With the increasing attention to the state and role of people in intelligent manufacturing, there is a strong demand for human-cyber-physical systems (HCPS) that focus on human-robot interaction. The existing intellig...With the increasing attention to the state and role of people in intelligent manufacturing, there is a strong demand for human-cyber-physical systems (HCPS) that focus on human-robot interaction. The existing intelligent manufacturing system cannot satisfy efcient human-robot collaborative work. However, unlike machines equipped with sensors, human characteristic information is difcult to be perceived and digitized instantly. In view of the high complexity and uncertainty of the human body, this paper proposes a framework for building a human digital twin (HDT) model based on multimodal data and expounds on the key technologies. Data acquisition system is built to dynamically acquire and update the body state data and physiological data of the human body and realize the digital expression of multi-source heterogeneous human body information. A bidirectional long short-term memory and convolutional neural network (BiLSTM-CNN) based network is devised to fuse multimodal human data and extract the spatiotemporal features, and the human locomotion mode identifcation is taken as an application case. A series of optimization experiments are carried out to improve the performance of the proposed BiLSTM-CNN-based network model. The proposed model is compared with traditional locomotion mode identifcation models. The experimental results proved the superiority of the HDT framework for human locomotion mode identifcation.展开更多
Deep neural networks are vulnerable to attacks from adversarial inputs.Corresponding attack research on human pose estimation(HPE),particularly for body joint detection,has been largely unexplored.Transferring classif...Deep neural networks are vulnerable to attacks from adversarial inputs.Corresponding attack research on human pose estimation(HPE),particularly for body joint detection,has been largely unexplored.Transferring classification-based attack methods to body joint regression tasks is not straightforward.Another issue is that the attack effectiveness and imperceptibility contradict each other.To solve these issues,we propose local imperceptible attacks on HPE networks.In particular,we reformulate imperceptible attacks on body joint regression into a constrained maximum allowable attack.Furthermore,we approximate the solution using iterative gradient-based strength refinement and greedy-based pixel selection.Our method crafts effective perceptual adversarial attacks that consider both human perception and attack effectiveness.We conducted a series of imperceptible attacks against state-of-the-art HPE methods,including HigherHRNet,DEKR,and ViTPose.The experimental results demonstrate that the proposed method achieves excellent imperceptibility while maintaining attack effectiveness by significantly reducing the number of perturbed pixels.Approximately 4%of the pixels can achieve sufficient attacks on HPE.展开更多
A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain...A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion.The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network.Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods,especially of long-term prediction.展开更多
We established a QT interval assessment system that uses human embryonic stem cell-derived cardiomyocyte clusters (hES-CMCs) in which the field potential duration (FPD) or corrected FPD (FPDc) was measured as an indic...We established a QT interval assessment system that uses human embryonic stem cell-derived cardiomyocyte clusters (hES-CMCs) in which the field potential duration (FPD) or corrected FPD (FPDc) was measured as an indicator of drug-induced QT interval prolongation. To investigate the applicability of the hES-CMC system to drug safety assessment, we investigated short-term variability in FPDc (STVFPDc) (beat rate rhythmicity) as a marker of torsadogenic risk. We investigated the FPDc and STVFPDc of hES-CMCs treated with hERG channel blockers (E-4031 or cisapride) or with our proprietary compounds X, Y, and Z. We also evaluated the electrocardiograms and hemodynamics of dogs treated with compound X, Y, or Z. The torsadogenic hERG channel blockers increased STVFPDc and prolonged FPDc. Compounds X, Y, and Z had hERG inhibitory activity. Compound X prolonged FPDc with increased STVFPDc, whereas compounds Y and Z tended to shorten FPDc in the hES-CMC system. In the in vivo canine study, compound X prolonged corrected QT (QTc), and compounds Y and Z tended to shorten QTc, showing a good correlation with the results in hES-CMCs. These findings suggest that combined assessment of FPDc and STVFPDc in the hES-CMC system increases the predictability of torsadogenic risk.展开更多
尽管深度神经网络在很多任务上取得了良好的结果,但是它们对于微小的对抗扰动却很容易出现预测错误.然而在人体姿态估计的对抗攻击任务中,通常需要添加较大的扰动噪声才能攻击成功,这使得其不可察性变差;减少扰动噪声又会削弱攻击效果....尽管深度神经网络在很多任务上取得了良好的结果,但是它们对于微小的对抗扰动却很容易出现预测错误.然而在人体姿态估计的对抗攻击任务中,通常需要添加较大的扰动噪声才能攻击成功,这使得其不可察性变差;减少扰动噪声又会削弱攻击效果.为了克服该矛盾,提出一种面向人体姿态估计的两阶段局部对抗攻击方法.所提方法首先通过预攻击估计出扰动关键区域,然后利用不可察性约束在关键区域内生成扰动.方法不仅可以对人体姿态进行有效攻击,而且还能确保最终扰动区域具有低可察性.采用COCO2017作为对抗扰动实验数据集并使用PCK(percentage of correct keypoints)作为评价指标,比较在人体姿态估计模型中IGSM和C&W方法的攻击效果,其PCK降低值分别提高了15.4%与2.8%.实验结果表明所提方法在保证攻击的低可察的同时,能够取得较好的攻击效果.展开更多
A new safety assessment method for parallel routes is presented. From the aspects of safety guard system of air traffic control（ATC） and considering the flight conflict as causing event of air collision accidents, t...A new safety assessment method for parallel routes is presented. From the aspects of safety guard system of air traffic control（ATC） and considering the flight conflict as causing event of air collision accidents, this paper fosters a four-layer safety guard of controller command, short-term conflict alerts （STCAs）, pilot visual avoidance, and traffic alert collision avoidance system（TCAS）. Then, the problem of parallel routes collision risk is divided into two parts：the calculation of potential flight conflict and the analysis of failure probability of the four-layer safety guard. A calculation model for controller interference times is induced. By using cognitive reliability and error analysis method（CREAM）,the calculation problem to failure probability of controller sequencing flight conflicts is solved and a fault tree model of guard failure of STCA and TCAS is established. Finally, the Beijing-Shanghai parallel routes are taken as an example to be calculated and the collision risk of the parallel routes is obtained under the condition of radar control. Results show that the parallel routes can satisfy the safety demands.展开更多
Physiological signal based biometric analysis has recently attracted attention as a means of meeting increasing privacy and security requirements.The real-time nature of an electrocardiogram(ECG)and the hidden nature ...Physiological signal based biometric analysis has recently attracted attention as a means of meeting increasing privacy and security requirements.The real-time nature of an electrocardiogram(ECG)and the hidden nature of the information make it highly resistant to attacks.This paper focuses on three major bottlenecks of existing deep learning driven approaches:the lengthy time requirements for optimizing the hyperparameters,the slow and computationally intense identification process,and the unstable and complicated nature of ECG acquisition.We present a novel deep neural network framework for learning human identification feature representations directly from ECG time series.The proposed framework integrates deep bidirectional long short-term memory(BLSTM)and adaptive particle swarm optimization(APSO).The overall approach not only avoids the inefficient and experience-dependent search for hyperparameters,but also fully exploits the spatial information of ordinal local features and the memory characteristics of a recognition algorithm.The effectiveness of the proposed approach is thoroughly evaluated in two ECG datasets,using two protocols,simulating the influence of electrode placement and acquisition sessions in identification.Comparing four recurrent neural network structures and four classical machine learning and deep learning algorithms,we prove the superiority of the proposed algorithm in minimizing overfitting and self-learning of time series.The experimental results demonstrated an average identification rate of 97.71%,99.41%,and 98.89% in training,validation,and test sets,respectively.Thus,this study proves that the application of APSO and LSTM techniques to biometric human identification can achieve a lower algorithm engineering effort and higher capacity for generalization.展开更多
基金Supported by National Natural Science Foundation of China(Grant Nos.52205288,52130501,52075479)Zhejiang Provincial Key Research&Development Program(Grant No.2021C01110).
文摘With the increasing attention to the state and role of people in intelligent manufacturing, there is a strong demand for human-cyber-physical systems (HCPS) that focus on human-robot interaction. The existing intelligent manufacturing system cannot satisfy efcient human-robot collaborative work. However, unlike machines equipped with sensors, human characteristic information is difcult to be perceived and digitized instantly. In view of the high complexity and uncertainty of the human body, this paper proposes a framework for building a human digital twin (HDT) model based on multimodal data and expounds on the key technologies. Data acquisition system is built to dynamically acquire and update the body state data and physiological data of the human body and realize the digital expression of multi-source heterogeneous human body information. A bidirectional long short-term memory and convolutional neural network (BiLSTM-CNN) based network is devised to fuse multimodal human data and extract the spatiotemporal features, and the human locomotion mode identifcation is taken as an application case. A series of optimization experiments are carried out to improve the performance of the proposed BiLSTM-CNN-based network model. The proposed model is compared with traditional locomotion mode identifcation models. The experimental results proved the superiority of the HDT framework for human locomotion mode identifcation.
基金National Natural Science Foundation of China,No.61972458Natural Science Foundation of Zhejiang Province,No.LZ23F020002.
文摘Deep neural networks are vulnerable to attacks from adversarial inputs.Corresponding attack research on human pose estimation(HPE),particularly for body joint detection,has been largely unexplored.Transferring classification-based attack methods to body joint regression tasks is not straightforward.Another issue is that the attack effectiveness and imperceptibility contradict each other.To solve these issues,we propose local imperceptible attacks on HPE networks.In particular,we reformulate imperceptible attacks on body joint regression into a constrained maximum allowable attack.Furthermore,we approximate the solution using iterative gradient-based strength refinement and greedy-based pixel selection.Our method crafts effective perceptual adversarial attacks that consider both human perception and attack effectiveness.We conducted a series of imperceptible attacks against state-of-the-art HPE methods,including HigherHRNet,DEKR,and ViTPose.The experimental results demonstrate that the proposed method achieves excellent imperceptibility while maintaining attack effectiveness by significantly reducing the number of perturbed pixels.Approximately 4%of the pixels can achieve sufficient attacks on HPE.
文摘A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion.The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network.Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods,especially of long-term prediction.
文摘We established a QT interval assessment system that uses human embryonic stem cell-derived cardiomyocyte clusters (hES-CMCs) in which the field potential duration (FPD) or corrected FPD (FPDc) was measured as an indicator of drug-induced QT interval prolongation. To investigate the applicability of the hES-CMC system to drug safety assessment, we investigated short-term variability in FPDc (STVFPDc) (beat rate rhythmicity) as a marker of torsadogenic risk. We investigated the FPDc and STVFPDc of hES-CMCs treated with hERG channel blockers (E-4031 or cisapride) or with our proprietary compounds X, Y, and Z. We also evaluated the electrocardiograms and hemodynamics of dogs treated with compound X, Y, or Z. The torsadogenic hERG channel blockers increased STVFPDc and prolonged FPDc. Compounds X, Y, and Z had hERG inhibitory activity. Compound X prolonged FPDc with increased STVFPDc, whereas compounds Y and Z tended to shorten FPDc in the hES-CMC system. In the in vivo canine study, compound X prolonged corrected QT (QTc), and compounds Y and Z tended to shorten QTc, showing a good correlation with the results in hES-CMCs. These findings suggest that combined assessment of FPDc and STVFPDc in the hES-CMC system increases the predictability of torsadogenic risk.
文摘尽管深度神经网络在很多任务上取得了良好的结果,但是它们对于微小的对抗扰动却很容易出现预测错误.然而在人体姿态估计的对抗攻击任务中,通常需要添加较大的扰动噪声才能攻击成功,这使得其不可察性变差;减少扰动噪声又会削弱攻击效果.为了克服该矛盾,提出一种面向人体姿态估计的两阶段局部对抗攻击方法.所提方法首先通过预攻击估计出扰动关键区域,然后利用不可察性约束在关键区域内生成扰动.方法不仅可以对人体姿态进行有效攻击,而且还能确保最终扰动区域具有低可察性.采用COCO2017作为对抗扰动实验数据集并使用PCK(percentage of correct keypoints)作为评价指标,比较在人体姿态估计模型中IGSM和C&W方法的攻击效果,其PCK降低值分别提高了15.4%与2.8%.实验结果表明所提方法在保证攻击的低可察的同时,能够取得较好的攻击效果.
基金Supported by the National High Technology Research and Development Program of China("863"Program)(2006AA12A105)~~
文摘A new safety assessment method for parallel routes is presented. From the aspects of safety guard system of air traffic control（ATC） and considering the flight conflict as causing event of air collision accidents, this paper fosters a four-layer safety guard of controller command, short-term conflict alerts （STCAs）, pilot visual avoidance, and traffic alert collision avoidance system（TCAS）. Then, the problem of parallel routes collision risk is divided into two parts：the calculation of potential flight conflict and the analysis of failure probability of the four-layer safety guard. A calculation model for controller interference times is induced. By using cognitive reliability and error analysis method（CREAM）,the calculation problem to failure probability of controller sequencing flight conflicts is solved and a fault tree model of guard failure of STCA and TCAS is established. Finally, the Beijing-Shanghai parallel routes are taken as an example to be calculated and the collision risk of the parallel routes is obtained under the condition of radar control. Results show that the parallel routes can satisfy the safety demands.
基金Project supported by the Zhejiang Province Public Welfare Technology Application Research Project(No.LGG20F010008)the National Natural Science Foundation of China(No.61571173)the Welfare Project of the Science Technology Department of Zhejiang Province,China(No.LGG18F010012)。
文摘Physiological signal based biometric analysis has recently attracted attention as a means of meeting increasing privacy and security requirements.The real-time nature of an electrocardiogram(ECG)and the hidden nature of the information make it highly resistant to attacks.This paper focuses on three major bottlenecks of existing deep learning driven approaches:the lengthy time requirements for optimizing the hyperparameters,the slow and computationally intense identification process,and the unstable and complicated nature of ECG acquisition.We present a novel deep neural network framework for learning human identification feature representations directly from ECG time series.The proposed framework integrates deep bidirectional long short-term memory(BLSTM)and adaptive particle swarm optimization(APSO).The overall approach not only avoids the inefficient and experience-dependent search for hyperparameters,but also fully exploits the spatial information of ordinal local features and the memory characteristics of a recognition algorithm.The effectiveness of the proposed approach is thoroughly evaluated in two ECG datasets,using two protocols,simulating the influence of electrode placement and acquisition sessions in identification.Comparing four recurrent neural network structures and four classical machine learning and deep learning algorithms,we prove the superiority of the proposed algorithm in minimizing overfitting and self-learning of time series.The experimental results demonstrated an average identification rate of 97.71%,99.41%,and 98.89% in training,validation,and test sets,respectively.Thus,this study proves that the application of APSO and LSTM techniques to biometric human identification can achieve a lower algorithm engineering effort and higher capacity for generalization.
