检索结果-内蒙古大学图书馆

Flight Pattern Recognition and Precision Tracking algorithm for UAV Cluster Targets Imitating Geese Flocks

IEEE SENSORS JOURNAL 2025年第1期25卷 709-724页

作者： Gao, Wei Rao, Bin Song, Dan Lai, Tao Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen 518000 Peoples R China Natl Univ Def Technol Test Ctr Xian 710106 Peoples R China

The rise of biomimetic unmanned aerial vehicle clusters has brought new challenges to radar target tracking and recognition. The purpose of flying imitating geese flocks is long-distance transport with low energy consumption. In this article, the methods of recognition and tracking are proposed for cluster targets with flight pattern of geese. The pattern recognition method, by detecting specific distance pairs according to five constraints including distance, vertical, pedal, orientation, and slope, judges whether there is a "V" characteristic in the measurement set and selects the key individuals such as the leading or following geese. Based on the pattern recognition result, the hypothetical pattern measurements are introduced into the filtering process as additional observation information, which aims to solve the problem of tracking accuracy decrease caused by high maneuverability in the formation stage of flying geese. Simulation results show that the proposed methods can not only judge the pattern of the cluster effectively and identify the key individuals but also improve the accuracy compared with the traditional tracking algorithms.

关键词： Radar tracking Target tracking Autonomous aerial vehicles Pattern recognition Clustering algorithms Sensors filtering Cluster targets filtering algorithm geese flight pattern recognition radar target tracking

来源：评论

学校读者我要写书评

暂无评论

Locally enhanced denoising self-attention networks and decoupled position encoding for sequential recommendation

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 123卷

作者： Yang, Xingyao Dong, Xinsheng Yu, Jiong Li, Shuangquan Xiong, Xinyu Shen, Hongtao Xinjiang Univ Urumqi Peoples R China

Most of the existing Transformer-based models have been shown to have great advantages in sequential recommendation by modeling temporal dynamics through the self-attention mechanism. Nevertheless, the original self-attention mechanism requires the equal weighting and computation of all interactions between each item and every other item. This method presents limitations in effectively capturing shifts in users' local interests. In addition, this approach ignores the noise in user data, while absolute position encoding leads to inaccurate sequential relations between items. An innovative Locally Enhanced Denoising Self-Attention Network and Decoupled Position Encoding for Sequential Recommendation, named LEDADP, is presented to resolve these issues. Specifically, we use the noise filtering module to convert the original data into the frequency domain to reduce the noise and achieve the purpose of filtering the noise. We integrate convolution into self-attention for local interest transfer, and we provide a multi-scale local enhanced convolution module that models local dependencies taking into account various local preferences at several scales, collecting more detailed local semantic information. Furthermore, in order to more precisely depict the sequential link between items, we additionally employ decoupled position encoding. Extensive experiments conducted on three real-world datasets : Beauty, Toys, and ML-1M. The experimental results show that compared with the suboptimal model, the proposed model has respectively improved by 2.87%, 7.83% and 4.1% on Recall@5, and by 2.03%, 4.08% and 6.8% on NDCG@5, which proves the validity of the model.

关键词： Sequential recommendation Attention mechanism filtering algorithm Convolutional neural networks (CNNs) Multi-scale local preferences Local enhanced convolution

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware hourly load forecasting of hydrogen-blended natural gas with a hybrid deep learning model

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2025年 127卷 541-563页

作者： Wang, Lin Xie, Qiuyun Wang, Zhiyuan Guo, Junyu Xu, Zifei Kang, Hooi Siang Li, He Southwest Petr Univ Sch Mechatron Engn Chengdu 610500 Peoples R China Sharing & Serv Platform Sichuan Prov Oil & Gas Equipment Technol Chengdu Peoples R China Univ Liverpool Sch Engn Brownlow Hill Liverpool L69 3BX England Univ Liverpool Sch Engn Brownlow Hill Liverpool L69 3GH England Univ Teknol Malaysia Fac Mech Engn Johor Baharu Johor Malaysia Liverpool John Moores Univ Sch Engn Liverpool L3 3AF England

Hydrogen-blended natural gas (HBNG) represents a significant option in the clean energy transition, offering emission reduction benefits and compatibility with existing pipelines. However, forecasting hourly loads for HBNG is more challenging than for pure natural gas due to demand uncertainties and the complex properties introduced by hydrogen blending. To address this, the paper proposes an hourly load forecasting method for hydrogen-doped natural gas, EWMA-TCN-BiGRU, incorporating uncertainty considerations. This method employs EWMA filtering to smooth the data, TCN convolutional blocks to extract features, and Monte Carlo (MC) Dropout to generate prediction intervals. These intervals provide upper and lower bounds for the predictions, quantifying uncertainty and assessing the confidence of the results. The study is validated using experimental load and climate data from a station in Southwest China. The results demonstrate that the proposed method outperforms under complex fluctuating conditions, significantly enhancing prediction accuracy compared to the EWMA-BiGRU method. Specifically, the mean absolute percentage error (MAPE) is reduced from 13.8811 to 1.94151, confirming the method's effectiveness.

关键词： Hydrogen-doped natural gas Short-term load forecasting filtering algorithm EWMA-TCN-BiGRU model Uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Enhanced Knowledge Tracing With Learnable Filter

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年第1期12卷 198-209页

作者： Qian, Fulan Hu, Yetong Li, Guangyao Chen, Jie Wang, Shijin Zhao, Shu Anhui Univ Artificial Intelligence Inst Hefei 230601 Peoples R China Anhui Univ Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Peoples R China Anhui Univ Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China IFLYTEK AI Res Hefei 230088 Peoples R China

The primary objective of knowledge tracing (KT) is to evaluate students' understanding and mastery of knowledge through their responses to exercises, which aids in predicting their future performance. Deep neural networks have been widely applied in the area of knowledge tracing and have demonstrated encouraging results. Nevertheless, in real-world scenarios, there is a substantial amount of noise in students' response records. These noises may amplify the inherent risk of overfitting in deep neural networks, leading to a decrease in model performance. To address these issues, we introduce a new model called filter knowledge tracing (FKT). This innovative model incorporates a learnable filter into KT to filter out noise information from students' exercise sequences. We redefine the input paradigm of the data, using learnable filters to perform filtering operations in its frequency domain representation space, effectively removing noise. Additionally, an attention module has been introduced in the FKT model to evaluate the impact of students' historical interactions on their current knowledge state. To validate our model, we conduct extensive experiments utilizing four publicly available datasets. The results demonstrate that FKT outperforms existing benchmarks, particularly on larger datasets, signifying an improvement in KT performance while effectively reducing the risk of overfitting.

关键词： Data models Noise Noise reduction Signal processing algorithms Knowledge engineering Prediction algorithms Noise measurement Heuristic algorithms Frequency-domain analysis filtering algorithms Attention mechanism denoising filtering algorithm knowledge tracing (KT)

来源：评论

学校读者我要写书评

暂无评论

Adaptive enhancement method of irregular low-pixel architectural design image based on lightness component

引用

IMAGING SCIENCE JOURNAL 2025年第1期73卷 70-83页

作者： Qu, Mei Nanyang Inst Technol Sch Architecture Nanyang 473000 Henan Peoples R China

This study explores adaptive enhancement for irregular, low-pixel architectural design images, focusing on lightness components. Utilizing a median filter and wavelet threshold method removes image noise, followed by grayscale conversion in HSV space. Applying Retinex theory generates the initial enhanced image, further improved through wavelet transform image fusion technology, resulting in the final enhanced architectural design image. Experimental results demonstrate the method's effectiveness in adapting and enhancing irregular, low-pixel architectural design images, achieving notably improved outcomes. The proposed approach successfully extracts and utilizes valuable image information, enhancing overall image quality. This study found that the proposed method can effectively extract and better utilize useful information in images, achieving more ideal image enhancement effects.

关键词： Lightness component low-pixel image irregular image architectural design image adaptive enhancement image fusion filtering algorithm module structure

来源：评论

学校读者我要写书评

暂无评论

FARec: frequency domain enhanced filter for sequential recommendation

引用

COMPUTING 2025年第5期107卷 1-28页

作者： Yang, Zhibin Qin, Jiwei Ma, Jie Zhang, Donghao Xinjiang Univ Sch Comp Sci & Technol Urumqi 830017 Xinjiang Uygur Peoples R China Xinjiang Univ Key Lab Signal Detect & Proc Urumqi 830046 Xinjiang Uygur Peoples R China

Sequential recommendation aims to model user preferences by analyzing their historical behavioral data. However, most existing approaches focus on modeling user preferences in the time domain, ignoring the impact of various frequency patterns on user behavior. These frequency patterns are often intertwined in the time domain and are challenging to distinguish, which limits the model's ability to capture users' behaviors at different frequencies. In addition, based on the F-principle, deep learning models pay more attention to low-frequency information, which may lead to poor performance in high-frequency tasks. To alleviate these problems, we propose a novel frequency-enhanced filter (FARec) for sequential recommendation. The model uses a learnable filter as an encoder to capture user preference features and introduces a data augmentation module and a frequency ladder structure to improve the model's ability to capture different frequency features. The data augmentation module draws on the magnitude spectrum in Fourier analysis to introduce two data augmentation methods to accommodate events of different frequency magnitudes: frequency masking and frequency mixing. Moreover, we use frequency domain regularization to align the enhanced view with the original view. The frequency ladder structure splits the original sequence spectrum into multiple frequency bands, allowing the encoder to focus on different spectrum to capture different frequency patterns. Finally, comprehensive tests conducted across four benchmark datasets reveal that FARec outperforms the leading baseline models in effectiveness.

关键词： Sequential recommendation Frequency domain Data augmentation filtering algorithm

来源：评论

学校读者我要写书评

暂无评论

Frequency Feature Enhanced Mix Calibration Attention Network for Sequential Recommendation 7th

Frequency Feature Enhanced Mix Calibration Attention Network...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Shen, Hongtao Yang, Xingyao Li, Shuangquan Yu, Jiong Li, Zhilin Qi, Zheng Xinjiang Univ Sch Software Urumqi 830091 Xinjiang Peoples R China

ISBN: (纸本)9789819785018;9789819785025

Sequential recommendation (SR) aims to model user preferences through their historical interaction data. In recent years, Transformer has been widely used for SR due to its strong capability of modeling long-term dependencies. However, recent studies have shown that current Transformer-based SR models are susceptible to the over-parameterisation and suffer from inaccurate allocation of attention weights. Moreover, most methods model user preferences only in the time domain and cannot filter noisy input, leading to inaccurate recommendation. In this work, we propose a novel Frequency Feature Enhanced Mix Calibration Attention Network for Sequential Recommendation, named FMCARec. Specifically, we design a Squeeze-and-Excitation filtering strategy to capture the frequency features and filter noisy terms in user interaction data. Convolution operation is then used to mitigate the effects of over-parameterisation on self-attention mechanism. And a spatial information calibration strategy is used to calibrate attention weights and decoupled location coding weights. Finally, contrastive learning is utilized to improve the quality of user embedding. Experimental evaluations conducted on three public datasets demonstrate that our proposed model performs significantly better than the state-of-the-art methods.

关键词： Sequential recommendation filtering algorithm Attention mechanism Feature fusion Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-information Feature Fusion MLP with Filter Enhancement for Sequential Recommendation 7th

Adaptive Multi-information Feature Fusion MLP with Filter En...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Li, Shuangquan Yang, Xingyao Shen, Hongtao Yu, Jiong Wu, Yanfu Xinjiang Univ Sch Software Urumqi 830000 Xinjiang Peoples R China

ISBN: (纸本)9789819784868;9789819784875

In recent years, many self-attention models have achieved good sequence recommendation performance by, capture the sequential dependencies between users and items. However, user behavior data inevitably contains noise, and the embedding of location information may interfere with item embedding semantics, causing noise in the data to further increase. At the same time, these self-attention models ignore the impact of high-relevance user-item interactions on the next item. To address these problems, we propose a new sequential recommendation system (AMFRec). Specifically, we adopted a three-way information (sequence, cross-channel, cross-feature) adaptive fusion scheme enhanced by a filtering algorithm. The proposed system is completely based on the MLP architecture attenuates noise in the frequency domain to reduce its impact on the model, and is naturally sensitive to location information. Finally, we designed a squeeze incentive module suitable for recommendation systems to activate multiple highly relevant projects. Experiments were conducted on three widely used datasets to demonstrate the effectiveness and efficiency of the proposed method.

关键词： Sequential recommendation ALL-MLP model filtering algorithm

来源：评论

学校读者我要写书评

暂无评论

Some studies on detection and filtering algorithms for the removal of random valued impulse noise

引用

IET IMAGE PROCESSING 2017年第11期11卷 953-963页

作者： Singh, Neeti Thilagavathy, Thirusangu Lakshmipriya, Ramasubramanian T. Umamaheswari, Oorkavalan Anna Univ Dept Elect & Commun Engn CEG Chennai Tamil Nadu India

Removing random valued impulse noise (RVIN) is a challenging task in corrupted images. This article aims to study some detection and filtering algorithms which remove RVIN in images. In addition to some state-of-the-art detection and filtering algorithms, a new detection technique, measures of dispersion (MOD) algorithm, for removing very high-density RVIN proposed by authors is also compared with existing methods. In the detection stage, rank order absolute difference, rank order logarithmic difference, adaptive switching median, triangle-based linear interpolation, and MOD algorithms are considered. Median filter, fuzzy switching median filter, and fuzzy switching weighted median filter are used for filtering followed by the detection algorithms. Comparative studies in terms of peak signal-to-noise ratio and structural similarity have been devised to evaluate the performance of various filtering schemes.

关键词： fuzzy set theory interpolation median filters adaptive filters impulse noise image denoising image filtering random valued impulse noise removal filtering algorithm RVIN removal corrupted image measures of dispersion algorithm MOD algorithm rank order absolute difference rank order logarithmic difference adaptive switching median triangle-based linear interpolation MOD algorithms fuzzy switching median filter fuzzy switching weighted median filter peak signal-to-noise ratio structural similarity

来源：评论

学校读者我要写书评

暂无评论

Optimal Crowd-Powered Rating and filtering algorithms

引用

PROCEEDINGS OF THE VLDB ENDOWMENT 2014年第9期7卷 685-696页

作者： Parameswaran, Aditya Boyd, Stephen Garcia-Molina, Hector Gupta, Ashish Polyzotis, Neoklis Widom, Jennifer Stanford Univ & UIUC Stanford CA 94305 USA Stanford Univ Stanford CA USA UCSC & Google Santa Cruz CA USA

We focus on crowd-powered filtering, i.e., filtering a large set of items using humans. filtering is one of the most commonly used building blocks in crowdsourcing applications and systems. While solutions for crowd-powered filtering exist, they make a range of implicit assumptions and restrictions, ultimately rendering them not powerful enough for real-world applications. We describe two approaches to discard these implicit assumptions and restrictions: one, that carefully generalizes prior work, leading to an optimal, but often-times intractable solution, and another, that provides a novel way of reasoning about filtering strategies, leading to a sometimes sub-optimal, but efficiently computable solution (that is provably close to optimal). We demonstrate that our techniques lead to significant reductions in error of up to 30-40% for fixed cost over prior work in a novel crowdsourcing application: peer evaluation in online courses.

关键词： Crowdsourcing Signal filtering and prediction Building blockes filtering algorithm Fixed cost Online course Peer evaluations Real world

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

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

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：