绵羊的姿态与其健康及福利密切相关。随着智能化畜牧业需求的增长,自动、准确地检测绵羊姿态尤为尤为重要。本研究提出基于Mask R-CNN基准网络的新型RDS-Mask R-CNN绵羊姿态检测算法,以Res2Net101作为特征提取网络,同时引入可变形卷积(D...绵羊的姿态与其健康及福利密切相关。随着智能化畜牧业需求的增长,自动、准确地检测绵羊姿态尤为尤为重要。本研究提出基于Mask R-CNN基准网络的新型RDS-Mask R-CNN绵羊姿态检测算法,以Res2Net101作为特征提取网络,同时引入可变形卷积(Deformable convolution network,DCN),以更精准捕捉绵羊在不同位置的姿态特征,并运用软非极大值抑制(Soft non-maximum suppression,Soft NMS)算法实现重叠实例目标的准确分割。结果表明:1)目标检测框架算法对比:与该领域最经典的YOLOv3和Faster R-CNN相比,改进的算法在平均精度均值(Mean average precision,mAP)上分别提升了16.68%和8.64%;2)不同改进策略的算法对比:改进算法相较于基准网络,边界框平均精度均值(Bounding box mean average precision,Bbox mAP)提高6.21%,分割平均精度均值(Segmentation mean average precision,Segm mAP)提高6.61%,分别达到87.34%和81.50%;3)相较于Mask R-CNN,改进模型在识别绵羊站立与躺卧姿态时边界框平均精度(Bounding box average precision,Bbox AP)分别提高了6.84%和5.58%,分割平均精度(Segmentation average precision,Segm AP)分别提高了7.25%和5.17%;4)模型可解释性可视化结果表明RDS-Mask R-CNN能精准捕获绵羊站立和躺卧姿态关键部位深度特征,表明模型自动检测可行且具有可解释性。综上,本研究提出的RDS-Mask R-CNN算法,有效提升了绵羊姿态检测的精准度,为智慧养殖提供了技术支撑。展开更多
Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from...Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from class imbalances due to the uneven distribution of case types across legal domains.This leads to biased model performance,in the form of high accuracy for overrepresented categories and underperformance for minority classes.To address this issue,in this study,we propose a data augmentation method that masks unimportant terms within a document selectively while preserving key terms fromthe perspective of the legal domain.This approach enhances data diversity and improves the generalization capability of conventional models.Our experiments demonstrate consistent improvements achieved by the proposed augmentation strategy in terms of accuracy and F1 score across all models,validating the effectiveness of the proposed method in legal case classification.展开更多
The airborne diffusion of saliva droplets during respiratory activities is one of the major factors in the spread of infections.During the COVID-19 pandemic,the use of protective face masks was essential to reduce the...The airborne diffusion of saliva droplets during respiratory activities is one of the major factors in the spread of infections.During the COVID-19 pandemic,the use of protective face masks was essential to reduce the risk of infection and spread of SARS-CoV-2.The face mask is able to significantly reduce the saliva droplet emission in front of the person.However,the use of masks also produces a particle leakage towards the back of the person,which could increase the infection risk of people behind the subject.Most of the experimental investigations applied invasive and/or complex experimental techniques to evaluate the face masks leakage.The primary objective of this study is to develop a novel,non-invasive methodology for assessing rearward droplet emission associated with the use of protective face masks.Specifically,a thermographic analysis of the thermal footprint released during ordinary and extraordinary respiratory activities is presented,evaluating the maximum temperature,the detection time,and the spread area of the thermal footprint.Both surgical and FFP2 face masks were tested.Two different subjects were involved in the experimentation to evaluate the influence of face conformation.The findings indicate that the area influenced by droplet dispersion is larger when wearing a surgical mask compared to an FFP2 mask,with the highest recorded temperatures observed for the surgical mask.The thermal footprint was found to be strongly dependent on individual facial morphology and mask fit.Notably,the FFP2 mask also altered the position of the thermal footprint,which was primarily confined to the region near the neck.展开更多
To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervis...To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.展开更多
In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,...In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.展开更多
The Nuo mask is the core visual vehicle within China’s Nuo culture and constitutes a complex symbolic system through facial features(icons),patterns(indexes),and colors(symbols).Within the context of intangible cultu...The Nuo mask is the core visual vehicle within China’s Nuo culture and constitutes a complex symbolic system through facial features(icons),patterns(indexes),and colors(symbols).Within the context of intangible cultural heritage(ICH)preservation,its value lies in the continuation and revitalization of its dynamic symbolic functions.Grounded in semiotic theory,this paper elaborates on three core dimensions of symbolic value manifested by Nuo masks in ICH preservation:a ritual symbol for living transmission,a symbol of identity for collective memory,and an aesthetic symbol as a source of creativity.展开更多
文摘绵羊的姿态与其健康及福利密切相关。随着智能化畜牧业需求的增长,自动、准确地检测绵羊姿态尤为尤为重要。本研究提出基于Mask R-CNN基准网络的新型RDS-Mask R-CNN绵羊姿态检测算法,以Res2Net101作为特征提取网络,同时引入可变形卷积(Deformable convolution network,DCN),以更精准捕捉绵羊在不同位置的姿态特征,并运用软非极大值抑制(Soft non-maximum suppression,Soft NMS)算法实现重叠实例目标的准确分割。结果表明:1)目标检测框架算法对比:与该领域最经典的YOLOv3和Faster R-CNN相比,改进的算法在平均精度均值(Mean average precision,mAP)上分别提升了16.68%和8.64%;2)不同改进策略的算法对比:改进算法相较于基准网络,边界框平均精度均值(Bounding box mean average precision,Bbox mAP)提高6.21%,分割平均精度均值(Segmentation mean average precision,Segm mAP)提高6.61%,分别达到87.34%和81.50%;3)相较于Mask R-CNN,改进模型在识别绵羊站立与躺卧姿态时边界框平均精度(Bounding box average precision,Bbox AP)分别提高了6.84%和5.58%,分割平均精度(Segmentation average precision,Segm AP)分别提高了7.25%和5.17%;4)模型可解释性可视化结果表明RDS-Mask R-CNN能精准捕获绵羊站立和躺卧姿态关键部位深度特征,表明模型自动检测可行且具有可解释性。综上,本研究提出的RDS-Mask R-CNN算法,有效提升了绵羊姿态检测的精准度,为智慧养殖提供了技术支撑。
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)[RS-2021-II211341,Artificial Intelligence Graduate School Program(Chung-Ang University)],and by the Chung-Ang University Graduate Research Scholarship in 2024.
文摘Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from class imbalances due to the uneven distribution of case types across legal domains.This leads to biased model performance,in the form of high accuracy for overrepresented categories and underperformance for minority classes.To address this issue,in this study,we propose a data augmentation method that masks unimportant terms within a document selectively while preserving key terms fromthe perspective of the legal domain.This approach enhances data diversity and improves the generalization capability of conventional models.Our experiments demonstrate consistent improvements achieved by the proposed augmentation strategy in terms of accuracy and F1 score across all models,validating the effectiveness of the proposed method in legal case classification.
文摘The airborne diffusion of saliva droplets during respiratory activities is one of the major factors in the spread of infections.During the COVID-19 pandemic,the use of protective face masks was essential to reduce the risk of infection and spread of SARS-CoV-2.The face mask is able to significantly reduce the saliva droplet emission in front of the person.However,the use of masks also produces a particle leakage towards the back of the person,which could increase the infection risk of people behind the subject.Most of the experimental investigations applied invasive and/or complex experimental techniques to evaluate the face masks leakage.The primary objective of this study is to develop a novel,non-invasive methodology for assessing rearward droplet emission associated with the use of protective face masks.Specifically,a thermographic analysis of the thermal footprint released during ordinary and extraordinary respiratory activities is presented,evaluating the maximum temperature,the detection time,and the spread area of the thermal footprint.Both surgical and FFP2 face masks were tested.Two different subjects were involved in the experimentation to evaluate the influence of face conformation.The findings indicate that the area influenced by droplet dispersion is larger when wearing a surgical mask compared to an FFP2 mask,with the highest recorded temperatures observed for the surgical mask.The thermal footprint was found to be strongly dependent on individual facial morphology and mask fit.Notably,the FFP2 mask also altered the position of the thermal footprint,which was primarily confined to the region near the neck.
基金supported by the National Natural Science Foundation of China Funded Project(Project Name:Research on Robust Adaptive Allocation Mechanism of Human Machine Co-Driving System Based on NMS Features,Project Approval Number:52172381).
文摘To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.
文摘In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.
基金National Social Science Fund project“Research on the Narrative of the Sense of Community for the Chinese Nation in Southwest Nuo Opera”(24XMZ063).
文摘The Nuo mask is the core visual vehicle within China’s Nuo culture and constitutes a complex symbolic system through facial features(icons),patterns(indexes),and colors(symbols).Within the context of intangible cultural heritage(ICH)preservation,its value lies in the continuation and revitalization of its dynamic symbolic functions.Grounded in semiotic theory,this paper elaborates on three core dimensions of symbolic value manifested by Nuo masks in ICH preservation:a ritual symbol for living transmission,a symbol of identity for collective memory,and an aesthetic symbol as a source of creativity.
