检索结果-内蒙古大学图书馆

Scale adaptive fitness evaluation‐based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 849-862页

作者： Ye‐Qun Wang Jian‐Yu Li Chun‐Hua Chen Jun Zhang Zhi‐Hui Zhan School of Computer Science and Engineering South China University of TechnologyGuangzhouChina School of Software Engineering South China University of TechnologyGuangzhouChina Hanyang University AnsanSouth Korea

Research into automatically searching for an optimal neural network(NN)by optimi-sation algorithms is a significant research topic in deep learning and artificial ***,this is still challenging due to two issues:Both the hyperparameter and ar-chitecture should be optimised and the optimisation process is computationally *** tackle these two issues,this paper focusses on solving the hyperparameter and architecture optimization problem for the NN and proposes a novel light‐weight scale‐adaptive fitness evaluation‐based particle swarm optimisation(SAFE‐PSO)***,the SAFE‐PSO algorithm considers the hyperparameters and architectures together in the optimisation problem and therefore can find their optimal combination for the globally best ***,the computational cost can be reduced by using multi‐scale accuracy evaluation methods to evaluate ***,a stagnation‐based switch strategy is proposed to adaptively switch different evaluation methods to better balance the search performance and computational *** SAFE‐PSO algorithm is tested on two widely used datasets:The 10‐category(i.e.,CIFAR10)and the 100−cate-gory(i.e.,CIFAR100).The experimental results show that SAFE‐PSO is very effective and efficient,which can not only find a promising NN automatically but also find a better NN than compared algorithms at the same computational cost.

关键词： deep learning evolutionary computation hyperparameter and architecture optimisation neural networks particle swarm optimisation scale‐adaptive fitness evaluation

来源：评论

学校读者我要写书评

暂无评论

LSRN-AED: lightweight super-resolution network based on asymmetric encoder–decoder

引用

Soft Computing 2024年第13-14期28卷 8513-8525页

作者： Huang, Shuying Li, Wei Yang, Yong Wan, Weiguo Lai, Houzeng School of Software Tiangong University Tianjin300387 China School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics Nanchang330032 China School of Computer Science and Technology Tiangong University Tianjin300387 China

Due to limited memory and computing resources, the application of deep neural networks on embedded and mobile devices is still a great challenge. To tackle this problem, this paper proposes a lightweight super-resolution network based on asymmetric encoder–decoder (LSRN-AED), which achieves better performance while reducing model parameters and computation. On the basis of rethinking the roles of encoder and decoder, an asymmetric encoder–decoder (AED) composed of complex encoders and simple decoders is designed to achieve feature extraction and reconstruction. Here, the decoder only adopts one inverted residual block, which can reduce the computational cost of the model and the redundancy of mapping features. For the encoder, inspired by the Transformer structure, an epiphany encoder is designed to realize the feature extraction and representation. In the encoder, a multi-way epiphany attention module (MEAM) is constructed, in which inverted residual blocks are used to replace traditional residual blocks to extract features and reduce model complexity. To realize the selection and enhancement of spatial features, an epiphany attention block (EAB) is designed by exploiting depth-wise convolutions which can learn the significant spatial information of the feature maps. Experimental results demonstrate that the proposed LSRN-AED can achieve better performance at lower parameter cost and outperform some existing state-of-the-art lightweight models. For example, compared to the advanced SMSR method, the proposed LSRN-AED has better evaluation metrics while reducing the number of parameters by 45%, 44%, and 44%, and FLOPs by 44%, 42%, and 41% on the × 2/3/4 SR tasks, respectively. The code will be published on GitHub after our paper is accepted for publication. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Chinese Speech Recognition Method Based on the Squeezeformer Model

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第1期52卷 23-31页

作者： Guo, Ying Wang, Li School of Computer Science and software Engineering University of Science and Technology Liaoning Anshan114051 China College of Computer Science and Technology Liaoning Anshan114051 China

End-to-end training has emerged as a prominent trend in speech recognition, with Conformer models effectively integrating Transformer and CNN architectures. However, their complexity and high computational cost pose deployment challenges. To address these issues, we propose a multi-task Chinese speech recognition method based on the Squeezeformer model. We replace the FMCF structure in Conformer with an MF/CF structure, leveraging the convolutional module as a local Multi- Head Attention (MHA) module to enhance efficiency. Multilevel down-sampling and up-sampling using a time-series U-Net further reduce computational costs. By eliminating redundant LayerNorm layers and employing depthwise separable convolutions, we streamline the model, reduce parameters, and lower deployment costs. An Adaptor Layer is integrated into the MHSA module to mitigate the vanishing gradient problem, and a ScaleVar Layer is added to enhance flexibility. Additionally, the RealFormer module is introduced on the decoding side to improve context understanding. Combining Connectionist Temporal Classification (CTC) with attention-based encoding and decoding models for multi-task learning improves performance and accuracy. Experimental results show that the proposed method reduces the parameters on AISHELL-1 dataset by 16% and reduces the character error rate to 5.50%. At the same time, it also shows good performance on AISHELL-2 dataset. © (2025), (International Association of Engineers). All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Reflective clothing detection based on YOLOv5s fused with SE attention mechanism

引用

International Journal of Reasoning-based Intelligent Systems 2025年第1期17卷 9-16页

作者： Wang, Yuanyuan Gu, Dingyun Zhu, Yemeng Zhang, Zhihan Cao, Jiahui Zhang, Haiyan School of Computer and Software Engineering Huaiyin Institute of Technology Huaian223001 China Engineering Laboratory of Mobile Interconnection Technology for Internet of Things Jiangsu Province Huai’an Huaian City223001 China

This paper proposes a YOLOv5s deep learning algorithm incorporating the SE attention mechanism to address the issue of workers failing to wear reflective clothing on duty, which has resulted in casualties from time to time. The YOLOv5s model is used to train the reflective clothing dataset obtained by collecting images of construction sites, and the SE attention mechanism module is added to the network structure of YOLOv5 for improved performance. The reflective clothing detection algorithm is then deployed to the web for real-time detection. The experimental results show that the algorithm achieves mAP value of 96.70% with the SE attention module, resulting in an accuracy improvement of 1.09% compared to the model without the SE module. This enables practical applications to reduce the incidence of construction accidents at construction sites. Coрyright © 2025 Inderscience Enterрrises Ltd.

关键词： attention mechanism flask reflective clothing detection vue YOLOv5

来源：评论

学校读者我要写书评

暂无评论

Research of news text classification method based on hierarchical semantics and prior correction

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8185-8203页

作者： Sun, Ping Song, LinLin Yuan, Ling Yu, Haiping Wei, Yinzhen Wuhan Vocational College of Software and Engineering Hubei Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Hubei Wuhan China

News text is an important branch of natural language processing. Compared to ordinary texts, news text has significant economic and scientific value. The characteristics of news text include structural hierarchy, diverse label categories, and limited high-quality annotation samples. Many machine learning and deep learning methods exist to analyze various forms of news text. However, due to label imbalance, hierarchical semantics, and confusing labels, current methods have limitations. Therefore, this paper proposes a news text classification framework based on hierarchical semantics and prior correction (HSPC). Firstly, data augmentation is used to enhance the diversity of the training set and adversarial learning is employed to improve the resistance of the model with its robustness. Then, a hierarchical feature extraction approach is employed to extract semantic features from different levels of news texts. Consequentially, a feature fusion method is designed to allow the model to focus on relevant hierarchical semantics for label classification. Finally, highly confusing label predictions are corrected to optimize the label prediction of the model and improve confidence. Multiple experiments are performed on four widely used public datasets. The experimental results indicate that HSPC achieves higher classification accuracy compared to other models. On the FCT, AGNews, THUCNews, and Ohsumed datasets, HSPC improves the accuracy by 1.03%, 1.38%, 2.55%, and 1.15%, respectively, compared to state-of-the-art methods. This validates the rationality and effectiveness of the designed mechanisms. © 2024 - The authors. Published by IOS Press.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A grid planning method for large urban rail transit using hybrid genetic algorithm

Advances in Transportation Studies

引用

Advances in Transportation Studies 2023年第Special Issue期3卷 67-78页

作者： Han, L.D. Yang, J. Wang, J. School of Mechanical and Electrical Engineering Suzhou Global Institute of Software Technology Suzhou215163 China

In response to the shortcomings of existing rail transit grid planning methods such as longer route lengths and longer travel times, this paper applies a hybrid genetic algorithm to design a large-scale urban rail transit grid planning method. Firstly, the transportation efficiency of the transportation grid is taken as the main objective function, and genetic algorithm coding is adopted, Then, a fitness function is designed to optimize the objective function through crossover, mutation operations, and elite retention strategies, Finally, the immune clone algorithm is introduced to obtain the final grid planning results for large-scale urban rail transit. Through experiments, it has been proven that the total length of the line in this article is 118.37km, with a total number of 56 stations. The total length of the line is the shortest, and the travel time is always less than 42min, which has high travel efficiency and good planning effect. © 2023, Aracne Editrice. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Music source separation via hybrid waveform and spectrogram based generative adversarial network

引用

Multimedia Tools and Applications 2024年 1-15页

作者： Wu, Qiuxia Deng, Haipeng Hu, Kun Wang, Zhiyong School of Software Engineering South China University of Technology Guangdong Province Guangzhou China School of Computer Science The University of Sydney SydneyNSW Australia

Music source separation aims to disentangle individual sources from the mixture of musical signals. Existing generative adversarial network (GAN) based methods generally work on the spectrogram domain only. However, this practice ignores the patterns from the waveform domain, which are more informative for modelling some categories of sources. In this paper, we propose a fully hybrid GAN framework to integrate knowledge from both domains. In particular, the generator formulates acoustical patterns from waveform and spectrogram domains, while the discriminator provides discriminative information based on the local patch-level spectrograms such that the generator can produce more plausible separation results. Furthermore, to enhance the quality of estimated sources, we devise a perceptual spectrogram loss term, which is a complement of the waveform-level loss. The proposed method is evaluated on two widely used music source separation datasets, producing music sources of high signal-to-distortion ratio (12.03 in MIR-1K dataset and 8.08 in MUSDB18 dataset). These results demonstrate the superiority of the proposed method compared with the state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Uvcgan-Dehaze: a dehazing method for unpaired images

引用

Soft Computing 2024年第20期28卷 12217-12226页

作者： Li, Canlin Zhang, Xiangfei Zhang, Wenjiao Su, Haowen Bi, Lihua School of Computer Science and Technology Zhengzhou University of Light Industry Zhengzhou China School of Software Engineering Zhengzhou University of Light Industry Zhengzhou China

To solve the problems of feature loss and color difference after image dehazing and poor dehazing effect in real hazy images, a method UVCGAN-Dehaze is proposed for unpaired image dehazing. In the proposed model, the generator learns the relationship between image features and low-frequency features at multiple scales by combining the U-Net with the transformer. We strengthen the connection between spatial and channel features by adding Convolutional Block Attention Module(CBAM) before the skip connection of each layer of U-Net of the generator and adaptively adjusting the weight allocation of the feature map, so that the image after dehazing can better retain the detailed information of the image. Simultaneously, in order to reduce the feature loss and color difference after image dehazing, we propose a loss function named Feature Laplacian Perception (FLP) loss, which jointly constrains the generator by fusing the perception loss and Laplacian loss, so that the generated image reduces the feature loss and color difference. The method not only generates dehazing images with high perceptual quality in terms of important regions and details, but also avoids content and color loss. Extensive experiments verify the effectiveness of the method on synthetic images and real hazy images, and the proposed method achieves better dehazing results when compared with the experimental results of previous typical methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

A Secure Mutual Authentication Protocol Based on Visual Cryptography Technique for IoT-Cloud

引用

Chinese Journal of Electronics 2024年第1期33卷 43-57页

作者： Brou Bernard Ehui Chen CHEN Shirui WANG Hua GUO Jianwei LIU School of Cyber Sciences and Technology Beihang University State Key Laboratory of Software Development Environment Beihang University Sino-French Engineering School Beihang University Beihang Hangzhou Innovation Institute Yuhang

Because of the increasing number of threats in the IoT cloud, an advanced security mechanism is needed to guard data against hacking or attacks. A user authentication mechanism is also required to authenticate the user accessing the cloud services. The conventional cryptographic algorithms used to provide security mechanisms in cloud networks are often vulnerable to various cyber-attacks and inefficient against new attacks. Therefore,developing new solutions based on different mechanisms from traditional cryptography methods is required to protect data and users' privacy from attacks. Different from the conventional cryptography method, we suggest a secure mutual authentication protocol based on the visual cryptography technique in this paper. We use visual cryptography to encrypt and decrypt the secret images. The mutual authentication is based on two secret images and *** user requests the ticket from the authentication server(AS) to obtain the permission for accessing the cloud services. Three shared secret keys are used for encrypting and decrypting the authentication process. We analyze the protocol using the Barrows-Abadi-Needham(BAN)-logic method and the results show that the protocol is robust and can protect the user against various attacks. Also, it can provide a secure mutual authentication mechanism.

关键词： Internet of things Visual cryptography Security Mutual authentication IoT-cloud

来源：评论

学校读者我要写书评

暂无评论

Developing a comprehensive service quality model for online to offline e-commerce platforms using a hybrid model

引用

Electronic Commerce Research 2024年 1-30页

作者： Shao, QiGan Liou, James J. H. Weng, SungShun Jiang, HongBo Shao, Ting Lin, ZhenWen School of Economics and Management Xiamen University of Technology Xiamen China Department of Industrial Engineering and Management National Taipei University of Technology Taipei Taiwan Department of Information and Finance Management National Taipei University of Technology Taipei Taiwan Department of Software Engineering Xiamen Institute of Software Technology Xiamen China

One of the impacts of the COVID pandemic has been to force people to find alternates sources for daily supplies, turning to online to offline (O2O) platforms. The service quality of the O2O platform naturally affects the satisfaction which in turn has an impact on customer retention. The aim of this study is to evaluate the service quality of O2O platform to find strategies to improve consumer satisfaction. This study proposed a hybrid RS-DANP-CoCoSo model, which applies the rough set (RS) method to obtain the factors which influence the service quality of O2O platforms. The Analytic Network Process based on the Decision-making Trial and Evaluation Laboratory method (DANP) is applied to obtain the relationships and weights of the factors. The results indicate that empathy, social interaction and recommendation quality are the three most important factors. The practicability of our evaluation model is verified using the combined compromise solution (CoCoSo) method to evaluate the service quality of four O2O platforms in China. The hybrid model proposed in this study is applied to evaluate and diagnose online consumer satisfaction levels, providing personalized solutions for merchants to improve services. Finally, management implications based on the findings are also discussed. © 2024, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Rough set theory

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：