Sign language dataset is essential in sign language recognition and translation(SLRT). Current public sign language datasets are small and lack diversity, which does not meet the practical application requirements for...Sign language dataset is essential in sign language recognition and translation(SLRT). Current public sign language datasets are small and lack diversity, which does not meet the practical application requirements for SLRT. However, making a large-scale and diverse sign language dataset is difficult as sign language data on the Internet is scarce. In making a large-scale and diverse sign language dataset, some sign language data qualities are not up to standard. This paper proposes a two information streams transformer(TIST) model to judge whether the quality of sign language data is qualified. To verify that TIST effectively improves sign language recognition(SLR), we make two datasets, the screened dataset and the unscreened dataset. In this experiment, this paper uses visual alignment constraint(VAC) as the baseline model. The experimental results show that the screened dataset can achieve better word error rate(WER) than the unscreened dataset.展开更多
Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition ...Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition algorithms often relies on expert knowledge to enhance the image feature extraction networks,necessitating image preprocessing and model parameter tuning.This increases the complexity of the model design process.This study introduces an evolutionary neural architecture search(ENAS)algorithm for the automatic design of neural network models tailored for traffic sign recognition.By integrating the construction parameters of residual network(ResNet)into evolutionary algorithms(EAs),we automatically generate lightweight networks for traffic sign recognition,utilizing blocks as the fundamental building units.Experimental evaluations on the German traffic sign recognition benchmark(GTSRB)dataset reveal that the algorithm attains a recognition accuracy of 99.32%,with a mere 2.8×10^(6)parameters.Experimental results comparing the proposed method with other traffic sign recognition algorithms demonstrate that the method can more efficiently discover neural network architectures,significantly reducing the number of network parameters while maintaining recognition accuracy.展开更多
A graph whose edges are labeled either as positive or negative is called a signed graph.Hameed et al.introduced signed distance and distance compatibility in 2021,initially to characterize balanced signed graphs which...A graph whose edges are labeled either as positive or negative is called a signed graph.Hameed et al.introduced signed distance and distance compatibility in 2021,initially to characterize balanced signed graphs which have nice spectral properties.This article mainly studies the conjecture proposed by Shijin et al.on the distance compatibility of the direct product of signed graphs,and provides necessary and sufficient conditions for the distance compatibility of the direct product of signed graphs.Some further questions regarding distance compatibility are also posed.展开更多
To explore the influence of emergency evacuation signs on passenger behavior during subway fires and improve evacuation efficiency in emergencies,this paper proposes a dynamic emergency evacuation sign system.A simula...To explore the influence of emergency evacuation signs on passenger behavior during subway fires and improve evacuation efficiency in emergencies,this paper proposes a dynamic emergency evacuation sign system.A simulation platform integrating building information modeling(BIM)and virtual reality(VR)technologies was em-ployed to create subway fire evacuation scenarios using both the current and proposed dynamic emergency evacuation signage systems.Through simulation experiments,fine-grained microscopic data on passenger behavior was collected.Seven indicators were selected to assess evacuation efficiency and wayfinding difficulty.The analysis explored the influence of evacuation signs on passenger behavior in both overall and decision-making areas,thereby validating the effectiveness of the new emergency evacuation signage system.The results show that the dynamic evacuation signage system significantly improves overall passenger evacuation efficiency and reduces decision-making errors.It also improves wayfinding efficiency in critical decision areas by reducing the need for direction identification,minimizing stopping times,and lowering the frequency of decision errors.The method for evaluating the effects of emergency evacuation signs on passenger evacuation behavior proposed in this study provides a robust theoretical basis for the design and optimization of emergency-oriented signs.展开更多
The unique structure of signed networks,characterized by positive and negative edges,poses significant challenges for analyzing network topology.In recent years,various statistical algorithms have been developed to ad...The unique structure of signed networks,characterized by positive and negative edges,poses significant challenges for analyzing network topology.In recent years,various statistical algorithms have been developed to address this issue.However,there remains a lack of a unified framework to uncover the nontrivial properties inherent in signed network structures.To support developers,researchers,and practitioners in this field,we introduce a Python library named SNSAlib(Signed Network Structure Analysis),specifically designed to meet these analytical requirements.This library encompasses empirical signed network datasets,signed null model algorithms,signed statistics algorithms,and evaluation indicators.The primary objective of SNSAlib is to facilitate the systematic analysis of micro-and meso-structure features within signed networks,including node popularity,clustering,assortativity,embeddedness,and community structure by employing more accurate signed null models.Ultimately,it provides a robust paradigm for structure analysis of signed networks that enhances our understanding and application of signed networks.展开更多
Once a train stops in a tunnel section and requires emergency evacuation,the large distance between stations and long walking distances in the underground spaces of suburban railway systems pose potential risks to the...Once a train stops in a tunnel section and requires emergency evacuation,the large distance between stations and long walking distances in the underground spaces of suburban railway systems pose potential risks to the evacuation process on tunnel platforms,especially in complex environments.This study utilized Virtual Reality(VR)technology to construct a virtual experimental platform for tunnel evacuation in suburban railway systems,simulating different combinations of smoke and obstacle conditions.By requiring participants to wear VR glasses and walk on an omnidirectional treadmill for moving,as well as complete psychological questionnaires,the study reveals the influences of No Guiding(NG)signs,Wall-Guided(WG)signs,and Central axis Guidance(CG)signs on the movement abilities and psychological behaviors of participants contrastively.The results show that either smoke conditions or obstacle positions affect the mental stress of participants,and the guidance sign has a positive effect on reducing the mental stress.There is an inverse relationship between mental stress and movement abilities.WG and CG signs respectively lead participants to walk closer to walls and along the central axis,which is conducive to reducing the variation in participants’behavior characteristics when circumventing obstacles on the wall side or track side under smoke conditions,respectively.Additionally,CG signs reduce the speed fluctuations of participants before circumventing obstacles,improving the stability of the distance from the wall and speed under smoke conditions,compared to NG and WG signs.These findings contribute to understanding the evacuation psychological-behavioral-movement characteristics of pedestrians on evacuation platforms in suburban railway tunnels and provide a basis for improving the safety design of evacuation guidance signs.展开更多
Dynamic sign language recognition holds significant importance, particularly with the application of deep learning to address its complexity. However, existing methods face several challenges. Firstly, recognizing dyn...Dynamic sign language recognition holds significant importance, particularly with the application of deep learning to address its complexity. However, existing methods face several challenges. Firstly, recognizing dynamic sign language requires identifying keyframes that best represent the signs, and missing these keyframes reduces accuracy. Secondly, some methods do not focus enough on hand regions, which are small within the overall frame, leading to information loss. To address these challenges, we propose a novel Video Transformer Attention-based Network (VTAN) for dynamic sign language recognition. Our approach prioritizes informative frames and hand regions effectively. To tackle the first issue, we designed a keyframe extraction module enhanced by a convolutional autoencoder, which focuses on selecting information-rich frames and eliminating redundant ones from the video sequences. For the second issue, we developed a soft attention-based transformer module that emphasizes extracting features from hand regions, ensuring that the network pays more attention to hand information within sequences. This dual-focus approach improves effective dynamic sign language recognition by addressing the key challenges of identifying critical frames and emphasizing hand regions. Experimental results on two public benchmark datasets demonstrate the effectiveness of our network, outperforming most of the typical methods in sign language recognition tasks.展开更多
The arterial pulse tapping artifact,known as Aslanger’s sign,is an electrocardiographic artifact resulting from the transmission of arterial pulsation onto the limb electrodes of the standard 12-lead electrocardiogra...The arterial pulse tapping artifact,known as Aslanger’s sign,is an electrocardiographic artifact resulting from the transmission of arterial pulsation onto the limb electrodes of the standard 12-lead electrocardiograph(ECG)which are placed near the radial or posterior tibial arteries.[1-16]This electromechanical artifact is of cardiac origin and is synchronous with the cardiac cycle.[17]Nearly all reported cases of Aslanger’s sign exhibit an unusual waveform morphology in all 12 leads except one limb lead.[1-14,16]However,we previously reported a case of Aslanger’s sign that showed distorted waveforms from the ST to TP segments observed only in five limb leads among 12 leads.展开更多
This paper presents a predefined-time controller for Multiple Space transportation Robots System (MSRS), which can be applied in on-orbit assembly tasks to transport modules to pre-assembly configuration quickly. Firs...This paper presents a predefined-time controller for Multiple Space transportation Robots System (MSRS), which can be applied in on-orbit assembly tasks to transport modules to pre-assembly configuration quickly. Firstly, to simplify the analysis and design of predefined-time controller, a Predefined-time Stability Criterion is proposed in the form of Composite Lyapunov Function (CLF-PSC). Besides simplicity, the CLF-PSC also has the advantage of less conservativeness due to utilization of initial state information. Secondly, a concept of Lp-Norm-Normalized Sign Function (LPNNSF) is proposed based on the CLF-PSC. Different from traditional norm-normalized sign function, the Lp-norm of LPNNSF can be selected arbitrarily according to practical control task requirements, which means that the proposed LPNNSF is more generalized and more convenient for calculation. Thirdly, a predefined-time disturbance observer and predefined-time controller are designed based on the LPNNSF. The observer has the property of predefined-time convergence to achieve quicker and more accurate estimation of the lumped disturbance. The controller has less control input and chattering phenomenon than traditional predefined-time controller. In addition, by introducing the observer into the controller, the closed-loop system enjoys high precision and strong robustness. Finally, the effectiveness of the proposed controller is verified by numerical simulations. By employing the controller, the MSRS can carry assembly modules to the desired pre-assembly configuration accurately within predefined time.展开更多
This paper proposes a lightweight traffic sign detection system based on you only look once(YOLO).Firstly,the classification to fusion(C2f)structure is integrated into the backbone network,employing deformable convolu...This paper proposes a lightweight traffic sign detection system based on you only look once(YOLO).Firstly,the classification to fusion(C2f)structure is integrated into the backbone network,employing deformable convolution and bi-directional feature pyramid network(BiFPN)_Concat to improve the adaptability of the network.Secondly,the simple attention module(SimAm)is embedded to prioritize key features and reduce the complexity of the model after the C2f layer at the end of the backbone network.Next,the focal efficient intersection over union(EloU)is introduced to adjust the weights of challenging samples.Finally,we accomplish the design and deployment for the mobile app.The results demonstrate improvements,with the F1 score of 0.8987,mean average precision(mAP)@0.5 of 98.8%,mAP@0.5:0.95 of 75.6%,and the detection speed of 50 frames per second(FPS).展开更多
Arabic Sign Language(ArSL)recognition plays a vital role in enhancing the communication for the Deaf and Hard of Hearing(DHH)community.Researchers have proposed multiple methods for automated recognition of ArSL;howev...Arabic Sign Language(ArSL)recognition plays a vital role in enhancing the communication for the Deaf and Hard of Hearing(DHH)community.Researchers have proposed multiple methods for automated recognition of ArSL;however,these methods face multiple challenges that include high gesture variability,occlusions,limited signer diversity,and the scarcity of large annotated datasets.Existing methods,often relying solely on either skeletal data or video-based features,struggle with generalization and robustness,especially in dynamic and real-world conditions.This paper proposes a novel multimodal ensemble classification framework that integrates geometric features derived from 3D skeletal joint distances and angles with temporal features extracted from RGB videos using the Inflated 3D ConvNet(I3D).By fusing these complementary modalities at the feature level and applying a majority-voting ensemble of XGBoost,Random Forest,and Support Vector Machine classifiers,the framework robustly captures both spatial configurations and motion dynamics of sign gestures.Feature selection using the Pearson Correlation Coefficient further enhances efficiency by reducing redundancy.Extensive experiments on the ArabSign dataset,which includes RGB videos and corresponding skeletal data,demonstrate that the proposed approach significantly outperforms state-of-the-art methods,achieving an average F1-score of 97%using a majority-voting ensemble of XGBoost,Random Forest,and SVM classifiers,and improving recognition accuracy by more than 7%over previous best methods.This work not only advances the technical stateof-the-art in ArSL recognition but also provides a scalable,real-time solution for practical deployment in educational,social,and assistive communication technologies.Even though this study is about Arabic Sign Language,the framework proposed here can be extended to different sign languages,creating possibilities for potentially worldwide applicability in sign language recognition tasks.展开更多
A signed graph S=(S^(u),σ)has an underlying graph Suand a functionσ:E(S^(u))-→{+,-}.Let E^(-)(S)denote the set of negative edges of S.Then S is eulerian signed graph(or subeulerian signed graph,or balanced eulerian...A signed graph S=(S^(u),σ)has an underlying graph Suand a functionσ:E(S^(u))-→{+,-}.Let E^(-)(S)denote the set of negative edges of S.Then S is eulerian signed graph(or subeulerian signed graph,or balanced eulerian signed graph,respectively)if Suis eulerian(or subeulerian,or eulerian and|E-(S)|is even,respectively).We say that S is balanced subeulerian signed graph if there exists a balanced eulerian signed graph S′such that S′is spanned by S.The signed line graph L(S)of a signed graph S is a signed graph with the vertices of L(S)being the edges of S,where an edge eiej is in L(S)if and only if the edges e_(i)and e_(j)of S have a vertex in common in S such that an edge eiej in L(S)is negative if and only if both edges ei and ej are negative in S.In this paper,two families of signed graphs S and S′are identified,which are applied to characterize balanced subeulerian signed graphs and balanced subeulerian signed line graphs.In particular,it is proved that a signed graph S is balanced subeulerian if and only if S∈S,and that a signed line graph of signed graph S is balanced subeulerian if and only if S∈S′.展开更多
BACKGROUND Ileal atresia is a congenital abnormality where there is significant stenosis or complete absence of a portion of the ileum.The overall diagnostic accuracy of prenatal ultrasound in detecting jejunal and il...BACKGROUND Ileal atresia is a congenital abnormality where there is significant stenosis or complete absence of a portion of the ileum.The overall diagnostic accuracy of prenatal ultrasound in detecting jejunal and ileal atresia is low.We report a case of ileal atresia diagnosed prenatally by ultrasound examination with the“keyboard sign”and“coffee bean sign”.CASE SUMMARY We report a case of ileal atresia diagnosed in utero at 31 weeks'of gestation.Prenatal ultrasound examination revealed two rows of intestines arranged in an‘S’shape in the middle abdomen.The inner diameters were 1.7 cm and 1.6 cm,respectively.A typical“keyboard sign”was observed.The intestine canal behind the“keyboard sign”showed an irregular strong echo.There was no normal intestinal wall structure,showing a typical“coffee bean sign”.Termination of the pregnancy and autopsy findings confirmed the diagnosis.CONCLUSION The prenatal diagnosis of ileal atresia is difficult.The sonographic features of the“keyboard sign”and“coffee bean sign”are helpful in diagnosing the location of congenital jejunal and ileal atresia.展开更多
Language barrier is the main cause of disagreement.Sign language,which is a common language in all the worldwide language families,is difficult to be entirely popularized due to the high cost of learning as well as th...Language barrier is the main cause of disagreement.Sign language,which is a common language in all the worldwide language families,is difficult to be entirely popularized due to the high cost of learning as well as the technical barrier in real-time translation.To solve these problems,here,we constructed a wearable organohydrogel-based electronic skin(e-skin)with fast self-healing,strong adhesion,extraor-dinary anti-freezing and moisturizing properties for sign language recognition under complex environ-ments.The e-skin was obtained by using an acrylic network as the main body,aluminum(III)and bay-berry tannin as the crosslinking agent,water/ethylene glycol as the solvent system,and a polyvinyl al-cohol network to optimize the network performance.Using this e-skin,a smart glove was further built,which could carry out the large-scale data collection of common gestures and sign languages.With the help of the deep learning method,specific recognition and translation for various gestures and sign lan-guages could be achieved.The accuracy was 93.5%,showing the ultra-high classification accuracy of a sign language interpreter.In short,by integrating multiple characteristics and combining deep learning technology with hydrogel materials,the e-skin achieved an important breakthrough in human-computer interaction and artificial intelligence,and provided a feasible strategy for solving the dilemma of mutual exclusion between flexible electronic devices and human bodies.展开更多
Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automa...Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automatically recognizing and interpreting sign language gestures,has gained significant attention in recent years due to its potential to bridge the communication gap between the hearing impaired and the hearing world.The emergence and continuous development of deep learning techniques have provided inspiration and momentum for advancing SLR.This paper presents a comprehensive and up-to-date analysis of the advancements,challenges,and opportunities in deep learning-based sign language recognition,focusing on the past five years of research.We explore various aspects of SLR,including sign data acquisition technologies,sign language datasets,evaluation methods,and different types of neural networks.Convolutional Neural Networks(CNN)and Recurrent Neural Networks(RNN)have shown promising results in fingerspelling and isolated sign recognition.However,the continuous nature of sign language poses challenges,leading to the exploration of advanced neural network models such as the Transformer model for continuous sign language recognition(CSLR).Despite significant advancements,several challenges remain in the field of SLR.These challenges include expanding sign language datasets,achieving user independence in recognition systems,exploring different input modalities,effectively fusing features,modeling co-articulation,and improving semantic and syntactic understanding.Additionally,developing lightweight network architectures for mobile applications is crucial for practical implementation.By addressing these challenges,we can further advance the field of deep learning for sign language recognition and improve communication for the hearing-impaired community.展开更多
BACKGROUND Crochetage sign is a specific electrocardiographic manifestation of ostium secundum atrial septal defects(ASDs),which is associated with the severity of the left-to-right shunt.Herein,we reported a case of ...BACKGROUND Crochetage sign is a specific electrocardiographic manifestation of ostium secundum atrial septal defects(ASDs),which is associated with the severity of the left-to-right shunt.Herein,we reported a case of selective his bundle pacing(SHBP)that eliminated crochetage sign in a patient with ostium secundum ASD.CASE SUMMARY A 77-year-old man was admitted with a 2-year history of chest tightness and shortness of breath.Transthoracic echocardiography revealed an ostium secundum ASD.Twelve-lead electrocardiogram revealed atrial fibrillation with a prolonged relative risk interval,incomplete right bundle branch block,and crochetage sign.The patient was diagnosed with an ostium secundum ASD,atrial fibrillation with a second-degree atrioventricular block,and heart failure.The patient was treated with selective his bundle pacemaker implantation.After the procedure,crochetage sign disappeared during his bundle pacing on the electrocardiogram.CONCLUSION S-HBP eliminated crochetage sign on electrocardiogram.Crochetage sign may be a manifestation of a conduction system disorder.展开更多
While progress has been made in information source localization,it has overlooked the prevalent friend and adversarial relationships in social networks.This paper addresses this gap by focusing on source localization ...While progress has been made in information source localization,it has overlooked the prevalent friend and adversarial relationships in social networks.This paper addresses this gap by focusing on source localization in signed network models.Leveraging the topological characteristics of signed networks and transforming the propagation probability into effective distance,we propose an optimization method for observer selection.Additionally,by using the reverse propagation algorithm we present a method for information source localization in signed networks.Extensive experimental results demonstrate that a higher proportion of positive edges within signed networks contributes to more favorable source localization,and the higher the ratio of propagation rates between positive and negative edges,the more accurate the source localization becomes.Interestingly,this aligns with our observation that,in reality,the number of friends tends to be greater than the number of adversaries,and the likelihood of information propagation among friends is often higher than among adversaries.In addition,the source located at the periphery of the network is not easy to identify.Furthermore,our proposed observer selection method based on effective distance achieves higher operational efficiency and exhibits higher accuracy in information source localization,compared with three strategies for observer selection based on the classical full-order neighbor coverage.展开更多
基金supported by the National Language Commission to research on sign language data specifications for artificial intelligence applications and test standards for language service translation systems (No.ZDI145-70)。
文摘Sign language dataset is essential in sign language recognition and translation(SLRT). Current public sign language datasets are small and lack diversity, which does not meet the practical application requirements for SLRT. However, making a large-scale and diverse sign language dataset is difficult as sign language data on the Internet is scarce. In making a large-scale and diverse sign language dataset, some sign language data qualities are not up to standard. This paper proposes a two information streams transformer(TIST) model to judge whether the quality of sign language data is qualified. To verify that TIST effectively improves sign language recognition(SLR), we make two datasets, the screened dataset and the unscreened dataset. In this experiment, this paper uses visual alignment constraint(VAC) as the baseline model. The experimental results show that the screened dataset can achieve better word error rate(WER) than the unscreened dataset.
基金supported by the National Natural Science Foundation of China(No.62066041).
文摘Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition algorithms often relies on expert knowledge to enhance the image feature extraction networks,necessitating image preprocessing and model parameter tuning.This increases the complexity of the model design process.This study introduces an evolutionary neural architecture search(ENAS)algorithm for the automatic design of neural network models tailored for traffic sign recognition.By integrating the construction parameters of residual network(ResNet)into evolutionary algorithms(EAs),we automatically generate lightweight networks for traffic sign recognition,utilizing blocks as the fundamental building units.Experimental evaluations on the German traffic sign recognition benchmark(GTSRB)dataset reveal that the algorithm attains a recognition accuracy of 99.32%,with a mere 2.8×10^(6)parameters.Experimental results comparing the proposed method with other traffic sign recognition algorithms demonstrate that the method can more efficiently discover neural network architectures,significantly reducing the number of network parameters while maintaining recognition accuracy.
基金Supported by the National Natural Science Foundation of China(Grant No.12071260)。
文摘A graph whose edges are labeled either as positive or negative is called a signed graph.Hameed et al.introduced signed distance and distance compatibility in 2021,initially to characterize balanced signed graphs which have nice spectral properties.This article mainly studies the conjecture proposed by Shijin et al.on the distance compatibility of the direct product of signed graphs,and provides necessary and sufficient conditions for the distance compatibility of the direct product of signed graphs.Some further questions regarding distance compatibility are also posed.
基金Beijing Natural Science Foundation-Fengtai Rail Transit Frontier Research Joint Foundation(No.L211024),the National Natural Science Foundation of China(No.52072012).
文摘To explore the influence of emergency evacuation signs on passenger behavior during subway fires and improve evacuation efficiency in emergencies,this paper proposes a dynamic emergency evacuation sign system.A simulation platform integrating building information modeling(BIM)and virtual reality(VR)technologies was em-ployed to create subway fire evacuation scenarios using both the current and proposed dynamic emergency evacuation signage systems.Through simulation experiments,fine-grained microscopic data on passenger behavior was collected.Seven indicators were selected to assess evacuation efficiency and wayfinding difficulty.The analysis explored the influence of evacuation signs on passenger behavior in both overall and decision-making areas,thereby validating the effectiveness of the new emergency evacuation signage system.The results show that the dynamic evacuation signage system significantly improves overall passenger evacuation efficiency and reduces decision-making errors.It also improves wayfinding efficiency in critical decision areas by reducing the need for direction identification,minimizing stopping times,and lowering the frequency of decision errors.The method for evaluating the effects of emergency evacuation signs on passenger evacuation behavior proposed in this study provides a robust theoretical basis for the design and optimization of emergency-oriented signs.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.72371031,62173065,62476045)Fundamental Research Funds for the Central Universities(Grant No.124330008)。
文摘The unique structure of signed networks,characterized by positive and negative edges,poses significant challenges for analyzing network topology.In recent years,various statistical algorithms have been developed to address this issue.However,there remains a lack of a unified framework to uncover the nontrivial properties inherent in signed network structures.To support developers,researchers,and practitioners in this field,we introduce a Python library named SNSAlib(Signed Network Structure Analysis),specifically designed to meet these analytical requirements.This library encompasses empirical signed network datasets,signed null model algorithms,signed statistics algorithms,and evaluation indicators.The primary objective of SNSAlib is to facilitate the systematic analysis of micro-and meso-structure features within signed networks,including node popularity,clustering,assortativity,embeddedness,and community structure by employing more accurate signed null models.Ultimately,it provides a robust paradigm for structure analysis of signed networks that enhances our understanding and application of signed networks.
基金supported by the National Natural Science Foundation of China(Grant Number 52472322)the Shanghai Sailing Program(Grant Number 21YF1415800)+1 种基金the Open Project of Key Laboratory of Advanced Public Transportation Science(Grant Number 2023-APTS-05)the Shanghai SASAC Enterprise Innovation and Capability Enhancement Project(Grant Number 2022016,2023020).
文摘Once a train stops in a tunnel section and requires emergency evacuation,the large distance between stations and long walking distances in the underground spaces of suburban railway systems pose potential risks to the evacuation process on tunnel platforms,especially in complex environments.This study utilized Virtual Reality(VR)technology to construct a virtual experimental platform for tunnel evacuation in suburban railway systems,simulating different combinations of smoke and obstacle conditions.By requiring participants to wear VR glasses and walk on an omnidirectional treadmill for moving,as well as complete psychological questionnaires,the study reveals the influences of No Guiding(NG)signs,Wall-Guided(WG)signs,and Central axis Guidance(CG)signs on the movement abilities and psychological behaviors of participants contrastively.The results show that either smoke conditions or obstacle positions affect the mental stress of participants,and the guidance sign has a positive effect on reducing the mental stress.There is an inverse relationship between mental stress and movement abilities.WG and CG signs respectively lead participants to walk closer to walls and along the central axis,which is conducive to reducing the variation in participants’behavior characteristics when circumventing obstacles on the wall side or track side under smoke conditions,respectively.Additionally,CG signs reduce the speed fluctuations of participants before circumventing obstacles,improving the stability of the distance from the wall and speed under smoke conditions,compared to NG and WG signs.These findings contribute to understanding the evacuation psychological-behavioral-movement characteristics of pedestrians on evacuation platforms in suburban railway tunnels and provide a basis for improving the safety design of evacuation guidance signs.
基金supported by the National Natural Science Foundation of China under Grant Nos.62076117 and 62166026the Jiangxi Provincial Key Laboratory of Virtual Reality under Grant No.2024SSY03151.
文摘Dynamic sign language recognition holds significant importance, particularly with the application of deep learning to address its complexity. However, existing methods face several challenges. Firstly, recognizing dynamic sign language requires identifying keyframes that best represent the signs, and missing these keyframes reduces accuracy. Secondly, some methods do not focus enough on hand regions, which are small within the overall frame, leading to information loss. To address these challenges, we propose a novel Video Transformer Attention-based Network (VTAN) for dynamic sign language recognition. Our approach prioritizes informative frames and hand regions effectively. To tackle the first issue, we designed a keyframe extraction module enhanced by a convolutional autoencoder, which focuses on selecting information-rich frames and eliminating redundant ones from the video sequences. For the second issue, we developed a soft attention-based transformer module that emphasizes extracting features from hand regions, ensuring that the network pays more attention to hand information within sequences. This dual-focus approach improves effective dynamic sign language recognition by addressing the key challenges of identifying critical frames and emphasizing hand regions. Experimental results on two public benchmark datasets demonstrate the effectiveness of our network, outperforming most of the typical methods in sign language recognition tasks.
文摘The arterial pulse tapping artifact,known as Aslanger’s sign,is an electrocardiographic artifact resulting from the transmission of arterial pulsation onto the limb electrodes of the standard 12-lead electrocardiograph(ECG)which are placed near the radial or posterior tibial arteries.[1-16]This electromechanical artifact is of cardiac origin and is synchronous with the cardiac cycle.[17]Nearly all reported cases of Aslanger’s sign exhibit an unusual waveform morphology in all 12 leads except one limb lead.[1-14,16]However,we previously reported a case of Aslanger’s sign that showed distorted waveforms from the ST to TP segments observed only in five limb leads among 12 leads.
基金co-supported by the National Natural Science Foundation of China(Nos.12372048,12102343)the Key Program of the National Natural Science Foundation of China(No.U2013206)+1 种基金the China Postdoctoral Science Foundation(No.2023M742835)the Guangdong Basic and Applied Basic Research Foundation,China(No.2023A1515011421).
文摘This paper presents a predefined-time controller for Multiple Space transportation Robots System (MSRS), which can be applied in on-orbit assembly tasks to transport modules to pre-assembly configuration quickly. Firstly, to simplify the analysis and design of predefined-time controller, a Predefined-time Stability Criterion is proposed in the form of Composite Lyapunov Function (CLF-PSC). Besides simplicity, the CLF-PSC also has the advantage of less conservativeness due to utilization of initial state information. Secondly, a concept of Lp-Norm-Normalized Sign Function (LPNNSF) is proposed based on the CLF-PSC. Different from traditional norm-normalized sign function, the Lp-norm of LPNNSF can be selected arbitrarily according to practical control task requirements, which means that the proposed LPNNSF is more generalized and more convenient for calculation. Thirdly, a predefined-time disturbance observer and predefined-time controller are designed based on the LPNNSF. The observer has the property of predefined-time convergence to achieve quicker and more accurate estimation of the lumped disturbance. The controller has less control input and chattering phenomenon than traditional predefined-time controller. In addition, by introducing the observer into the controller, the closed-loop system enjoys high precision and strong robustness. Finally, the effectiveness of the proposed controller is verified by numerical simulations. By employing the controller, the MSRS can carry assembly modules to the desired pre-assembly configuration accurately within predefined time.
基金supported by the Shanxi Agricultural University Science and Technology Innovation Enhancement Project。
文摘This paper proposes a lightweight traffic sign detection system based on you only look once(YOLO).Firstly,the classification to fusion(C2f)structure is integrated into the backbone network,employing deformable convolution and bi-directional feature pyramid network(BiFPN)_Concat to improve the adaptability of the network.Secondly,the simple attention module(SimAm)is embedded to prioritize key features and reduce the complexity of the model after the C2f layer at the end of the backbone network.Next,the focal efficient intersection over union(EloU)is introduced to adjust the weights of challenging samples.Finally,we accomplish the design and deployment for the mobile app.The results demonstrate improvements,with the F1 score of 0.8987,mean average precision(mAP)@0.5 of 98.8%,mAP@0.5:0.95 of 75.6%,and the detection speed of 50 frames per second(FPS).
基金funding this work through Research Group No.KS-2024-376.
文摘Arabic Sign Language(ArSL)recognition plays a vital role in enhancing the communication for the Deaf and Hard of Hearing(DHH)community.Researchers have proposed multiple methods for automated recognition of ArSL;however,these methods face multiple challenges that include high gesture variability,occlusions,limited signer diversity,and the scarcity of large annotated datasets.Existing methods,often relying solely on either skeletal data or video-based features,struggle with generalization and robustness,especially in dynamic and real-world conditions.This paper proposes a novel multimodal ensemble classification framework that integrates geometric features derived from 3D skeletal joint distances and angles with temporal features extracted from RGB videos using the Inflated 3D ConvNet(I3D).By fusing these complementary modalities at the feature level and applying a majority-voting ensemble of XGBoost,Random Forest,and Support Vector Machine classifiers,the framework robustly captures both spatial configurations and motion dynamics of sign gestures.Feature selection using the Pearson Correlation Coefficient further enhances efficiency by reducing redundancy.Extensive experiments on the ArabSign dataset,which includes RGB videos and corresponding skeletal data,demonstrate that the proposed approach significantly outperforms state-of-the-art methods,achieving an average F1-score of 97%using a majority-voting ensemble of XGBoost,Random Forest,and SVM classifiers,and improving recognition accuracy by more than 7%over previous best methods.This work not only advances the technical stateof-the-art in ArSL recognition but also provides a scalable,real-time solution for practical deployment in educational,social,and assistive communication technologies.Even though this study is about Arabic Sign Language,the framework proposed here can be extended to different sign languages,creating possibilities for potentially worldwide applicability in sign language recognition tasks.
基金Supported by the National Natural Science Foundation of China(Grant No.12261016)。
文摘A signed graph S=(S^(u),σ)has an underlying graph Suand a functionσ:E(S^(u))-→{+,-}.Let E^(-)(S)denote the set of negative edges of S.Then S is eulerian signed graph(or subeulerian signed graph,or balanced eulerian signed graph,respectively)if Suis eulerian(or subeulerian,or eulerian and|E-(S)|is even,respectively).We say that S is balanced subeulerian signed graph if there exists a balanced eulerian signed graph S′such that S′is spanned by S.The signed line graph L(S)of a signed graph S is a signed graph with the vertices of L(S)being the edges of S,where an edge eiej is in L(S)if and only if the edges e_(i)and e_(j)of S have a vertex in common in S such that an edge eiej in L(S)is negative if and only if both edges ei and ej are negative in S.In this paper,two families of signed graphs S and S′are identified,which are applied to characterize balanced subeulerian signed graphs and balanced subeulerian signed line graphs.In particular,it is proved that a signed graph S is balanced subeulerian if and only if S∈S,and that a signed line graph of signed graph S is balanced subeulerian if and only if S∈S′.
文摘BACKGROUND Ileal atresia is a congenital abnormality where there is significant stenosis or complete absence of a portion of the ileum.The overall diagnostic accuracy of prenatal ultrasound in detecting jejunal and ileal atresia is low.We report a case of ileal atresia diagnosed prenatally by ultrasound examination with the“keyboard sign”and“coffee bean sign”.CASE SUMMARY We report a case of ileal atresia diagnosed in utero at 31 weeks'of gestation.Prenatal ultrasound examination revealed two rows of intestines arranged in an‘S’shape in the middle abdomen.The inner diameters were 1.7 cm and 1.6 cm,respectively.A typical“keyboard sign”was observed.The intestine canal behind the“keyboard sign”showed an irregular strong echo.There was no normal intestinal wall structure,showing a typical“coffee bean sign”.Termination of the pregnancy and autopsy findings confirmed the diagnosis.CONCLUSION The prenatal diagnosis of ileal atresia is difficult.The sonographic features of the“keyboard sign”and“coffee bean sign”are helpful in diagnosing the location of congenital jejunal and ileal atresia.
基金supported by the National Natural Science Foundation of China(No.21978180).
文摘Language barrier is the main cause of disagreement.Sign language,which is a common language in all the worldwide language families,is difficult to be entirely popularized due to the high cost of learning as well as the technical barrier in real-time translation.To solve these problems,here,we constructed a wearable organohydrogel-based electronic skin(e-skin)with fast self-healing,strong adhesion,extraor-dinary anti-freezing and moisturizing properties for sign language recognition under complex environ-ments.The e-skin was obtained by using an acrylic network as the main body,aluminum(III)and bay-berry tannin as the crosslinking agent,water/ethylene glycol as the solvent system,and a polyvinyl al-cohol network to optimize the network performance.Using this e-skin,a smart glove was further built,which could carry out the large-scale data collection of common gestures and sign languages.With the help of the deep learning method,specific recognition and translation for various gestures and sign lan-guages could be achieved.The accuracy was 93.5%,showing the ultra-high classification accuracy of a sign language interpreter.In short,by integrating multiple characteristics and combining deep learning technology with hydrogel materials,the e-skin achieved an important breakthrough in human-computer interaction and artificial intelligence,and provided a feasible strategy for solving the dilemma of mutual exclusion between flexible electronic devices and human bodies.
基金supported from the National Philosophy and Social Sciences Foundation(Grant No.20BTQ065).
文摘Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automatically recognizing and interpreting sign language gestures,has gained significant attention in recent years due to its potential to bridge the communication gap between the hearing impaired and the hearing world.The emergence and continuous development of deep learning techniques have provided inspiration and momentum for advancing SLR.This paper presents a comprehensive and up-to-date analysis of the advancements,challenges,and opportunities in deep learning-based sign language recognition,focusing on the past five years of research.We explore various aspects of SLR,including sign data acquisition technologies,sign language datasets,evaluation methods,and different types of neural networks.Convolutional Neural Networks(CNN)and Recurrent Neural Networks(RNN)have shown promising results in fingerspelling and isolated sign recognition.However,the continuous nature of sign language poses challenges,leading to the exploration of advanced neural network models such as the Transformer model for continuous sign language recognition(CSLR).Despite significant advancements,several challenges remain in the field of SLR.These challenges include expanding sign language datasets,achieving user independence in recognition systems,exploring different input modalities,effectively fusing features,modeling co-articulation,and improving semantic and syntactic understanding.Additionally,developing lightweight network architectures for mobile applications is crucial for practical implementation.By addressing these challenges,we can further advance the field of deep learning for sign language recognition and improve communication for the hearing-impaired community.
文摘BACKGROUND Crochetage sign is a specific electrocardiographic manifestation of ostium secundum atrial septal defects(ASDs),which is associated with the severity of the left-to-right shunt.Herein,we reported a case of selective his bundle pacing(SHBP)that eliminated crochetage sign in a patient with ostium secundum ASD.CASE SUMMARY A 77-year-old man was admitted with a 2-year history of chest tightness and shortness of breath.Transthoracic echocardiography revealed an ostium secundum ASD.Twelve-lead electrocardiogram revealed atrial fibrillation with a prolonged relative risk interval,incomplete right bundle branch block,and crochetage sign.The patient was diagnosed with an ostium secundum ASD,atrial fibrillation with a second-degree atrioventricular block,and heart failure.The patient was treated with selective his bundle pacemaker implantation.After the procedure,crochetage sign disappeared during his bundle pacing on the electrocardiogram.CONCLUSION S-HBP eliminated crochetage sign on electrocardiogram.Crochetage sign may be a manifestation of a conduction system disorder.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.62103375 and 62006106)the Zhejiang Provincial Philosophy and Social Science Planning Project(Grant No.22NDJC009Z)+1 种基金the Education Ministry Humanities and Social Science Foundation of China(Grant Nos.19YJCZH056 and 21YJC630120)the Natural Science Foundation of Zhejiang Province of China(Grant Nos.LY23F030003 and LQ21F020005).
文摘While progress has been made in information source localization,it has overlooked the prevalent friend and adversarial relationships in social networks.This paper addresses this gap by focusing on source localization in signed network models.Leveraging the topological characteristics of signed networks and transforming the propagation probability into effective distance,we propose an optimization method for observer selection.Additionally,by using the reverse propagation algorithm we present a method for information source localization in signed networks.Extensive experimental results demonstrate that a higher proportion of positive edges within signed networks contributes to more favorable source localization,and the higher the ratio of propagation rates between positive and negative edges,the more accurate the source localization becomes.Interestingly,this aligns with our observation that,in reality,the number of friends tends to be greater than the number of adversaries,and the likelihood of information propagation among friends is often higher than among adversaries.In addition,the source located at the periphery of the network is not easy to identify.Furthermore,our proposed observer selection method based on effective distance achieves higher operational efficiency and exhibits higher accuracy in information source localization,compared with three strategies for observer selection based on the classical full-order neighbor coverage.
