Artificial Intelligence 29

A Trajectory Tracking System for Zebrafish Based on Embedded...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zang, Chuanhao Dong, Anming Yu, Jiguo School of Computer Science and Technology Jinan China Big Data Institute Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

Trajectory tracking of zebrafish is an important requirement in studying neurological disorders and developing new psychoactive drug. However, many challenges emerge for stable tracking, since zebrafish are similar in appearance, occlusion, agile, non-linear in moving and easy to swarm, all of which will lead to mistrack for multiple fish. And there is no precedent for tracking zebrafish through embedded edge artificial intelligence device. To overcome these difficulties, we present a tracking system for zebrafish based on RK3588-S. First, We construct an embedded edge AI hardware system consisting of two cameras driven by the RK3588-S, one for the front view and the other for top view of the fish. Then, we develop a 2D tracking algorithm based on YOLOv5 and the Observation-Centric Simple online and real-time tracking (OC-SORT) algorithm, which are transplanted to the RK3588-S for tracking the top and front views of the fish at the edge device. Compared with the previous methods, our method has fewer ID exchanges and highly real-time. Moreover, we apply the MQTT mechanism to establish communication links between the edge and the cloud to reliably transmit data to the cloud. The correspondence between cloud server and embedded AI is 1: N. Finally, we design a multi-view data fusion association algorithm to fuse the data of the two views in the cloud, which are further utilized to build the 3D tracklets of the zebrafish. © 2023 IEEE.

关键词： A Tracking System for Zebrafish Embedded edge artificial intelligence RK3588-S Zebrafish

来源：评论

学校读者我要写书评

暂无评论

Exploring EfficientNet Variants for Image Encoding in Auxiliary Signal Guided Knowledge Encoder-Decoder Framework 9th

Exploring EfficientNet Variants for Image Encoding in Auxili...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Henry, Matthew Martianus Heryanto, Nur Adhianti Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

The growing number of medical images has led to radiologist burnout, which seriously impacts the radiologist's performance. To address the previously mentioned issue, an Auxiliary Signal Guided Knowledge (ASGK) multimodal encoder-decoder framework was designed to automatically generate the medical report based on the proposed medical graph and natural language decoder. It utilizes DenseNet-121 as the image encoder. With DenseNet-121 lack of computational and memory efficiency, this study aims to explore the potential of EfficientNetB0 to EfficientNetB4 as an ASGK image encoder substitute. The framework is trained with IU X-Ray dataset for 30 epochs, with Adam optimizer, a learning rate of 0.01 with 0.8 decay rate, binary cross entropy loss for the medical tags, and cross-entropy loss for the generated medical captions. During the framework training process with each image encoder, the parameter that achieves the highest CIDEr score on the validation set is considered the best image encoder parameter and will be used on the test set. On the test set, EfficientNetB3 as an ASGK image encoder has been shown to increase the CIDEr score to 0.35, a significant increase from the 0.28 CIDEr score obtained by the ASGK using DenseNet-121. This score is only a 1% decrease from the best validation score. It suggests that not only EfficientNetB3 increases the framework's performance, it is also less prone to overfitting. This study has demonstrated that EfficientNetB3 is a potential image encoder substitute for DenseNet-121 in the ASGK framework. © 2024 The Authors.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Localizing Action Moments with Dual-Guidance Augmented Discriminability 2

Localizing Action Moments with Dual-Guidance Augmented Discr...

引用

2nd IEEE International Conference on Image Processing and computer Applications, ICIPCA 2024

作者： Chen, Qiantai Wang, Meiqing Cheng, Hang Chen, Fei Luo, Danni Dong, Yuxin College of Mathematics and Statistics Fuzhou University Fuzhou China College of Computer Science and Big Data Fuzhou University Fuzhou China

ISBN: (纸本)9798350360240

Temporal action detection (TAD) aims at locating the action boundaries and recognizing their categories among video action clips. However, vague boundary predictions suffer from quick switches of short action moments. At the same time, due to the vulnerable boundaries cheated by similar video backgrounds altering instead of the motion, the model's fine-grained discrimination is highly reliant on the background. To mitigate these issues, we present a novel dual-guidance graph-based architecture, dubbed as dual-guidance self-augmented graph network (DSGN). Specifically, we first exploit an effective expansion approach, inserting a full zero gap sequence between the original feature and the enhanced feature to eliminate the effect and increase the localization accuracy of short action boundaries. Then, a relational dual-aggregation method is designed to integrate two levels of context representations, namely, the local fragment-level feature and the global video-level feature, into the target proposal-level feature, based on their attention correlations according to the self-attention mechanism, to augment the destination proposal clip. We demonstrate that our model outperforms other state-of-the-art methods experimentally on HACS, ActivityNet vI.3 and FineActions. © 2024 IEEE.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Designing Smart Grid and Irrigation Management Systems for Information Sharing for Enhanced Efficiency and Sustainability

Designing Smart Grid and Irrigation Management Systems for I...

引用

2023 IEEE International Conference on Modelling, Simulation and Intelligent Computing, MoSICom 2023

作者： Singh, Jagendra Neeraj Garg, Neha Saini, Mayank Singh, Ishaan Mall, Shachi Bennett University School of Computer Science Engineering and Technology Greater Noida India Publicis Sapient Manager Data Science Greater Noida India Galgotias University School of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350393415

In this paper, the Secure Entry Gateway (SEG) was devised and tested, to optimize Smart Grid and Smart Irrigation systems, aiming to assess its efficiency and security in managing data within a home irrigation network. It showed promising results with a data throughput of 98 Mbps and a 97% cyber-Attack detection rate, exceeding expectations. However, a 20% increase in latency and minor command response delays were noted. The user-friendly SEG, with its seamless smartphone interface, represents a shift towards intuitively accessible advanced systems. It serves as a pivotal gatekeeper in an envisioned future of interconnected smart systems, emphasizing balanced functionality and robust security, reaffirming the importance of innovative, secure, and user-friendly systems. © 2023 IEEE.

关键词： Irrigation

来源：评论

学校读者我要写书评

暂无评论

A Multiclass Semi-Supervised Deep Convolutional Generative Adversarial Network for Music Genre Classification Using Mel-Frequency Cepstral Coefficients 2

A Multiclass Semi-Supervised Deep Convolutional Generative A...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Satapathy, Ashutosh Duda, Neelima MacHcha, Jaswanthi Thottempudi, Kokila Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science and Engineering Vijayawada India Velagapudi Ramakrishna Siddhartha Engineering College Department of Artificial Intelligence and Data Science Vijayawada India

ISBN: (纸本)9798350306415

The growing consumer base and expanding market for various music styles highlight the necessity of classifying music genres to cater to people's preferences. Manual music ranking is a labor-intensive process for listeners, prompting the need for a more efficient approach. This involves the extraction of Mel-frequency cepstral coefficient feature maps from the log Mel-spectrograms of audio clips. The extracted feature maps are supplied to a multiclass semi-supervised deep convolutional generative adversarial network where the discriminator behaves as a classifier. The training of models involves utilizing the GTZAN standardized dataset, a publicly accessible collection of thousands of audio files spanning ten different genres, from which 80% and 20% of the data are used for training and testing, respectively. Finally, the paper discusses the performance of the semi-supervised deep convolutional generative adversarial network through the RMSprop and Adam optimizers on the original and augmented labeled and unlabeled MFCC feature maps. Without any data augmentation, the discriminator achieves a training accuracy of 97.9% and a test accuracy of about 45.67%. In contrast, the discriminator's training accuracy is about 98.3%, and the test accuracy is 84.75% with data augmentation. © 2024 IEEE.

关键词： data Augmentation GTZAN Indian Music Genre Mel-frequency Cepstral Coefficients Multiclass Classification Semi-Supervised Deep Convolutional Generative Adversarial Network

来源：评论

学校读者我要写书评

暂无评论

Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise 38

Resfusion: Denoising Diffusion Probabilistic Models for Imag...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Shi, Zhenning Zheng, Haoshuai Xu, Chen Dong, Changsheng Pan, Bin Xie, Xueshuo He, Along Li, Tao Fu, Huazhu College of Computer Science Nankai University China School of Statistics and Data Science Nankai University China Haihe Lab of ITAI China Institute of High Performance Computing A*STAR Singapore

Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the reverse generation process, without modifying the original denoising diffusion process. However, since the degraded images already include low-frequency information, starting from Gaussian white noise will result in increased sampling steps. We propose Resfusion, a general framework that incorporates the residual term into the diffusion forward process, starting the reverse process directly from the noisy degraded images. The form of our inference process is consistent with the DDPM. We introduced a weighted residual noise, named resnoise, as the prediction target and explicitly provide the quantitative relationship between the residual term and the noise term in resnoise. By leveraging a smooth equivalence transformation, Resfusion determine the optimal acceleration step and maintains the integrity of existing noise schedules, unifying the training and inference processes. The experimental results demonstrate that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps. Furthermore, Resfusion can be easily applied to image generation and emerges with strong versatility. Our code and model are available at https://***/nkicsl/Resfusion. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：