检索结果-内蒙古大学图书馆

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Yang, Dan Peng, Xin Su, Cheng Tan, Dayu Chen, Chaoyang Zhong, Weimin Ministry of Education East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai200237 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Anhui Hefei230601 China School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9798350361674

Transfer learning aims to leverage the knowledge of the source domain to help the learning of unlabeled target domain models. However, all conventional transfer learning methods assume that samples from source and target domains are always freely accessible. However, this assumption is rarely plausible in real-world due to data privacy. To combat this challenge, we introduce Structure-constrain Source Free Domain Adaptation with regularized Knowledge Distillation of source model (SSFDA-KD). Our method is based on the observations that a deterministic classification result can be obtained when the target data distribution aligns with the source data distribution, and a well-trained model not only yields a deterministic classification for a sample but also has clear category boundaries, which implies samples that are close together belong to the same category. From those, we first generate the source model with labeled source data, which is regarded as a well-trained model. Then, we identify target prototypes with lower self-entropy and assign the pseudo-labels to other samples according to the neighborhood structure. Finally, we refine the target model by minimizing prediction loss, constraining internal structure via triplet loss, and reducing knowledge distillation loss. Experiments of fault diagnosis based on WWTPs are conducted to validate its effectiveness. © 2024 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Frontal person image generation based on arbitrary-view human images

Frontal person image generation based on arbitrary-view huma...

引用

作者： Zhang, Yong Zhang, Yuqing Chen, Lufei Yin, Baocai Sun, Yongliang Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Department of Information Science Beijing University of Technology Beijing China China Electronics Technology Group Taiji Co LTD Beijing China

Frontal person images contain the richest detailed features of humans, which can effectively assist in behavioral recognition, virtual dress fitting and other applications. While many remarkable networks are devoted to the person image generation task, most of them need accurate target poses as the network inputs. However, the target pose annotation is difficult and time-consuming. In this work, we proposed a first frontal person image generation network based on the proposed anchor pose set and the generative adversarial network. Specifically, our method first classify a rough frontal pose to the input human image based on the proposed anchor pose set, and regress all key points of the rough frontal pose to estimate an accurate frontal pose. Then, we consider the estimated frontal pose as the target pose, and construct a two-stream generator based on the generative adversarial network to update the person's shape and appearance feature in a crossing way and generate a realistic frontal person image. Experiments on the challenging CMU Panoptic dataset show that our method can generate realistic frontal images from arbitrary-view human images. © 2024 John Wiley & Sons Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Abstractive Text Summarization Model Based on BERT Vectorization and Bidirectional Decoding

Abstractive Text Summarization Model Based on BERT Vectoriza...

引用

2023 International Conference on Cyber Security, Artificial Intelligence, and Digital Economy, CSAIDE 2023

作者： Teng, Keliang Qiang, Baohua Wang, Yufeng Yang, Xianyi Wang, Yuemeng Wang, Chen Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC Shijiazhuang050081 China

ISBN: (纸本)9781510666597

Facing the pressure of the extremely inflated network information and data overload surplus, it is extremely important to locate "valuable information" efficiently and accurately. Text summarization technology in the field of Natural Language Processing (NLP) is an effective means to analyze and process network information. In this paper, we propose an abstractive text summarization model based on bidirectional encoder representations from transformers (BERT) vectorization and bidirectional decoding. The BERT is adopted to obtain a more global vector representation, which helps the subsequent encoder and decoder to fuse the full-text information to generate a summary with high generality. The decoding phase adopts a bidirectional decoding structure and combines the attention mechanism to maintain the bilateral decoding result to generate summaries. The bidirectional decoding structure can be fine-tuned according to the bidirectional results, which can overcome the tilt problem of the unidirectional structure, and the generated summaries are more consistent. The experimental results on the NLPCC2017 text summarization dataset show that the summaries generated by our model have the higher coherence at the word and sentence level, and the stronger generalization of the full text. © 2023 SPIE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Location Data Publishing Mechanism in Semi-Trusted Vehicle Networks based on Differential Privacy

Location Data Publishing Mechanism in Semi-Trusted Vehicle N...

引用

2024 International Conference on Mechatronics and intelligent Control, ICMIC 2024

作者： Zhao, Zheng Zhang, Tianhao Mao, Qian Zhao, Qi Xie, Xin Dalian Maritime University Dalian China Liaoning University Shenyang China Northeastern University Shenyang China Hunan University of Information Technology Changsha China Hunan Province Higher Education Key Laboratory of Intelligent Sensing and Computing Changsha China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

Vehicular ad-hoc networks (VANETs) are essential in mobile ad-hoc network applications, utilizing vehicle location data. However, safeguarding the privacy and security of this data is challenging, especially with untrusted roadside units. To address this, we propose a novel differential privacy-based location data publishing mechanism. It consists of three key components: dynamic group leader selection, data aggregation, and privacy-preserving data publishing. The group leader selection algorithm is based on directional thresholds, hop cycles, and lifespans, assuming semi-trusted vehicles. Additionally, the differential privacy-based algorithm uses map grid segmentation, privacy budget recovery, and a filtering mechanism to ensure location privacy. Comparative experiments show that our scheme outperforms existing models in total hops, group leader lifetime, and mean absolute error. © 2025 SPIE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

引用

2024 China Automation Congress, CAC 2024

作者： Lang, Yumin Wu, Jiande Lang, Xun Yu, Wanke Yang, Chuanyan Su, Hongye Department of Electronic Engineering Information School Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Automation China University of Geosciences Wuhan China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350368604

Oscillation is a significant indication of the deterioration of control system performance and needs to be carefully monitored to ensure safe and stable process operations. However, industrial processes are often prone to noisy artifacts and nonstationary trends, resulting in low signal-to-noise ratios. In order to tackle this problem, this study introduces a novel framework for enhanced trend removal and noise reduction, which is featured by the following steps:(i) The circulant singular spectrum analysis (CiSSA) is used to decompose oscillation data into several reconstructed components (RCs). (ii) The estimated power spectral density (PSD) ofthese RCs is then smoothed using the Savitzky-Golay filter (SGF) to eliminate noise and identify the RCs corresponding to oscillatory components. (iii) These identified RCs are subsequently reconstructed to produce purified oscillatory data. The effectiveness of the suggested approach is validated using simulations and real-world industrial case studies. The findings indicate that the method notably enhances the quality of oscillatory data. © 2024 IEEE.

关键词： Power spectral density

来源：评论

学校读者我要写书评

暂无评论

Short-term power load forecasting based on TCN-LSTM model 3

Short-term power load forecasting based on TCN-LSTM model

引用

3rd International Conference on Energy, Power and Electrical technology, ICEPET 2024

作者： Xu, Xinyu Zhou, Zhenliu Zhao, Huaxin Electrical Engineering College of Shenyang Institute of Engineering Shenyang China Shenyang Key Laboratory of Energy Internet Intelligent Perception and Security Technology Shenyang China Information College of Shenyang Institute of Engineering Shenyang China

ISBN: (纸本)9798350352658

In order to improve the accuracy of short-term power load forecasting and provide a stronger guarantee for the stable operation of the power system, this paper proposes a short-term power load forecasting method TCN-LSTM, which combines time convolution network ( TCN ) and long short-term memory ( LSTM ). Firstly, the time series features in the original load data are extracted by using the characteristics of TCN. Then, the extracted temporal features and non-temporal features are input into the LSTM model to train the model;finally, the trained model is used to predict the short-term power load data. Through the simulation experiment of the load data of a certain area in the south, the TCN-LSTM combined model is compared with the single model. It is found that the prediction accuracy of the TCN-LSTM model is higher, indicating that the model has better short-term power load forecasting *** experimental simulation comparison shows that the prediction accuracy of the combined model proposed in this paper is 0.66 % higher than that of the basic model. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

On non-von Neumann flexible neuromorphic vision sensors

引用

npj Flexible Electronics 2024年第1期8卷 638-663页

作者： Hao Wang Bin Sun Shuzhi Sam Ge Jie Su Ming Liang Jin Institute for Future Shandong Key Laboratory of Industrial Control TechnologySchool of AutomationQingdao UniversityQingdao 266071China College of Electronic and Information Engineering Qingdao UniversityQingdao 266071China Department of Electrical and Computer Engineering and Institute for Functional Intelligent MaterialsNational University of SingaporeSingapore 117583Singapore

The structure andmechanismof thehuman visual system contain rich treasures,and surprising effects can be achieved by simulating the human visual *** this article,starting from the human visual system,we compare and discuss the discrepancies between the human visual system and traditional machine vision *** the wide variety and large volume of visual information,the use of nonvon Neumann structured,flexible neuromorphic vision sensors can effectively compensate for the limitations of traditional machine vision systems based on the von Neumann ***,this article addresses the emulation of retinal functionality and provides an overview of the principles and circuit implementation methods of non-von Neumann computing ***,in terms of mimicking the retinal surface structure,this article introduces the fabrication approach for flexible sensor ***,this article analyzes the challenges currently faced by non-von Neumann flexible neuromorphic vision sensors and offers a perspective on their future development.

关键词： Neumann system starting

来源：评论

学校读者我要写书评

暂无评论

Short-term wind power load forecasting based on ISSA-CNN-BiLSTM 3

Short-term wind power load forecasting based on ISSA-CNN-BiL...

引用

3rd International Conference on Energy, Power and Electrical technology, ICEPET 2024

作者： Liu, Shaoxiong Zhou, Zhenliu Zhao, Huaxin Electrical Engineering College of Shenyang Institute of Engineering Shenyang China Shenyang Key Laboratory of Energy Internet Intelligent Perception and Security Technology Shenyang China Information College of Shenyang Institute of Engineering Shenyang China

ISBN: (纸本)9798350352658

Accurate wind power prediction is of great significance in the balance of electricity supply and demand. Aiming at the problems of poor convergence and easy to fall into local extremes of the power prediction model using the traditional sparrow algorithm (SSA) to optimise the parameters of the bidirectional long- and short-term memory neural network (CNN-BiLSTM), this paper adopts the refractive inverse learning strategy, the positive cosine strategy and the Cauchy variation strategy to improve the sparrow search algorithm, and a better convergence is obtained. An improved sparrow search algorithm (ISSA) with stronger convergence is obtained. The ISSA algorithm is used to optimise the bi-directional long and short-term memory neural network, and the ISSA-CNN-BiLSTM neural network prediction model is established. This paper takes the data of a wind farm in Inner Mongolia as the research object, and uses SSA-CNN-BiLSTM algorithm,CNN-BiLSTM algorithm and ISSA-CNN-BiLSTM algorithm to simulate and test the measured historical data of this wind farm, respectively. The experimental simulation comparison shows that the combined model proposed in this paper has a 7.6% improvement in prediction accuracy over its base model. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Data quantity governance for machine learning in materials science

引用

National Science Review 2023年第7期10卷 234-250页

作者： Yue Liu Zhengwei Yang Xinxin Zou Shuchang Ma Dahui Liu Maxim Avdeev Siqi Shi School of Computer Engineering and Science Shanghai University Shanghai Engineering Research Center of Intelligent Computing System Australian Nuclear Science and Technology Organisation School of Chemistry The University of Sydney State Key Laboratory of Advanced Special Steel School of Materials Science and Engineering Shanghai University Materials Genome Institute Shanghai University

Data-driven machine learning(ML) is widely employed in the analysis of materials structure-activity relationships,performance optimization and materials design due to its superior ability to reveal latent data patterns and make accurate ***,because of the laborious process of materials data acquisition,ML models encounter the issue of the mismatch between a high dimension of feature space and a small sample size(for traditional ML models) or the mismatch between model parameters and sample size(for deep-learning models),usually resulting in terrible ***,we review the efforts for tackling this issue via feature reduction,sample augmentation and specific ML approaches,and show that the balance between the number of samples and features or model parameters should attract great attention during data quantity *** this,we propose a synergistic data quantity governance flow with the incorporation of materials domain *** summarizing the approaches to incorporating materials domain knowledge into the process of ML,we provide examples of incorporating domain knowledge into governance schemes to demonstrate the advantages of the approach and *** work paves the way for obtaining the required high-quality data to accelerate materials design and discovery based on ML.

关键词： machine learning data governance data quantity materials science

来源：评论

学校读者我要写书评

暂无评论

A Hf0.5Zr0.5O2 Non-Volatile Capacitor Based on SrTiO3 Substrate 3

A Hf0.5Zr0.5O2 Non-Volatile Capacitor Based on SrTiO3 Substr...

引用

3rd International Conference on New Materials, Machinery, and Vehicle Engineering, NMMVE 2024

作者： Liu, Xingpeng Wei, Chunshu Tang, Huiping Peng, Yiming Jiang, Chunsheng Aurora Technologies Co. Ltd. Guangzhou511453 China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin541004 China

ISBN: (纸本)9781510686267

The rapid of development of the Internet of Things (Iot), 5G communications, and smart technologies placing higher demands on storage-integrated hardware devices. The discovery of HfO2-based ferroelectric materials has opened up a new avenue for achieving low-power logic and high-density non-volatile memory by utilizing this silicon-tolerant ferroelectric material. In this work, a 10 nm Hf0.5Zr0.5O2 (HZO) ferroelectric films ware prepared on SrTiO3 (STO) substrate using an atomic layer deposition system (ALD). After rapid annealing treatment, the surface roughness of HZO films showed nanometer level (Ra∼1.033 nm, Rq∼1.321 nm). HZO ferroelectric films with molybdenum (Mo) electrodes exhibit low coercive field (Ec∼1.48 MV/cm) and excellent ferroelectric property (2Pr∼56.143 μC/cm2, and 2Pmax∼ 81.070 μC/cm2). Under the fatigue signal of 100 kHz, the device exhibits stable anti-fatigue characteristics. Mo/HZO/Mo/STO devices exhibit fast response time (1ms) and stable polarization retention characteristics (over 103 s). This work introduces a novel method for the next-generation non-volatile memory solutions (NVM). © 2024 SPIE.

关键词： Ferroelectric films

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：