检索结果-内蒙古大学图书馆

5th World Conference on Mechanical engineering and Intelligent Manufacturing, WCMEIM 2022

作者： Zhao, Xueyan Zhang, Zhao Niu, Shuqi Tian, Xintong School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9781665473699

In this paper, a novel image encryption algorithm is proposed by combining Logistic chaotic map, 4D NHS hyperchaotic system, compressed sensing (CS), computer generated hologram (CGH) and two-dimensional discrete cosine transform (DCT). Firstly, the gray image is sparse represented by two-dimensional discrete cosine transform (DCT). The sparse matrix obtained by index sort scrambling is scrambled. For further encryption, the pixel scrambling uses the Logistic chaotic system to generate the scrambling vector. Subsequently, CGH encryption was performed and the Logistic chaotic map and 4D NHS hyperchaotic system were used as double keys to obtain the final encrypted picture. © 2022 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Research on ship detection of optical remote sensing image based on Yolo V5

Research on ship detection of optical remote sensing image b...

引用

2021 International Conference on Intelligent Power and Systems, ICIPS 2021

作者： Sun, X.M. Zhang, Y.J. Wang, H. Du, Y.X. School of Computer Science and Software Engineering University of Science and Technology Liao Ning China

In order to achieve ship target detection based on remote sensing images in complex backgrounds, this paper proposes a ship target detection algorithm based on YOLO V5. First, the improved Kmeans is used to cluster the data set, DIOU_loss is used for the candidate frame selection strategy, and finally the channel attention mechanism is introduced. The experimental results show that under the same conditions, the improved network has a slight decrease in detection speed compared with the original YOLOv5 network, and the effect of images with densely distributed small targets is significantly improved. On the same test set, the accuracy rate is reduced by 3.84%, the recall rate is increased by 32.73%, and mAP is increased by 22.48%. © Published under licence by IOP Publishing Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis in social internet of things using contextual representations and dilated convolution neural network

引用

Neural Computing and Applications 2024年第20期36卷 12357-12370页

作者： Abid, Fazeel Rasheed, Jawad Hamdi, Mohammed Alshahrani, Hani Al Reshan, Mana Saleh Shaikh, Asadullah Department of Information Systems Dr. Hassan Murad School of Management University of Management and Technology Lahore Pakistan Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul34303 Turkey Department of Software Engineering Istanbul Nisantasi University Istanbul34394 Turkey Department Computer Science College of Computer Science and Information Systems Najran University Najran61441 Saudi Arabia Department Information Systems College of Computer Science and Information Systems Najran University Najran61441 Saudi Arabia

The methodologies based on neural networks are substantial to accomplish sentiment analysis in the Social Internet of Things (SIoT). With social media sentiment analysis, significant insights can produce efficient and intelligent applications. Neural networks such as recurrent neural networks (RNNs) and convolution neural networks (CNNs) have been considered widely in many text classification tasks. However, RNNs are computationally expensive and require complex training to capture contextual information and long-term dependencies. Similarly, traditional CNNs must stack multiple convolutional layers, requiring massive computations and additional parameters. To address these problems, this work initialized the novel architecture, in which contextual representations (CRs) based on the textual framework are proposed at the initial step. In CRs, state-of-the-art word representation models, such as GloVe (global vectors) and FastText (subword information), collectively produce word representations upon the input sequence using a weight mechanism. Secondly, a unique way is introduced: a three-parallel layered dilated convolutional network with global mean pooling. The experimental results show that the proposed methods when compared with baseline methods, the dilation in CNNs following CRs significantly increases the accuracy from 72.45 to 98.98% and reduces computational resources. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Research and application of data-driven carbon emission analysis and prediction 2

Research and application of data-driven carbon emission anal...

引用

2nd International Conference on Cloud Computing, Big Data Application and software engineering, CBASE 2023

作者： Wei, Dongmei Meng, Dan Southwest University of Finance and Economics School of Management Science and Engineering Chengdu611130 China Xihua University School of Computer and Software Engineering Chengdu610039 China

ISBN: (纸本)9798350331448

The issue of carbon emissions has become an important policy direction for countries around the world to promote healthy socio-economic development and address climate change issues. This article conducts feature extraction and data analysis on various major energy data in China from 1997 to 2017, and constructs a model for verifying and predicting total carbon emissions. The model can not only accurately reflect China's carbon emissions over the past twenty years, but also predict future carbon emissions. This not only provides scientific basis for government decision-making, but also enriches the application of data-driven and artificial intelligence methods in this field. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Improved Kernel Fuzzy C-Means Clustering Method Based on Smart Grid 5

Improved Kernel Fuzzy C-Means Clustering Method Based on Sma...

引用

5th World Conference on Mechanical engineering and Intelligent Manufacturing, WCMEIM 2022

作者： Niu, Shuqi Zhang, Zhao Tian, Xintong Zhao, Xueyan School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9781665473699

The improved kernel fuzzy clustering method is used to classify the load data of the smart grid accurately. It lays a good foundation for the subsequent work of power load forecasting and provides a more efficient, safe, and reliable direction for the operation of the power system. Firstly, the collected power load data is preprocessed to reduce data redundancy and improve data quality. Secondly, the kernel fuzzy C-means clustering algorithm based on particle swarm optimization is used to cluster the load data with the same power consumption characteristics. Finally, the improved kernel fuzzy clustering method is compared with the fuzzy C-means clustering method through a simulation example to verify the effectiveness of this method. © 2022 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

EEG-EMG FAConformer: Frequency Aware Conv-Transformer for the fusion of EEG and EMG

EEG-EMG FAConformer: Frequency Aware Conv-Transformer for th...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： He, ZhengXiao Cai, Minghong Li, Letian Tian, Siyuan Dai, Ren-Jie Tongji University College of Electronic and Information Engineering Shanghai China Tongji University School of Software Engineering Shanghai China Shanghai Jiao Tong University Department of Computer Science and Engineering China

ISBN: (纸本)9798350386226

Motor pattern recognition paradigms are the main forms of Brain-computer Interfaces(BCI) aimed at motor function rehabilitation and are the most easily promoted applications. In recent years, many researchers have suggested encouraging patients to perform real motor control execution simultaneously in MI-based BCI rehabilitation training systems. Electromyography (EMG) signals are the most direct physiological signals that can assess the execution of movements. Multimodal signal fusion is practically significant for decoding motor patterns. Therefore, we introduce a multimodal motion pattern recognition algorithm for EEG and EMG signals: EEG-EMG FAConformer, a method with several attention modules correlated with temporal and frequency information for motor pattern recognition. We especially devise a frequency band attention module to encode EEG information accurately and efficiently. What's more, modules like Multi-Scale Fusion Module, Independent ChannelSpecific Convolution Module(ICSCM), and Fuse Module which can effectively eliminate irrelevant information in EEG and EMG signals and fully exploit hidden dynamics are developed and show great effects. Extensive experiments show that EEGEMG FAConformer surpasses existing methods on Jeong2020 dataset, showcasing outstanding performance, high robustness and impressive stability. © 2024 IEEE.

关键词： Electromyography

来源：评论

学校读者我要写书评

暂无评论

Unconditional Generation of Scalable Chinese Characters as Bézier Curve Sequences 3

Unconditional Generation of Scalable Chinese Characters as B...

引用

3rd International Conference on Artificial Intelligence and Signal Processing, AISP 2023

作者： Lasrado, Rohan Nolan Vijayasherly, V. VIT University School of Computer Science and Engineering Vellore India VIT University Department of Software Systems Vellore India

ISBN: (纸本)9798350320749

Neural generative modelling of sketches has been an active research direction. SketchRNN set a milestone with their sequence-to-sequence variational autoencoder architecture being able to generate hand drawn sketches in various classes by modelling them as sequences of displacements between consecutive stroke points. The diversity and variety in the set of handwritten Chinese characters makes them a good candidate for such generative modelling enabling their unconditional generation. However, modelling them as sequences of points causes coarse looking strokes and much longer sequences, consequently requiring use of polygonal approximation algorithms to cut down on points. Instead, we propose and investigate the modelling of Chinese characters as sequences of Bézier curves using the SketchRNN architecture with a few modifications, to allow the model to directly generate smooth curves. This way the encoded representation is smaller while more of the stroke's characteristics are retained and the generated characters are truly scalable. We also suggest the appropriate preprocessing strategy for the KanjiVG dataset to make it suitable for this purpose. Qualitative evaluation of the results suggests the model demonstrates generation of characters with mostly well-structured and ordered strokes. This was substantiated by quantitative evaluation based on the FrFréchetchet Inception Distance score. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control for a Second-order Chaotic System with Unknown Nonsymmetric Actuator Dead-Zone 5

Adaptive Control for a Second-order Chaotic System with Unkn...

引用

5th World Conference on Mechanical engineering and Intelligent Manufacturing, WCMEIM 2022

作者： Tian, Xintong Zhang, Zhao Niu, Shuqi Zhao, Xueyan School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9781665473699

In this paper, an adaptive controller design method is proposed for chaotic systems with unknown actuator dead-zone. First, the terminal sliding mode (TSM) manifold is proposed to ensure exponential stability as well as faster finite-time stability. In addition, a neural network (NN) is introduced to estimate the partially unknown nonlinear dynamic behavior of the object, and according to the implicit function theorem, the unknown asymmetric dead zone of the actuator is overcome by another static neural network. Furthermore, a robust terminology updated online deals with refactoring errors and external interferences of neural networks. Finally, the system can stably track any smooth target trajectory online is rigidly proved via Lyapunov analysis, and numerical simulation shows its effectiveness and feasibility. © 2022 IEEE.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

MKGL: Mastery of a Three-Word Language 38

MKGL: Mastery of a Three-Word Language

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guo, Lingbing Bo, Zhongpu Chen, Zhuo Zhang, Yichi Chen, Jiaoyan Lan, Yarong Sun, Mengshu Zhang, Zhiqiang Luo, Yangyifei Li, Qian Zhang, Qiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China Department of Computer Science The University of Manchester United Kingdom School of Computer Science and Engineering Beihang University China School of Computer Science Beijing University of Posts and Telecommunications China School of Software Technology Zhejiang University China

Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In this paper, we investigate the integration of LLMs with KGs by introducing a specialized KG Language (KGL), where a sentence precisely consists of an entity noun, a relation verb, and ends with another entity noun. Despite KGL's unfamiliar vocabulary to the LLM, we facilitate its learning through a tailored dictionary and illustrative sentences, and enhance context understanding via real-time KG context retrieval and KGL token embedding augmentation. Our results reveal that LLMs can achieve fluency in KGL, drastically reducing errors compared to conventional KG embedding methods on KG completion. Furthermore, our enhanced LLM shows exceptional competence in generating accurate three-word sentences from an initial entity and interpreting new unseen terms out of KGs. © 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

Device Action Prediction Based on K-means and Apriori for Smart Home

Device Action Prediction Based on K-means and Apriori for Sm...

引用

2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and computers, IPEC 2022

作者： Liu, Qinghua Shi, Tianwei Ren, Ling University of Science and Technology Liaoning School of Computer Science and Software Engineering Anshan China

ISBN: (纸本)9781665409025

This paper proposes to use K-means and Apriori to prediction device action based on time in Smart Home System. In the existing methods, the system provides services to human when conditions are met, such as high temperature and low humidity. However, those methods ignoring the correlation between device action and human activity time. In order to solve this problem, we combine K-means and Apriori algorithm to generate association rules with time information. First, calculate the appropriate K-value for K-means. We select consecutive data in weeks. The data contains the time information of device action. Second, run K-means to classify based on device action time information, and run Apriori to mine association rules based on classification. Finally, decode the associate rules and realize device action prediction. In our work, K-means experiments show that clustering according to the difference of working days is an effective way to process user time information;Apriori experiments proved that the association rules mined with the results of K-means can predict device actions in the Smart Home environment. © 2022 IEEE.

关键词： Automation

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：